CN118332017B - Monitoring self-adaptive regulation and control method and device for movable formwork bridge fabrication machine - Google Patents

Abstract

The invention discloses a monitoring self-adaptive regulation and control method and device of a movable mould frame bridge fabrication machine, and relates to the technical field of data processing, wherein the method comprises the following steps: the template library of the interactive target movable mould frame bridge fabrication machine obtains N template basic information of N templates; obtaining N historical template use record sets and N cloud template use record sets; performing usage record adaptability extraction to obtain N sound databases; generating N parameter outlier clusters; carrying out centralized anomaly analysis and extracting a monitoring data set; acquiring an overrun monitoring parameter set and an overrun monitoring parameter value set; and analyzing by using a regulation and control self-adaptive identifier to generate a target regulation and control scheme, and regulating and controlling the target movable mould frame bridge fabrication machine according to the target regulation and control scheme. The invention solves the technical problem of reduced bridge construction quality caused by inaccurate basis of monitoring and regulation of the movable mould frame bridge fabrication machine in the prior art, and achieves the technical effect of improving the regulation accuracy.

Description

A monitoring and adaptive control method and device for a mobile formwork bridge-building machine

Technical Field

The present invention relates to the technical field of data processing, and in particular to a monitoring and adaptive control method and device for a mobile formwork bridge-building machine.

Background Art

If the basis for monitoring and regulating the mobile formwork bridge-building machine is inaccurate, the quality of bridge construction will be reduced. In actual work, the working condition of the mobile formwork bridge-building machine is closely related to its own operation. At present, it is often monitored based on the standard range of parameters, which is easy to deviate from the actual working condition of the mobile formwork bridge-building machine. This will lead to the inability to timely discover abnormal conditions in the construction of the bridge during concrete pouring. The existing technology has the technical problem that the basis for monitoring and regulating the mobile formwork bridge-building machine is inaccurate, resulting in reduced bridge construction quality.

Summary of the invention

The present application provides a monitoring and adaptive control method and device for a mobile formwork bridge-building machine, which is used to solve the technical problem in the prior art that the basis for monitoring and controlling the mobile formwork bridge-building machine is inaccurate, resulting in reduced bridge-building quality.

In view of the above problems, the present application provides a monitoring and adaptive control method and device for a mobile formwork bridge-building machine.

In a first aspect of the present application, a monitoring and adaptive control method for a mobile formwork bridge-building machine is provided, the method comprising:

Interact with the template library of the target mobile formwork bridge-building machine to obtain N template basic information of the N templates, wherein the N template basic information includes N template plate parameters and N template structure design information;

Using the N template plate parameters and the N template structure design information as indexes, searching in the historical database and the cloud database respectively, to obtain N historical template usage record sets and N cloud template usage record sets;

Performing consistency evaluation on the N historical template usage record sets respectively to generate N consistency factors;

Based on the N consistency factors, N harmonic coefficients are configured, and according to the N harmonic coefficients, usage records are adaptively extracted from the N historical template usage record sets and the N cloud template usage record sets, respectively, to obtain N harmony databases, wherein each harmony database includes a plurality of historical template usage records and a plurality of cloud template usage records;

The N harmony databases are searched with construction anomalies as indexes to generate N construction anomaly template usage record sets, and parameter values are extracted from the N construction anomaly template usage record sets according to a preset monitoring parameter set to generate N parameter anomaly value clusters, wherein the preset monitoring parameter set includes P monitoring parameters, and each parameter anomaly value cluster includes P monitoring parameter anomaly value sets;

Performing centralized anomaly analysis on the N parameter anomaly value clusters respectively, and determining N anomaly threshold range clusters corresponding to the N templates respectively according to the analysis results, each anomaly threshold range cluster including P anomaly threshold ranges corresponding to P monitoring parameters;

Retrieve the target abnormal threshold range cluster of the target template, and extract the monitoring data set of the target mobile formwork bridge-building machine when working with the target template, wherein the monitoring data set includes P target monitoring parameter values;

Using the target abnormal threshold range cluster, perform over-limit detection on the P target monitoring parameter values to obtain an over-limit monitoring parameter set and an over-limit monitoring parameter value set;

The over-limit monitoring parameter set and the over-limit monitoring parameter value set are analyzed by using a control adaptive identifier to generate a target control scheme, and the target mobile formwork bridge-building machine is controlled according to the target control scheme.

The second aspect of the present application provides a monitoring and adaptive control device for a mobile formwork bridge-building machine, the device comprising:

A template basic information acquisition module is used to interact with the template library of the target mobile formwork bridge-building machine to obtain N template basic information of N templates, wherein the N template basic information includes N template plate parameters and N template structure design information;

A usage record set acquisition module, used to use the N template plate parameters and the N template structure design information as indexes, to search in the historical database and the cloud database respectively, to obtain N historical template usage record sets and N cloud template usage record sets;

A consistency factor generation module, used to perform consistency evaluation on the N historical template usage record sets respectively to generate N consistency factors;

A harmony database acquisition module, configured to configure N harmonic coefficients based on the N consistency factors, and adaptively extract usage records from the N historical template usage record sets and the N cloud template usage record sets according to the N harmonic coefficients, to obtain N harmony databases, wherein each harmony database includes a plurality of historical template usage records and a plurality of cloud template usage records;

A parameter abnormal value cluster generation module is used to search the N harmony databases with construction abnormalities as indexes to generate N construction abnormality template usage record sets, and extract parameter values from the N construction abnormality template usage record sets according to a preset monitoring parameter set to generate N parameter abnormal value clusters, wherein the preset monitoring parameter set includes P monitoring parameters, and each parameter abnormal value cluster includes P monitoring parameter abnormal value sets;

An abnormal threshold range cluster acquisition module is used to perform centralized abnormal analysis on the N parameter abnormal value clusters respectively, and determine N abnormal threshold range clusters corresponding to the N templates respectively according to the analysis results, each abnormal threshold range cluster includes P abnormal threshold ranges corresponding to P monitoring parameters;

A monitoring data set acquisition module is used to retrieve a target abnormal threshold range cluster of a target template and extract a monitoring data set of the target mobile formwork bridge-building machine when the target template is used, wherein the monitoring data set includes P target monitoring parameter values;

An over-limit monitoring parameter value set acquisition module is used to perform over-limit detection on the P target monitoring parameter values using the target abnormal threshold range cluster to obtain an over-limit monitoring parameter set and an over-limit monitoring parameter value set;

The control module is used to analyze the over-limit monitoring parameter set and the over-limit monitoring parameter value set by using the control adaptive identifier, generate a target control scheme, and control the target mobile formwork bridge-building machine according to the target control scheme.

One or more technical solutions provided in this application have at least the following technical effects or advantages:

The present application obtains N basic template information of N templates through the template library of the interactive target mobile formwork bridge-building machine, and then uses N template plate parameters and N template structure design information as indexes to search in the historical database and the cloud database respectively to obtain N historical template usage record sets and N cloud template usage record sets, respectively perform consistency evaluation on the N historical template usage record sets, configure N harmonic coefficients based on N consistency factors, and adaptively extract usage records from the N historical template usage record sets and the N cloud template usage record sets according to the N harmonic coefficients to obtain N harmony databases, and then use construction anomalies as indexes to search the N harmony databases to generate N construction abnormality template usage record sets, and perform parameter evaluation on the N construction abnormality template usage record sets according to the preset monitoring parameter set. Numerical extraction, generating N parameter abnormal value clusters, and then performing centralized abnormal analysis on the N parameter abnormal value clusters respectively, and determining the N abnormal threshold range clusters corresponding to the N templates according to the analysis results, each abnormal threshold range cluster includes P abnormal threshold ranges corresponding to P monitoring parameters, calling the target abnormal threshold range cluster of the target template, and extracting the monitoring data set of the target mobile formwork bridge-building machine when using the target template, wherein the monitoring data set includes P target monitoring parameter values, and then using the P abnormal threshold ranges to perform over-limit detection on the P target monitoring parameter values, obtaining the over-limit monitoring parameter set and the over-limit monitoring parameter value set, and analyzing the over-limit monitoring parameter set and the over-limit monitoring parameter value set by using the control adaptive identifier, generating a target control scheme, and controlling the target mobile formwork bridge-building machine according to the target control scheme. The technical effect of improving the control reliability of the mobile formwork bridge-building machine and avoiding over-control or under-control is achieved.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

FIG1 is a schematic flow chart of a monitoring and adaptive control method for a mobile formwork bridge-building machine provided in an embodiment of the present application;

FIG2 is a schematic diagram of the structure of a monitoring and adaptive control device for a mobile formwork bridge-building machine provided in an embodiment of the present application.

Explanation of the accompanying drawings: template basic information acquisition module 11, usage record set acquisition module 12, consistency factor generation module 13, harmony database acquisition module 14, parameter anomaly value cluster generation module 15, abnormal threshold range cluster acquisition module 16, monitoring data set acquisition module 17, out-of-limit monitoring parameter value set acquisition module 18, control module 19.

DETAILED DESCRIPTION

The present application provides a monitoring and adaptive control method and device for a mobile formwork bridge-building machine, which is used to solve the technical problem in the prior art that the basis for monitoring and controlling the mobile formwork bridge-building machine is inaccurate, resulting in reduced bridge-building quality.

The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or server comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products or devices.

Embodiment 1

As shown in FIG1 , the present application provides a monitoring and adaptive control method for a mobile formwork bridge-building machine, wherein the method comprises:

S100: Interacting with the template library of the target mobile formwork bridge-building machine, obtaining N template basic information of N templates, wherein the N template basic information includes N template plate parameters and N template structure design information;

In an embodiment of the present application, the target mobile formwork bridge-building machine is a construction machine that comes with its own formwork and casts bridges on site. The target mobile formwork bridge-building machine is mainly composed of a leg mechanism, internal and external formworks, a main beam lifting mechanism, etc., and can complete a series of construction processes from mobile supports to casting and molding. The template library is a collection of templates for building bridges, and these templates can be used by mobile formwork bridge-building machines to quickly build bridges. Optionally, the templates in the template library are usually designed and manufactured according to the required bridge type and specifications to ensure that a bridge that meets the requirements is built. The templates usually include the main structure templates of the bridge, support templates, templates for pouring concrete, etc. By using the template library, the technical effects of improving construction efficiency, reducing costs, and ensuring the quality and safety of the bridge are achieved.

Basic information of the N templates in the template library is collected to generate N template basic information. The N template basic information is used to describe the structural design of the N templates and the material of the template itself, including N template plate parameters and N template structural design information. The N template plate parameters include plate type, plate size, plate strength, etc. The N template structural design information includes template layout scheme, template connection method, template adjustable design data, etc.

S200: using the N template plate parameters and the N template structure design information as indexes, searching in the historical database and the cloud database respectively to obtain N historical template usage record sets and N cloud template usage record sets;

In a possible embodiment, after obtaining the N template plate parameters and the N template structure design information, the basic situation of the target mobile formwork bridge building machine is mastered. In order to analyze the actual working situation of the mobile formwork bridge building machine, it is necessary to search in the historical database to obtain N historical template usage record sets. The historical database is the work record generated when the target mobile formwork bridge building machine works in the historical time.

In one embodiment, since there are N templates in the template library of the target mobile formwork bridge-building machine, in actual work, there are situations where multiple templates are frequently used and multiple templates are not used. The actual working conditions of the target mobile formwork bridge-building machine are not fully reflected in the historical database, and reliable data support cannot be provided for subsequent monitoring and adaptive regulation. Therefore, it is necessary to use the N template plate parameters and the N template structure design information as indexes to search in the cloud database, so as to obtain N cloud template usage record sets. Among them, the N cloud template usage record sets are the usage records of the N templates of the same model as the target mobile formwork bridge-building machine obtained by big data retrieval. The technical effect of providing rich records of bridge-building machine usage and improving the reliability of analysis data is achieved.

S300: performing consistency evaluation on the N historical template usage record sets respectively to generate N consistency factors;

Further, the N historical template usage record sets are respectively evaluated for consistency to generate N consistency factors. Step S300 of the embodiment of the present application further includes:

According to the preset consistency indicator set, the indicator values of the N historical template usage record sets are respectively extracted to obtain N consistency indicator value clusters, wherein each consistency indicator value cluster includes a maximum design load indicator value set, a template application height indicator value set and a working span indicator value set corresponding to a historical template usage record set;

The N consistency index value clusters are traversed respectively to perform variance fluctuation identification, and N consistency factors are generated according to the identification results.

Furthermore, the preset consistency indicator set includes maximum design load capacity, template application height, and working span.

In one possible embodiment, the N historical template usage record sets in the historical database reflect the conditions of the target mobile formwork bridge-building machine during its historical use. In order to provide data support for the subsequent full analysis of the scope of abnormalities of different monitoring parameters of the target mobile formwork bridge-building machine in actual work, the N historical template usage record sets in the historical database need to have a lower consistency, thereby ensuring a comprehensive analysis of different working conditions of the template, improving the richness of the analysis data, and avoiding local analysis. The N consistency factors are generated by performing consistency evaluation on the N historical template usage record sets. Among them, as the consistency factor increases, the data similarity in the corresponding historical template usage record set also increases, and the quality of the historical template usage record set decreases accordingly.

Optionally, the index values of the N historical template usage record sets are extracted respectively according to the preset consistency index set to obtain N consistency index value clusters, wherein each consistency index value cluster includes a maximum design load capacity index value set, a template application height index value set and a working span index value set corresponding to a historical template usage record set. The preset consistency index set includes the maximum design load capacity, the template application height and the working span.

Optionally, a consistency indicator cluster of the first historical template usage record set is matched from the N consistency indicator clusters, and data is extracted from the consistency indicator cluster according to the maximum design load capacity, template application height, and working span to obtain the first maximum design load capacity indicator set, the first template application height indicator value set, and the first working span indicator value set.

The variances of the first maximum design load capacity indicator set, the first template application height indicator value set, and the first working span indicator value set are calculated respectively to obtain the first maximum design load capacity variance, the first template application height variance, and the first working span variance. Furthermore, according to the weight ratios pre-set by technicians in this field, the first maximum design load capacity variance, the first template application height variance, and the first working span variance are weightedly calculated to generate a consistency factor of the first historical template usage record set. Based on the same principle, the variance fluctuations of the N consistency indicator value clusters are identified respectively, and N consistency factors are generated according to the identification results.

S400: configuring N harmonic coefficients based on the N consistency factors, and adaptively extracting usage records from the N historical template usage record sets and the N cloud template usage record sets according to the N harmonic coefficients, to obtain N harmony databases, wherein each harmony database includes a plurality of historical template usage records and a plurality of cloud template usage records;

Further, N harmonic coefficients are configured based on the N consistency factors, and adaptive extraction of usage records is performed from the N historical template usage record sets and the N cloud template usage record sets according to the N harmonic coefficients to obtain N harmony databases. Step S400 of the embodiment of the present application also includes:

Comparing the N consistency factors with the preset standard consistency factors respectively to obtain N harmonic coefficients;

Multiplying the N harmonic coefficients by a preset extraction amount to obtain N historical extraction amounts;

Determine N cloud extraction amounts based on the N historical extraction amounts and the preset extraction amount;

Based on the N historical extraction amounts and the N cloud extraction amounts, respectively, the N historical template usage record sets and the N cloud template usage record sets are extracted to obtain N initial harmony databases;

The N initial harmony databases are evaluated for consistency, and it is determined whether the N consistency evaluation results are greater than or equal to the preset standard consistency factor. If not, the N initial harmony databases are updated and iterated until the requirements are met to obtain the N harmony databases.

Furthermore, step S400 in the embodiment of the present application further includes:

When the N consistency evaluation results are less than the preset standard consistency factor, N consistency deviations are calculated, wherein the N consistency deviations are calculated by calculating the difference between the N consistency evaluation results and the preset standard consistency factor, and comparing the N differences with the preset standard consistency factor;

Multiplying the N consistency deviations by the preset extraction amount to obtain N adjustment step lengths;

Adaptively adjusting the N historical extraction amounts based on the N adjustment step sizes, extracting usage records according to the adjustment results, and generating N adjusted harmony databases;

Perform consistency evaluation on the N adjusted harmony databases, and continue to update and iterate according to the N adjusted consistency evaluation results until the N adjusted consistency evaluation results of the N adjusted harmony databases are all greater than or equal to the preset standard consistency factor, stop iteration, and obtain the N harmony databases.

In one possible embodiment, the amount of data to be extracted from the N historical template usage record sets is determined according to the size of the N consistency factors to obtain N harmonic coefficients. Further, the usage records are adaptively extracted from the N historical template usage record sets and the N cloud template usage record sets according to the N harmonic coefficients to obtain N harmony databases, wherein each harmony database includes a plurality of historical template usage records and a plurality of cloud template usage records. The goal of enriching the data types in the database by extracting usage records from the cloud database while ensuring the actual working records of the target mobile formwork bridge-building machine is achieved, thereby achieving the technical effect of providing data support for subsequent reliable monitoring and adaptive regulation.

Optionally, the N consistency factors are compared with the preset standard consistency factors respectively to obtain N reconciliation coefficients. The N reconciliation coefficients reflect the degree to which the data richness in the N historical template usage record sets meets the requirements. Among them, the preset standard consistency factor is the minimum consistency factor when the database richness meets the requirements, which is preset by a technician in this field. Then, the N reconciliation coefficients are multiplied by the preset extraction amount to obtain N historical extraction amounts. The preset extraction amount is the amount of data for analysis preset by a technician in this field, which can be 500, 600, 1000, etc.

Then, the preset extraction amount is subtracted from the N historical extraction amounts to obtain the N cloud extraction amounts, wherein the N cloud extraction amounts are the number of usage records extracted from the N cloud template usage record sets.

According to the number of usage records in the N historical extractions and the N cloud extractions, usage record extraction is performed on the N historical template usage record sets and the N cloud template usage record sets to obtain N initial harmony databases.

Furthermore, in order to ensure data reliability, the N initial harmony databases are subjected to consistency evaluation, and it is determined whether the N consistency evaluation results are greater than or equal to the preset standard consistency factor. Thus, the goal of analyzing the quality of the initial harmony database is achieved.

If not, it indicates that the quality of the N initial harmony databases is low, and the historical extraction amount and the cloud extraction amount need to be readjusted, and then the N initial harmony databases are updated and iterated according to the adjustment results until the requirements are met to obtain the N harmony databases.

Optionally, when the N consistency evaluation results are less than the preset standard consistency factor, the difference between the N consistency evaluation results and the preset standard consistency factor is calculated, and the N differences are compared with the preset standard consistency factor to obtain N consistency deviation degrees, wherein the N consistency deviation degrees reflect the degree of difference between the N initial harmony databases and the expected quality requirements.

Then, the N consistency deviations are multiplied by the preset extraction amount to obtain N adjustment steps. The N adjustment steps are the number of reductions or increases from the N historical extraction amounts at a time. The N historical extraction amounts are adaptively adjusted according to the N adjustment steps, and the usage records are extracted according to the adjustment results to generate N adjusted harmony databases. Based on the same consistency evaluation principle as the N historical template usage record set, the N adjusted harmony databases are evaluated for consistency, and the update iteration is continued according to the N adjustment consistency evaluation results until the N adjustment consistency evaluation results of the N adjusted harmony databases are greater than or equal to the preset standard consistency factor, and the iteration is stopped to obtain the N harmony databases.

S500: Retrieve the N harmony databases with construction anomalies as indexes to generate N construction anomaly template usage record sets, and extract parameter values from the N construction anomaly template usage record sets according to a preset monitoring parameter set to generate N parameter anomaly value clusters, wherein the preset monitoring parameter set includes P monitoring parameters, and each parameter anomaly value cluster includes P monitoring parameter anomaly value sets;

In a possible embodiment, the N harmony databases are searched using construction anomalies as indexes to generate N construction anomaly template usage record sets, wherein the N construction anomaly template usage record sets reflect situations where construction anomalies occur when the N templates are used.

And according to the preset monitoring parameter set, the parameter values of the N construction abnormal templates are extracted using the record set to generate N parameter abnormal value clusters, wherein the preset monitoring parameter set includes P monitoring parameters, and each parameter abnormal value cluster includes P monitoring parameter abnormal value sets. Optionally, the preset monitoring parameter set includes parameters such as deformation, load, displacement, etc. of the bridge structure. The N parameter abnormal value clusters reflect the data status of the monitoring parameters of the N templates during construction. The technical effect of providing data support for the subsequent determination of the abnormal threshold range of different monitoring parameters of different templates is achieved.

S600: performing centralized anomaly analysis on the N parameter abnormal value clusters respectively, and determining N abnormal threshold range clusters corresponding to the N templates respectively according to the analysis results, each abnormal threshold range cluster including P abnormal threshold ranges corresponding to P monitoring parameters;

Further, centralized abnormality analysis is performed on the N parameter abnormal value clusters respectively, and N abnormal threshold range clusters corresponding to the N templates are determined according to the analysis results, each abnormal threshold range cluster includes P abnormal threshold ranges corresponding to P monitoring parameters. Step S600 of the embodiment of the present application also includes:

Extracting a first parameter outlier value cluster from the N parameter outlier value clusters, wherein the first parameter outlier value cluster includes P parameter outlier value sets;

Calculate the mean values of the parameter outlier values of the P parameter outlier value sets respectively to obtain the mean values of the P parameter outlier values;

Taking the mean of the P parameter outliers as the center of the P intervals and the preset concentration step length as the interval length, P first parameter concentration intervals and P second parameter concentration intervals are constructed on the left and right sides respectively, wherein the P first parameter concentration intervals have P first parameter concentration coefficients, and the P second parameter concentration intervals have P second parameter concentration coefficients.

Furthermore, step S600 of the embodiment of the present application further includes:

Determine whether the P first parameter concentration coefficients are greater than the P second parameter concentration coefficients. If so, update the left endpoints of the P first parameter concentration intervals to the P interval centers, and construct P stage parameter concentration intervals to the left of the interval centers;

Determine whether the difference between the P stage parameter concentration coefficients of the P stage parameter concentration intervals and the P first parameter concentration coefficients meets the preset gain, and if so, update the left endpoint of the P stage parameter concentration intervals to the P interval centers;

If not, stop updating, and generate P abnormal threshold ranges according to the left endpoint of the stage parameter concentration interval on the left side of the center of the P intervals and the stage parameter concentration interval on the right side;

Taking the P abnormal threshold ranges as a first abnormal threshold range cluster;

Centralized anomaly analysis is performed on the N parameter outlier value clusters to obtain N anomaly threshold range clusters.

In one possible embodiment, the ranges where the parameter abnormal values are densely distributed in the N parameter abnormal value clusters are analyzed, and N abnormal threshold range clusters corresponding to the N templates are determined according to the analysis results, and each abnormal threshold range cluster includes P abnormal threshold ranges corresponding to P monitoring parameters. The technical effect of providing a reliable basis for the subsequent abnormal identification of monitoring data when working with N templates is achieved.

In an embodiment of the present application, a first parameter outlier cluster is extracted from the N parameter outlier clusters, wherein the first parameter outlier cluster includes P parameter outlier sets. Then, the parameter outlier means of the P parameter outlier sets are calculated respectively to obtain the P parameter outlier means. The P parameter outlier means reflect the average level of the P parameter outlier sets.

Furthermore, with the mean of the P parameter outliers as the P interval centers and the preset concentration step length as the interval length, P first parameter concentration intervals and P second parameter concentration intervals are constructed to the left and right sides of the P interval centers, respectively, wherein the P first parameter concentration intervals have P first parameter concentration coefficients, and the P second parameter concentration intervals have P second parameter concentration coefficients. The preset concentration step length is the value range size when a technician in this field performs concentrated anomaly analysis.

Optionally, the number of parameter outliers in the P first parameter concentration intervals is counted, and the statistical result is compared with the preset concentration step length to obtain the P first parameter concentration coefficients. The P first parameter concentration coefficients reflect the density of parameter distribution in the P first parameter concentration intervals. Based on the same principle, the concentration coefficient analysis is performed on the P second parameter concentration intervals to obtain the P second parameter concentration coefficients. The P second parameter concentration coefficients reflect the density of parameter distribution in the P second parameter concentration intervals.

Optionally, determine whether the P first parameter concentration coefficients are greater than the P second parameter concentration coefficients. If so, it indicates that the parameter outlier density distributed on the left side of the P interval centers is greater than the parameter outlier density distributed on the right side. At this time, the left endpoints of the P first parameter concentration intervals are updated to the P interval centers, and P stage parameter concentration intervals are constructed to the left of the interval centers.

Furthermore, it is determined whether the difference between the P stage parameter concentration coefficients of the P stage parameter concentration intervals and the P first parameter concentration coefficients meets the preset gain (the minimum difference for continuing to update set by those skilled in the art). If so, it indicates that the concentrated analysis has not yet reached the interval with a denser distribution, and the left endpoint of the P stage parameter concentration interval is updated to the center of the P intervals.

If not, it indicates that the interval with denser distribution has been reached, and the update is stopped. P abnormal threshold ranges are generated according to the left endpoint of the stage parameter concentration interval on the left side of the center of the P intervals and the stage parameter concentration interval on the right side. Among them, the P abnormal threshold ranges are the parameter range values for the P monitoring parameters that need abnormal warning. The P abnormal threshold ranges are used as the first abnormal threshold range cluster. Optionally, according to the same principle as obtaining the first abnormal threshold range cluster, the N parameter abnormal value clusters are subjected to centralized abnormal analysis to obtain N abnormal threshold range clusters.

S700: Retrieve a target abnormal threshold range cluster of a target template, and extract a monitoring data set of the target mobile formwork bridge-building machine when the target template is used, wherein the monitoring data set includes P target monitoring parameter values;

In one embodiment, the target template is the template currently used by the target mobile formwork bridge-building machine, and the target abnormal threshold range cluster of the target template is retrieved from the N abnormal threshold range clusters. The monitoring data of the monitoring sensor array (including bridge structure deformation sensors, load sensors, displacement sensors, etc.) of the target mobile formwork bridge-building machine is extracted to obtain the monitoring data set. The monitoring data set includes P target monitoring parameter values. The P target detection parameter values reflect the construction status of the target mobile formwork bridge-building machine when it is working using the target template.

S800: Performing over-limit detection on the P target monitoring parameter values using the target abnormal threshold range cluster to obtain an over-limit monitoring parameter set and an over-limit monitoring parameter value set;

S900: Analyze the over-limit monitoring parameter set and the over-limit monitoring parameter value set using a control adaptive identifier to generate a target control scheme, and control the target mobile formwork bridge-building machine according to the target control scheme.

In a possible embodiment, the target abnormal threshold range cluster is used to perform over-limit detection on the P target monitoring parameter values, and the target detection parameter values that do not meet the target abnormal threshold range cluster are added to the over-limit monitoring parameter value set. Then, the monitoring parameters corresponding to the over-limit monitoring parameter value set are added to the over-limit monitoring parameter set.

Optionally, the over-limit monitoring parameter set and the over-limit monitoring parameter value set are input into the control adaptive identifier for analysis, and a target control scheme is generated, and the target mobile formwork bridge-building machine is controlled according to the target control scheme. The target control scheme is a scheme for adjusting the working parameters of the target mobile formwork bridge-building machine, including control parameters (formwork position adjustment, formwork angle and working intensity, etc.) and control parameter values (mold position adjustment movement value, formwork angle adjustment value, working intensity adjustment value, etc.).

Optionally, multiple sample overrun monitoring parameter sets and multiple sample overrun monitoring parameter value sets, as well as multiple sample target control schemes are obtained as training data, and supervised training is performed on the framework constructed by the convolutional neural network. During the training, the mapping relationship between the overrun monitoring parameters and the overrun monitoring parameter values and the control schemes is learned until the model output reaches convergence, and the trained control adaptive identifier is obtained. The control adaptive identifier is a functional device for identifying and controlling the working state of the target mobile formwork bridge-building machine.

In summary, the embodiments of the present application have at least the following technical effects:

The present application uses the template library of the interactive target mobile formwork bridge-building machine to master the N basic template information of the N templates, and then searches the historical database and the cloud database respectively to obtain N historical template usage record sets and N cloud template usage record sets, thereby achieving the goal of paving the way for the subsequent construction of a harmony database, and respectively evaluating the consistency of the N historical template usage record sets, and adaptively extracting usage records from the N historical template usage record sets and the N cloud template usage record sets according to the N harmonic coefficients to obtain N harmony databases, thereby achieving the goal of improving the quality of analysis data, and according to the preset monitoring parameters, The data set extracts parameter values from the N construction abnormal template usage record set, generates N parameter abnormal value clusters, and performs centralized abnormal analysis to determine the N abnormal threshold range clusters corresponding to the N templates, retrieve the target abnormal threshold range cluster of the target template, and extract the monitoring data set of the target mobile formwork bridge-building machine when using the target template. Then, the P abnormal threshold ranges are used to perform over-limit detection on the P target monitoring parameter values, and the over-limit monitoring parameter set and the over-limit monitoring parameter value set are obtained. The target control scheme is generated by analyzing the control adaptive identifier, and the target mobile formwork bridge-building machine is controlled according to the target control scheme. The technical effect of improving the control reliability of the mobile formwork bridge-building machine and avoiding excessive or insufficient control is achieved.

Embodiment 2

Based on the same inventive concept as the monitoring and adaptive control method of a mobile formwork bridge-building machine in the aforementioned embodiment, as shown in FIG2 , the present application provides a monitoring and adaptive control device for a mobile formwork bridge-building machine, and the device and method embodiments in the embodiments of the present application are based on the same inventive concept. The device includes:

The template basic information acquisition module 11 is used to interact with the template library of the target mobile formwork bridge-building machine to obtain N template basic information of N templates, wherein the N template basic information includes N template plate parameters and N template structure design information;

A usage record set obtaining module 12 is used to retrieve N historical template usage record sets and N cloud template usage record sets respectively by using the N template plate material parameters and the N template structure design information as indexes;

A consistency factor generating module 13, used to perform consistency evaluation on the N historical template usage record sets respectively to generate N consistency factors;

A harmony database acquisition module 14 is used to configure N harmonic coefficients based on the N consistency factors, and adaptively extract usage records from the N historical template usage record sets and the N cloud template usage record sets according to the N harmonic coefficients to obtain N harmony databases, wherein each harmony database includes multiple historical template usage records and multiple cloud template usage records;

The parameter abnormal value cluster generation module 15 is used to search the N harmony databases with construction abnormality as an index, generate N construction abnormality template usage record sets, and extract parameter values from the N construction abnormality template usage record sets according to a preset monitoring parameter set to generate N parameter abnormal value clusters, wherein the preset monitoring parameter set includes P monitoring parameters, and each parameter abnormal value cluster includes P monitoring parameter abnormal value sets;

The abnormal threshold range cluster acquisition module 16 is used to perform centralized abnormal analysis on the N parameter abnormal value clusters respectively, and determine N abnormal threshold range clusters corresponding to the N templates respectively according to the analysis results, each abnormal threshold range cluster includes P abnormal threshold ranges corresponding to P monitoring parameters;

The monitoring data set acquisition module 17 is used to retrieve the target abnormal threshold range cluster of the target template and extract the monitoring data set of the target mobile formwork bridge-building machine when working with the target template, wherein the monitoring data set includes P target monitoring parameter values;

An over-limit monitoring parameter value set obtaining module 18 is used to perform over-limit detection on the P target monitoring parameter values using the target abnormal threshold range cluster to obtain an over-limit monitoring parameter set and an over-limit monitoring parameter value set;

The control module 19 is used to analyze the over-limit monitoring parameter set and the over-limit monitoring parameter value set by using the control adaptive identifier, generate a target control scheme, and control the target mobile formwork bridge-building machine according to the target control scheme.

Furthermore, the consistency factor generation module 13 is used to perform the following steps:

According to the preset consistency indicator set, the indicator values of the N historical template usage record sets are respectively extracted to obtain N consistency indicator value clusters, wherein each consistency indicator value cluster includes a maximum design load indicator value set, a template application height indicator value set and a working span indicator value set corresponding to a historical template usage record set;

The N consistency index value clusters are traversed respectively to perform variance fluctuation identification, and N consistency factors are generated according to the identification results.

Furthermore, the preset consistency indicator set includes maximum design load capacity, template application height, and working span.

Furthermore, the harmony database obtaining module 14 is used to perform the following steps:

Comparing the N consistency factors with the preset standard consistency factors respectively to obtain N harmonic coefficients;

Multiplying the N harmonic coefficients by a preset extraction amount to obtain N historical extraction amounts;

Determine N cloud extraction amounts based on the N historical extraction amounts and the preset extraction amount;

Based on the N historical extraction amounts and the N cloud extraction amounts, respectively, the N historical template usage record sets and the N cloud template usage record sets are extracted to obtain N initial harmony databases;

The N initial harmony databases are evaluated for consistency, and it is determined whether the N consistency evaluation results are greater than or equal to the preset standard consistency factor. If not, the N initial harmony databases are updated and iterated until the requirements are met to obtain the N harmony databases.

Furthermore, the harmony database obtaining module 14 is used to perform the following steps:

When the N consistency evaluation results are less than the preset standard consistency factor, N consistency deviations are calculated, wherein the N consistency deviations are calculated by calculating the difference between the N consistency evaluation results and the preset standard consistency factor, and comparing the N differences with the preset standard consistency factor;

Multiplying the N consistency deviations by the preset extraction amount to obtain N adjustment step lengths;

Adaptively adjusting the N historical extraction amounts based on the N adjustment step sizes, extracting usage records according to the adjustment results, and generating N adjusted harmony databases;

Perform consistency evaluation on the N adjusted harmony databases, and continue to update and iterate according to the N adjusted consistency evaluation results until the N adjusted consistency evaluation results of the N adjusted harmony databases are all greater than or equal to the preset standard consistency factor, stop iteration, and obtain the N harmony databases.

Furthermore, the abnormal threshold range cluster acquisition module 16 is used to perform the following steps:

Extracting a first parameter outlier value cluster from the N parameter outlier value clusters, wherein the first parameter outlier value cluster includes P parameter outlier value sets;

Calculate the mean values of the parameter outlier values of the P parameter outlier value sets respectively to obtain the mean values of the P parameter outlier values;

Taking the mean of the P parameter outliers as the center of the P intervals and the preset concentration step length as the interval length, P first parameter concentration intervals and P second parameter concentration intervals are constructed on the left and right sides respectively, wherein the P first parameter concentration intervals have P first parameter concentration coefficients, and the P second parameter concentration intervals have P second parameter concentration coefficients.

Furthermore, the abnormal threshold range cluster acquisition module 16 is used to perform the following steps:

Determine whether the P first parameter concentration coefficients are greater than the P second parameter concentration coefficients. If so, update the left endpoints of the P first parameter concentration intervals to the P interval centers, and construct P stage parameter concentration intervals to the left of the interval centers;

Determine whether the difference between the P stage parameter concentration coefficients of the P stage parameter concentration intervals and the P first parameter concentration coefficients meets the preset gain, and if so, update the left endpoint of the P stage parameter concentration intervals to the P interval centers;

If not, stop updating, and generate P abnormal threshold ranges according to the left endpoint of the stage parameter concentration interval on the left side of the center of the P intervals and the stage parameter concentration interval on the right side;

Taking the P abnormal threshold ranges as a first abnormal threshold range cluster;

Centralized anomaly analysis is performed on the N parameter outlier value clusters to obtain N anomaly threshold range clusters.

It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims (8)

1. A monitoring and adaptive control method for a mobile formwork bridge-building machine, characterized in that the method comprises: Interact with the template library of the target mobile formwork bridge-building machine to obtain N template basic information of the N templates, wherein the N template basic information includes N template plate parameters and N template structure design information; Using the N template plate parameters and the N template structure design information as indexes, searching in the historical database and the cloud database respectively, to obtain N historical template usage record sets and N cloud template usage record sets; Performing consistency evaluation on the N historical template usage record sets respectively to generate N consistency factors; Based on the N consistency factors, N harmonic coefficients are configured, and according to the N harmonic coefficients, usage records are adaptively extracted from the N historical template usage record sets and the N cloud template usage record sets, respectively, to obtain N harmony databases, wherein each harmony database includes a plurality of historical template usage records and a plurality of cloud template usage records; The N harmony databases are searched with construction anomalies as indexes to generate N construction anomaly template usage record sets, and parameter values are extracted from the N construction anomaly template usage record sets according to a preset monitoring parameter set to generate N parameter anomaly value clusters, wherein the preset monitoring parameter set includes P monitoring parameters, and each parameter anomaly value cluster includes P monitoring parameter anomaly value sets; Performing centralized anomaly analysis on the N parameter anomaly value clusters respectively, and determining N anomaly threshold range clusters corresponding to the N templates respectively according to the analysis results, each anomaly threshold range cluster including P anomaly threshold ranges corresponding to P monitoring parameters; Retrieve the target abnormal threshold range cluster of the target template, and extract the monitoring data set of the target mobile formwork bridge-building machine when working with the target template, wherein the monitoring data set includes P target monitoring parameter values; Using the target abnormal threshold range cluster, perform over-limit detection on the P target monitoring parameter values to obtain an over-limit monitoring parameter set and an over-limit monitoring parameter value set; The over-limit monitoring parameter set and the over-limit monitoring parameter value set are analyzed by using a control adaptive identifier to generate a target control scheme, and the target mobile formwork bridge-building machine is controlled according to the target control scheme, wherein the control adaptive identifier includes: obtaining multiple sample over-limit monitoring parameter sets and multiple sample over-limit monitoring parameter value sets, and multiple sample target control schemes as training data, and performing supervised training on the framework constructed by the convolutional neural network. During the training, the mapping relationship between the over-limit monitoring parameters and the over-limit monitoring parameter values and the control schemes is learned until the model output converges, thereby obtaining the trained control adaptive identifier. 2. The method according to claim 1, characterized in that the consistency evaluation is performed on the N historical template usage record sets respectively to generate N consistency factors, and the method comprises: According to the preset consistency indicator set, the indicator values of the N historical template usage record sets are respectively extracted to obtain N consistency indicator value clusters, wherein each consistency indicator value cluster includes a maximum design load indicator value set, a template application height indicator value set and a working span indicator value set corresponding to a historical template usage record set; The N consistency index value clusters are traversed respectively to perform variance fluctuation identification, and N consistency factors are generated according to the identification results. 3. The method as claimed in claim 2 is characterized in that the preset consistency indicator set includes maximum design load capacity, template application height, and working span. 4. The method according to claim 1, characterized in that N harmonic coefficients are configured based on the N consistency factors, and adaptive extraction of usage records is performed from the N historical template usage record sets and the N cloud template usage record sets according to the N harmonic coefficients to obtain N harmony databases, the method comprising: Comparing the N consistency factors with the preset standard consistency factors respectively to obtain N harmonic coefficients; Multiplying the N harmonic coefficients by a preset extraction amount to obtain N historical extraction amounts; Determine N cloud extraction amounts based on the N historical extraction amounts and the preset extraction amount; Based on the N historical extraction amounts and the N cloud extraction amounts, respectively, the N historical template usage record sets and the N cloud template usage record sets are extracted to obtain N initial harmony databases; The N initial harmony databases are evaluated for consistency, and it is determined whether the N consistency evaluation results are greater than or equal to the preset standard consistency factor. If not, the N initial harmony databases are updated and iterated until the requirements are met to obtain the N harmony databases. 5. The method according to claim 4, characterized in that the method comprises: When the N consistency evaluation results are less than the preset standard consistency factor, N consistency deviations are calculated, wherein the N consistency deviations are calculated by calculating the difference between the N consistency evaluation results and the preset standard consistency factor, and comparing the N differences with the preset standard consistency factor; Multiplying the N consistency deviations by the preset extraction amount to obtain N adjustment step lengths; Adaptively adjusting the N historical extraction amounts based on the N adjustment step sizes, extracting usage records according to the adjustment results, and generating N adjusted harmony databases; Perform consistency evaluation on the N adjusted harmony databases, and continue to update and iterate according to the N adjusted consistency evaluation results until the N adjusted consistency evaluation results of the N adjusted harmony databases are all greater than or equal to the preset standard consistency factor, stop iteration, and obtain the N harmony databases. 6. The method according to claim 1, characterized in that the N parameter abnormal value clusters are respectively subjected to centralized abnormal analysis, and N abnormal threshold range clusters corresponding to the N templates are determined according to the analysis results, each abnormal threshold range cluster includes P abnormal threshold ranges corresponding to P monitoring parameters, and the method comprises: Extracting a first parameter outlier value cluster from the N parameter outlier value clusters, wherein the first parameter outlier value cluster includes P parameter outlier value sets; Calculate the mean values of the parameter outlier values of the P parameter outlier value sets respectively to obtain the mean values of the P parameter outlier values; Taking the mean of the P parameter outliers as the center of the P intervals and the preset concentration step length as the interval length, P first parameter concentration intervals and P second parameter concentration intervals are constructed on the left and right sides respectively, wherein the P first parameter concentration intervals have P first parameter concentration coefficients, and the P second parameter concentration intervals have P second parameter concentration coefficients. 7. The method according to claim 6, characterized in that the method comprises: Determine whether the P first parameter concentration coefficients are greater than the P second parameter concentration coefficients. If so, update the left endpoints of the P first parameter concentration intervals to the P interval centers, and construct P stage parameter concentration intervals to the left of the interval centers; Determine whether the difference between the P stage parameter concentration coefficients of the P stage parameter concentration intervals and the P first parameter concentration coefficients meets the preset gain, and if so, update the left endpoint of the P stage parameter concentration intervals to the P interval centers; If not, stop updating, and generate P abnormal threshold ranges according to the left endpoint of the stage parameter concentration interval on the left side of the center of the P intervals and the stage parameter concentration interval on the right side; Taking the P abnormal threshold ranges as a first abnormal threshold range cluster; Centralized anomaly analysis is performed on the N parameter outlier value clusters to obtain N anomaly threshold range clusters. 8. A monitoring and adaptive control device for a mobile formwork bridge-building machine, characterized in that the device comprises: A template basic information acquisition module is used to interact with the template library of the target mobile formwork bridge-building machine to obtain N template basic information of N templates, wherein the N template basic information includes N template plate parameters and N template structure design information; A usage record set acquisition module, used to use the N template plate parameters and the N template structure design information as indexes, to search in the historical database and the cloud database respectively, to obtain N historical template usage record sets and N cloud template usage record sets; A consistency factor generation module, used to perform consistency evaluation on the N historical template usage record sets respectively to generate N consistency factors; A harmony database acquisition module, configured to configure N harmonic coefficients based on the N consistency factors, and adaptively extract usage records from the N historical template usage record sets and the N cloud template usage record sets according to the N harmonic coefficients, to obtain N harmony databases, wherein each harmony database includes a plurality of historical template usage records and a plurality of cloud template usage records; A parameter abnormal value cluster generation module is used to search the N harmony databases with construction abnormalities as indexes to generate N construction abnormality template usage record sets, and extract parameter values from the N construction abnormality template usage record sets according to a preset monitoring parameter set to generate N parameter abnormal value clusters, wherein the preset monitoring parameter set includes P monitoring parameters, and each parameter abnormal value cluster includes P monitoring parameter abnormal value sets; An abnormal threshold range cluster acquisition module is used to perform centralized abnormal analysis on the N parameter abnormal value clusters respectively, and determine N abnormal threshold range clusters corresponding to the N templates respectively according to the analysis results, each abnormal threshold range cluster includes P abnormal threshold ranges corresponding to P monitoring parameters; A monitoring data set acquisition module is used to retrieve a target abnormal threshold range cluster of a target template and extract a monitoring data set of the target mobile formwork bridge-building machine when the target template is used, wherein the monitoring data set includes P target monitoring parameter values; An over-limit monitoring parameter value set acquisition module is used to perform over-limit detection on the P target monitoring parameter values using the target abnormal threshold range cluster to obtain an over-limit monitoring parameter set and an over-limit monitoring parameter value set; A control module is used to use a control adaptive identifier to analyze the over-limit monitoring parameter set and the over-limit monitoring parameter value set, generate a target control scheme, and control the target mobile formwork bridge-building machine according to the target control scheme, wherein the control adaptive identifier includes: obtaining multiple sample over-limit monitoring parameter sets and multiple sample over-limit monitoring parameter value sets, and multiple sample target control schemes as training data, and performing supervised training on the framework constructed by the convolutional neural network. During the training, the mapping relationship between the over-limit monitoring parameters and the over-limit monitoring parameter values and the control schemes is learned until the model output converges, thereby obtaining the trained control adaptive identifier.