CN120725975A - Steel structure defect recognition system and method based on image analysis - Google Patents

Steel structure defect recognition system and method based on image analysis

Info

Publication number
CN120725975A
CN120725975A CN202510801261.1A CN202510801261A CN120725975A CN 120725975 A CN120725975 A CN 120725975A CN 202510801261 A CN202510801261 A CN 202510801261A CN 120725975 A CN120725975 A CN 120725975A
Authority
CN
China
Prior art keywords
image
steel structure
area
image data
region
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202510801261.1A
Other languages
Chinese (zh)
Other versions
CN120725975B (en
Inventor
王佳平
赵剑
吴杰
秦佳星
季冰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changshu Fengfan Power Equipment Co ltd
Original Assignee
Changshu Fengfan Power Equipment Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Changshu Fengfan Power Equipment Co ltd filed Critical Changshu Fengfan Power Equipment Co ltd
Priority to CN202510801261.1A priority Critical patent/CN120725975B/en
Publication of CN120725975A publication Critical patent/CN120725975A/en
Application granted granted Critical
Publication of CN120725975B publication Critical patent/CN120725975B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30136—Metal
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Multimedia (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Image Processing (AREA)

Abstract

本发明涉及钢结构图像分析技术领域，且公开了基于图像分析的钢结构缺陷识别系统及方法，包括数据获取模块、图像数据分析模块和钢结构缺陷识别判断模块，数据获取模块包括区域划分单元和图像数据获取单元。该系统通过获取钢结构在进行超声检测后出现的异常点位，并进行区域标注，对清晰的图像进行分析输出对应的区域图像影响系数和局部缺陷影响系数，当局部缺陷影响系数超出局部缺陷阈值时，进行预警，当局部缺陷影响系数未超出局部缺陷阈值时，对整体图像数据进行分析，基于整体图像缺陷系数判断是否进行预警，从而能够快速准确地完成钢结构表面缺陷的识别，避免了对整体图像分析导致的无需检测的区域占用设备算力的情况，缩短了检测时间。

The present invention relates to the technical field of steel structure image analysis, and discloses a steel structure defect recognition system and method based on image analysis, including a data acquisition module, an image data analysis module and a steel structure defect recognition and judgment module, wherein the data acquisition module includes a region division unit and an image data acquisition unit. The system obtains abnormal points that appear on the steel structure after ultrasonic testing, and performs regional annotation, analyzes the clear image and outputs the corresponding regional image influence coefficient and local defect influence coefficient. When the local defect influence coefficient exceeds the local defect threshold, an early warning is issued. When the local defect influence coefficient does not exceed the local defect threshold, the overall image data is analyzed, and whether to issue an early warning is determined based on the overall image defect coefficient. This system can quickly and accurately complete the identification of surface defects of the steel structure, avoid the situation where the area that does not need to be detected due to the overall image analysis occupies the equipment computing power, and shorten the detection time.

Description

Steel structure defect identification system and method based on image analysis
Technical Field
The invention relates to the technical field of steel structure image analysis, in particular to a steel structure defect identification system and method based on image analysis.
Background
Steel structure image recognition is of great importance in the engineering and manufacturing fields. The steel structure image recognition can be used for detecting surface defects, cracks, deformation and other problems, and helps to control quality and repair in time, so that the safety and reliability of the steel structure are ensured. Through the image recognition technology, the automatic detection and recognition of the steel structure parts can be realized, the production efficiency and the product quality are improved, and the method can be used for positioning and recognition in the automatic assembly process, and can be used for monitoring the steel structure in real time and finding and recognizing potential problems in time, so that the maintenance and overhaul can be performed in advance, the service life of equipment is prolonged, and the maintenance cost is reduced;
However, the existing image recognition technology is to judge and analyze the whole image of the steel structure, and the situation of misjudgment can be generated because the local definition degree of the main steel structure in the acquired image is lower due to the limited width of the longer steel structure;
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a steel structure defect identification system and method based on image analysis, which have the advantages of quickly and accurately identifying defects and the like, and solve the technical problems.
In order to achieve the aim, the invention provides the technical scheme that the steel structure defect identification system based on image analysis comprises a data acquisition module, an image data analysis module and a steel structure defect identification judgment module;
the data acquisition module comprises a region dividing unit and an image data acquisition unit, wherein the region labeling unit is used for acquiring abnormal points of the steel structure after ultrasonic detection, labeling the regions and transmitting the divided regions to the image data acquisition unit, and the image data acquisition unit is used for acquiring the image data of each region of the steel structure and the whole image data of the steel structure labeled in the region labeling unit;
the image data analysis module comprises an image blurring degree analysis unit, a region image analysis unit and an integral image analysis unit, wherein the image blurring degree analysis unit is used for analyzing the image data of each region of the steel structure in the image data acquisition unit, giving out a definition coefficient of each region, determining whether to re-shoot a region corresponding to the region based on the definition coefficient of each region, and the region image analysis unit is used for carrying out secondary analysis on the judged region and outputting a corresponding region image influence coefficient;
The steel structure defect identification judging module comprehensively calculates the steel structure to be detected based on all regional image influence coefficients to finally obtain a local defect influence coefficient, when the local defect influence coefficient exceeds a local defect threshold value, early warning is carried out, when the local defect influence coefficient does not exceed the local defect threshold value, the whole image analysis unit in the image data analysis module is called, the whole image data is analyzed, the whole image defect coefficient is output, and the steel structure defect identification judging module judges whether early warning is carried out or not based on the whole image defect coefficient.
As a preferred technical solution of the present invention, the specific expression of the image data obtaining unit for obtaining the image data of each region of the steel structure marked in the region marking unit is as follows:
TXSJ=[TSXJ1,…,TSXJi,…,TSXJI]
Wherein TXSJ denotes the region image dataset, TSXJ 1,…,TSXJi,…,TSXJI represent image data of the 1 st region,..+ -. Image data of the I th region, I is epsilon [1, I ], and the image data of the ith area is shot and acquired by the mobile shooting equipment.
As a preferred technical solution of the present invention, the image blur degree analysis unit is configured to analyze the image data of each region of the steel structure in the image data acquisition unit, and provide a sharpness coefficient of each region, and determine whether to re-photograph the corresponding region based on the sharpness coefficient of each region, where the specific steps are as follows:
a1, acquiring a shooting factor PSYZ i of shooting in an ith area;
A2, acquiring an image factor GRYZ i shot by an ith area;
And step A3, comprehensively calculating a definition coefficient QXXS i of the ith area, wherein the specific expression is as follows:
QXXSi＝ω1*WJFSYZi+ω2*GRYZi
wherein ω 1 and ω 2 represent two weight coefficients summed to 1, respectively;
And step A4, judging whether the definition coefficient QXXS i of the ith area exceeds a definition threshold, if so, terminating the step A4, sending the image data TSXJ i of the ith area to an area image analysis unit, if not, re-shooting, setting the number of re-shooting of the ith area to be CP i =N, wherein N represents the execution number of the step A4, and when the number of re-shooting of the ith area to be CP i exceeds the maximum number of re-shooting.
As a preferable technical scheme of the invention, the data acquisition module also stores a proportion set of black areas after the steel structure original image of each area is subjected to graying treatment;
the specific steps for acquiring the shooting factor PSYZ i of the ith area shooting in the step A1 are as follows:
A1.1, reading the image data TSXj i of the ith area, and performing binarization processing on the image data TSXJ i of the ith area;
Step A1.2, obtaining the proportion MJZB i of all black areas of the ith area, and calculating the shooting factor PSYZ i of the shooting of the ith area, wherein the specific expression is as follows:
Where, | MJZB i-MJZBi,0 | denotes an absolute value of MJZB i-MJZBi,0, MJZB i,0 denotes a proportion of a black region of the i-th region stored in the set of the ratios, and MJZB i denotes a proportion of a black region of the i-th region.
As a preferred technical solution of the present invention, the specific steps for obtaining the image factor GRYZ i captured by the ith area in the step A2 are as follows:
Step A2.1, reading shaking times DDCS i of the mobile shooting device when shooting an ith area;
And step A2.2, calculating an image factor GRYZ i shot by the ith area, wherein the specific expression is as follows:
Where e denotes a natural constant, DDCS i denotes the number of times the mobile photographing apparatus shakes when photographing the i-th region, and σ denotes the number of balance factors avoiding the denominator being 0.
As a preferred technical solution of the present invention, the specific steps of the area image analysis unit for performing secondary analysis on the determined area and outputting the corresponding area image influence coefficient are as follows:
Step B1, reading image data TSXJ i of the ith area, cutting the image, and only reserving a steel structure area;
Step B2, recognizing the surface of the steel structure, and carrying out gray-scale treatment on the image data TSXJ i of the ith area;
Step B3, identifying all the pixel points in the non-black areas in the step B2, and clustering the adjacent non-black pixel points to obtain a plurality of clustered areas;
step B4, obtaining the area JX j of the minimum rectangular outline and the area YX j of the minimum closed circle outline of the jth clustering area;
Step B5, judging whether the smaller area of the minimum rectangular outline of the jth clustering area JX j and the minimum closed circle outline area YX j exceeds an area threshold value, judging the jth+1th clustering area if the smaller area is not exceeded, and storing the smaller area until all the clustering areas are judged to be completed, and calculating to obtain an area image influence coefficient QYYXXS i of the ith area, wherein the specific expression is as follows:
Wherein min { JX j,YXj } represents the smaller one of the area JX j of the smallest rectangular outline and the area YX j of the smallest closed circle outline of the jth cluster region, QYYXXS i represents the region image influence coefficient of the ith region, ZMJ represents the total area of the image after clipping, Representing the sum of the contour areas of the total J cluster region outputs, j.epsilon.1, J.
As a preferable technical scheme of the invention, the steel structure defect identification judging module carries out comprehensive calculation on the steel structure to be detected based on all the regional image influence coefficients to finally obtain the specific expression of the local defect influence coefficient as follows:
wherein JBQX denotes a local defect influence coefficient, Representing the summation of the region image influence coefficients for a total of I regions, I e 1, I.
As a preferred technical solution of the present invention, the step of analyzing the whole image data and outputting the defect coefficient of the whole image by the whole image analysis unit is as follows:
Step C1, acquiring integral image data of a steel structure, and respectively acquiring lengths of two sides of the steel structure;
and step C2, calculating a defect coefficient CYZ of the whole image of the steel structure, wherein the concrete expression is as follows:
Wherein, l a and l b respectively represent lengths of different sides of the steel structure, CYZ represents an integral image defect coefficient of the steel structure, and l a-lb represents an absolute value of l a-lb.
As a preferable technical scheme of the invention, the steel structure defect identification judging module judges whether to perform early warning based on the integral image defect coefficient, wherein the specific steps are that early warning is performed when the integral image defect coefficient CYZ of the steel structure exceeds the integral judgment threshold delta, and early warning is not performed when the integral image defect coefficient CYZ of the steel structure does not exceed the integral judgment threshold delta.
The invention also provides a steel structure defect identification method based on image analysis, which is based on the steel structure defect identification system based on image analysis and comprises the following steps:
step one, obtaining abnormal points of a steel structure after ultrasonic detection and marking areas;
Acquiring image data of each region of the marked steel structure and integral image data of the steel structure;
Analyzing the image data of each region of the steel structure, giving out the definition coefficient of each region, and determining whether to re-shoot the corresponding region based on the definition coefficient of each region;
Performing secondary analysis on the judged area and outputting a corresponding area image influence coefficient;
comprehensively calculating the steel structure to be detected based on all the regional image influence coefficients to finally obtain a local defect influence coefficient;
And step six, early warning is carried out when the local defect influence coefficient exceeds the local defect threshold value, and when the local defect influence coefficient does not exceed the local defect threshold value, the whole image data is analyzed, the whole image defect coefficient is output, and meanwhile, whether early warning is carried out or not is judged based on the whole image defect coefficient.
Compared with the prior art, the invention provides a steel structure defect identification system and method based on image analysis, which have the following beneficial effects:
According to the invention, the abnormal point positions of the steel structure after ultrasonic detection are obtained, region labeling is carried out, image shooting is carried out on the labeled regions, the definition coefficient of each region is given, whether the region corresponding to the region is re-shot or not is determined based on the definition coefficient of each region, the image influence coefficient and the local defect influence coefficient of the region corresponding to the region are analyzed and output, when the local defect influence coefficient exceeds the local defect threshold value, early warning is carried out, when the local defect influence coefficient does not exceed the local defect threshold value, the whole image data is analyzed, and whether early warning is carried out is judged based on the whole image defect coefficient, so that the recognition of the surface defects of the steel structure can be rapidly and accurately completed, the condition that the region which is not required to be detected and is caused by the whole image analysis occupies equipment calculation force is avoided, and the detection time is shortened.
Drawings
FIG. 1 is a schematic diagram of a system framework of the present invention;
FIG. 2 is a flow chart of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the steel structure defect recognition system based on image analysis includes a data acquisition module, an image data analysis module and a steel structure defect recognition judgment module;
The data acquisition module comprises a region dividing unit and an image data acquisition unit, wherein the region labeling unit is used for acquiring abnormal points of the steel structure after ultrasonic detection, labeling the regions and transmitting the divided regions to the image data acquisition unit, the image data acquisition unit is used for acquiring image data of each region of the steel structure labeled in the region labeling unit and integral image data of the steel structure, and the image data acquisition unit is used for acquiring the specific expression of the image data of each region of the steel structure labeled in the region labeling unit as follows:
TXSJ=[TSXJ1,…,TSXJi,…,TSXJI]
Wherein TXSJ represents an area image dataset, TSXJ 1,…,TSXJi,…,TSXJI represents image data of a1 st area, & gt, image data of an I th area, I epsilon [1, I ], and the image data of the I th area is photographed by a mobile photographing device, wherein the mobile photographing device can be a crawling robot or an unmanned aerial vehicle, and the image can be photographed after stabilization because the distance of a specific abnormal point is given by ultrasonic detection, and the crawling robot or the unmanned aerial vehicle can move to a target point position;
the image data analysis module comprises an image blurring degree analysis unit, a region image analysis unit and an integral image analysis unit, wherein the image blurring degree analysis unit is used for analyzing the image data of each region of the steel structure in the image data acquisition unit, giving out a definition coefficient of each region, determining whether to re-shoot the corresponding region or not based on the definition coefficient of each region, and the region image analysis unit is used for carrying out secondary analysis on the judged region and outputting a corresponding region image influence coefficient;
The image blurring degree analysis unit is used for analyzing the image data of each region of the steel structure in the image data acquisition unit, giving out the definition coefficient of each region, and determining whether to re-shoot the corresponding region based on the definition coefficient of each region, wherein the specific steps are as follows:
a1, acquiring a shooting factor PSYZ i of shooting in an ith area;
the specific steps for acquiring the shooting factor PSYZ i of the ith area shooting in the step A1 are as follows:
A1.1, reading the image data TSXJ i of the ith area, and performing binarization processing on the image data TSXJ i of the ith area;
Step A1.2, obtaining the proportion MJZB i of all black areas of the ith area, and calculating the shooting factor PSYZ i of the shooting of the ith area, wherein the specific expression is as follows:
Where, | MJZB i-MJZBi,0 | denotes an absolute value of MJZB i-MJZBi,0, MJZB i,0 denotes a proportion of a black region of the i-th region stored in the set of the ratios, and MJZB i denotes a proportion of a black region of the i-th region;
A2, acquiring an image factor GRYZ i shot by an ith area;
The specific steps for acquiring the image factor GRYZ i shot by the ith area in the step A2 are as follows:
Step A2.1, reading shaking times DDCS i of the mobile shooting device when shooting an ith area;
And step A2.2, calculating an image factor GRYZ i shot by the ith area, wherein the specific expression is as follows:
Wherein e represents a natural constant, DDCS i represents the shaking times of the mobile shooting device when shooting an ith area, and sigma represents a balance factor for avoiding denominator to be 0;
And step A3, comprehensively calculating a definition coefficient QXXS i of the ith area, wherein the specific expression is as follows:
QXXSi＝ω1*WJFSYZi+ω2*GRYZi
wherein ω 1 and ω 2 represent two weight coefficients summed to 1, respectively;
And step A4, judging whether the definition coefficient QXXS i of the ith area exceeds a definition threshold, if so, terminating the step A4, sending the image data TSXJ i of the ith area to an area image analysis unit, if not, re-shooting, setting the number of re-shooting of the ith area to be CP i =N, wherein N represents the execution number of the step A4, and when the number of re-shooting of the ith area to be CP i exceeds the maximum number of re-shooting.
The data acquisition module also stores a proportion set of black areas after the steel structure original image of each area is subjected to gray processing;
The area image analysis unit is used for carrying out secondary analysis on the judged area and outputting the corresponding area image influence coefficient, and the specific steps are as follows:
Step B1, reading image data TSXJ i of the ith area, cutting the image, and only reserving a steel structure area;
Step B2, recognizing the surface of the steel structure, and carrying out gray-scale treatment on the image data TSXJ i of the ith area;
Step B3, identifying all the pixel points in the non-black areas in the step B2, and clustering the adjacent non-black pixel points to obtain a plurality of clustered areas;
step B4, obtaining the area JX j of the minimum rectangular outline and the area YX j of the minimum closed circle outline of the jth clustering area;
Step B5, judging whether the smaller area of the minimum rectangular outline of the jth clustering area JX j and the minimum closed circle outline area YX j exceeds an area threshold value, judging the jth+1th clustering area if the smaller area is not exceeded, and storing the smaller area until all the clustering areas are judged to be completed, and calculating to obtain an area image influence coefficient QYYXXS i of the ith area, wherein the specific expression is as follows:
Wherein min { JX j,YXj } represents the smaller one of the area JX j of the smallest rectangular outline and the area YX j of the smallest closed circle outline of the jth cluster region, QYYXXS i represents the region image influence coefficient of the ith region, ZMJ represents the total area of the image after clipping, Representing the sum of the contour areas of the total J cluster region outputs, j.epsilon.1, J.
The steel structure defect identification judging module comprehensively calculates a steel structure to be detected based on all regional image influence coefficients to finally obtain a local defect influence coefficient, when the local defect influence coefficient exceeds a local defect threshold value, early warning is carried out, when the local defect influence coefficient does not exceed the local defect threshold value, an integral image analysis unit in the image data analysis module is called, integral image data is analyzed, an integral image defect coefficient is output, and the steel structure defect identification judging module judges whether early warning is carried out or not based on the integral image defect coefficient;
The steel structure defect identification judging module carries out comprehensive calculation on the steel structure to be detected based on all the regional image influence coefficients to finally obtain the specific expression of the local defect influence coefficient as follows:
wherein JBQX denotes a local defect influence coefficient, The specific steps of summing the area image influence coefficients of the total I areas, I epsilon p1, I, analyzing the whole image data by the whole image analysis unit and outputting the whole image defect coefficients are as follows:
Step C1, acquiring integral image data of a steel structure, and respectively acquiring lengths of two sides of the steel structure;
and step C2, calculating a defect coefficient CYZ of the whole image of the steel structure, wherein the concrete expression is as follows:
Wherein, l a and l b respectively represent lengths of different sides of the steel structure, CYZ represents an integral image defect coefficient of the steel structure, and l a-lb represents an absolute value of l a-lb.
The steel structure defect identification judging module judges whether to perform early warning based on the integral image defect coefficient, namely, early warning is performed when the integral image defect coefficient CYZ of the steel structure exceeds the integral judging threshold delta, and early warning is not performed when the integral image defect coefficient CYZ of the steel structure does not exceed the integral judging threshold delta;
and when early warning is carried out, the shot pictures are sent to staff for checking, so that the staff can see the pictures.
Embodiment one:
In the implementation process, 2 abnormal results are obtained, and an unmanned aerial vehicle is adopted for shooting;
when the 1 st position is abnormal, the definition coefficient of the 1 st area is judged specifically as shown in the following table 1:
TABLE 1
Parameters (parameters) Numerical value
MJZB1 80%
MJZB1,0 83%
DDCS1 0
σ 0.45
ω1 0.56
ω2 0.44
Sharpness threshold 0.90
PSYZ 1＝1-0.036＝0.963,GRYZ1 =0.891, wherein QXXS 1 =0.93132 >0.90 is calculated, the judgment is clear, 2 clusters are obtained through the regional image analysis unit, and specific parameters are shown in the following table 2;
TABLE 2
Parameters (parameters) Numerical value
ZMJ 122
JX1 16
YX1 12.56
JX2 12
YX2 28.27
At this time, QYYXXS 1 =0.201 was calculated;
when the 2 nd position is abnormal, the definition coefficient of the 2 nd area is judged specifically as shown in the following table 3:
TABLE 3 Table 3
Parameters (parameters) Numerical value
MJZB2 85%
MJZB2,0 83%
DDCS2 0
σ 0.45
ω1 0.56
ω2 0.44
Sharpness threshold 0.90
PSYZ 2＝0.976,GRYZ2 =0.891, wherein QXXS 2 =0.9386 >0.90 is calculated, the judgment is clear, 1 cluster is obtained through the regional image analysis unit, and specific parameters are shown in the following table 4;
TABLE 4 Table 4
Parameters (parameters) Numerical value
ZMJ 122
JX1 13.5
YX1 12.56
At this time, QYYXXS 2 =0.103 was calculated;
At the moment, JBQX =0.201+0.103=0.304 is judged for early warning, and the whole image data of the steel structure is not acquired at the moment, so that the identification of the surface defects of the steel structure can be rapidly and accurately finished, the condition that equipment calculation force is occupied by an area which is not required to be detected and is caused by the analysis of the whole image is avoided, and the detection time is shortened;
embodiment two:
In this embodiment, the local defect influence coefficient does not exceed the local defect threshold, at this time, the whole image data of the steel structure is obtained, and the lengths of two sides of the steel structure are respectively obtained as shown in table 5 below:
TABLE 5
Parameters (parameters) Numerical value
la 61
lb 63.5
δ 0.05
The defect coefficient CYZ=0.04 of the steel structure integral image does not exceed the integral judgment threshold delta, and early warning is not carried out at the moment;
The size of the threshold in the above embodiment is set for convenience of comparison, and the size of the threshold depends on the number of sample data and the number of cardinalities set for each group of sample data by a person skilled in the art, so long as the proportional relationship between the parameter and the quantized value is not affected, and the threshold can be determined by the person skilled in the art according to each sample data and the multiple experimental processes;
The invention also provides a steel structure defect identification method based on image analysis, which is based on the steel structure defect identification system based on image analysis and comprises the following steps:
step one, obtaining abnormal points of a steel structure after ultrasonic detection and marking areas;
Acquiring image data of each region of the marked steel structure and integral image data of the steel structure;
Analyzing the image data of each region of the steel structure, giving out the definition coefficient of each region, and determining whether to re-shoot the corresponding region based on the definition coefficient of each region;
Performing secondary analysis on the judged area and outputting a corresponding area image influence coefficient;
comprehensively calculating the steel structure to be detected based on all the regional image influence coefficients to finally obtain a local defect influence coefficient;
And step six, early warning is carried out when the local defect influence coefficient exceeds the local defect threshold value, and when the local defect influence coefficient does not exceed the local defect threshold value, the whole image data is analyzed, the whole image defect coefficient is output, and meanwhile, whether early warning is carried out or not is judged based on the whole image defect coefficient.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (10)

1.基于图像分析的钢结构缺陷识别系统，其特征在于：包括数据获取模块、图像数据分析模块和钢结构缺陷识别判断模块；1. A steel structure defect recognition system based on image analysis, characterized by comprising a data acquisition module, an image data analysis module, and a steel structure defect recognition and judgment module; 所述数据获取模块包括区域划分单元和图像数据获取单元，所述区域标注单元用于获取钢结构在进行超声检测后出现的异常点位，并进行区域标注，并将划分完成的区域传输给图像数据获取单元，所述图像数据获取单元用于获取区域标注单元中标注的钢结构每一个区域的图像数据和钢结构整体图像数据；The data acquisition module includes a region division unit and an image data acquisition unit. The region marking unit is used to obtain abnormal points appearing on the steel structure after ultrasonic testing, mark the regions, and transmit the divided regions to the image data acquisition unit. The image data acquisition unit is used to obtain image data of each region of the steel structure marked in the region marking unit and image data of the entire steel structure. 所述图像数据分析模块包括图像模糊程度分析单元、区域图像分析单元和整体图像分析单元，所述图像模糊程度分析单元用于对图像数据获取单元中的钢结构每一个区域的图像数据进行分析，并给出每一个区域的清晰系数，并基于每一个区域的清晰系数确定是否对其对应的区域进行重新拍摄，所述区域图像分析单元用于对判断完成的区域进行二次分析，并输出对应的区域图像影响系数；The image data analysis module includes an image blur degree analysis unit, a regional image analysis unit, and an overall image analysis unit. The image blur degree analysis unit is used to analyze the image data of each area of the steel structure in the image data acquisition unit, and provide a clarity coefficient for each area. Based on the clarity coefficient of each area, it is determined whether to re-photograph the corresponding area. The regional image analysis unit is used to perform a secondary analysis on the area where the judgment has been completed, and output the corresponding regional image influence coefficient. 所述钢结构缺陷识别判断模块基于所有的区域图像影响系数对待检测的钢结构进行综合计算最终得到局部缺陷影响系数，当局部缺陷影响系数超出局部缺陷阈值时，进行预警，当局部缺陷影响系数未超出局部缺陷阈值时，则调用图像数据分析模块中的整体图像分析单元，对整体图像数据进行分析，并输出整体图像缺陷系数，所述钢结构缺陷识别判断模块基于整体图像缺陷系数判断是否进行预警。The steel structure defect recognition and judgment module performs a comprehensive calculation on the steel structure to be inspected based on all regional image influence coefficients to finally obtain a local defect influence coefficient. When the local defect influence coefficient exceeds the local defect threshold, an early warning is issued. When the local defect influence coefficient does not exceed the local defect threshold, the overall image analysis unit in the image data analysis module is called to analyze the overall image data and output the overall image defect coefficient. The steel structure defect recognition and judgment module determines whether to issue an early warning based on the overall image defect coefficient. 2.根据权利要求1所述的基于图像分析的钢结构缺陷识别系统，其特征在于：所述图像数据获取单元用于获取区域标注单元中标注的钢结构每一个区域的图像数据的具体表达式如下：2. The steel structure defect recognition system based on image analysis according to claim 1, wherein the image data acquisition unit is used to acquire the image data of each area of the steel structure marked in the area marking unit using the following specific expression: TSXJ＝[TSXJ1,…,TSXJi,…,TSXJI]TSXJ＝[TSXJ 1 ,…,TSXJ i ,…,TSXJ i ] 其中，TSXJI表示区域图像数据集，TSXJ1,…,TSXJi,…,TSXJI分别表示第1个区域的图像数据、…、第i个区域的图像数据、…、第I个区域的图像数据，i∈[1,I]，且第i个区域的图像数据由移动式拍摄设备拍摄获取。Wherein, TSXJI represents a regional image dataset, TSXJ 1 ,…,TSXJ i ,…,TSXJ I respectively represent the image data of the 1st region,…, the image data of the i-th region,…, the image data of the I-th region, i∈[1,I], and the image data of the i-th region is obtained by photographing with a mobile shooting device. 3.根据权利要求2所述的基于图像分析的钢结构缺陷识别系统，其特征在于：所述图像模糊程度分析单元用于对图像数据获取单元中的钢结构每一个区域的图像数据进行分析，并给出每一个区域的清晰系数，并基于每一个区域的清晰系数确定是否对其对应的区域进行重新拍摄的具体步骤如下：3. The steel structure defect recognition system based on image analysis according to claim 2 is characterized in that the image blur degree analysis unit is configured to analyze the image data of each area of the steel structure in the image data acquisition unit, and provide a clarity coefficient for each area, and determine whether to re-photograph the corresponding area based on the clarity coefficient of each area, and the specific steps are as follows: 步骤A1：获取第i个区域拍摄的拍摄因子PSYZi；Step A1: Obtain the shooting factor PSYZ i of the i-th region; 步骤A2：获取第i个区域拍摄的图像因子GRYZi；Step A2: Obtain the image factor GRYZ i captured in the i-th region; 步骤A3：综合计算第i个区域的清晰系数QXXSi，具体表达式如下：Step A3: Comprehensively calculate the clarity coefficient QXXS i of the i-th region. The specific expression is as follows: QXXSi＝ω1*WJFSYZi+ω2*GRYZi QXXS i ＝ω 1 *WJFSYZ i +ω 2 *GRYZ i 其中，ω1和ω2分别表示两个和为1的权重系数；Where ω 1 and ω 2 represent two weight coefficients whose sum is 1; 步骤A4：判断第i个区域的清晰系数QXXSi是否超出清晰阈值，若超出清晰阈值，则终止步骤A4，并将第i个区域的图像数据TSXJi发送至区域图像分析单元，若未超出清晰阈值，则重新拍摄，并设置第i个区域的重拍次数CPi＝N，N表示步骤A4执行次数，当第i个区域的重拍次数CPi超出最大重拍次数时进行报错。Step A4: Determine whether the clarity coefficient QXXS i of the i-th region exceeds the clarity threshold. If so, terminate step A4 and send the image data TSXJ i of the i-th region to the regional image analysis unit. If not, retake the image and set the retake count CP i of the i-th region to N, where N represents the number of times step A4 is executed. If the retake count CP i of the i-th region exceeds the maximum retake count, an error is reported. 4.根据权利要求3所述的基于图像分析的钢结构缺陷识别系统，其特征在于：所述数据获取模块还存储有每一区域的钢结构原始图像进行灰度化处理后黑色区域的比例集；4. The steel structure defect recognition system based on image analysis according to claim 3, characterized in that: the data acquisition module further stores a set of black area ratios after grayscale processing of the original steel structure image of each area; 所述步骤A1中获取第i个区域拍摄的拍摄因子PSYZi的具体步骤如下：The specific steps of obtaining the shooting factor PSYZ i of the i-th area shooting in step A1 are as follows: 步骤A1.1：读取第i个区域的图像数据TSXJi，将第i个区域的图像数据TSXJi进行二值化处理；Step A1.1: Read the image data TSXJ i of the i-th region and perform binarization processing on the image data TSXJ i of the i-th region; 步骤A1.2：得到第i个区域的所有黑色区域的比例MJZBi，并计算第i个区域拍摄的拍摄因子PSYZi，具体表达式如下：Step A1.2: Obtain the ratio of all black areas in the i-th area MJZB i and calculate the shooting factor PSYZ i of the i-th area. The specific expression is as follows: 其中，|MJZBi-MJZBi,0|表示MJZBi-MJZBi,0的绝对值，MJZBi,0表示占比集中存储的第i个区域的黑色区域的比例，MJZBi表示第i个区域的黑色区域的比例。Among them, |MJZBi - MJZBi ,0 | represents the absolute value of MJZBi - MJZBi ,0 , MJZBi ,0 represents the proportion of the black area of the i-th area stored in the proportion set, and MJZBi represents the proportion of the black area of the i-th area. 5.根据权利要求4所述的基于图像分析的钢结构缺陷识别系统，其特征在于：所述步骤A2中获取第i个区域拍摄的图像因子GRYZi的具体步骤如下：5. The steel structure defect recognition system based on image analysis according to claim 4, characterized in that the specific steps of obtaining the image factor GRYZ i captured in the i-th area in step A2 are as follows: 步骤A2.1：读取移动式拍摄设备在拍摄第i个区域拍摄时抖动次数DDCSi；Step A2.1: Read the number of shakes DDCS i of the mobile shooting device when shooting the i-th area; 步骤A2.2：计算第i个区域拍摄的图像因子GRYZi，具体表达式如下：Step A2.2: Calculate the image factor GRYZ i captured in the i-th region. The specific expression is as follows: 其中，e表示自然常数，DDCSi表示移动式拍摄设备在拍摄第i个区域拍摄时抖动次数，σ表示避免分母为0的平衡因子。Wherein, e represents a natural constant, DDCS i represents the number of times the mobile camera shakes when shooting the i-th area, and σ represents a balance factor to avoid the denominator being zero. 6.根据权利要求3所述的基于图像分析的钢结构缺陷识别系统，其特征在于：所述区域图像分析单元用于对判断完成的区域进行二次分析，并输出对应的区域图像影响系数的具体步骤如下：6. The steel structure defect recognition system based on image analysis according to claim 3 is characterized in that the specific steps of the regional image analysis unit for performing secondary analysis on the determined region and outputting the corresponding regional image influence coefficient are as follows: 步骤B1：读取第i个区域的图像数据TSXJi，并对图像进行裁剪，只保留钢结构区域；Step B1: Read the image data TSXJ i of the i-th region and crop the image to retain only the steel structure region; 步骤B2：对钢结构的表面进行识别，并对第i个区域的图像数据TSXJi进行灰度化处理；Step B2: Identify the surface of the steel structure and perform grayscale processing on the image data TSXJ i of the i-th region; 步骤B3：识别步骤B2中所有非黑色区域的像素点，并对相邻的非黑色像素点进行聚类，得到若干个聚类区域；Step B3: Identify all pixels in the non-black area in step B2, and cluster adjacent non-black pixels to obtain several cluster areas; 步骤B4：获取第j个聚类区域的最小矩形轮廓的面积JXj和最小闭圆轮廓的面积YXj；Step B4: Obtain the area JX j of the minimum rectangular outline and the area YX j of the minimum closed circle outline of the j-th cluster region; 步骤B5：判断第j个聚类区域的最小矩形轮廓的面积JXj和最小闭圆轮廓的面积YXj中较小的一个是否超出面积阈值，若未超出，则判断第j+1个聚类区域，若超出，则将较小的一个面积进行存储，直到所有的聚类区域判断完成，计算得到第i个区域的区域图像影响系数QYYXXSi，具体表达式如下：Step B5: Determine whether the smaller of the area of the minimum rectangular outline JX j and the area of the minimum closed circle outline YX j of the j-th cluster area exceeds the area threshold. If not, determine the j+1-th cluster area. If not, store the smaller area until all cluster areas are determined. Calculate the regional image influence coefficient QYYXXS i of the i-th area. The specific expression is as follows: 其中，min{JXj,YXj}表示第j个聚类区域的最小矩形轮廓的面积JXj和最小闭圆轮廓的面积YXj中较小的一个，QYYXXSi表示第i个区域的区域图像影响系数，ZMJ表示裁剪后图像总面积，表示对共J个聚类区域输出的轮廓面积进行求和，j∈[1,J]。Where min{JX j ,YX j } represents the smaller one of the area of the minimum rectangular contour JX j and the area of the minimum closed circle contour YX j of the j-th cluster region, QYYXXS i represents the regional image influence coefficient of the i-th region, and ZMJ represents the total area of the cropped image. It means summing the contour areas outputted by a total of J cluster regions, j∈[1,J]. 7.根据权利要求6所述的基于图像分析的钢结构缺陷识别系统，其特征在于：所述钢结构缺陷识别判断模块基于所有的区域图像影响系数对待检测的钢结构进行综合计算最终得到局部缺陷影响系数的具体表达式如下：7. The steel structure defect recognition system based on image analysis according to claim 6 is characterized in that the steel structure defect recognition and judgment module performs a comprehensive calculation of all regional image influence coefficients on the steel structure to be inspected, and finally obtains the specific expression of the local defect influence coefficient as follows: 其中，JBQX表示局部缺陷影响系数，表示对共I个区域的区域图像影响系数进行求和，i∈[1,I]。Among them, JBQX represents the local defect influence coefficient, It means summing the regional image influence coefficients of a total of I regions, i∈[1,I]. 8.根据权利要求7所述的基于图像分析的钢结构缺陷识别系统，其特征在于：所述整体图像分析单元对整体图像数据进行分析，并输出整体图像缺陷系数的具体步骤如下：8. The steel structure defect recognition system based on image analysis according to claim 7, wherein the overall image analysis unit analyzes the overall image data and outputs the overall image defect coefficient in the following specific steps: 步骤C1：获取钢结构整体图像数据，并对钢结构两侧长度进行分别获取；Step C1: Obtain the overall image data of the steel structure and obtain the lengths of both sides of the steel structure respectively; 步骤C2：计算钢结构整体图像缺陷系数CYZ，具体表达式如下：Step C2: Calculate the overall image defect coefficient CYZ of the steel structure. The specific expression is as follows: 其中，la和lb分别表示钢结构不同侧的长度，CYZ表示钢结构整体图像缺陷系数，|la-lb|表示la-lb的绝对值。Where la and l b represent the lengths of different sides of the steel structure, respectively, CYZ represents the overall image defect coefficient of the steel structure, and | la - lb | represents the absolute value of la - lb . 9.根据权利要求8所述的基于图像分析的钢结构缺陷识别系统，其特征在于：所述钢结构缺陷识别判断模块基于整体图像缺陷系数判断是否进行预警的具体步骤为：当钢结构整体图像缺陷系数CYZ超出整体判断阈值δ时，进行预警，当钢结构整体图像缺陷系数CYZ未超出整体判断阈值δ时，不进行预警。9. The steel structure defect recognition system based on image analysis according to claim 8 is characterized in that: the specific steps of the steel structure defect recognition and judgment module to judge whether to issue an early warning based on the overall image defect coefficient are: when the overall image defect coefficient CYZ of the steel structure exceeds the overall judgment threshold δ, an early warning is issued; when the overall image defect coefficient CYZ of the steel structure does not exceed the overall judgment threshold δ, no early warning is issued. 10.基于图像分析的钢结构缺陷识别方法，基于权利要求1-9任一所述的基于图像分析的钢结构缺陷识别系统，其特征在于：包括以下步骤：10. A method for identifying defects in steel structures based on image analysis, based on the system for identifying defects in steel structures based on image analysis according to any one of claims 1 to 9, characterized in that it comprises the following steps: 步骤一：获取钢结构在进行超声检测后出现的异常点位，并进行区域标注；Step 1: Obtain abnormal points on the steel structure after ultrasonic testing and mark the areas; 步骤二：获取标注的钢结构每一个区域的图像数据和钢结构整体图像数据；Step 2: Obtain image data of each marked area of the steel structure and image data of the entire steel structure; 步骤三：对钢结构每一个区域的图像数据进行分析，并给出每一个区域的清晰系数，并基于每一个区域的清晰系数确定是否对其对应的区域进行重新拍摄；Step 3: Analyze the image data of each area of the steel structure, and give a clarity coefficient for each area. Based on the clarity coefficient of each area, determine whether to re-photograph the corresponding area; 步骤四：对判断完成的区域进行二次分析，并输出对应的区域图像影响系数；Step 4: Perform secondary analysis on the determined area and output the corresponding regional image influence coefficient; 步骤五：基于所有的区域图像影响系数对待检测的钢结构进行综合计算最终得到局部缺陷影响系数；Step 5: Based on all the regional image influence coefficients, the steel structure to be inspected is comprehensively calculated to finally obtain the local defect influence coefficient; 步骤六：当局部缺陷影响系数超出局部缺陷阈值时，进行预警，当局部缺陷影响系数未超出局部缺陷阈值时，对整体图像数据进行分析，并输出整体图像缺陷系数，同时基于整体图像缺陷系数判断是否进行预警。Step 6: When the local defect influence coefficient exceeds the local defect threshold, an early warning is issued. When the local defect influence coefficient does not exceed the local defect threshold, the overall image data is analyzed and the overall image defect coefficient is output. At the same time, whether to issue an early warning is determined based on the overall image defect coefficient.
CN202510801261.1A 2025-06-16 2025-06-16 Steel structure defect identification system and method based on image analysis Active CN120725975B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202510801261.1A CN120725975B (en) 2025-06-16 2025-06-16 Steel structure defect identification system and method based on image analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202510801261.1A CN120725975B (en) 2025-06-16 2025-06-16 Steel structure defect identification system and method based on image analysis

Publications (2)

Publication Number Publication Date
CN120725975A true CN120725975A (en) 2025-09-30
CN120725975B CN120725975B (en) 2026-03-06

Family

ID=97157397

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202510801261.1A Active CN120725975B (en) 2025-06-16 2025-06-16 Steel structure defect identification system and method based on image analysis

Country Status (1)

Country Link
CN (1) CN120725975B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120912609A (en) * 2025-10-10 2025-11-07 南通理工学院 Steel-wood combined member surface defect detection system and method based on image sensing

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005316550A (en) * 2004-04-27 2005-11-10 Fuji Xerox Co Ltd Image processor, image reader, image inspection device and program
JP2007040855A (en) * 2005-08-03 2007-02-15 Showa Denko Kk Surface inspection method and surface inspection device
CN116030342A (en) * 2022-12-09 2023-04-28 四川天艺生态园林集团股份有限公司 Method, device, equipment and storage medium for detecting water shortage state of greening plants
CN117309766A (en) * 2023-10-20 2023-12-29 苏州宣雄智能科技有限公司 A visual inspection method and system for product surface defects
CN117664991A (en) * 2023-12-25 2024-03-08 蚌埠学院 A defect detection system
CN118230172A (en) * 2024-05-08 2024-06-21 中冶建筑研究总院有限公司 Panoramic visual inspection method, system and device for corrosion defects of steel structure metal roof
CN119595634A (en) * 2023-09-11 2025-03-11 中国石油化工股份有限公司 Method and system for detecting defect of petrochemical equipment

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005316550A (en) * 2004-04-27 2005-11-10 Fuji Xerox Co Ltd Image processor, image reader, image inspection device and program
JP2007040855A (en) * 2005-08-03 2007-02-15 Showa Denko Kk Surface inspection method and surface inspection device
CN116030342A (en) * 2022-12-09 2023-04-28 四川天艺生态园林集团股份有限公司 Method, device, equipment and storage medium for detecting water shortage state of greening plants
CN119595634A (en) * 2023-09-11 2025-03-11 中国石油化工股份有限公司 Method and system for detecting defect of petrochemical equipment
CN117309766A (en) * 2023-10-20 2023-12-29 苏州宣雄智能科技有限公司 A visual inspection method and system for product surface defects
CN117664991A (en) * 2023-12-25 2024-03-08 蚌埠学院 A defect detection system
CN118230172A (en) * 2024-05-08 2024-06-21 中冶建筑研究总院有限公司 Panoramic visual inspection method, system and device for corrosion defects of steel structure metal roof

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
QIWU LUO ET AL.: "Automated Visual Defect Detection for Flat Steel Surface: A Survey", IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, vol. 69, no. 3, 1 January 2020 (2020-01-01) *
张建川: "红钢棒材表面缺陷图像采集与检测系统研究", 信息科技辑, 15 May 2013 (2013-05-15) *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120912609A (en) * 2025-10-10 2025-11-07 南通理工学院 Steel-wood combined member surface defect detection system and method based on image sensing

Also Published As

Publication number Publication date
CN120725975B (en) 2026-03-06

Similar Documents

Publication Publication Date Title
CN108711148B (en) An intelligent detection method for tire defects based on deep learning
CN114581446B (en) Battery core abnormity detection method and system of laminated battery
CN115995056A (en) A method for automatic identification of bridge defects based on deep learning
CN117557570B (en) A rail vehicle abnormality detection method and system
CN113112501A (en) Vehicle-mounted track inspection device and method based on deep learning
CN120147263B (en) An automatic bearing surface defect detection system based on image recognition
CN113591973B (en) Intelligent comparison method for appearance state change of track plate
CN117252840B (en) Photovoltaic array defect elimination evaluation method and device and computer equipment
CN112508911A (en) Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof
CN120451175B (en) Embedded method, system, equipment and storage medium for defect identification of insulator strings in transmission lines
CN120725975A (en) Steel structure defect recognition system and method based on image analysis
CN119151938A (en) Surface defect detection method and detection system based on vision
CN119152397A (en) Unmanned aerial vehicle power line image line equipment defect labeling method
CN108765365A (en) A kind of rotor winding image qualification detection method
CN117690846B (en) Visual detection method, device and equipment for solar silicon wafer and storage medium
CN120298396A (en) Photovoltaic defect intelligent analysis method and system
Evstafev et al. Surface defect detection and recognition based on CNN
CN117455917B (en) Establishment of false alarm library of etched lead frame and false alarm on-line judging and screening method
CN116778520B (en) Mass license data quality inspection method
CN118982522A (en) Flange surface defect detection method based on deep learning
CN116703862B (en) An intelligent big data monitoring system and method for visual inspection
CN116468373B (en) Power plant equipment warehouse management system based on Internet of things
CN118096747B (en) Automatic PCBA (printed circuit board assembly) board detection method and system based on deep learning
CN116630711B (en) A wind power equipment analysis system based on AI vision assistance
CN120852422B (en) AI vision-based real-time detection system for welding quality of power calculation card

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant