CN118846581B - Nickel nitrate separating and impurity removing device and impurity removing method - Google Patents

Nickel nitrate separating and impurity removing device and impurity removing method Download PDF

Info

Publication number
CN118846581B
CN118846581B CN202411329524.5A CN202411329524A CN118846581B CN 118846581 B CN118846581 B CN 118846581B CN 202411329524 A CN202411329524 A CN 202411329524A CN 118846581 B CN118846581 B CN 118846581B
Authority
CN
China
Prior art keywords
nickel nitrate
extraction
nitrate solution
regulator
solution
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.)
Active
Application number
CN202411329524.5A
Other languages
Chinese (zh)
Other versions
CN118846581A (en
Inventor
张庆军
李智
王六平
李中军
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.)
Huaihua Heng'an Petrochemical Co ltd
Original Assignee
Huaihua Heng'an Petrochemical 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 Huaihua Heng'an Petrochemical Co ltd filed Critical Huaihua Heng'an Petrochemical Co ltd
Priority to CN202411329524.5A priority Critical patent/CN118846581B/en
Publication of CN118846581A publication Critical patent/CN118846581A/en
Application granted granted Critical
Publication of CN118846581B publication Critical patent/CN118846581B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01D—SEPARATION
    • B01D11/00—Solvent extraction
    • B01D11/04—Solvent extraction of solutions which are liquid
    • B01D11/0484—Controlling means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01D—SEPARATION
    • B01D11/00—Solvent extraction
    • B01D11/04—Solvent extraction of solutions which are liquid
    • B01D11/0492—Applications, solvents used
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01D—SEPARATION
    • B01D36/00—Filter circuits or combinations of filters with other separating devices
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01J—CHEMICAL OR PHYSICAL PROCESSES, e.g. CATALYSIS OR COLLOID CHEMISTRY; THEIR RELEVANT APPARATUS
    • B01J19/00—Chemical, physical or physico-chemical processes in general; Their relevant apparatus
    • B01J19/0006—Controlling or regulating processes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01J—CHEMICAL OR PHYSICAL PROCESSES, e.g. CATALYSIS OR COLLOID CHEMISTRY; THEIR RELEVANT APPARATUS
    • B01J19/00—Chemical, physical or physico-chemical processes in general; Their relevant apparatus
    • B01J19/0086—Processes carried out with a view to control or to change the pH-value; Applications of buffer salts; Neutralisation reactions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01J—CHEMICAL OR PHYSICAL PROCESSES, e.g. CATALYSIS OR COLLOID CHEMISTRY; THEIR RELEVANT APPARATUS
    • B01J19/00—Chemical, physical or physico-chemical processes in general; Their relevant apparatus
    • B01J19/18—Stationary reactors having moving elements inside
    • C—CHEMISTRY; METALLURGY
    • C01—INORGANIC CHEMISTRY
    • C01G—COMPOUNDS CONTAINING METALS NOT COVERED BY SUBCLASSES C01D OR C01F
    • C01G53/00—Compounds of nickel
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D21/00—Control of chemical or physico-chemical variables, e.g. pH value
    • G05D21/02—Control of chemical or physico-chemical variables, e.g. pH value characterised by the use of electric means
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • Y02P10/00—Technologies related to metal processing
    • Y02P10/20—Recycling

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • General Physics & Mathematics (AREA)
  • Organic Chemistry (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Inorganic Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Health & Medical Sciences (AREA)
  • Manufacture And Refinement Of Metals (AREA)

Abstract

本发明涉及硝酸镍除杂技术领域，特别涉及一种硝酸镍分离除杂装置及除杂方法，包括杂质过滤器，其用于对需要处理的初始硝酸镍溶液进行初步过滤，去除不溶性固体杂质；萃取反应器，其与所述杂质过滤器出液口导通连接，初始硝酸镍溶液通过杂质过滤器初步过滤后，排入到萃取反应器内；加药组件，设置在萃取反应器上，进行pH调节剂的自动添加。本发明实现了根据pH调节剂的特性和原料的差异智能化自适应地调整pH调节剂的添加量，保证了对溶液的酸度调整效果，使其溶液的酸度适合萃取剂的工作范围，保证了萃取效果。

The present invention relates to the technical field of nickel nitrate impurity removal, and in particular to a nickel nitrate separation and impurity removal device and impurity removal method, comprising an impurity filter, which is used to preliminarily filter the initial nickel nitrate solution to be treated to remove insoluble solid impurities; an extraction reactor, which is conductively connected to the liquid outlet of the impurity filter, and the initial nickel nitrate solution is discharged into the extraction reactor after being preliminarily filtered by the impurity filter; and a dosing component, which is arranged on the extraction reactor to automatically add a pH regulator. The present invention realizes intelligent and adaptive adjustment of the addition amount of the pH regulator according to the characteristics of the pH regulator and the difference of the raw materials, ensures the acidity adjustment effect of the solution, makes the acidity of the solution suitable for the working range of the extractant, and ensures the extraction effect.

Description

Nickel nitrate separating and impurity removing device and impurity removing method
Technical Field
The invention relates to the technical field of nickel nitrate impurity removal, in particular to a nickel nitrate separation impurity removal device and an impurity removal method.
Background
Nickel nitrate is an important chemical raw material and is widely applied to the fields of electroplating, battery manufacturing, catalysts and the like. However, during the production process, the nickel nitrate solution often contains some impurities, which affect the quality of the nickel nitrate product and even its application properties. Therefore, the development of the high-efficiency nickel nitrate separating and impurity removing device and the production method has important industrial significance.
The Chinese patent application with publication number of CN106865626A discloses a method for removing cobalt impurities from nickel nitrate, which comprises the following specific steps: (1) Dissolving reagent nickel nitrate in water to form a solution, adding reagent sodium hydroxide and sodium hypochlorite solution to generate trivalent nickel hydroxide precipitate, and washing the trivalent nickel hydroxide precipitate for later use; (2) Adding ammonia water and hydrogen peroxide into industrial nickel nitrate solution, filtering to remove iron impurities, adding the trivalent nickel hydroxide precipitate prepared in the step (1), heating and stirring for 30 minutes to oxidize Co 2+ in the solution into Co 3+, and separating out the precipitate in the form of Co (OH) 3; (3) Concentrating and crystallizing the solution after separating the precipitate to obtain a nickel nitrate finished product meeting the reagent grade index; the method is convenient to operate, and the nickel nitrate finished product (cobalt is less than or equal to 0.01%) meeting the requirements can be obtained.
As described in the above application, the conventional nickel nitrate separating and purifying device and purifying method generally adopt an extraction method, but before extraction, the acidity of the solution needs to be adjusted to a range suitable for the working of the extractant, and the pH regulator is different in addition amount due to the difference in concentration and pH value of the nickel nitrate solution and the difference in characteristics of the pH regulator, and the conventional technology is to add the pH regulator by means of artificial experience or a preset addition amount, and it cannot be intelligently and adaptively adjusted according to the characteristics of the pH regulator and the difference of raw materials, thereby affecting the effect of purifying the product.
Disclosure of Invention
In order to solve the problems, the invention provides a nickel nitrate separating and impurity removing device and a nickel nitrate separating and impurity removing method.
The invention adopts the following technical scheme that the nickel nitrate separating and impurity removing device comprises:
An impurity filter for preliminarily filtering the initial nickel nitrate solution to be treated to remove insoluble solid impurities;
the extraction reactor is connected with the liquid outlet of the impurity filter in a conducting way, and the initial nickel nitrate solution is discharged into the extraction reactor after being preliminarily filtered by the impurity filter;
The dosing component is arranged on the extraction reactor and is used for automatically adding the pH regulator;
A reaction control unit, the reaction control unit comprising:
The first data acquisition module acquires comprehensive parameters of historical initial nickel nitrate solution extraction and impurity removal, wherein the comprehensive parameters comprise characteristic parameters of the initial nickel nitrate solution and the addition amount of a pH regulator;
The first data analysis module is used for training a machine learning model for predicting the addition amount of the pH regulator based on the collected comprehensive parameters of the extraction and impurity removal of the historical initial nickel nitrate solution, collecting the characteristic parameters of the initial nickel nitrate solution in real time, predicting the addition amount of the pH regulator based on the machine learning model after training, and controlling the dosing assembly to work based on the predicted addition amount of the pH regulator;
The second data acquisition module acquires the pH value of the nickel nitrate solution after the addition of the pH regulator is finished, and marks the pH value as an extraction pH value;
The second data analysis module inputs the acquired characteristic parameters of the extraction pH value and the initial nickel nitrate solution into a pre-constructed extraction parameter recommendation model to obtain an extraction parameter recommendation set label, so that an extraction parameter recommendation set corresponding to the extraction parameter recommendation set label is obtained, the working parameters of the extraction reactor are controlled based on the control parameters in the extraction parameter recommendation set, and the nickel nitrate solution is subjected to extraction treatment.
As a further description of the above technical solution: further comprises:
a stirring assembly installed in the extraction reactor for stirring and mixing the liquid in the extraction reactor;
And a heater installed in the extraction reactor for heating the solution in the extraction reactor.
As a further description of the above technical solution: the dosing assembly comprises a storage box, a perfusion tube and a flow pump, wherein the storage box is used for storing the pH regulator, the storage box is connected with the extraction reactor through the perfusion tube in a conducting way, the flow pump is arranged on the perfusion tube and is used for pumping the pH regulator in the storage box into the extraction reactor.
As a further description of the above technical solution: further comprises: the centrifugal machine is connected with the extraction reactor in a conducting way and is used for separating the extracting agent;
the evaporator is connected with the extraction reactor in a conducting way;
And the crystallizer is connected with the evaporator in a conducting way.
As a further description of the above technical solution: the stirring assembly comprises a stirring shaft, a stirring motor and stirring blades, the stirring She Luoshuan is fixed on the stirring shaft, the stirring motor is fixed on the outer wall of the extraction reactor through bolts, and an output shaft of the stirring motor is fixedly connected with the stirring shaft through a coupler.
As a further description of the above technical solution: the characteristic parameters of the nickel nitrate solution comprise a nickel nitrate solution adjusting coefficient, the type of a pH regulator, the concentration of the pH regulator and the type of impurities in the nickel nitrate solution;
parameters affecting the adjustment coefficient of the nickel nitrate solution comprise the concentration of the nickel nitrate solution, the pH value of the nickel nitrate solution and the total amount of the nickel nitrate solution;
The expression of the regulating coefficient of the nickel nitrate solution is as follows:
；
In the formula, The coefficient of the nickel nitrate solution is adjusted,For the concentration of the nickel nitrate solution,Is the pH value of the nickel nitrate solution,For the total amount of the nickel nitrate solution,、AndAs the weight factor of the weight factor,、AndAre all greater than zero.
As a further description of the above technical solution: the training method of the machine learning model for predicting the addition amount of the pH regulator comprises the following steps:
converting the collected characteristic parameters of the initial nickel nitrate solution into a corresponding group of characteristic vectors;
Taking each group of characteristic vectors as input of the machine learning model, taking the adding amount of the pH regulator corresponding to the characteristic parameters of each group of initial nickel nitrate solution as output, taking the adding amount of the pH regulator actually corresponding to the characteristic parameters of each group of initial nickel nitrate solution as a prediction target, and taking the minimized loss function value of the machine learning model as a training target; and stopping training when the loss function value of the machine learning model is smaller than or equal to a preset target loss value.
As a further description of the above technical solution: the extraction parameter recommendation set is as follows:
Wherein, For the aggregate label asThe type of the corresponding extractant is that of the liquid,For the aggregate label asThe corresponding dosage of the extractant is adopted in the process,For the aggregate label asThe corresponding extraction temperature is used for the extraction,For the aggregate label asThe corresponding extraction time.
As a further description of the above technical solution: the training method of the extraction parameter recommendation model comprises the following steps:
presetting a corresponding number for the extraction parameter recommendation set;
Converting the characteristic parameters of the extracted pH value and the initial nickel nitrate solution into a corresponding set of characteristic vectors, taking each set of characteristic vectors as input of a machine learning model, taking a set of extraction parameter recommendation set numbers corresponding to the characteristic parameters of each set of extracted pH value and the initial nickel nitrate solution as output, taking a set of extraction parameter recommendation set numbers actually corresponding to the characteristic parameters of each set of extracted pH value and the initial nickel nitrate solution as a prediction target, and taking a minimum machine learning model loss function value as a training target; and stopping training when the machine learning model loss function value is smaller than or equal to a preset target loss value.
The nickel nitrate separating and impurity removing method is realized based on the nickel nitrate separating and impurity removing device and comprises the following steps of:
introducing an initial nickel nitrate solution to be treated into an impurity filter, and performing preliminary filtration to remove insoluble solid impurities;
Adding the filtered nickel nitrate solution into an extraction reactor, adding a pH regulator into the extraction reactor through a dosing assembly, and adjusting the acidity of the solution to a range suitable for the working of the extractant;
Adding an extracting agent into the extraction reactor, controlling a heater and a stirring assembly in the extraction reactor to work, heating and stirring and mixing liquid in the extraction reactor, ensuring that the reaction is carried out at a proper temperature, ensuring that the solution and the extracting agent are fully mixed, and improving the reaction efficiency and the product quality;
Separating the extracted solution and the extracting agent by a centrifugal machine, enriching target metals in the extracting agent, introducing the extracting agent enriched with the target metals into the extraction reactor again, and separating the target metals from the extracting agent by adding a back extracting agent;
And (3) removing residual impurities from the back extraction liquid through filtering equipment, concentrating and crystallizing the back extraction liquid through an evaporator and a crystallizer to obtain a high-purity nickel nitrate product.
The beneficial effects are that:
according to the nickel nitrate separating and impurity removing device provided by the invention, the pH regulator addition amount is predicted by collecting the nickel nitrate solution regulating coefficient, the type of the pH regulator, the concentration of the pH regulator and the type of impurities in the nickel nitrate solution, so that the addition amount of the pH regulator is intelligently and adaptively regulated according to the characteristics of the pH regulator and the difference of raw materials, the acidity regulating effect of the solution is ensured, the acidity of the solution is suitable for the working range of an extractant, and the extraction effect is ensured;
Further, the collected characteristic parameters of the extraction pH value and the initial nickel nitrate solution are input into a pre-built extraction parameter recommendation model to obtain an extraction parameter recommendation set label, so that an extraction parameter recommendation set corresponding to the extraction parameter recommendation set label is obtained, the working parameters of an extraction reactor are controlled based on the control parameters in the extraction parameter recommendation set, the nickel nitrate solution is subjected to extraction treatment, the automatic generation control parameters are realized to control the operation of the extraction reactor, namely the intelligent selection of the optimal extractant type and the optimal extractant dosage, the optimal extraction temperature and the optimal extraction time is realized, the impurity removal efficiency is improved, the cost is reduced, and the defects that the impurity removal is incomplete and the product quality is unstable easily occur due to the fact that the control parameters cannot be automatically generated based on the characteristics of the nickel nitrate solution in the prior art are overcome.
Drawings
The invention is further explained below with reference to the drawings and examples:
FIG. 1 is a schematic structural diagram of a nickel nitrate separating and impurity removing device according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an extraction reactor according to an embodiment of the present invention;
FIG. 3 is a block diagram of a reaction control unit according to an embodiment of the present invention;
fig. 4 is a flow chart of a method for separating and removing impurities from nickel nitrate according to an embodiment of the present invention.
Reference numerals: 1. an impurity filter; 2. an extraction reactor; 21. a dosing assembly; 211. a storage box; 212. an infusion tube; 213. a flow pump; 22. a stirring assembly; 221. a stirring shaft; 222. a stirring motor; 223. stirring the leaves; 23. a heater; 24. a reaction control unit; 3. a centrifuge; 4. an evaporator; 5. and (3) a crystallizer.
Detailed Description
The application is further described with reference to the following detailed drawings in order to make the technical means, the creation characteristics, the achievement of the purpose and the effect of the implementation of the application easy to understand. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
Example 1
Referring to fig. 1-3, an embodiment of the present invention provides a technical solution: a nickel nitrate separating and impurity removing device, comprising:
the impurity filter 1 is used for preliminarily filtering an initial nickel nitrate solution to be treated to remove insoluble solid impurities, and the initial nickel nitrate solution is generally obtained by leaching nickel in an ore or an alloy by using nitric acid or other acid, so that the initial nickel nitrate solution contains a certain amount of impurities.
And the extraction reactor 2 is connected with the liquid outlet of the impurity filter 1 in a conducting way, and the initial nickel nitrate solution is discharged into the extraction reactor 2 after being preliminarily filtered by the impurity filter 1.
The dosing assembly 21 is arranged on the extraction reactor 2 and is used for automatically adding the pH regulator, the dosing assembly 21 comprises a storage box 211, a liquid conveying pipe 212 and a flow pump 213, the storage box 211 is used for storing the pH regulator, the storage box 211 is connected with the extraction reactor 2 in a conducting way through the liquid conveying pipe 212, and the liquid conveying pipe 212 is provided with the flow pump 213 which is used for pumping the pH regulator in the storage box 211 into the extraction reactor 2.
The stirring assembly 22 is arranged in the extraction reactor 2 and is used for stirring and mixing liquid in the extraction reactor 2, the stirring assembly 22 comprises a stirring shaft 221, a stirring motor 222 and stirring blades 223, the stirring blades 223 are fixed on the stirring shaft 221 in a bolt manner, the stirring motor 222 is fixed on the outer wall of the extraction reactor 2 in a bolt manner, and an output shaft of the stirring motor 222 is fixedly connected with the stirring shaft 221 through a coupling.
A heater 23 installed in the extraction reactor 2 for heating the solution in the extraction reactor 2.
The centrifugal machine 3 is connected with the extraction reactor 2 in a conducting way and is used for separating the extracting agent;
the evaporator 4 is connected with the extraction reactor 2 in a conducting way;
And the crystallizer 5, and the crystallizer 5 is connected with the evaporator 4 in a conducting way.
A reaction control unit 24 for controlling the dosage of the nitric acid solution, adjusting the pH value of the nickel nitrate solution, the reaction control unit 24 comprising:
the first data acquisition module acquires comprehensive parameters of historical initial nickel nitrate solution extraction and impurity removal, wherein the comprehensive parameters comprise characteristic parameters of the initial nickel nitrate solution and the addition amount of a pH regulator;
characteristic parameters of the nickel nitrate solution comprise a nickel nitrate solution adjusting coefficient, the type of a pH regulator, the concentration of the pH regulator and the type of impurities in the nickel nitrate solution;
it should be noted that, the types of impurities in the nickel nitrate solution can be obtained by a chromatographic analysis method, and the impurity types can be detected by the separation behavior of the impurities in the solution in a chromatographic column, and the common chromatographic analysis method includes:
Liquid chromatography HPLC: the method is suitable for detecting non-volatile organic impurities, and is used for separation analysis through a high performance liquid chromatographic column;
Ion chromatography IC: the method is suitable for detecting the ion impurities in the solution, and separation analysis is carried out through an ion exchange chromatographic column.
The type of the pH adjuster and the concentration thereof also affect the pH adjusting process, and the type of the pH adjuster includes hydrochloric acid and nitric acid.
Parameters affecting the adjustment coefficient of the nickel nitrate solution include the concentration of the nickel nitrate solution, the pH of the nickel nitrate solution, and the total amount of the nickel nitrate solution.
The expression of the adjustment coefficient of the nickel nitrate solution is as follows:
；
In the formula, The coefficient of the nickel nitrate solution is adjusted,For the concentration of the nickel nitrate solution,Is the pH value of the nickel nitrate solution,For the total amount of the nickel nitrate solution,、AndAs the weight factor of the weight factor,、AndAre all greater than zero.
It should be noted that, in the case of a nickel nitrate solution having a high concentration, more pH adjuster is required to achieve the desired pH, and similarly, the more total amount of the nickel nitrate solution, the more pH adjuster is required to achieve the desired pH, and the greater the pH of the nickel nitrate solution, the more pH adjuster is required to achieve the desired pH.
It should be noted that the size of the weight coefficient is a specific numerical value obtained by quantizing each data, so that the subsequent comparison is convenient, and the size of the weight coefficient depends on the number of the comprehensive parameters and the corresponding weight coefficient is preliminarily set for each group of comprehensive parameters by a person skilled in the art.
The first data analysis module is used for training a machine learning model for predicting the addition amount of the pH regulator based on the collected comprehensive parameters of the extraction and impurity removal of the historical initial nickel nitrate solution, collecting the real-time characteristic parameters of the initial nickel nitrate solution, predicting the addition amount of the pH regulator based on the machine learning model after training, and controlling the dosing assembly 21 to work based on the predicted addition amount of the pH regulator;
The training method of the machine learning model for predicting the addition amount of the pH regulator comprises the following steps:
converting the collected characteristic parameters of the initial nickel nitrate solution into a corresponding group of characteristic vectors;
taking each group of characteristic vectors as input of a machine learning model, taking the added quantity of the pH regulator corresponding to the characteristic parameters of each group of initial nickel nitrate solution as output, taking the added quantity of the pH regulator actually corresponding to the characteristic parameters of each group of initial nickel nitrate solution as a prediction target, and taking the minimized loss function value of the machine learning model as a training target; and stopping training when the loss function value of the machine learning model is smaller than or equal to a preset target loss value.
The machine learning model may be one of a support vector machine regression, a random forest regression, a neural network regression, or the like.
The machine learning model loss function value is the mean square error.
The mean square error is one of the usual loss functions by combining the loss functionsThe minimization is targeted to train the model so that the machine learning model fits the data better, thereby improving the performance and accuracy of the model.
In the loss functionFor the machine learning model to lose function values,Is the feature vector group number; The number of the feature vector groups; is the predicted first The added amount of the pH regulator corresponding to the group characteristic vector,Is the firstThe group characteristic vector actually corresponds to the added amount of the pH regulator.
In the embodiment, the pH regulator addition amount is predicted based on a trained machine learning model for predicting the pH regulator addition amount by collecting the nickel nitrate solution adjustment coefficient, the type of the pH regulator, the concentration of the pH regulator and the type of impurities in the nickel nitrate solution, controlling the operation of the dosing assembly 21 based on the predicted pH regulator addition amount, adding a specified amount of the pH regulator into the extraction reactor 2, adjusting the acidity of the solution to a range suitable for the operation of the extractant, realizing the accurate control of the pH value, and improving the purity of the product after impurity removal;
The method realizes the intelligent self-adaptive adjustment of the addition amount of the pH regulator according to the characteristics of the pH regulator and the difference of raw materials, ensures the acidity adjustment effect on the solution, ensures that the acidity of the solution is suitable for the working range of the extractant, and ensures the extraction effect.
Example 2
1-3, The present embodiment further includes a second data acquisition module and a second data analysis module;
specifically, the embodiment is used for solving the problems that in the prior art, in the extraction process of the nickel nitrate solution, the extraction control parameters, namely the type of the extractant, the dosage of the extractant, the extraction time and the extraction temperature, are usually manually controlled or controlled based on preset parameters, namely a user can only control the operation of the extraction reactor 2 according to the preset parameters, can not automatically generate control parameters based on the characteristics of the nickel nitrate solution, and control the operation of the extraction reactor 2, so that the defects of incomplete impurity removal and unstable product quality are easily caused.
The second data acquisition module acquires the pH value of the nickel nitrate solution after the addition of the pH regulator is finished, and marks the pH value as an extraction pH value;
The second data analysis module inputs the acquired characteristic parameters of the extraction pH value and the initial nickel nitrate solution into a pre-constructed extraction parameter recommendation model to obtain an extraction parameter recommendation set label, so that an extraction parameter recommendation set corresponding to the extraction parameter recommendation set label is obtained, the working parameters of the extraction reactor 2 are controlled based on the control parameters in the extraction parameter recommendation set, and the nickel nitrate solution is subjected to extraction treatment.
The extraction parameter recommendation set is as follows:
Wherein, For the aggregate label asThe type of the corresponding extractant is that of the liquid,For the aggregate label asThe corresponding dosage of the extractant is adopted in the process,For the aggregate label asThe corresponding extraction temperature is used for the extraction,For the aggregate label asThe corresponding extraction time.
The training method of the extraction parameter recommendation model comprises the following steps:
presetting a corresponding number for the extraction parameter recommendation set;
Converting the characteristic parameters of the extracted pH value and the initial nickel nitrate solution into a corresponding set of characteristic vectors, taking each set of characteristic vectors as input of a machine learning model, taking a set of extraction parameter recommendation set numbers corresponding to the characteristic parameters of each set of extracted pH value and the initial nickel nitrate solution as output, taking a set of extraction parameter recommendation set numbers actually corresponding to the characteristic parameters of each set of extracted pH value and the initial nickel nitrate solution as a prediction target, and taking a minimum machine learning model loss function value as a training target; and stopping training when the machine learning model loss function value is smaller than or equal to a preset target loss value.
The machine learning model loss function value is the mean square error.
By combining the loss functions: The model is trained for the purpose of minimization, so that the machine learning model is better fitted with data, and the performance and accuracy of the model are improved;
In the loss function For the machine learning model to lose function values,Is the feature vector group number; The number of the feature vector groups; Is the first The extraction parameter recommendation set number of the group feature vector prediction,Is the firstThe extraction parameter recommendation set numbers actually corresponding to the group feature vectors.
Other model parameters of the machine learning model, target loss values, optimization algorithms, verification set proportion of training set test sets, optimization of loss functions and the like are all realized through actual engineering, and the model parameters are obtained after experimental optimization is continuously carried out.
In this embodiment, the collected pH value of extraction and the characteristic parameters of the initial nickel nitrate solution are input into a pre-built extraction parameter recommendation model to obtain an extraction parameter recommendation set label, so as to obtain an extraction parameter recommendation set corresponding to the extraction parameter recommendation set label, and the working parameters of the extraction reactor 2 are controlled based on the control parameters in the extraction parameter recommendation set, so that the nickel nitrate solution is extracted, the work of the extraction reactor 2 is controlled by automatically generating the control parameters, that is, the best extractant type and the optimal extractant dosage, the optimal extraction temperature and the optimal extraction time are intelligently selected, the impurity removal efficiency is improved, the cost is reduced, and the defects that the impurity removal is incomplete and the product quality is unstable easily caused by the fact that the control parameters cannot be automatically generated based on the nickel nitrate solution characteristics in the prior art are overcome, and the work of the extraction reactor 2 is controlled.
Example 3
Referring to fig. 4, the embodiment discloses a method for separating and removing impurities from nickel nitrate;
The nickel nitrate separating and impurity removing method is realized based on a nickel nitrate separating and impurity removing device and comprises the following steps:
introducing an initial nickel nitrate solution to be treated into an impurity filter 1, and performing preliminary filtration to remove insoluble solid impurities;
Adding the filtered nickel nitrate solution into the extraction reactor 2, adding a pH regulator into the extraction reactor 2 through a dosing assembly 21, and adjusting the acidity of the solution to a range suitable for the working of the extractant;
Adding an extracting agent into the extraction reactor 2, controlling a heater 23 and a stirring assembly 22 in the extraction reactor 2 to work, heating and stirring and mixing liquid in the extraction reactor 2, ensuring that the reaction is carried out at a proper temperature, ensuring that the solution and the extracting agent are fully mixed, and improving the reaction efficiency and the product quality;
Separating the extracted solution and the extracting agent by a centrifugal machine 3, enriching target metals in the extracting agent, reintroducing the extracting agent enriched with the target metals into an extraction reactor 2, and separating the target metals from the extracting agent by adding a back-extracting agent;
The back extraction liquid is filtered by a filtering device to remove residual impurities, and concentrated and crystallized by an evaporator 4 and a crystallizer 5 to obtain a high-purity nickel nitrate product.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the foregoing embodiments, and that the foregoing embodiments and description are merely illustrative of the principles of this invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, and these changes and modifications fall within the scope of the invention as hereinafter claimed. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (10)

1. The utility model provides a nickel nitrate separation edulcoration device which characterized in that includes:
an impurity filter (1) for preliminarily filtering the initial nickel nitrate solution to remove insoluble solid impurities;
the extraction reactor (2) is connected with the liquid outlet of the impurity filter (1) in a conducting way, and the initial nickel nitrate solution is discharged into the extraction reactor (2) after being preliminarily filtered by the impurity filter (1);
the dosing assembly (21) is arranged on the extraction reactor (2) and is used for automatically adding the pH regulator;
a reaction control unit (24), the reaction control unit (24) comprising:
The first data acquisition module acquires comprehensive parameters of historical initial nickel nitrate solution extraction and impurity removal, wherein the comprehensive parameters comprise characteristic parameters of the initial nickel nitrate solution and the addition amount of a pH regulator;
the first data analysis module is used for training a machine learning model for predicting the addition amount of the pH regulator based on the collected comprehensive parameters of the extraction and impurity removal of the historical initial nickel nitrate solution, collecting the real-time characteristic parameters of the initial nickel nitrate solution, predicting the addition amount of the pH regulator based on the machine learning model after training, and controlling the dosing assembly (21) to work based on the predicted addition amount of the pH regulator;
The second data acquisition module acquires the pH value of the nickel nitrate solution after the addition of the pH regulator is finished, and marks the pH value as an extraction pH value;
the second data analysis module inputs the collected characteristic parameters of the extraction pH value and the initial nickel nitrate solution into a pre-constructed extraction parameter recommendation model to obtain an extraction parameter recommendation set label, so that an extraction parameter recommendation set corresponding to the extraction parameter recommendation set label is obtained, the working parameters of the extraction reactor (2) are controlled based on the control parameters in the extraction parameter recommendation set, and the nickel nitrate solution is subjected to extraction treatment.
2. The nickel nitrate separating and purifying device according to claim 1, further comprising:
A stirring assembly (22) installed in the extraction reactor (2) for stirring and mixing the liquid in the extraction reactor (2);
And a heater (23) installed in the extraction reactor (2) for heating the solution in the extraction reactor (2).
3. The nickel nitrate separating and purifying device according to claim 1, wherein the dosing assembly (21) comprises a storage tank (211), a liquid conveying pipe (212) and a flow pump (213), the storage tank (211) is used for storing a pH regulator, the storage tank (211) is in conductive connection with the extraction reactor (2) through the liquid conveying pipe (212), the flow pump (213) is arranged on the liquid conveying pipe (212), and the flow pump (213) is used for pumping the pH regulator in the storage tank (211) into the extraction reactor (2).
4. The nickel nitrate separating and purifying device according to claim 1, further comprising: the centrifugal machine (3) is connected with the extraction reactor (2) in a conducting way and is used for separating the extracting agent;
the evaporator (4) is connected with the extraction reactor (2) in a conducting way;
And the crystallizer (5) is connected with the evaporator (4) in a conducting way.
5. The nickel nitrate separating and impurity removing device according to claim 2, wherein the stirring assembly (22) comprises a stirring shaft (221), a stirring motor (222) and stirring blades (223), the stirring blades (223) are fixed on the stirring shaft (221) through bolts, the stirring motor (222) is fixed on the outer wall of the extraction reactor (2) through bolts, and an output shaft of the stirring motor (222) is fixedly connected with the stirring shaft (221) through a coupling.
6. The nickel nitrate separating and purifying device according to claim 1, wherein the characteristic parameters of the nickel nitrate solution comprise a nickel nitrate solution adjusting coefficient, a type of a pH regulator, a concentration of the pH regulator and a type of impurities in the nickel nitrate solution;
parameters affecting the adjustment coefficient of the nickel nitrate solution comprise the concentration of the nickel nitrate solution, the pH value of the nickel nitrate solution and the total amount of the nickel nitrate solution;
The expression of the regulating coefficient of the nickel nitrate solution is as follows:
；
In the formula, The coefficient of the nickel nitrate solution is adjusted,For the concentration of the nickel nitrate solution,Is the pH value of the nickel nitrate solution,For the total amount of the nickel nitrate solution,、AndAs the weight factor of the weight factor,、AndAre all greater than zero.
7. The nickel nitrate separating and purifying device according to claim 1, wherein the training method of the machine learning model for predicting the addition amount of the pH adjustor comprises:
converting the collected characteristic parameters of the initial nickel nitrate solution into a corresponding group of characteristic vectors;
Taking each group of characteristic vectors as input of the machine learning model, taking the adding amount of the pH regulator corresponding to the characteristic parameters of each group of initial nickel nitrate solution as output, taking the adding amount of the pH regulator actually corresponding to the characteristic parameters of each group of initial nickel nitrate solution as a prediction target, and taking the minimized loss function value of the machine learning model as a training target; and stopping training when the loss function value of the machine learning model is smaller than or equal to a preset target loss value.
8. The nickel nitrate separating and purifying device according to claim 1, wherein the recommended set of extraction parameters is:
；
Wherein, For the aggregate label asThe type of the corresponding extractant is that of the liquid,For the aggregate label asThe corresponding dosage of the extractant is adopted in the process,For the aggregate label asThe corresponding extraction temperature is used for the extraction,For the aggregate label asThe corresponding extraction time.
9. The nickel nitrate separating and purifying device according to claim 8, wherein the training method of the extraction parameter recommendation model comprises the following steps:
presetting a corresponding number for the extraction parameter recommendation set;
Converting the characteristic parameters of the extracted pH value and the initial nickel nitrate solution into a corresponding set of characteristic vectors, taking each set of characteristic vectors as input of a machine learning model, taking a set of extraction parameter recommendation set numbers corresponding to the characteristic parameters of each set of extracted pH value and the initial nickel nitrate solution as output, taking a set of extraction parameter recommendation set numbers actually corresponding to the characteristic parameters of each set of extracted pH value and the initial nickel nitrate solution as a prediction target, and taking a minimum machine learning model loss function value as a training target; and stopping training when the machine learning model loss function value is smaller than or equal to a preset target loss value.
10. A method for separating and removing impurities from nickel nitrate, which is realized based on the nickel nitrate separating and removing device as claimed in any one of claims 1-4, and is characterized by comprising the following steps:
introducing an initial nickel nitrate solution to be treated into an impurity filter (1), and performing preliminary filtration to remove insoluble solid impurities;
Adding the filtered nickel nitrate solution into an extraction reactor (2), adding a pH regulator into the extraction reactor (2) through a dosing assembly (21), and adjusting the acidity of the solution to a range suitable for the working of the extractant;
Adding an extracting agent into the extraction reactor (2), controlling a heater (23) and a stirring assembly (22) in the extraction reactor (2) to work, heating and stirring and mixing liquid in the extraction reactor (2), ensuring that the reaction is carried out at a proper temperature, and ensuring that the solution and the extracting agent are fully mixed;
separating the extracted solution and the extracting agent by a centrifugal machine (3), enriching target metals in the extracting agent, introducing the extracting agent enriched with the target metals into an extraction reactor (2) again, and separating the target metals from the extracting agent by adding a back extracting agent;
Residual impurities are removed from the back extraction liquid through filtering equipment, and the back extraction liquid is concentrated and crystallized through an evaporator (4) and a crystallizer (5) to obtain a high-purity nickel nitrate product.
CN202411329524.5A 2024-09-24 2024-09-24 Nickel nitrate separating and impurity removing device and impurity removing method Active CN118846581B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411329524.5A CN118846581B (en) 2024-09-24 2024-09-24 Nickel nitrate separating and impurity removing device and impurity removing method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411329524.5A CN118846581B (en) 2024-09-24 2024-09-24 Nickel nitrate separating and impurity removing device and impurity removing method

Publications (2)

Publication Number Publication Date
CN118846581A CN118846581A (en) 2024-10-29
CN118846581B true CN118846581B (en) 2024-11-22

Family

ID=93177174

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411329524.5A Active CN118846581B (en) 2024-09-24 2024-09-24 Nickel nitrate separating and impurity removing device and impurity removing method

Country Status (1)

Country Link
CN (1) CN118846581B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102154549A (en) * 2011-02-21 2011-08-17 宇辰新能源材料科技无锡有限公司 Production method for high-purity hard-agglomeration-free superfine nickel oxide or cobalt and nickel or cobalt powder
CA2949580A1 (en) * 2015-12-09 2017-06-09 Bhp Billiton Nickel West Pty Ltd Process for selective acid leaching nickel and cobalt from a mixed hydroxide intermediate

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103818973B (en) * 2014-02-28 2016-08-17 金川集团股份有限公司 A kind of preparation method of nickel nitrate
US10754334B2 (en) * 2016-05-09 2020-08-25 Strong Force Iot Portfolio 2016, Llc Methods and systems for industrial internet of things data collection for process adjustment in an upstream oil and gas environment
CN110963534A (en) * 2019-11-25 2020-04-07 怀化恒安石化有限公司 Deep extraction and impurity removal device for production process of nickel nitrate product
CN111652090A (en) * 2020-05-18 2020-09-11 黑龙江省科学院智能制造研究所 Digital management method for China hemp planting
CN216863873U (en) * 2022-03-17 2022-07-01 绍兴英格利新材料有限公司 Nickel metal draws with filtering edulcoration device
CN116272323A (en) * 2023-02-10 2023-06-23 华能景泰热电有限公司 Regulation method of anti-blinding wide-load regulation system for wet desulfurization slurry
CN117926002A (en) * 2024-02-22 2024-04-26 万华化学集团股份有限公司 Nickel sulfate solution separation impurity removal process

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102154549A (en) * 2011-02-21 2011-08-17 宇辰新能源材料科技无锡有限公司 Production method for high-purity hard-agglomeration-free superfine nickel oxide or cobalt and nickel or cobalt powder
CA2949580A1 (en) * 2015-12-09 2017-06-09 Bhp Billiton Nickel West Pty Ltd Process for selective acid leaching nickel and cobalt from a mixed hydroxide intermediate

Also Published As

Publication number Publication date
CN118846581A (en) 2024-10-29

Similar Documents

Publication Publication Date Title
CN103466870A (en) Material recovery method of wastewater containing high-concentration ammonia-nitrogen and heavy metal ions and treatment system
CN103343239B (en) Method for separating and purifying rhodium
CN105385851A (en) Treatment method of acid pickling waste liquid
CN119285041A (en) A system and method for recycling pickling waste liquid
CN118846581B (en) Nickel nitrate separating and impurity removing device and impurity removing method
CN114159835A (en) Automatic circulating cadmium removal device and method for cobalt chloride solution
CN211771501U (en) Device for continuously preparing mixed rare earth chloride feed liquid by using rare earth sulfate solution
CN105712542A (en) Hydrofluoric acid wastewater recycling treatment device for photovoltaic and semiconductor industries and technology thereof
CN118996173B (en) A continuous impurity removal and precipitation method for an ionic rare earth candle filter device
CN109355499B (en) Method for removing chloride ions from nickel sulfate solution
CN217780770U (en) System for producing nickel sulfate solution
CN110453246A (en) A method for in-situ synthesis of copper-arsenic alloy from copper electrolyte
CN205556320U (en) Be used for photovoltaic, semiconductor trade hydrofluoric acid waste water recycling processing apparatus
CN217015415U (en) Automatic circulating cadmium removing device for cobalt chloride solution
CN210419602U (en) Raw material recovery device for 1, 2-benzisothiazolin-3-ketone production wastewater
CN208562480U (en) A kind of recovery system of cupric silicon powder
CN101532086B (en) A vanadium-containing resin desorption method
CN223980479U (en) A pH-controlled deammoniation separation device for a mixed solution of ammonium tungstate and molybdate
CN113388866B (en) Combined recovery system and method for palladium-containing waste liquid of circuit board
CN112708780A (en) Method for removing aluminum from nickel-cobalt solution
CN205999177U (en) A kind of processing system for producing the waste water that manufacture demineralized water is produced in viscose rayon
CN222593560U (en) Automatic mixing system for RO membrane treatment of ammonium nitrate process wastewater
CN218435399U (en) Chemical nickel waste water resourceful treatment device
CN217264941U (en) Contain noble metal waste water recovery system
CN223201613U (en) Device for continuously preparing low-impurity rare earth carbonate by using mixed precipitant

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