Control method and system for discharging electroplating wastewater

Abstract

The invention discloses a control method and system for electroplating wastewater discharge, and the method comprises the steps: carrying out the analysis and recognition of an electroplating process, obtaining the technological parameters of each process, carrying out the sampling detection in a discharge pipeline corresponding to each process, and obtaining the first detection data of a corresponding pollutant; according to the process parameters, based on a stoichiometric model, the putting amount is obtained, reaction substances with the corresponding putting amount are put into the corresponding discharging pipelines for reaction, sampling detection is conducted after the reaction is sufficient, and second detection data are obtained; constructing a prediction model based on the process parameters, the first detection data, the actual delivery amount and the second detection data; and inputting the process parameters detected in real time into the prediction model to obtain the predicted putting amount of the reaction substance. By means of the mode, more accurate dosing control can be achieved, the treatment efficiency of the electroplating wastewater is effectively improved, and the dosing cost is controlled.

Description

Technical Field

[0001] This application relates to the field of electroplating technology, and in particular to a method and system for controlling the discharge of electroplating wastewater. Background Technology

[0002] Industrial electroplating processes generate various types of wastewater, which contain a variety of metal ions or toxic substances that are harmful to human health. Therefore, the wastewater generated in the electroplating process must be strictly treated until it meets the discharge standards before it can be discharged harmlessly.

[0003] In existing electroplating wastewater treatment processes, wastewater at each stage is often classified and tested. If the test results are satisfactory, the wastewater proceeds to the next step; if not, it is recycled for repeated treatment to ensure that discharge standards are met and to avoid exceeding limits. However, this testing and treatment method prolongs wastewater treatment time and leads to repeated treatment. Furthermore, the dosage of reactants used in the classified testing and treatment is highly dependent on experience, and inaccurate dosage can easily result in excessive reagent consumption, making it difficult to achieve a balance between cost control and efficiency. Summary of the Invention

[0004] This application provides a method and system for controlling the discharge of electroplating wastewater, in order to solve the problems of precision and cost in the treatment of electroplating wastewater.

[0005] To solve the above-mentioned technical problems, one technical solution adopted in this application is: to provide a method for controlling the discharge of electroplating wastewater, comprising: S10: Analyze and identify the electroplating process, obtain the process parameters of each process, and take samples from the emission pipelines corresponding to each process to obtain the first detection data of the corresponding pollutants. S20: Based on the process parameters, the dosage is obtained according to the stoichiometric model, and the corresponding dosage of reactant is added into the corresponding discharge pipeline to react. After the reaction is complete, sampling and testing are performed to obtain the second detection data. S30: Construct a prediction model based on the process parameters, the first detection data, the actual dosage, and the second detection data; S40: Input the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants.

[0006] In one possible implementation, the step of analyzing and identifying the electroplating process, obtaining process parameters for each process, and sampling and detecting the corresponding pollutants in the emission pipelines of each process to obtain the first detection data of the pollutants includes: S11: According to the electroplating process, each process step and corresponding discharge pipeline are marked and associated with the corresponding pollutants.

[0007] In one possible implementation, the step of obtaining the dosage based on the process parameters and a stoichiometric model includes: S21: Calculate the amount of each of the pollutants to be released based on the relevant chemical reaction equations corresponding to each of the emission pipelines.

[0008] In one possible implementation, the step of constructing a prediction model based on the process parameters, the first detection data, the actual dosage, and the second detection data includes: S31: Define the process parameters, the first detection data, the actual dosage, and the second detection data as basic features, and extract derived features based on the training set. The derived features include concentration gradient, reaction efficiency, and stability. Concatenate the basic features and the derived features to form structured data. Several structured data sets form a dataset, which is used to train the model.

[0009] In one possible implementation, the step of concatenating the basic features with the derived features to form structured data, and the formation of a dataset from several structured data sets, wherein the dataset is used to train the model, includes: S32: Based on the timestamp and sample dimension, the basic features and the derived features are concatenated to form the structured data.

[0010] In one possible implementation, the step of concatenating the basic features with the derived features to form structured data, and the formation of a dataset from several structured data sets, wherein the dataset is used to train the model, includes: S33: Detect and filter the structured data, remove outliers and impute default values.

[0011] In one possible implementation, after the step of inputting the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants, the method further includes: S41: After the reaction, the discharge pipeline is sampled and tested, and third test data is obtained; S42: Compare the third detection data with the emission standard. If the third detection data does not meet the emission standard, input the third detection data into the prediction model and obtain the supplementary dosage. If the third detection data meets the emission standard, execute the subsequent wastewater discharge process.

[0012] In one possible implementation, after the step of inputting the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants, the method further includes: S50: Sample and test at the inlet of each of the discharge pipes to obtain inlet test data; sample and test at the outlet of each of the discharge pipes to obtain outlet test data; compare the inlet test data with the outlet test data, and start cleaning of the corresponding discharge pipe when the difference exceeds a threshold.

[0013] To solve the above-mentioned technical problems, another technical solution adopted in this application is: to provide a control system for electroplating wastewater discharge, applicable to the control method for electroplating wastewater discharge as described above, including: The primary detection module is used to analyze and identify the electroplating process, obtain the process parameters of each process, and take samples from the emission pipelines corresponding to each process to obtain the first detection data of the corresponding pollutants. The secondary detection module is used to calculate the dosage based on the process parameters and the stoichiometric model, and to add the corresponding dosage of the reactant into the corresponding discharge pipeline to carry out a primary reaction. After the reaction is complete, sampling and detection are performed to obtain the second detection data. The prediction module is used to construct a prediction model based on the process parameters, the first detection data, the actual dosage, and the second detection data. The control module is used to input the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants.

[0014] In one possible implementation, a cleaning module is also included. The monitoring module is used to sample and detect the inlet of each of the discharge pipes to obtain inlet detection data; to sample and detect the outlet of each of the discharge pipes to obtain outlet detection data; and to compare the inlet detection data with the outlet detection data. When the difference exceeds a threshold, the cleaning of the corresponding discharge pipe is initiated.

[0015] The beneficial effects of this application are as follows: Unlike the prior art, this application discloses a method and system for controlling the discharge of electroplating wastewater. By recording the process parameters of each step in the electroplating process and using them to calculate the amount of reactants to be added, and by constructing a model based on the changes in detection data before and after the addition amount to make accurate predictions and adjustments to the dosing, more precise dosing control can be achieved, effectively improving the treatment efficiency of electroplating wastewater and controlling the cost of dosing. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein: Figure 1 This is a schematic flowchart of an embodiment of the method for controlling the discharge of electroplating wastewater according to this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] The terms "first," "second," and "third" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] Please see Figure 1 The embodiments of this application include: a method for controlling the discharge of electroplating wastewater, comprising: S10: Analyze and identify the electroplating process, obtain the process parameters of each process, and take samples from the emission pipelines corresponding to each process to obtain the first detection data of the corresponding pollutants. S20: Based on the process parameters and the stoichiometric model, the dosage is obtained, and the corresponding dosage of the reactant is added into the corresponding discharge pipeline to react. After the reaction is complete, sampling and testing are performed to obtain the second test data. S30: Construct a prediction model based on process parameters, first test data, actual dosage, and second test data; S40: Input the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants.

[0021] In actual production, electroplating processes can involve electroplating steps with various metals, and the workpieces are processed sequentially in a linear flow. Step S10 analyzes the electroplating process, identifying each step, including pretreatment, electroplating deposition, and post-treatment. Electroplating deposition may include one or more of the following depending on the current process: chromium plating, nickel plating, copper plating, acid-base treatment, passivation, etc., which also need to be identified and specified. Simultaneously, sampling and testing are performed on the corresponding discharge pipelines. The detection targets at the detection ends of each discharge pipeline correspond to the process flow of that discharge pipeline, such as detecting chromium ion concentration for chromium plating and detecting nickel ion concentration for nickel plating.

[0022] In step S20, the specific process parameters for each process are as follows, such as the chemical reaction equation for the wastewater treatment of chromium plating in this embodiment: .

[0023] Sodium sulfite, as a reducing agent, is used to reduce hexavalent chromium to trivalent chromium in an environment with a pH of 2-3. Then, based on the concentration C of hexavalent chromium in the wastewater, the wastewater flow rate Q, the molar mass M1 of sodium sulfite, and the molar mass M2 of chromium, the total amount of hexavalent chromium n1 per unit time is calculated sequentially. .

[0024] Based on chemical reaction equations and The molar ratio is 1:3, that is, 1 mol Corresponding to 3mol ,therefore Theoretical value of the amount of delivery X for: .

[0025] Considering the sufficiency of the reaction, an excess coefficient k can be further calculated to obtain the final dosage. The dosage is a theoretical amount obtained through calculation. The actual dosage may be affected by factors such as the degree of reaction, reagent quality, and electroplating quality, and may not be sufficient for complete treatment. Therefore, it is necessary to conduct a second sampling and testing after the reaction to obtain secondary test data to further verify the actual effect of the initial dosage. This embodiment is for illustrative purposes only. Specific parameters can be preset according to the adopted process, the reactants used, and the chemical reaction equations involved. In subsequent actual treatment, the corresponding scheme can be directly selected for calculation, improving the efficiency of wastewater treatment.

[0026] In step S30, the data from the previous step is organized, including the specific process parameters used, the first detection data, the actual dosage, and the second detection data, and a model is constructed for prediction. This embodiment uses a random forest model, primarily considering its high robustness and applicability to large amounts of data. The large data characteristics involved in this technical background, as well as the uncertainties arising from the complexities of wastewater treatment, perfectly align with the advantages of the random forest model. Other prediction models can also be selected under appropriate circumstances; the choice of this model in this embodiment is merely an example and not a limitation. The process parameters refer to the relevant parameters corresponding to each step of the specific electroplating deposition process. Mapping these parameters to the actual detection values ​​improves the accuracy of subsequent model calculations, thereby achieving the goal of directly predicting the subsequent dosage based on the input process parameters. Simultaneously, the predicted dosage is constrained and verified by combining the emission standards of various pollutants to ensure the accuracy of the predicted dosage.

[0027] After organizing and summarizing the data, a dataset is obtained. A random forest model is trained based on this dataset. Initial parameters are set during model training. In this embodiment, the number of decision trees is 100, the maximum depth is set to 15, the splitting criterion is mean squared error, and a bootstrap sampling method is used to construct a subset of the dataset. The dataset is divided into a training set and a validation set in an 8:2 ratio. 100 decision trees are constructed based on the training set, and each tree infers the predicted delivery amount. Finally, the average of all results is used as the output.

[0028] In step S40, based on the established prediction model, the real-time detected process parameters are input to directly obtain the corresponding predicted dosage. Specifically, the input end of the electroplating equipment can be directly linked to the input end of the prediction model. When the operator sets the electroplating process parameters, the wastewater treatment end starts processing simultaneously, ensuring the synchronization of data and processing efficiency at both ends.

[0029] In one embodiment, the steps of analyzing and identifying the electroplating process, obtaining process parameters for each process, and sampling and detecting the corresponding pollutants in the emission pipelines of each process to obtain first detection data include: S11: According to the electroplating process, mark each process step and the corresponding emission pipeline, and associate them with the corresponding pollutants.

[0030] Since the pollutants produced by each process are fixed and their respective emission pipelines are independent of each other, marking and associating the emission pipelines corresponding to each process step facilitates subsequent direct data collection and sampling.

[0031] In one embodiment, the step of obtaining the dosage based on a stoichiometric model according to process parameters includes: S21: Calculate the amount of each reactant to be added based on the pollutants corresponding to each discharge pipeline and the relevant chemical reaction equations.

[0032] The pollutants corresponding to different emission pipelines are specific and fixed. Therefore, it is necessary to calculate the required amount of each pollutant based on the input material and its corresponding chemical reaction equation, using stoichiometric relationships. Although the pollutants are fixed, different input materials will be selected for specific processes, and the corresponding chemical reactions for different input materials are also different. Therefore, the actual dosage must be calculated separately during dosing.

[0033] In one embodiment, the step of constructing a prediction model based on process parameters, first detection data, actual dosage, and second detection data includes: S31: Define process parameters, first detection data, actual dosage, and second detection data as basic features, and extract derived features based on the training set. Derived features include concentration gradient, reaction efficiency, and stability. Concatenate the basic features and derived features to form structured data. Several structured data sets form a dataset, which is used to train the model.

[0034] Specifically, basic features refer to known conditions that can be directly obtained through detection or input, while derived features refer to conditions obtained through analysis and processing based on basic features, in order to capture hidden relationships between variables.

[0035] In terms of basic features, process parameters can be synchronously input through the electroplating section or directly obtained by calling the information of the electroplating system; the first and second detection data are the pollution levels before and after the dosing, which are obtained directly through sampling and detection. Although the dosing amount has been calculated, the actual dosing amount can be directly read through the flow meter or the metering device in the medicine tank at the time of dosing, which is closer to the actual usage amount than the dosing amount obtained by calculation.

[0036] Derivative characteristics include concentration gradient, which is the actual amount of pollutants removed, reflecting the treatment effect and difficulty of the additive; reaction efficiency, which is the amount of pollutants removed per unit dosage, reflecting the reaction efficiency of the additive; and stability, which is the concentration fluctuation coefficient of the pollutants, calculated by dividing the standard deviation by the average value, reflecting the fluctuation of pollutant concentration. For cases with drastic fluctuations, it is necessary to increase the redundancy of the additive.

[0037] If necessary, other features such as environmental pH and temperature can be incorporated to improve the accuracy of the prediction model. The aforementioned basic and derived features are then concatenated to form a dataset, which is used to train the model.

[0038] In one embodiment, the steps of concatenating basic features and derived features to form structured data, and using the structured data to form a dataset for training a model include: S32: Based on timestamps and sample dimensions, basic features and derived features are concatenated to form structured data.

[0039] Based on timestamps, data from the same moment are grouped together and organized into structured data with the same sample dimensions. In this embodiment, a single piece of structured data is presented as follows: [Chromium plating, 5A / dm] 2 , 50mg / L, 200g / L, 10mg / L, 40mg / L, 0.5mg / g, 0.08].

[0040] The data sequentially indicates the process, electroplating current density, first detection data (initial concentration), actual dosage, second detection concentration (post-reaction concentration), concentration gradient, reaction efficiency, and stability. More data features can be added based on actual process conditions and requirements. Fixed-structure processing of the data facilitates subsequent model training and prediction.

[0041] In one embodiment, the steps of concatenating basic features and derived features to form structured data, and using the structured data to form a dataset for training a model include: S33: Perform detection and filtering on structured data, removing outliers and imputing default values.

[0042] Outliers are removed, and then the missing values ​​are imputed. Specifically, the structured data can be arranged according to the timestamp, and then the missing values ​​can be filled by imputation based on the data before and after the missing values. Various methods such as mean imputation and regression imputation can be used, and this application does not limit this.

[0043] In one embodiment, after the step of inputting the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants, the method further includes: S41: After the reaction, samples are taken from the discharge pipeline for testing, and third test data is obtained; S42: Compare the third detection data with the emission standards. If the third detection data does not meet the emission standards, input the third detection data into the prediction model and obtain the supplementary dosage. If the third detection data meets the emission standards, execute the subsequent wastewater discharge process.

[0044] A third sampling test is conducted after the initial application to ensure that the wastewater concentration meets discharge standards for subsequent discharge and transportation. Simultaneously, the third test data can be used to validate and constrain the prediction model, further refining it. Specifically, the third test data is substituted into the positions of the original second test data to construct a new dataset for training.

[0045] In one embodiment, after the step of inputting the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants, the method further includes: S50: Sample and test at the inlet of each discharge pipeline to obtain inlet test data; sample and test at the outlet of each discharge pipeline to obtain outlet test data; compare the inlet test data with the outlet test data, and start cleaning of the corresponding discharge pipeline when the difference exceeds the threshold.

[0046] In actual treatment, long-term use of discharge pipelines can lead to pipe pollution and blockage. These problems can affect the accuracy of wastewater treatment reactions and detection. Therefore, regular inspection and cleaning, as well as regular maintenance of discharge pipelines, can effectively improve the accuracy of detection and the efficiency of wastewater treatment.

[0047] The control system for electroplating wastewater discharge is applicable to the control methods for electroplating wastewater discharge described above, including: The primary detection module is used to analyze and identify the electroplating process, obtain the process parameters of each process, and take samples from the emission pipelines corresponding to each process to obtain the first detection data of the corresponding pollutants. The secondary detection module is used to calculate the dosage based on the process parameters and the stoichiometric model, and to add the corresponding dosage of the reactant into the corresponding discharge pipeline to carry out the first reaction. After the reaction is complete, the sample is taken for detection to obtain the second detection data. The prediction module is used to build a prediction model based on process parameters, first detection data, actual dosage and second detection data; The control module is used to input the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants.

[0048] In one embodiment, the control system for electroplating wastewater discharge further includes a cleaning module. The monitoring module is used to sample and detect the inlet of each discharge pipeline to obtain inlet detection data; to sample and detect the outlet of each discharge pipeline to obtain outlet detection data; and to compare the inlet detection data with the outlet detection data. When the difference exceeds a threshold, the cleaning of the corresponding discharge pipeline is initiated.

[0049] Specifically, detection devices need to be installed at the inlet and outlet of the discharge pipeline to ensure data sampling and testing at both locations.

[0050] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for controlling the discharge of electroplating wastewater, characterized in that, include: S10: Analyze and identify the electroplating process, obtain the process parameters of each process, and take samples from the emission pipelines corresponding to each process to obtain the first detection data of the corresponding pollutants. S20: Based on the process parameters, the dosage is obtained according to the stoichiometric model, and the corresponding dosage of reactant is added into the corresponding discharge pipeline to react. After the reaction is complete, sampling and testing are performed to obtain the second detection data. S30: Construct a prediction model based on the process parameters, the first detection data, the actual dosage, and the second detection data; S40: Input the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants.

2. The method for controlling the discharge of electroplating wastewater according to claim 1, characterized in that, The steps of analyzing and identifying the electroplating process, obtaining process parameters for each process, and sampling and testing the corresponding pollutants in the emission pipelines of each process to obtain the first detection data of the corresponding pollutants include: S11: According to the electroplating process, each process step and corresponding discharge pipeline are marked and associated with the corresponding pollutants.

3. The method for controlling the discharge of electroplating wastewater according to claim 2, characterized in that, The step of obtaining the dosage based on the process parameters and a stoichiometric model includes: S21: Calculate the amount of each of the pollutants to be released based on the relevant chemical reaction equations corresponding to each of the emission pipelines.

4. The method for controlling the discharge of electroplating wastewater according to claim 1, characterized in that, The step of constructing a prediction model based on the process parameters, the first detection data, the actual dosage, and the second detection data includes: S31: Define the process parameters, the first detection data, the actual dosage, and the second detection data as basic features, and extract derived features based on the training set. The derived features include concentration gradient, reaction efficiency, and stability. Concatenate the basic features and the derived features to form structured data. Several structured data sets form a dataset, which is used to train the model.

5. The method for controlling the discharge of electroplating wastewater according to claim 4, characterized in that, The step of concatenating the basic features and the derived features to form structured data, and then using several pieces of structured data to form a dataset for training the model, includes: S32: Based on the timestamp and sample dimension, the basic features and the derived features are concatenated to form the structured data.

6. The method for controlling the discharge of electroplating wastewater according to claim 5, characterized in that, The step of concatenating the basic features and the derived features to form structured data, and then using several pieces of structured data to form a dataset for training the model, includes: S33: Detect and filter the structured data, remove outliers and impute default values.

7. The method for controlling the discharge of electroplating wastewater according to claim 1, characterized in that, After the step of inputting the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants, the method further includes: S41: After the reaction, the discharge pipeline is sampled and tested, and third test data is obtained; S42: Compare the third detection data with the emission standard. If the third detection data does not meet the emission standard, input the third detection data into the prediction model and obtain the supplementary dosage. If the third detection data meets the emission standard, execute the subsequent wastewater discharge process.

8. The method for controlling the discharge of electroplating wastewater according to claim 1, characterized in that, After the step of inputting the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants, the method further includes: S50: Sample and test at the inlet of each of the discharge pipes to obtain inlet test data; sample and test at the outlet of each of the discharge pipes to obtain outlet test data; compare the inlet test data with the outlet test data, and start cleaning of the corresponding discharge pipe when the difference exceeds a threshold.

9. A control system for electroplating wastewater discharge, applicable to the control method for electroplating wastewater discharge as described in any one of claims 1 to 8, characterized in that, include: The primary detection module is used to analyze and identify the electroplating process, obtain the process parameters of each process, and take samples from the emission pipelines corresponding to each process to obtain the first detection data of the corresponding pollutants. The secondary detection module is used to calculate the dosage based on the process parameters and the stoichiometric model, and to add the corresponding dosage of the reactant into the corresponding discharge pipeline to carry out a primary reaction. After the reaction is complete, sampling and detection are performed to obtain the second detection data. The prediction module is used to construct a prediction model based on the process parameters, the first detection data, the actual dosage, and the second detection data. The control module is used to input the real-time detected process parameters into the prediction model to obtain the predicted dosage of the reactants.

10. The control system for electroplating wastewater discharge according to claim 9, characterized in that, It also includes a cleaning module, which is used to sample and detect at the inlet of each of the discharge pipes to obtain inlet detection data; to sample and detect at the outlet of each of the discharge pipes to obtain outlet detection data; to compare the inlet detection data with the outlet detection data, and to start cleaning of the corresponding discharge pipe when the difference exceeds a threshold.

Images