Intelligent identification dispensing method, system, equipment and medium for removing copper from PCB (Printed Circuit Board) wastewater

Abstract

The invention discloses an intelligent identification dispensing method, system and equipment for removing copper from PCB wastewater and a medium. The method comprises the following steps: acquiring an image of a wastewater sample by using an image acquisition device; preprocessing the collected image, wherein the preprocessing comprises noise reduction, automatic white balance, smoothing processing and color space conversion; identifying the color information and the corresponding color grade of the wastewater according to the preprocessed image by utilizing a computer vision algorithm, and judging the content of copper ions in the wastewater to obtain an identification result; according to the copper ion content in the wastewater, determining the dosing amount of the medicament, and executing medicament dosing through a medicament dosing control module; the identification result is sent to a preset user control terminal through the communication module; the PCB wastewater detection device has the effects of improving the accuracy of a PCB wastewater detection result and reducing chemical waste and labor cost.

Description

Technical Field

[0001] The present application relates to the technical field of wastewater treatment, and in particular, to an intelligent recognition and dosing method, system, device and medium for copper removal from PCB wastewater. Background Art

[0002] With the increasingly wide application fields of machine vision technology, there are more and more, and more complex application scenarios that require color recognition. The demand for using machine vision to recognize and detect the color of objects is increasing day by day, and color recognition has become a hot spot in machine vision detection.

[0003] At present, the wastewater of printed circuit board (PCB) is treated by "two-stage physical and chemical + biochemical", and finally the water produced by the MBR membrane meets the discharge standard. In the physical and chemical treatment link, long-term regular detection is required to monitor whether the treatment effect of the wastewater reaches the expectation. Among them, the copper ion concentration monitoring is to manually take samples from the physical and chemical treatment tank, add copper ion reaction reagents, and after mixing evenly, judge the copper ion concentration in the wastewater according to the color change after the reaction, and then decide whether to change the current dosing concentration of sodium sulfide to guide the dosing amount of the reagent.

[0004] In summary, in the current PCB wastewater treatment process, the monitoring of copper ion concentration relies on manual sampling and detection. This method is not only time-consuming and laborious, but also difficult to ensure the accuracy of the detection results, which may lead to improper use of the reagent and needs to be improved. Summary of the Invention

[0005] In order to improve the accuracy of PCB wastewater detection results, reduce reagent waste and labor costs, the present application provides an intelligent recognition and dosing method, system, device and medium for copper removal from PCB wastewater.

[0006] In the first aspect, the invention object of the present application is achieved by adopting the following technical solutions: An intelligent recognition and dosing method for copper removal from PCB wastewater, comprising: Obtaining an image of the wastewater sample using an image acquisition device; Preprocessing the acquired image, and the preprocessing includes noise reduction, automatic white balance, smoothing processing and color space conversion; using a computer vision algorithm, identifying the color information and corresponding color level of the wastewater based on the preprocessed image, and judging the content of copper ions in the wastewater to obtain an identification result; Determining the dosing amount of the reagent according to the content of copper ions in the wastewater, and executing the reagent dosing through a reagent dosing control module; Sending the identification result to a preset user control terminal through a communication module.

[0007] By adopting the above technical solution, combined with automated image acquisition and computer vision algorithms, it is possible to quickly acquire and process images of wastewater samples, greatly shortening the time of traditional manual detection, improving work efficiency, and being beneficial to saving labor costs; through image preprocessing of the sample images, noise reduction, automatic white balance, smoothing processing, and color space conversion in the preprocessing steps, the image smoothing processing can equalize the uneven water sample after the reaction and improve the accuracy of color recognition. The image preprocessing effectively improves the image quality, reduces the influence of external factors on color recognition, uses computer vision algorithms to accurately identify the color of the wastewater, and compares it with the standard color card information stored in the computer to determine the wastewater color level, thereby accurately judging the copper ion content and ensuring the high accuracy of the detection results. According to the recognition results, the system can automatically determine the dosage of the chemical agent and execute the chemical agent dosing through the chemical agent dosing control module, realizing the intelligence and automation of the dosing process, reducing human intervention, and improving the consistency and reliability of the dosing operation. This application uses color recognition technology to monitor the concentration of pollutants in water in real time, ensure the compliance of the effluent concentration, and at the same time significantly reduce the chemical agent cost and labor cost, improve the overall operation efficiency, and has good economic benefits.

[0008] In a preferred example of this application: The method further includes: Divide the wastewater sample to obtain a first test sample and a second test sample; According to the first test sample and the second test sample, obtain water quality impact factors related to the copper ion concentration, where the water quality impact factors include a first water quality impact factor and a second water quality impact factor; According to the water quality impact factors, obtain copper ion concentration impact factors representing the copper ion concentration level, where the copper ion concentration impact factors include a first copper ion concentration impact factor and a second copper ion concentration impact factor; According to the copper ion concentration impact factors, divide the first test sample and the second test sample; Obtain the division result, and according to the division result, obtain the test parameters; According to the test parameters, determine the types and dosages of chemical agents required for the chemical agent dosing control module to execute the chemical agent dosing process.

[0009] By adopting the above technical solution, due to the complex composition of PCB wastewater and the large fluctuation of copper ion concentration, a single detection method is difficult to comprehensively reflect the water quality status. Through sample division and multi-factor comprehensive evaluation, complex water quality conditions can be better coped with, and the treatment effect can be improved; in this application, wastewater samples are divided into a first detection sample and a second detection sample, and the water quality conditions in different regions can be analyzed more precisely. According to the water quality impact factors, the copper ion concentration impact factor can be calculated, and the copper ion concentration in the wastewater can be evaluated more scientifically, so as to optimize the dosage of the medicament; according to the calculated copper ion concentration impact factor, the type and dosage of the medicament are determined, avoiding excessive or insufficient medicament dosing, saving costs and improving the treatment efficiency. By dividing the detection samples according to the copper ion concentration impact factor and obtaining the corresponding detection parameters, the wastewater treatment process can be monitored in real time, and the treatment plan can be adjusted in time.

[0010] In a preferred example of this application: obtaining the copper ion concentration impact factor representing the copper ion concentration level according to the water quality impact factor specifically includes: Obtain a preset water quality impact association rule, and according to the preset water quality impact association rule, screen the first water quality impact factor to obtain the first water quality impact factor, where the first water quality impact factor includes pH value impact factor, temperature impact factor, conductivity impact factor, turbidity impact factor; Obtain the first copper ion concentration impact factor according to the first water quality impact factor; According to the preset water quality impact association rule, screen the second water quality impact factor to obtain the second water quality impact factor, where the second water quality impact factor includes organic matter content impact factor, other metal ion concentration impact factor, redox potential impact factor; Obtain the second copper ion concentration impact factor according to the second water quality impact factor.

[0011] By adopting the above technical solution, using the preset water quality impact association rule, the factors that have the greatest impact on the copper ion concentration can be scientifically screened out, avoiding the interference of irrelevant factors, and further improving the detection accuracy. In this application, the water quality impact factors are monitored in real time, and the system can flexibly adjust the treatment parameters to timely respond to water quality changes, ensuring the stability and reliability of the treatment effect. Through precise detection and optimized treatment, secondary pollution generated in the wastewater treatment process can be effectively reduced, protecting the environment.

[0012] In a preferred example of this application: dividing the first detection sample and the second detection sample according to the copper ion concentration impact factor specifically includes: Obtain the monitoring points of the first detection sample according to the first copper ion concentration impact factor, and divide the first detection sample according to the monitoring points of the first detection sample; Obtain the monitoring points of the second test sample according to the second copper ion concentration influencing factor, and divide the second test sample according to the monitoring points of the second test sample.

[0013] By adopting the above technical solution, according to the first copper ion concentration influencing factor and the second copper ion concentration influencing factor, the key monitoring points in the first test sample and the second test sample can be accurately located, which helps to more accurately reflect the copper ion concentration in each area and avoid detection errors caused by improper sample selection; by accurately dividing the samples and locating the monitoring points, the processing resources can be more reasonably allocated, avoiding resource waste and improving the processing efficiency.

[0014] In a preferred example of the present application: the first copper ion concentration influencing factor includes a first internal influencing factor and a first external influencing factor. Obtaining the first copper ion concentration influencing factor according to the first water quality influencing factor specifically includes: obtaining the first internal influencing factor according to the pH value influencing factor and the conductivity influencing factor; Obtaining the first external influencing factor according to the temperature influencing factor and the turbidity influencing factor; and / or The second copper ion concentration influencing factor includes a second internal influencing factor and a second external influencing factor. Obtaining the second copper ion concentration influencing factor according to the second water quality influencing factor specifically includes: Obtaining the second internal influencing factor according to the organic matter content influencing factor, the other metal ion concentration influencing factor and the redox potential influencing factor; Obtaining the second external influencing factor according to the temperature influencing factor and the turbidity influencing factor.

[0015] By adopting the above technical solution, according to the preset water quality influence association rules, the factors with the greatest influence on the copper ion concentration are scientifically screened out, avoiding the interference of irrelevant factors, ensuring the scientificity and rationality of the evaluation results. Through the systematic evaluation method, various water quality influencing factors are converted into specific internal influencing factors and external influencing factors, which can more scientifically evaluate the copper ion concentration level in the wastewater.

[0016] In a preferred example of the present application: obtaining the first copper ion concentration influencing factor includes: Calculating the first copper ion concentration influencing factor using a mathematical model: According to the pH value influencing factor P and the conductivity influencing factor C, using a linear regression model to calculate the first internal influencing factor I 1内 : I 1内 =α 1 P + β 1 C + γ 1 wherein, α 1 , β 1 and γ 1 are preset regression coefficients; According to the temperature influencing factor T and the turbidity influencing factor Z, use a non - linear regression model to calculate the first external influencing factor I 1外 : wherein, α 2 , β 2 , γ 2 , δ 2 are preset regression coefficients.

[0017] By adopting the above - mentioned technical solution, using a linear regression model and a non - linear regression model, the first internal influencing factor and the first external influencing factor can be calculated more accurately, thereby improving the evaluation accuracy of the copper ion concentration; various influencing factors such as pH value, conductivity, temperature, and turbidity are considered in the model, avoiding detection errors caused by a single factor and improving the comprehensiveness and accuracy of detection.

[0018] In the second aspect, the invention object of the present application is achieved by the following technical solution: An intelligent identification and dosing system for copper removal from PCB wastewater, the system includes: An image acquisition device for acquiring an image of the wastewater sample; An image pre - processing module for pre - processing the acquired image, and the pre - processing includes noise reduction, automatic white balance, smoothing processing, and color space conversion; A computer vision recognition module for recognizing the color information and the corresponding color grade of the wastewater based on the pre - processed image, and judging the content of copper ions in the wastewater to obtain a recognition result; A chemical agent dosing control module for determining the dosing amount of the chemical agent according to the content of copper ions in the wastewater and performing chemical agent dosing; A communication module for sending the recognition result to a preset user control terminal.

[0019] By adopting the above technical solutions, an image acquisition device, an image preprocessing module, a computer vision recognition module, a chemical agent dosing control module, and a communication module are used to achieve intelligent recognition and chemical agent preparation for copper removal from PCB wastewater. Specifically, an image of the wastewater sample is obtained through the image acquisition device, which can intuitively reflect the color and state of the wastewater and provide a high-quality data source for subsequent analysis. Through preprocessing steps such as noise reduction, automatic white balance, smoothing processing, and color space conversion, noise and interference in the image can be eliminated, the quality of the image can be improved, and the accuracy of subsequent recognition can be ensured. By using computer vision algorithms to recognize the color information of the wastewater and the corresponding color grades and judge the content of copper ions in the wastewater, high-precision detection of copper ion concentration can be achieved. According to the copper ion content obtained by the computer vision recognition module, the chemical agent dosing control module can accurately determine the dosing amount of the chemical agent and execute the chemical agent dosing, avoiding excessive or insufficient chemical agent dosing and improving the treatment efficiency.

[0020] In a preferred example of the present application: The system further includes: A sample division module for dividing the wastewater sample to obtain a first detection sample and a second detection sample; A water quality impact factor acquisition module for obtaining water quality impact factors related to copper ion concentration according to the first detection sample and the second detection sample, where the water quality impact factors include a first water quality impact factor and a second water quality impact factor; A copper ion concentration impact factor acquisition module for obtaining copper ion concentration impact factors representing the copper ion concentration level according to the water quality impact factors, where the copper ion concentration impact factors include a first copper ion concentration impact factor and a second copper ion concentration impact factor; A sample division optimization module for dividing the first detection sample and the second detection sample according to the copper ion concentration impact factors; A detection parameter acquisition module for obtaining the division result and obtaining detection parameters according to the division result; The chemical agent dosing control module is used to determine the types and dosages of chemical agents required for the chemical agent dosing control module to execute the chemical agent dosing process according to the detection parameters.

[0021] In the third aspect, the invention object of the present application is achieved by adopting the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above intelligent recognition and chemical agent preparation method for copper removal from PCB wastewater are implemented.

[0022] In the fourth aspect, the invention object of the present application is achieved by adopting the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned intelligent identification and dosing method for removing copper from PCB wastewater are implemented.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: 1. By combining automated image acquisition and computer vision algorithms, images of wastewater samples can be quickly obtained and processed, greatly shortening the time of traditional manual detection, improving work efficiency, and facilitating the saving of labor costs; through image preprocessing of the sample images, noise reduction, automatic white balance, smoothing processing, and color space conversion in the preprocessing steps, the image smoothing processing can homogenize the uneven water samples after the reaction, improving the accuracy of color recognition. The image preprocessing effectively improves the image quality, reduces the influence of external factors on color recognition, accurately identifies the color of the wastewater using computer vision algorithms, and compares it with the standard color card information stored in the computer to determine the wastewater color grade, thereby accurately judging the copper ion content and ensuring the high accuracy of the detection results. According to the recognition results, the system can automatically determine the dosing amount of the reagent and execute the reagent dosing through the reagent dosing control module, realizing the intelligence and automation of the dosing process, reducing human intervention, and improving the consistency and reliability of the dosing operation; 2. Using linear regression models and non-linear regression models, the first internal influencing factor and the first external influencing factor can be calculated more precisely, thereby improving the evaluation accuracy of copper ion concentration; various influencing factors such as pH value, conductivity, temperature, and turbidity are considered in the models, avoiding detection errors caused by a single factor and improving the comprehensiveness and accuracy of detection. Description of the Drawings

[0024] Figure 1 is a flowchart of an intelligent identification and dosing method for removing copper from PCB wastewater in an embodiment of the present application; Figure 2 is a process flowchart of an intelligent identification and dosing method for removing copper from PCB wastewater in an embodiment of the present application; Figure 3 is another flowchart of an intelligent identification and dosing method for removing copper from PCB wastewater in an embodiment of the present application; Figure 4 is a schematic diagram of the equipment in an embodiment of the present application. Detailed Description of the Embodiment

[0025] The following further describes the present application in detail with reference to the drawings.

[0026] In one embodiment, as Figure 1As shown in the figure, the present application discloses an intelligent recognition and dosing method for copper removal from PCB wastewater, which specifically includes the following steps: S1: Use an image acquisition device to obtain an image of the wastewater sample.

[0027] In this embodiment, as Figure 2 shown, the intelligent recognition and dosing system for copper removal from PCB wastewater uses computer vision algorithms to automatically identify the color grade of the sewage, intelligently judge the copper ion content in the sewage, establish the correlation between the sewage color and the dosing amount of the reagent, and realize the intelligence and automation of the dosing process. The visual detection consists of two parts: hardware and software. Among them, the hardware part is mainly composed of imaging devices, light sources, soft light boards, processors, etc. Among them, the visual recognition software is the core of the entire system. The software uses the image information obtained by the camera and uses digital image processing methods to identify the content of the image information and judge the reaction degree of the sewage. The rapid reaction of the sewage is manifested as the output amount of yellow reactants in the water. By comparing the reaction sample with the standard color card (or the standard color card information stored in the computer), the copper ion content of the sample is judged.

[0028] S2: Preprocess the collected image. The preprocessing includes noise reduction, automatic white balance, smoothing processing, and color space conversion.

[0029] Specifically, noise reduction is to use noise filtering algorithms (such as Gaussian filtering, median filtering) to remove the noise in the image. Automatic white balance is to use an automatic white balance algorithm to correct the color deviation of the image and ensure the accuracy of color information. Smoothing processing is to use a smoothing filter (such as bilateral filtering) to make the image edges soft and reduce the detailed noise in the image. Color space conversion is to convert the image from the RGB color space to the HSV or LAB color space for subsequent color analysis.

[0030] S3: Use computer vision algorithms to identify the color information and corresponding color grade of the wastewater based on the preprocessed image, and judge the copper ion content in the wastewater to obtain the recognition result.

[0031] In this embodiment, color recognition algorithms (such as K-means clustering, support vector machine SVM) are used to identify the color information in the image. According to the known standard color card, the identified color information is divided into different color grades. According to the preset corresponding relationship between the color grade and the copper ion content, the copper ion content in the wastewater is judged.

[0032] Specifically, a color database is constructed, which contains standard color information under different copper ion concentrations. Machine learning algorithms (such as random forest, neural network) are used to train the model, establish the mapping relationship between the color information and the copper ion content, input the preprocessed image, and output the recognition result of the copper ion content through the trained model.

[0033] S4: Determine the dosage of the medicament according to the copper ion content in the wastewater, and execute the medicament dosing through the medicament dosing control module.

[0034] In this embodiment, according to the identified copper ion content, use a preset medicament dosing formula to calculate the required medicament dosage, and execute the medicament dosing operation through the medicament dosing control module (such as a PLC controller).

[0035] S5: Send the recognition result to a preset user control terminal through the communication module.

[0036] Specifically, configure the parameters of the communication module to ensure the stability and security of data transmission, develop the software interface of the user control terminal, display the recognition result, medicament dosage and other relevant information, and provide an alarm function. When the copper ion content exceeds the preset threshold, an alarm is automatically sent to notify the user.

[0037] In one embodiment, as Figure 3 shown, the intelligent recognition and dosing method for copper removal from PCB wastewater further includes: S10: Divide the wastewater sample to obtain a first test sample and a second test sample.

[0038] In this embodiment, to improve the detection accuracy and processing efficiency of intelligent recognition and dosing on the basis of the technical solution in Figure 1 , this embodiment optimizes the medicament dosing through a detailed evaluation of the copper ion concentration influencing factors to improve the processing efficiency, so as to combine with the solution in Figure 1 to jointly ensure that the intelligent recognition and dosing system can monitor and adjust in real time to cope with water quality changes.

[0039] Specifically, extract a sample from the part of the wastewater flow identified as containing a high concentration of copper ions as the first test sample. This part of the sample needs to be preferentially tested and processed in detail to ensure the effective removal of copper ions; extract a sample from the remaining part of the wastewater flow as the second test sample. This part of the sample can be subjected to routine testing and processing to ensure the overall treatment effect; in actual application, the PCB wastewater flow can be monitored in real time, the wastewater flow can be automatically identified and divided to obtain a first treatment section for priority treatment and a second treatment section for routine treatment. Extract the first test sample from the first treatment section and extract the second test sample from the second treatment section.

[0040] S20: According to the first test sample and the second test sample, obtain water quality influencing factors related to the copper ion concentration, where the water quality influencing factors include a first water quality influencing factor and a second water quality influencing factor.

[0041] In this embodiment, instruments such as a pH meter, a conductivity meter, a thermometer, and a turbidity meter are used to measure the pH value, conductivity, temperature, and turbidity of the sample; chemical reagents and laboratory equipment are used to determine the organic matter content, the concentration of other metal ions, and the redox potential in the sample.

[0042] S30: According to the water quality impact factors, obtain the copper ion concentration impact factors representing the copper ion concentration level, where the copper ion concentration impact factors include the first copper ion concentration impact factor and the second copper ion concentration impact factor.

[0043] In this embodiment, a linear regression model and a non-linear regression model are used to calculate the copper ion concentration impact factors according to the water quality impact factors, and data processing software (such as Python, R, MATLAB) is used for model training and calculation.

[0044] S40: Divide the first test sample and the second test sample according to the copper ion concentration impact factors.

[0045] In this embodiment, a classification algorithm (such as support vector machine SVM, random forest) is used to classify the samples according to the copper ion concentration impact factors, and the samples are divided into a high copper ion concentration region and a low copper ion concentration region.

[0046] S50: Obtain the classification result, and according to the classification result, obtain the detection parameters.

[0047] In this embodiment, statistical analysis is performed on the classification results to obtain the quantity and proportion of high copper ion concentration samples and low copper ion concentration samples. According to the classification results, key detection parameters such as the average copper ion concentration and the maximum copper ion concentration are extracted; data processing software is used to perform statistical analysis on the classification results, generate a report, extract key detection parameters, record them in the database, and send the detection parameters to the chemical agent dosing control module for subsequent chemical agent dosing calculation.

[0048] S60: According to the detection parameters, determine the types and dosages of chemical agents required for the chemical agent dosing control module to perform chemical agent dosing processing.

[0049] In this embodiment, the calculation result is sent to the chemical agent dosing control module, and the chemical agent dosing control module performs chemical agent dosing operations according to the instructions, recording the time, type of chemical agent, and dosage of each chemical agent dosing for subsequent analysis and adjustment.

[0050] In one embodiment, in step S30, according to the water quality impact factors, obtaining the copper ion concentration impact factors representing the copper ion concentration level specifically includes: S301: Obtain the preset water quality impact association rules. According to the preset water quality impact association rules, screen the first water quality impact factors to obtain the first water quality impact factors, where the first water quality impact factors include pH value impact factors, temperature impact factors, conductivity impact factors, and turbidity impact factors.

[0051] Specifically, establish an association rule library that includes various water quality impact factors and their impacts on copper ion concentration. Use the preset water quality impact association rules to screen out the first water quality impact factors that are highly correlated with copper ion concentration from the measured water quality impact factors.

[0052] S302: According to the first water quality impact factors, obtain the first copper ion concentration impact factors.

[0053] Specifically, the first copper ion concentration impact factors include the first internal impact factors and the first external impact factors. Step S302 includes: S3021: According to the pH value impact factors and conductivity impact factors, obtain the first internal impact factors.

[0054] S3022: According to the temperature impact factors and turbidity impact factors, obtain the first external impact factors.

[0055] Specifically, establish a calculation model for the first internal impact factors. For example: According to the pH value impact factor P and conductivity impact factor C, use a linear regression model to calculate the first internal impact factor I 1内 : I 1内 =α 1 P + β 1 C + γ 1 In the formula, α 1 , β 1 and γ 1 are preset regression coefficients.

[0056] According to the temperature impact factor T and turbidity impact factor Z, use a non - linear regression model to calculate the first external impact factor I 1外 : In the formula, α 2 , β 2 , γ 2 , δ 2 are preset regression coefficients.

[0057] S303: According to the preset water quality impact association rules, screen the second water quality impact factors to obtain the second water quality impact factors, where the second water quality impact factors include organic matter content impact factors, other metal ion concentration impact factors, and redox potential impact factors.

[0058] In this embodiment, association rule mining algorithms (such as Apriori algorithm, FP-growth algorithm) are used to generate candidate rules, and significant association rules are selected according to indicators such as support and confidence; through cross-validation and model tuning, the accuracy and generalization ability of the rules are optimized.

[0059] For example, assume that we have collected a large amount of water quality data, including influencing factors such as pH value, conductivity, temperature, turbidity, organic matter content, concentration of other metal ions, and redox potential, as well as the corresponding copper ion concentration. The following are the example steps for establishing a water quality impact association rule base: Step 1: Data collection: Collect samples from the wastewater treatment system of the PCB manufacturing factory, and record the pH value, conductivity, temperature, turbidity, organic matter content, concentration of other metal ions, redox potential, and the corresponding copper ion concentration of each sample.

[0060] Step 2: Data preprocessing: Clean the data to remove invalid values and outliers; normalize data such as pH value and conductivity to between 0 and 1.

[0061] Step 3: Data analysis: Use the Pearson correlation coefficient to analyze the correlation between factors such as pH value, conductivity, temperature, and turbidity and the copper ion concentration.

[0062] Use a linear regression model to establish the relationship between pH value and conductivity and the copper ion concentration.

[0063] Use a non-linear regression model to establish the relationship between temperature and turbidity and the copper ion concentration.

[0064] Step 4: Rule extraction: Use the Apriori algorithm to generate candidate rules, for example: If the pH value > 7 and the conductivity < 100 μS / cm, then the copper ion concentration is high.

[0065] If the temperature > 30 °C and the turbidity > 50 NTU, then the copper ion concentration is high.

[0066] Select significant rules according to support and confidence.

[0067] Step 5: Rule verification: Verify the accuracy of the rules in the laboratory. For example, verify the influence of pH value and conductivity on the copper ion concentration through simulation experiments.

[0068] Apply the rules in the actual wastewater treatment system and observe the accuracy of their prediction of the copper ion concentration.

[0069] Step 6: Construction of the rule base: Encode the verified rules into a structured form, for example: Rule 1: If the pH value > 7 and the conductivity < 100 μS / cm, then the copper ion concentration is high.

[0070] Rule 2: If the temperature > 30 °C and the turbidity > 50 NTU, then the copper ion concentration is high.

[0071] Store the encoded rules in the database to form a water quality impact association rule base.

[0072] S304: Obtain the second copper ion concentration influencing factor according to the second water quality impact factor.

[0073] In this embodiment, step S304 includes: S3041: Obtain the second internal influencing factor according to the organic matter content influencing factor, other metal ion concentration influencing factor, and redox potential influencing factor.

[0074] S3042: Obtain the second external influencing factor according to the temperature influencing factor and the turbidity influencing factor.

[0075] Specifically, use a linear regression model to calculate the second copper ion concentration influencing factor according to the second water quality impact factor; use data processing software (such as Python, R, MATLAB) for model training and calculation.

[0076] Establish a calculation model for the second copper ion concentration influencing factor, for example: Use the organic matter content influencing factor, other metal ion concentration influencing factor, and redox potential influencing factor to calculate the second internal influencing factor: I 2内 =α 3 O+β 3 M+γ 3 E+δ 3 ; Use the temperature influencing factor T and the turbidity influencing factor Z to calculate the second external influencing factor: I 2外 =α 4 T+β 4 Z+γ 4 ; α 3 、β 3 、γ 3 、δ 3 、α 4 、β 4 、γ 4 are preset regression coefficients.

[0077] In one embodiment, in step S40, the first test sample and the second test sample are divided according to the copper ion concentration influencing factor, which specifically includes: S401: Obtain the monitoring points of the first test sample according to the first copper ion concentration influencing factor, and divide the first test sample according to the monitoring points of the first test sample.

[0078] In this embodiment, the first copper ion concentration influencing factor includes a first internal influencing factor and a first external influencing factor, which reflect the influence of the internal characteristics of the wastewater and the external environment on the copper ion concentration; according to the first copper ion concentration influencing factor, determine the key monitoring points of the first test sample, and divide the first test sample into a high copper ion concentration area and a low copper ion concentration area.

[0079] Specifically, according to the calculated first copper ion concentration influencing factor, determine the key monitoring points of the first test sample. For example, select the area with a higher copper ion concentration as the monitoring point; according to the position and quantity of the monitoring points, divide the first test sample into different sub-samples. For example, divide the first test sample into a high copper ion concentration area and a low copper ion concentration area.

[0080] S402: Obtain the monitoring points of the second test sample according to the second copper ion concentration influencing factor, and divide the second test sample according to the monitoring points of the second test sample.

[0081] In this embodiment, the second copper ion concentration influencing factor includes a second internal influencing factor and a second external influencing factor, which reflect the influence of the internal characteristics of the wastewater and the external environment on the copper ion concentration; according to the second copper ion concentration influencing factor, determine the key monitoring points of the second test sample, and divide the second test sample into a high organic matter content area and a low organic matter content area.

[0082] Specifically, according to the calculated second copper ion concentration influencing factor, determine the key monitoring points of the second test sample. For example, select the area with a higher organic matter content or a higher redox potential as the monitoring point; according to the position and quantity of the monitoring points, divide the second test sample into different sub-samples. For example, divide the second test sample into a high organic matter content area and a low organic matter content area.

[0083] It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0084] In one embodiment, a smart identification and dosing system for copper removal from PCB wastewater is provided, and the smart identification and dosing system for copper removal from PCB wastewater corresponds to the smart identification and dosing method for copper removal from PCB wastewater in the above embodiment.

[0085] An intelligent identification and dosing system for removing copper from PCB wastewater, comprising an image acquisition device, an image preprocessing module, a computer vision recognition module, a chemical dosing control module, and a communication module. The detailed descriptions of each functional module are as follows: The image acquisition device is used to obtain an image of the wastewater sample; The image preprocessing module is used to preprocess the acquired image, and the preprocessing includes noise reduction, automatic white balance, smoothing processing, and color space conversion; The computer vision recognition module is used to identify the color information of the wastewater and the corresponding color grade based on the preprocessed image, and judge the content of copper ions in the wastewater to obtain a recognition result; The chemical dosing control module is used to determine the dosing amount of the chemical according to the content of copper ions in the wastewater and execute the chemical dosing; The communication module is used to send the recognition result to a preset user control terminal.

[0086] For the specific limitations of the intelligent identification and dosing system for removing copper from PCB wastewater, reference can be made to the limitations of the intelligent identification and dosing method for removing copper from PCB wastewater in the above text, which will not be elaborated here; each module in the above intelligent identification and dosing system for removing copper from PCB wastewater can be implemented in whole or in part by software, hardware, and their combinations; the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0087] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store computer vision algorithms, recognition results, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes an intelligent identification and dosing method for removing copper from PCB wastewater.

[0088] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: S1: Obtain an image of the wastewater sample using an image acquisition device; S2: Preprocess the acquired image. The preprocessing includes noise reduction, automatic white balance, smoothing processing, and color space conversion; S3: Use computer vision algorithms to identify the color information and corresponding color grades of the wastewater based on the preprocessed image, and determine the copper ion content in the wastewater to obtain an identification result; S4: Determine the dosage of the chemical agent according to the copper ion content in the wastewater, and execute the chemical agent dosing through the chemical agent dosing control module; S5: Send the identification result to a preset user control terminal through the communication module.

[0089] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: S1: Obtain an image of the wastewater sample using an image acquisition device; S2: Preprocess the acquired image. The preprocessing includes noise reduction, automatic white balance, smoothing processing, and color space conversion; S3: Use computer vision algorithms to identify the color information and corresponding color grades of the wastewater based on the preprocessed image, and determine the copper ion content in the wastewater to obtain an identification result; S4: Determine the dosage of the chemical agent according to the copper ion content in the wastewater, and execute the chemical agent dosing through the chemical agent dosing control module; S5: Send the identification result to a preset user control terminal through the communication module.

[0090] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0091] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0092] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An intelligent identification and dispensing method for removing copper from PCB wastewater, characterized in that: include: acquiring an image of the wastewater sample using an image acquisition device; Preprocess the captured images, including noise reduction, automatic white balance, smoothing and color space conversion; Using computer vision algorithms, the color information and corresponding color grade of the wastewater are identified based on the preprocessed images, and the content of copper ions in the wastewater is determined to obtain the identification results; Determine the dosage of the reagent according to the copper ion content in the wastewater, and execute the reagent dosage through the reagent dosage control module; The recognition result is sent to a preset user control terminal through the communication module.

2. The intelligent identification and dispensing method for removing copper from PCB wastewater according to claim 1 is characterized in that: The method also includes: Dividing the wastewater sample to obtain a first test sample and a second test sample; According to the first test sample and the second test sample, obtaining a water quality influencing factor related to the copper ion concentration, wherein the water quality influencing factor includes a first water quality influencing factor and a second water quality influencing factor; According to the water quality influencing factor, a copper ion concentration influencing factor representing the copper ion concentration level is obtained, wherein the copper ion concentration influencing factor includes a first copper ion concentration influencing factor and a second copper ion concentration influencing factor; Dividing the first test sample and the second test sample according to the copper ion concentration influencing factor; Obtaining a division result, and obtaining a detection parameter according to the division result; According to the detection parameters, the type and amount of chemical agent required by the drug delivery control module to perform the drug delivery process are determined.

3. The intelligent identification and dispensing method for removing copper from PCB wastewater according to claim 2 is characterized in that: The step of obtaining the copper ion concentration influence factor representing the copper ion concentration level according to the water quality influence factor specifically includes: Obtaining a preset water quality impact association rule, and screening a first water quality impact factor according to the preset water quality impact association rule to obtain a first water quality impact factor, wherein the first water quality impact factor includes a pH impact factor, a temperature impact factor, a conductivity impact factor, and a turbidity impact factor; According to the first water quality influencing factor, obtaining a first copper ion concentration influencing factor; According to the preset water quality impact association rule, the second water quality impact factor is screened to obtain the second water quality impact factor, wherein the second water quality impact factor includes an organic matter content impact factor, other metal ion concentration impact factors, and an oxidation-reduction potential impact factor; According to the second water quality influencing factor, a second copper ion concentration influencing factor is obtained.

4. The intelligent identification and dispensing method for removing copper from PCB wastewater according to claim 3 is characterized in that: The dividing the first test sample and the second test sample according to the copper ion concentration influencing factor specifically includes: obtaining a monitoring point of the first test sample according to the first copper ion concentration influencing factor, and dividing the first test sample according to the monitoring point of the first test sample; According to the second copper ion concentration influencing factor, the monitoring points of the second detection sample are obtained, and according to the monitoring points of the second detection sample, the second detection sample is divided.

5. The intelligent identification and dispensing method for removing copper from PCB wastewater according to claim 3 is characterized in that: The first copper ion concentration influencing factor includes a first internal influencing factor and a first external influencing factor. The first copper ion concentration influencing factor is obtained according to the first water quality influencing factor, specifically including: Obtaining a first internal influencing factor according to the pH value influencing factor and the conductivity influencing factor; Acquire a first external influencing factor according to the temperature influencing factor and the turbidity influencing factor; and / or, The second copper ion concentration influencing factor includes a second internal influencing factor and a second external influencing factor. The second copper ion concentration influencing factor is obtained according to the second water quality influencing factor, specifically including: Obtaining a second internal influencing factor according to the influencing factor of the organic matter content, the influencing factor of the other metal ion concentration and the influencing factor of the oxidation-reduction potential; A second external influencing factor is obtained according to the temperature influencing factor and the turbidity influencing factor.

6. The intelligent identification and dispensing method for removing copper from PCB wastewater according to claim 3 is characterized in that: The obtaining of the first copper ion concentration influencing factor comprises: The mathematical model is used to calculate the first copper ion concentration influencing factor: According to the pH influencing factor P and the conductivity influencing factor C, the first internal influencing factor I is calculated using a linear regression model. 1内 : I 1内 =α1P+β1C+γ1 In the formula, α1, β1 and γ1 are the preset regression coefficients; According to the temperature influencing factor T and the turbidity influencing factor Z, the first external influencing factor I is calculated using a nonlinear regression model. 1外 : Where α2, β2, γ2, and δ2 are preset regression coefficients.

7. Intelligent identification and dispensing system for PCB wastewater copper removal, characterized in that: The system comprises: An image acquisition device for acquiring images of wastewater samples; Image preprocessing module, used to preprocess the collected images, including noise reduction, automatic white balance, smoothing and color space conversion; A computer vision recognition module is used to recognize the color information and corresponding color grade of the wastewater based on the pre-processed image, and to determine the content of copper ions in the wastewater to obtain a recognition result; The reagent delivery control module is used to determine the dosage of the reagent according to the copper ion content in the wastewater and execute the reagent delivery; The communication module is used to send the recognition result to a preset user control terminal.

8. The intelligent identification and dispensing system for removing copper from PCB wastewater according to claim 7 is characterized in that: The system further comprises: A sample division module is used to divide the wastewater sample into a first test sample and a second test sample; A water quality influencing factor acquisition module, used to acquire a water quality influencing factor related to the copper ion concentration according to the first test sample and the second test sample, wherein the water quality influencing factor includes a first water quality influencing factor and a second water quality influencing factor; A copper ion concentration influencing factor acquisition module, used to acquire a copper ion concentration influencing factor representing a copper ion concentration level according to the water quality influencing factor, wherein the copper ion concentration influencing factor includes a first copper ion concentration influencing factor and a second copper ion concentration influencing factor; A sample division optimization module, used for dividing the first test sample and the second test sample according to the copper ion concentration influencing factor; A detection parameter acquisition module, used to obtain the division result and obtain the detection parameter according to the division result; The drug delivery control module is used to determine the type and amount of chemical agents required by the drug delivery control module to perform drug delivery processing according to the detection parameters.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent identification and dispensing method for removing copper from PCB wastewater as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the intelligent identification and dispensing method for removing copper from PCB wastewater as described in any one of claims 1 to 6 are implemented.

Images