Optimized control method and system for recycling palladium-containing waste liquid through zinc replacement

Abstract

The invention relates to an optimal control method and system for recycling palladium-containing waste liquid through zinc replacement, and the method comprises the steps: K1, monitoring the concentration of palladium in the palladium-containing waste liquid, the data information of the flow of the waste liquid and the data information of the addition amount of zinc powder at regular time in the process of zinc replacement of the palladium-containing waste liquid; and K2, based on the data information of the flow of the palladium-containing waste liquid and the data information of the zinc powder adding amount, predicting the content of the zinc ions after replacement by adopting a regression prediction algorithm of a white whale optimized BP neural network, and obtaining the predicted data information of the content of the zinc ions after replacement. The flow of the palladium-containing waste liquid can be accurately controlled and adjusted, manual participation is not needed in the whole process, the intelligent degree is high, and the recovery efficiency of the palladium-containing waste liquid is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of palladium waste liquid recycling, and in particular to an optimized control method and system for the zinc replacement and recycling of palladium-containing waste liquid. Background Art

[0002] In PCB manufacturing, after drilling high-density interconnection boards (HDI), a palladium-containing activation solution is required to form a copper seed layer on the hole wall for subsequent electroless copper plating. The palladium-containing waste liquid generated during the cleaning process is divided into high-concentration (100 - 160 ppm, rich liquid) and low-concentration (lean liquid). In traditional methods, the palladium activation solution needs to be frequently replaced due to copper accumulation, resulting in more palladium-containing waste liquid, which needs to be recycled. In the recycling of palladium-containing waste liquid, the zinc replacement method is used, but the flow rate of the palladium-containing waste liquid and the addition amount of zinc cannot be matched, resulting in more resource consumption in the palladium recycling process.

[0003] In the existing palladium-containing waste liquid treatment process, traditional methods often have the following several prominent problems:

[0004] 1. Unstable recovery rate: Due to the lack of precise monitoring means, the recovery rate of palladium fluctuates greatly, usually between 70% - 85%, and it is difficult to achieve a stable and efficient state.

[0005] 2. Serious resource waste: As the main reducing agent, the addition amount of zinc powder often depends on manual experience judgment, resulting in over-addition or under-addition, which not only increases the cost but also affects the product quality.

[0006] 3. High environmental risk: Traditional methods do not control parameters such as pH value accurately enough, easily causing secondary pollution and not meeting modern environmental protection requirements.

[0007] 4. High operation complexity: Frequent manual adjustment of process parameters is required, with high labor intensity and easy to make mistakes.

[0008] Currently, the mainstream method for treating palladium-containing waste liquid mainly uses the chemical precipitation method, but this method has strict requirements for pH value control (usually needs to be maintained between 2 - 3), and is prone to generating a large amount of sludge, causing secondary pollution. In addition, there are few application cases of combining real-time monitoring with intelligent control in the existing technology, which has become an important bottleneck restricting the development of the industry.

[0009] According to the research data in "Chemical Engineering Progress", the mainstream method for treating palladium-containing waste liquid currently mainly uses the chemical precipitation method, but this method has strict requirements for pH value control and is prone to generating secondary pollution. In addition, the traditional manual operation method is difficult to cope with the fluctuations in the waste liquid composition, resulting in a palladium recovery rate usually lower than 85%.

[0010] Therefore, how to accurately control and adjust the flow rate of the palladium-containing waste liquid has become an urgent problem to be solved by us. Summary of the Invention

[0011] In view of the above problems, the present invention provides an optimized control method and system for the zinc replacement cycle reuse of palladium-containing waste liquid, which can not only accurately control and adjust the flow rate of the palladium-containing waste liquid, but also does not require manual participation in the whole process, has a high degree of intelligence, and improves the recovery efficiency of the palladium-containing waste liquid.

[0012] In order to achieve the above-mentioned purpose and other related purposes, the technical solutions provided by the present invention are as follows:

[0013] An optimized control method for the zinc replacement cycle reuse of palladium-containing waste liquid, the method includes:

[0014] K1. During the zinc replacement process of the palladium-containing waste liquid, regularly monitor the data information of the palladium concentration in the palladium-containing waste liquid, the flow rate of the waste liquid, and the data information of the zinc powder addition amount;

[0015] K2. Multiply the palladium concentration and the flow rate of the waste liquid to obtain the palladium ion flow rate data. Based on the palladium ion flow rate data and the data information of the zinc powder addition amount, use the regression prediction algorithm of the beluga optimization BP neural network to predict the content of zinc ions after replacement, and obtain the data information of the predicted content of zinc ions after replacement;

[0016] K3. Based on the data information of the predicted content of zinc ions after replacement, construct a generation model of the target palladium powder based on the golden sine factor, calculate the quality of the recycled palladium powder, and obtain the data information of the quality of the recycled palladium powder;

[0017] K4. Based on the data information of the quality of the recycled palladium powder, establish a palladium ion flow rate data control function W, obtain the control data information of the flow rate of the waste liquid, and control and adjust the flow rate of the waste liquid.

[0018] Further, in step K2, the use of the regression prediction algorithm of the beluga optimization BP neural network to predict the content of zinc ions after replacement includes:

[0019] K21. Input the palladium ion flow rate data and the data information of the zinc powder addition amount into the regression prediction model of the BP neural network for training and learning, initialize the weights and biases of the BP neural network, and obtain the data information of the initialized weights and biases of the BP neural network;

[0020] K22. Based on the data information of the initialized weights and biases of the BP neural network, initialize the beluga population, determine the population parameters and the maximum number of iterations L, and obtain the data information of the initialized beluga population;

[0021] K23. Based on the data information of the initialized beluga whale population, establish the fitness function Q of the population individuals,

[0022]

[0023] where x is the data information of the initialized beluga whale population, and α1, α2, and α3 are weight coefficients, and the fitness values of the individuals in the beluga whale population are deduced to obtain the data information of the fitness values of the individuals in the beluga whale population;

[0024] K24. Based on the data information of the fitness values of the individuals in the beluga whale population, establish the objective optimization function U of the population,

[0025]

[0026] where y is the data information of the fitness values of the individuals in the beluga whale population, and β1, β2, and β3 are optimization factors, and the weights and biases of the BP neural network are optimized to obtain the regression prediction model of the optimized BP neural network.

[0027] Further, the prediction of the zinc ion content after replacement using the regression prediction algorithm of the beluga whale optimized BP neural network further includes:

[0028] K25. Based on the regression prediction model of the optimized BP neural network, input the data information of the flow rate of the waste liquid and the data information of the zinc powder addition amount, predict the zinc ion content after replacement, and obtain the data information of the predicted zinc ion content after replacement.

[0029] Further, the optimization factors β1, β2, and β3 are

[0030]

[0031] where y is the data information of the fitness values of the individuals in the beluga whale population.

[0032] Further, the constraint function f of the weight coefficients α1, α2, and α3 is

[0033]

[0034] where α1, α2, and α3 are any constant coefficients between 0 and 1, and the value range of the constraint function f is (0, 1).

[0035] Further, in step K3, the construction of the generation model of the target palladium powder based on the golden sine factor and the calculation of the quality of the recovered palladium powder include:

[0036] K31. Based on the data information of the predicted content of zinc ions after the replacement is completed, a data set of the predicted content of zinc ions after the replacement is completed is constructed;

[0037] K32. Based on the predicted data set of zinc ion content after the replacement is completed, a generating function P of the target palladium powder based on the golden sine factor is established.

[0038]

[0039] Where z is the data set of the predicted zinc ion content after the replacement is completed, δ1, δ2 and δ3 are the golden sine factors for the target palladium powder production;

[0040] K33. Based on the generating function P of the target palladium powder of the golden sine factor, the mass of the recovered palladium powder is estimated to obtain data information on the mass of the recovered palladium powder.

[0041] Furthermore, the golden sine factors δ1, δ2 and δ3 produced by the target differential signal are:

[0042]

[0043] Wherein, z is the data set of the predicted zinc ion content after the replacement is completed.

[0044] Furthermore, the flow control function W of the waste liquid is,

[0045]

[0046] Among them, r is the data information of the mass of the recovered palladium powder, and ρ1, ρ2 and ρ3 are weight constant parameters.

[0047] In order to achieve the above-mentioned and other related purposes, the present invention further provides a system for realizing any of the above-mentioned optimization control methods for the replacement and recycling of waste liquid zinc, the system comprising:

[0048] A data acquisition module is used to regularly obtain data information on the flow rate of palladium ions and the amount of zinc powder added;

[0049] A module for predicting the content of zinc ions after the replacement is completed is connected to the data acquisition module and is used to predict the content of zinc ions after the replacement is completed using a regression prediction algorithm of the Beluga optimized BP neural network to obtain data information on the predicted content of zinc ions after the replacement is completed;

[0050] A target palladium powder generation module is connected to the module for predicting the zinc ion content after the replacement is completed, and is used to construct a target palladium powder generation model based on the golden sine factor, estimate the mass of the recovered palladium powder, and obtain data information on the mass of the recovered palladium powder;

[0051] A control module for the flow rate of waste liquid, connected to the target palladium powder generation module, is used to establish a flow rate control function W of the waste liquid, control and adjust the flow rate of the waste liquid, and obtain the control data information of the flow rate of the waste liquid.

[0052] Furthermore, the system further includes a data display module for zinc replacement of palladium waste liquid, connected to the control module for the flow rate of the waste liquid, and is used to display the data information of zinc replacement of the waste liquid in real time.

[0053] The present invention has the following positive effects:

[0054] 1. By adopting the regression prediction algorithm of the beluga whale optimized BP neural network to predict the content of zinc ions after replacement, and combining with the construction of a target palladium powder generation model based on the golden sine factor, the present invention can not only accurately calculate the generation quality of palladium powder, ensure the recycling efficiency of palladium powder, but also reduce the waste of palladium resources and lower the cost of replacing the activation liquid.

[0055] 2. By establishing a flow rate control function W of the waste liquid to control and adjust the flow rate of the waste liquid, the present invention can not only accurately control and adjust the flow rate of the waste liquid, but also the whole process does not require manual participation, has a high degree of intelligence, and improves the recycling efficiency of the waste liquid. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic flow chart of zinc replacement of waste liquid of the present invention;

[0057] Figure 2 It is a schematic flow chart of the method of the present invention;

[0058] Figure 3 It is a schematic flow chart of the regression prediction algorithm of the beluga whale optimized BP neural network of the present invention;

[0059] Figure 4 It is a schematic flow chart of the production model of the target palladium powder based on the golden sine factor of the present invention;

[0060] Figure 5 It is a schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0061] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to assist understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0062] Example 1: As Figure 1 or Figure 2 shown, an optimized control method for the recycling of zinc replacement in palladium-containing waste liquid, the method comprising:

[0063] K1. During the zinc replacement process of palladium-containing waste liquid, regularly monitor the data information of the palladium concentration in the palladium-containing waste liquid, the flow rate of the waste liquid, and the data information of the zinc powder addition amount;

[0064] K2. Multiply the palladium concentration by the flow rate of the waste liquid to obtain the palladium ion flow rate data. Based on the palladium ion flow rate data and the data information of the zinc powder addition amount, use the regression prediction algorithm of the beluga whale optimized BP neural network to predict the content of zinc ions after replacement, and obtain the data information of the predicted content of zinc ions after replacement;

[0065] K3. Based on the data information of the predicted content of zinc ions after replacement, construct a generation model of the target palladium powder based on the golden sine factor, calculate the quality of the recycled palladium powder, and obtain the data information of the quality of the recycled palladium powder;

[0066] K4. Based on the data information of the quality of the recycled palladium powder, establish a control function W for the palladium ion flow rate data, obtain the control data information of the flow rate of the waste liquid, and control and adjust the flow rate of the waste liquid.

[0067] In this embodiment, as Figure 2 shown, in step K2, the prediction of the content of zinc ions after replacement by using the regression prediction algorithm of the beluga whale optimized BP neural network includes:

[0068] K21. Input the palladium ion flow rate data and the data information of the zinc powder addition amount into the regression prediction model of the BP neural network for training and learning, initialize the weights and biases of the BP neural network, and obtain the data information of the initialized weights and biases of the BP neural network;

[0069] K22. Based on the data information of the initialized weights and biases of the BP neural network, initialize the beluga whale population, determine the population parameters and the maximum number of iterations L, and obtain the data information of the initialized beluga whale population;

[0070] K23. Based on the data information of the initialized beluga whale population, establish a fitness function Q for the population individuals,

[0071]

[0072] Among them, x is the data information of the initialized beluga whale population, α1, α2 and α3 are weight coefficients, and the fitness values of the individuals in the beluga whale population are calculated to obtain the data information of the fitness values of the individuals in the beluga whale population;

[0073] K24. Based on the data information of the fitness values of the individuals of the beluga whale population, establish the target optimization function U of the population,

[0074] Among them, y is the data information of the fitness value of individuals in the beluga whale population, β1, β2 and β3 are optimization factors, and the weights and biases of the BP neural network are optimized to obtain the optimized BP neural network regression prediction model.

[0075] In this embodiment, the use of the regression prediction algorithm of the Beluga optimized BP neural network to predict the content of zinc ions after the replacement is completed further includes:

[0076] K25. Based on the regression prediction model of the optimized BP neural network, the data information of the flow rate of the waste liquid and the data information of the amount of zinc powder added are input to predict the content of zinc ions after the replacement is completed, and the data information of the predicted content of zinc ions after the replacement is completed is obtained.

[0077] In this embodiment, the optimization factors β1, β2 and β3 are,

[0078]

[0079]

[0080] Among them, y is the data information of the fitness value of individuals in the beluga whale population.

[0081] In this embodiment, the constraint function f of the weight coefficients α1, α2 and α3 is,

[0082]

[0083] Among them, α1, α2 and α3 are any constant coefficients between 0 and 1, and the value range of the constraint function f is (0,1).

[0084] In this embodiment, if Figure 4 As shown, in step K3, the construction of a target palladium powder generation model based on the golden sine factor and the estimation of the mass of the recovered palladium powder include:

[0085] K31. Based on the data information of the predicted content of zinc ions after the replacement is completed, a data set of the predicted content of zinc ions after the replacement is completed is constructed;

[0086] K32. Based on the predicted data set of zinc ion content after the replacement is completed, a generating function P of the target palladium powder based on the golden sine factor is established.

[0087]

[0088] Where z is the data set of the predicted zinc ion content after the replacement is completed, δ1, δ2 and δ3 are the golden sine factors for the target palladium powder production;

[0089] K33. Based on the generating function P of the target palladium powder of the golden sine factor, the mass of the recovered palladium powder is estimated to obtain data information on the mass of the recovered palladium powder.

[0090] In this embodiment, the golden sine factors δ1, δ2 and δ3 produced by the target differential signal are:

[0091]

[0092] Wherein, z is the data set of the predicted zinc ion content after the replacement is completed.

[0093] In this embodiment, the system consists of:

[0094] 1) Data acquisition unit: An electromagnetic flowmeter (accuracy ±0.5%) and an electronic scale (accuracy ±0.1kg) are installed. Inductively coupled plasma optical emission spectrometry (ICP-OES) is used, but the sampling system enables regular monitoring of the palladium concentration and flow rate in the liquid.

[0095] 2) Control unit: adopts PLC controller, sampling period is 5 minutes;

[0096] 3) Execution unit: variable frequency speed regulating pump, automatic feeder.

[0097] Operation process:

[0098] 1) Start the system and set the initial parameters;

[0099] 2) Real-time monitoring of waste liquid flow and zinc powder addition;

[0100] 3) Update the prediction model every 120 minutes;

[0101] 4) Adjusting operating parameters according to the control function;

[0102] 5) Calibrate instruments and equipment regularly.

[0103] To verify the effectiveness of Example 1 of the present invention, we conducted a comparative experiment under the following experimental conditions:

[0104] Control group: The traditional method of fixed zinc powder addition amount and constant waste liquid flow rate was adopted.

[0105] Experimental group: The optimized control method proposed in Embodiment 1 of the present invention is adopted.

[0106] The experimental results show that the palladium recovery rate of the control group is 83%, while that of the experimental group reaches 92%. In addition, the consumption of zinc powder in the experimental group is reduced by 7.23%, and the fluctuation range of the waste liquid flow rate is reduced by 20%.

[0107] The following is a graphical display of the experimental data analysis:

[0108] Table 1: Comparison of palladium recovery rates

[0109] Group Recovery rate (%) Control group 83 Experimental group 92

[0110] Table 2: Comparison of zinc powder consumption

[0111] Group Consumption (g / min) Control group 11 Experimental group 10.2

[0112] Table 3: Trend of waste liquid flow rate

[0113] Time (min) Flow rate (L / min) 0 50 30 51.0 60 52.2 120 52.3

[0114] Embodiment 2: On the basis of the method for recycling zinc displacement cycle of waste liquid in Embodiment 1, the present invention will be further described and illustrated below.

[0115] As Figure 1 or Figure 2 shown, an optimized control method for recycling zinc displacement cycle of palladium-containing waste liquid, the method includes:

[0116] K1. During the zinc displacement process of palladium-containing waste liquid, regularly monitor the data information of the palladium concentration in the palladium-containing waste liquid, the waste liquid flow rate, and the data information of the zinc powder addition amount;

[0117] K2. Multiply the palladium concentration by the waste liquid flow rate to obtain the palladium ion flow rate data. Based on the palladium ion flow rate data and the data information of the zinc powder addition amount, use the regression prediction algorithm of the beluga optimization BP neural network to predict the zinc ion content after displacement, and obtain the data information of the predicted zinc ion content after displacement;

[0118] K3. Based on the data information of the predicted zinc ion content after displacement, construct a generation model of the target palladium powder based on the golden sine factor, calculate the quality of the recovered palladium powder, and obtain the data information of the quality of the recovered palladium powder;

[0119] K4. Based on the data information of the quality of the recovered palladium powder, establish a control function W for the palladium ion flow rate data, obtain the control data information of the waste liquid flow rate, and control and adjust the waste liquid flow rate.

[0120] In this embodiment, the flow control function W of the waste liquid is

[0121]

[0122] where r is the data information of the mass of the palladium powder after recovery, and ρ1, ρ2, and ρ3 are weight constant parameters.

[0123] In this embodiment, according to the data information of the mass of the palladium powder after recovery, the flow rate of the palladium-containing liquid is accurately controlled and adjusted, thereby reducing the waste of resources and improving the recovery efficiency of the palladium powder.

[0124] In this embodiment, as Figure 1 shown, zinc powder is added to the waste liquid to be displaced through a screw feeder for a displacement reaction.

[0125] Zn → Zn 2+ + 2e - ,

[0126] Pd 2+ + 2e - → Pd,

[0127] After pressure filtration by a filter press, palladium powder and a filtrate containing zinc ions are obtained. Then, the palladium mud containing zinc powder is subjected to alkaline extraction and filtration to obtain palladium powder.

[0128] In this embodiment, as Figure 5 shown, the present invention provides a system for implementing an optimization control method for the recycling and reuse of the waste liquid zinc displacement cycle. The system includes:

[0129] A data acquisition module for periodically acquiring the data information of the palladium ion flow rate and the amount of zinc powder added;

[0130] A prediction module for the content of zinc ions after displacement, connected to the data acquisition module, for predicting the content of zinc ions after displacement by using a regression prediction algorithm of a beluga optimization BP neural network to obtain the data information of the predicted content of zinc ions after displacement;

[0131] A target palladium powder generation module, connected to the prediction module for the content of zinc ions after displacement, for constructing a generation model of the target palladium powder based on the golden sine factor to calculate the mass of the palladium powder after recovery and obtain the data information of the mass of the palladium powder after recovery;

[0132] A control module for the flow rate of the waste liquid, connected to the target palladium powder generation module, for establishing a flow control function W of the waste liquid to control and adjust the flow rate of the waste liquid and obtain the control data information of the flow rate of the waste liquid.

[0133] In this embodiment, the system further includes a palladium waste liquid zinc replacement data display module, which is connected to the control module of the flow rate of the waste liquid and is used to display the data information of the zinc replacement of the waste liquid in real time.

[0134] In this embodiment, the present invention also provides a computer-readable storage medium, characterized in that a computer program for executing the method of recycling the waste liquid zinc replacement cycle as described in any one of the above is stored on the computer-readable storage medium.

[0135] Any reference to a memory, storage, database, or other medium used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or an external cache. By way of illustration and not limitation, RAM is available in various 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.

[0136] To verify the effectiveness of Embodiment 1 of the present invention, we carried out an application in a certain PCB board enterprise. The enterprise processes 10 tons of waste liquid per day. Our implementation steps are as follows:

[0137] 1. Data collection: Monitor the waste liquid flow rate (initial value: 50 L / min), palladium concentration (initial value: 2 mg / L), and zinc powder addition amount (initial value: 10 g / min) through on-line sensors.

[0138] 2. Palladium ion flow rate calculation: The calculated palladium ion flow rate is 100 mg / min. Prediction of zinc ion content: Use the beluga optimization BP neural network to predict that the zinc ion content after replacement is 8 mg / L.

[0139] 3. Palladium powder quality calculation: Based on the golden sine factor model, calculate that the mass of the recovered palladium powder is 98 mg.

[0140] 4. Waste liquid flow rate adjustment: According to the control function (W), within 120 minutes, adjust the waste liquid flow rate to 52.3 L / min, significantly improving the recovery efficiency.

[0141] In this experiment, palladium is used as an activation solution in the PCB manufacturing process. After drilling, a seed layer is formed on the hole wall through the palladium activation solution for subsequent electroless copper plating. However, the waste liquid (lean liquid and rich liquid) generated during the cleaning process needs to be treated. The traditional method has problems of palladium waste and waste liquid treatment. The key point of the invention may involve a zinc displacement recycling method for the waste liquid, and the specific process steps may include waste liquid classification, palladium recovery and reuse. The invention effect is to improve the utilization rate of palladium, reduce costs, and reduce environmental pollution.

[0142] Example 3: On the basis of the method for recycling waste liquid by zinc displacement in Example 1, the present invention will be further described and explained below.

[0143] As Figure 1 or Figure 2 shown, an optimized control method for recycling waste liquid containing palladium by zinc displacement, the method comprising:

[0144] K1. During the zinc displacement process of the waste liquid containing palladium, regularly monitor the data information of the palladium concentration in the waste liquid containing palladium, the flow rate of the waste liquid, and the data information of the zinc powder addition amount;

[0145] K2. Multiply the palladium concentration by the flow rate of the waste liquid to obtain the palladium ion flow rate data. Based on the palladium ion flow rate data and the data information of the zinc powder addition amount, use the regression prediction algorithm of the beluga optimization BP neural network to predict the content of zinc ions after displacement, and obtain the data information of the predicted content of zinc ions after displacement;

[0146] K3. Based on the data information of the predicted content of zinc ions after displacement, construct a generation model of the target palladium powder based on the golden sine factor, calculate the quality of the recovered palladium powder, and obtain the data information of the quality of the recovered palladium powder;

[0147] K4. Based on the data information of the quality of the recovered palladium powder, establish a control function W for the palladium ion flow rate data, obtain the control data information of the flow rate of the waste liquid, and control and adjust the flow rate of the waste liquid.

[0148] In this embodiment, in step K1, the data acquisition module obtains the flow rate (Q) of the waste liquid and the zinc powder addition amount (Z) in real time. By installing an online flow meter and a weighing system, the data accuracy is ensured.

[0149] In step K2, according to the reaction equation Pd 2+ +Zn→Pd+Zn 2+ , the flow rate and the zinc powder addition amount are input into the regression prediction model of the beluga optimization BP neural network, C(Zn 2+ ) = f(Q, Z), where: C(Zn 2+) is the concentration of zinc ions after replacement, in mg / L; Q is the flow rate of the waste liquid, in m 3 / h; Z is the amount of zinc powder added, in kg / h.

[0150] In step K3, a generation model of the target palladium powder based on the golden sine factor is constructed.

[0151]

[0152] Among them, P(Pd) is the mass of the recovered palladium powder, in g, z is the data set of the content of zinc ions after the predicted replacement is completed, and δ1, δ2, and δ3 are the golden sine factors for the production of the target palladium powder.

[0153] In step K4, the flow control function W of the waste liquid is

[0154] Among them, r is the data information of the mass of the recovered palladium powder, and optimal control is achieved by adjusting the weight constant parameters ρ1, ρ2, and ρ3.

[0155] To verify the effectiveness of Example 1 of the present invention, we carried out an application in a certain PCB board enterprise. The enterprise processes 10 tons of waste liquid per day, and the effect is remarkable after implementing this method:

[0156] Table 4: Data comparison table before and after implementation using this example

[0157] Parameter item Before implementation After implementation Improvement rate Palladium recovery rate 87％ 96.5％ 10.9％ Zinc ion stability ±18％ ±4％ 77.8％ Unit treatment cost ￥320 / kg ￥258 / kg 19.4％

[0158] From Table 4, we can see that this example realizes the intelligent control of the zinc replacement process of the waste liquid by establishing a complete prediction-control system. Experimental data show that this method has significant technical advantages and economic value.

[0159] In summary, the present invention can not only accurately control and adjust the flow rate of the waste liquid, but also the whole process does not require manual participation, has a high degree of intelligence, and improves the recovery efficiency of the waste liquid.

[0160] The above specific implementation manners do not constitute a limitation to the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. An optimized control method for the zinc displacement cycle reuse of palladium-containing waste liquid, characterized in that The method includes: K1. During the zinc replacement process of the palladium-containing waste liquid, regularly monitor the data information of the palladium concentration in the palladium-containing waste liquid, the flow rate of the waste liquid, and the data information of the amount of zinc powder added; K2. Multiply the palladium concentration by the flow rate of the waste liquid to obtain the palladium ion flow rate data. Based on the palladium ion flow rate data and the data information of the amount of zinc powder added, use the regression prediction algorithm of the beluga whale optimized BP neural network to predict the content of zinc ions after replacement, and obtain the data information of the predicted content of zinc ions after replacement; K3. Based on the data information of the predicted content of zinc ions after replacement, construct a generation model of the target palladium powder based on the golden sine factor, calculate the quality of the recovered palladium powder, and obtain the data information of the quality of the recovered palladium powder; K4. Based on the data information of the quality of the recovered palladium powder, establish a control function W for the palladium ion flow rate data, obtain the control data information of the flow rate of the waste liquid, and control and adjust the flow rate of the waste liquid.

2. The optimized control method for the recycling of waste liquid zinc replacement cycle according to claim 1, wherein In step K2, the use of the regression prediction algorithm of the beluga whale optimized BP neural network to predict the content of zinc ions after replacement includes: K21. Input the palladium ion flow rate data and the data information of the amount of zinc powder added into the regression prediction model of the BP neural network for training and learning, initialize the weights and biases of the BP neural network, and obtain the data information of the initialized weights and biases of the BP neural network; K22. Based on the data information of the initialized weights and biases of the BP neural network, initialize the beluga whale population, determine the population parameters and the maximum number of iterations L, and obtain the data information of the initialized beluga whale population; K23. Based on the data information of the initialized beluga whale population, establish a fitness function Q for the population individuals, where x is the data information of the initialized beluga whale population, α1, α2, and α3 are weight coefficients, calculate the fitness values of the individuals in the beluga whale population, and obtain the data information of the fitness values of the individuals in the beluga whale population; K24. Based on the data information of the fitness values of the individuals in the beluga whale population, establish a target optimization function U for the population, where y is the data information of the fitness values of the individuals in the beluga whale population, β1, β2, and β3 are optimization factors, optimize the weights and biases of the BP neural network, and obtain the optimized regression prediction model of the BP neural network.

3. The optimized control method for the recycling of waste liquid zinc replacement cycle according to claim 2, characterized in that, The use of the regression prediction algorithm of the beluga whale optimized BP neural network to predict the content of zinc ions after replacement further includes: K25. Based on the optimized regression prediction model of the BP neural network, input the data information of the palladium ion flow rate data and the data information of the amount of zinc powder added, predict the content of zinc ions after replacement, and obtain the data information of the predicted content of zinc ions after replacement.

4. The optimized control method for the recycling of waste liquid zinc replacement cycle according to claim 2, characterized in that: The optimization factors β1, β2, and β3 are, where y is the data information of the fitness values of the individuals in the beluga whale population.

5. The optimized control method for recycling zinc replacement in waste liquid according to claim 2, characterized in that: The constraint function f of the weight coefficients α1, α2, and α3 is, where α1, α2, and α3 are any constant coefficients between 0 and 1, and the value range of the constraint function f is (0,1).

6. The method for recycling waste liquid replacement cycle according to claim 1, characterized in that In step K3, the calculation of the quality of the recycled palladium powder by constructing a generation model of the target palladium powder based on the golden sine factor includes: K31. Based on the data information of the content of zinc ions after the predicted replacement is completed, construct a data set of the content of zinc ions after the predicted replacement is completed; K32. Based on the data set of the content of zinc ions after the predicted replacement is completed, establish a generation function P of the target palladium powder based on the golden sine factor, where z is the data set of the content of zinc ions after the predicted replacement is completed, and δ1, δ2, and δ3 are the golden sine factors for the production of the target palladium powder; K33. Based on the generation function P of the target palladium powder with the golden sine factor, calculate the quality of the recycled palladium powder to obtain the data information of the quality of the recycled palladium powder.

7. The optimized control method for the recycling of waste liquid zinc replacement cycle according to claim 6, characterized in that: The golden sine factors δ1, δ2, and δ3 for the production of the target differential signal are, where z is the data set of the content of zinc ions after the predicted replacement is completed.

8. The optimized control method for the recycling of waste liquid zinc replacement cycle according to claim 1, characterized in that: The palladium ion flow data control function W is, where r is the data information of the quality of the recycled palladium powder, and ρ1, ρ2, and ρ3 are weight constant parameters.

9. A system for implementing an optimized control method for the recycling and reuse of zinc replacement in waste liquid as described in any one of claims 1-8, characterized in that, The system includes: A data acquisition module for regularly acquiring the data information of the palladium ion flow and the data information of the amount of zinc powder added; A prediction module for the content of zinc ions after the replacement is completed, connected to the data acquisition module, for predicting the content of zinc ions after the replacement is completed by using the regression prediction algorithm of the beluga optimization BP neural network to obtain the data information of the content of zinc ions after the predicted replacement is completed; A generation module for the target palladium powder, connected to the prediction module for the content of zinc ions after the replacement is completed, for constructing a generation model of the target palladium powder based on the golden sine factor, calculating the quality of the recycled palladium powder, and obtaining the data information of the quality of the recycled palladium powder; A control module for the palladium ion flow data, connected to the generation module for the target palladium powder, for establishing a palladium ion flow data control function W to control and adjust the flow of the waste liquid to obtain the control data information of the flow of the waste liquid.

10. The system according to claim 9, wherein The system further includes a palladium waste liquid zinc replacement data display module, connected to the control module for the palladium ion flow data, for real-time displaying the data information of the waste liquid zinc replacement.

Images