Industrial wastewater treatment control method, device, equipment and medium

Abstract

The invention discloses an industrial wastewater treatment control method, device, equipment and medium, and belongs to the technical field of wastewater treatment. The method comprises the following steps: collecting water quality index parameters in an industrial wastewater treatment process and equipment operation parameters of wastewater treatment equipment in real time; carrying out pretreatment operation on the collected water quality index parameters, wherein the pretreatment operation comprises cleaning and normalization processing; based on the historical equipment operation parameters and the historical water quality index parameters, training to obtain a wastewater treatment control model; inputting the pretreated water quality index parameters into the trained wastewater treatment control model, dynamically calculating the optimal value of the equipment operation parameters, and generating a control instruction; and sending the control instruction to the wastewater treatment equipment, adjusting the equipment operation parameters of the wastewater treatment equipment in real time, and optimizing the industrial wastewater treatment process. According to the invention, the optimal value of the equipment operation parameter can be dynamically calculated and the control instruction is generated, so that the real-time adjustment and optimization of the wastewater treatment equipment are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of wastewater treatment, and more specifically, to an industrial wastewater treatment control method, device, equipment and medium. Background Art

[0002] With the rapid development of industrialization, the problem of industrial wastewater discharge has become increasingly prominent, causing serious damage to the environment. In particular, the discharge of harmful substances such as heavy metals and organic matter not only affects the natural purification capacity of water bodies but can also have long-term negative impacts on human health. To effectively manage and treat industrial wastewater, various wastewater treatment equipment and technologies have emerged, such as pumps, valves, mixers, aerators, and dosing mechanisms. While these devices and technologies have alleviated wastewater pollution to a certain extent, traditional industrial wastewater treatment methods have some shortcomings and are difficult to meet the requirements of modern environmental protection standards.

[0003] Existing industrial wastewater treatment methods mostly rely on manual operation and experience-based settings, and lack real-time and intelligent control mechanisms. For example, the monitoring of water quality indicators usually relies on regular sampling and laboratory analysis, and cannot achieve continuous and real-time monitoring. This results in the adjustment of equipment parameters lagging behind changes in water quality during the wastewater treatment process, and it is impossible to respond to emergencies in a timely manner, thus affecting the treatment effect. In addition, since the setting of equipment parameters is mostly based on the experience of the operator, it is often impossible to achieve the optimal treatment effect, resulting in waste of resources and increased processing costs. In complex wastewater treatment systems, the limitations of this manual control method are particularly obvious, and it is difficult to achieve comprehensive optimization of multiple water quality indicators. Summary of the Invention

[0004] In order to overcome the technical problems existing in the above-mentioned prior art, the present invention provides an industrial wastewater treatment control method, device, equipment and medium.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0006] An industrial wastewater treatment and control method comprises the following steps:

[0007] Real-time collection of water quality index parameters and equipment operating parameters of wastewater treatment equipment during industrial wastewater treatment;

[0008] Performing a preprocessing operation on the collected water quality index parameters, wherein the preprocessing operation includes cleaning and normalization processing;

[0009] Based on historical equipment operating parameters and historical water quality index parameters, a wastewater treatment control model is trained;

[0010] Inputting the pretreated water quality index parameters into the trained wastewater treatment control model, dynamically calculating the optimal values ​​of the equipment operating parameters, and generating control instructions;

[0011] The control instructions are sent to the wastewater treatment equipment to adjust the equipment operating parameters of the wastewater treatment equipment in real time and optimize the industrial wastewater treatment process.

[0012] Furthermore, the water quality index parameters include heavy metal ion concentration, organic matter concentration, pH value, turbidity, and dissolved oxygen content.

[0013] Furthermore, the data cleaning includes removing null values, abnormal values ​​and duplicate values ​​in the collected water quality index parameters, and the normalization processing includes converting the collected water quality index parameters to a range between 0 and 1.

[0014] Furthermore, the training process of the wastewater treatment control model includes:

[0015] Collect historical equipment operating parameters X and historical water quality index parameters Y, where X is an n×p matrix, and each sample contains p equipment operating parameters; Y is an n×q matrix, and each sample contains q water quality index parameters;

[0016] Construct a multi-layer feedforward neural network model, which consists of L layers, where the input layer is the first layer, the output layer is the Lth layer, and the middle layer is the hidden layer;

[0017] The number of nodes in the input layer is p, the number of nodes in the output layer is q, and the number of nodes in each hidden layer is h;

[0018] The forward propagation calculation formula of the model is:

[0019] z (l) =W (l) A (l-1) +b (l)

[0020] A (l) =σ(Z (l) );

[0021] Where Z(l) is the linear combination output of layer l, A(l) is the activation output of layer l, W(l) is the weight matrix of layer l, b(l) is the bias vector of layer l, and σ is the activation function;

[0022] Use mean square error (MSE) as the loss function to calculate the difference between the model's predicted value Y^ and the actual value Y;

[0023]

[0024] Among them, yij is the actual value of the j-th water quality index parameter of the i-th sample, is the predicted value of the jth water quality index parameter of the i-th sample, n is the number of samples, and q is the number of water quality index parameters;

[0025] Use the gradient descent method to optimize the model parameters. The update rules are as follows:

[0026]

[0027] Among them, α is the learning rate, which controls the step size of parameter update; and are the partial derivatives of the loss function with respect to the weights and biases of the lth layer, respectively, used to update the model parameters;

[0028] Divide the preprocessed data X and Y into training sets and validation sets;

[0029] Use the training set data for multiple rounds of iterative training. In each round of iteration, calculate the forward propagation output Calculating the loss function Calculating gradients and Update the model parameters W(l) and b(l). After each training cycle, use the validation set data to evaluate the model performance and finally select the model parameters with the best performance.

[0030] Furthermore, the wastewater treatment equipment includes a pump, a valve, a stirrer, an aerator and a dosing mechanism.

[0031] Furthermore, when the monitored water quality index parameters and / or the equipment operating parameters exceed a preset range, an alarm is triggered and preset corrective measures are automatically taken.

[0032] Furthermore, the collected water quality index parameters and equipment operating parameters are stored in the database for subsequent historical data analysis and model optimization.

[0033] An industrial wastewater treatment control device, comprising:

[0034] A data acquisition module, which is used to collect water quality index parameters and equipment operating parameters of wastewater treatment equipment in real time during industrial wastewater treatment;

[0035] A data preprocessing module, wherein the data preprocessing module performs preprocessing operations on the collected water quality index parameters, and the preprocessing operations include cleaning and normalization processing;

[0036] A model training module, wherein the model training module trains a wastewater treatment control model based on historical equipment operating parameters and historical water quality index parameters;

[0037] A control instruction generation module, which inputs the pre-treated water quality index parameters into the trained wastewater treatment control model, dynamically calculates the optimal values ​​of the equipment operating parameters, and generates control instructions;

[0038] The equipment control module sends the control instructions to the wastewater treatment equipment, adjusts the equipment operating parameters of the wastewater treatment equipment in real time, and optimizes the industrial wastewater treatment process.

[0039] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the aforementioned industrial wastewater treatment control method when executing the computer program.

[0040] A computer-readable storage medium stores a computer program that can be executed by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the aforementioned industrial wastewater treatment control method.

[0041] Compared with the prior art, the beneficial effects of the technical solution of the present invention are:

[0042] The present invention provides an industrial wastewater treatment control method, device, equipment, and medium. These methods collect and preprocess water quality parameters and equipment operating parameters during the industrial wastewater treatment process in real time, train them using a multi-layer feedforward neural network model, dynamically calculate optimal values ​​for the equipment operating parameters, and generate control instructions, thereby enabling real-time adjustment and optimization of wastewater treatment equipment. Compared with existing technologies, the present invention effectively removes null values, outliers, and duplicate values ​​from the collected data, performs normalization processing, improves data quality, and ensures the accuracy of model training and prediction precision. Furthermore, the control model of the present invention can capture the complex nonlinear relationships between water quality indicators and equipment operating parameters, optimizing the comprehensive treatment effects of multiple water quality indicators, thereby significantly improving the efficiency and effectiveness of industrial wastewater treatment and reducing resource waste and treatment costs. Furthermore, the present invention also features automatic alarm and corrective action functions, enabling timely action when monitored parameters exceed preset ranges, further ensuring the stability and safety of the treatment process. By storing real-time data in a database, the present invention also supports historical data analysis and model optimization, providing powerful data support for the continuous improvement of the wastewater treatment process. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 This is a flow chart of an industrial wastewater treatment control method provided in one embodiment of the present application;

[0045] Figure 2 This is a system block diagram of an industrial wastewater treatment control device provided in one embodiment of the present application;

[0046] Explanation of the marks in the figure: 1. Data acquisition module; 2. Data preprocessing module; 3. Model training module; 4. Control instruction generation module; 5. Equipment control module. DETAILED DESCRIPTION

[0047] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0048] Example 1:

[0049] like Figure 1 As shown, the present invention provides a technical solution:

[0050] An industrial wastewater treatment and control method comprises the following steps:

[0051] Real-time collection of water quality index parameters and equipment operating parameters of wastewater treatment equipment during industrial wastewater treatment;

[0052] Performing a preprocessing operation on the collected water quality index parameters, wherein the preprocessing operation includes cleaning and normalization processing;

[0053] Based on historical equipment operating parameters and historical water quality index parameters, a wastewater treatment control model is trained;

[0054] Inputting the pretreated water quality index parameters into the trained wastewater treatment control model, dynamically calculating the optimal values ​​of the equipment operating parameters, and generating control instructions;

[0055] The control instructions are sent to the wastewater treatment equipment to adjust the equipment operating parameters of the wastewater treatment equipment in real time and optimize the industrial wastewater treatment process.

[0056] This embodiment ensures the accuracy and integrity of the data by collecting water quality index parameters and equipment operating parameters in the industrial wastewater treatment process in real time, and performing data cleaning and normalization processing. The multi-layer feedforward neural network model trained based on historical data can capture the complex nonlinear relationship between water quality indicators and equipment operating parameters, improving the prediction accuracy and control effect of the model. By generating and sending control instructions in real time, dynamic adjustment of wastewater treatment equipment is achieved, which significantly improves the efficiency and effect of wastewater treatment and reduces resource waste and processing costs. In addition, the control method of this embodiment also supports the feedback mechanism of the equipment, ensuring the accuracy and timeliness of the adjustment action, extending the service life of the equipment, and reducing maintenance costs.

[0057] Example 2:

[0058] Based on Example 1, the water quality index parameters include heavy metal ion concentration, organic matter concentration, pH value, turbidity, and dissolved oxygen content, which correspond to heavy metal ion concentration sensors, organic matter concentration sensors, pH value sensors, turbidity sensors, and dissolved oxygen sensors, respectively; the acquisition frequency of heavy metal ion concentration and organic matter concentration can be set to once every 10 minutes, the acquisition frequency of pH value and turbidity can be set to once every 5 minutes, and the acquisition frequency of dissolved oxygen content can be set to once every 15 minutes; the acquisition frequency of equipment operating parameters can be dynamically adjusted according to the response speed and stability of the equipment, and can be set to once every 1-2 minutes.

[0059] Furthermore, the data cleaning includes removing null values, abnormal values ​​and duplicate values ​​in the collected water quality index parameters, and the normalization processing includes converting the collected water quality index parameters to a range between 0 and 1.

[0060] Furthermore, the training process of the wastewater treatment control model includes:

[0061] Collect historical equipment operating parameters X and historical water quality index parameters Y, where X is an n×p matrix, and each sample contains p equipment operating parameters; Y is an n×q matrix, and each sample contains q water quality index parameters;

[0062] Construct a multi-layer feedforward neural network model, which consists of L layers, where the input layer is the first layer, the output layer is the Lth layer, and the middle layer is the hidden layer;

[0063] The number of nodes in the input layer is p, the number of nodes in the output layer is q, and the number of nodes in each hidden layer is h;

[0064] The forward propagation calculation formula of the model is:

[0065] Z (l) =W (l) A (l-1) +b(l)

[0066] A (l) =σ(Z (l) );

[0067] Where Z(l) is the linear combination output of layer l, A(l) is the activation output of layer l, W(l) is the weight matrix of layer l, b(l) is the bias vector of layer l, and σ is the activation function;

[0068] Use mean square error (MSE) as the loss function to calculate the difference between the model's predicted value Y^ and the actual value Y;

[0069]

[0070] Among them, yij is the actual value of the j-th water quality index parameter of the i-th sample, is the predicted value of the jth water quality index parameter of the i-th sample, n is the number of samples, and q is the number of water quality index parameters;

[0071] Use the gradient descent method to optimize the model parameters. The update rules are as follows:

[0072]

[0073] Among them, α is the learning rate, which controls the step size of parameter update; and are the partial derivatives of the loss function with respect to the weights and biases of the lth layer, respectively, used to update the model parameters;

[0074] Divide the preprocessed data X and Y into training sets and validation sets;

[0075] Use the training set data for multiple rounds of iterative training. In each round of iteration, calculate the forward propagation output Calculating the loss function Calculating gradients and Update the model parameters W(l) and b(l). After each training cycle, use the validation set data to evaluate the model performance and finally select the model parameters with the best performance.

[0076] By constructing a multi-layer feedforward neural network model, the complex nonlinear relationship between water quality indicators and equipment operating parameters can be effectively captured, improving the model's prediction accuracy and control effectiveness. The use of the MSE loss function ensures that the model's prediction error is effectively controlled. The gradient descent method and advanced optimization algorithms can efficiently optimize the model parameters, improving the model's training effect and convergence speed. The partitioning of the data set and the use of a validation set further ensure the model's generalization ability and stability, prevent overfitting, and make the model more reliable and adaptable in practical applications. These optimization measures have significantly improved the intelligence level and treatment effectiveness of the wastewater treatment process, reducing resource waste and processing costs.

[0077] Furthermore, the wastewater treatment equipment includes a pump, valve, agitator, aerator, and a dosing mechanism. Control commands can be used to adjust various functions, such as pump speed, valve opening, agitator run time, aeration volume, and dosing volume. Pump speed control can be achieved using a frequency converter, which dynamically adjusts the motor speed according to control commands, thereby achieving precise control of the pump speed. Valve opening control can be achieved using an electric actuator or a pneumatic actuator, which can precisely adjust the valve opening according to control commands. The agitator can be controlled using a time relay or a programmable logic controller, which can precisely adjust the agitator's operating status according to control commands. The aerator can be controlled using an air flow meter and an air compressor, which can precisely adjust the aeration volume according to control commands. The dosing mechanism can be controlled using a metering pump and a flow control system, which can precisely adjust the dosage of the agent according to control commands. The dosing mechanism can also be equipped with an automatic detection and feedback mechanism to ensure that the actual dosage of the agent is consistent with the set value.

[0078] Furthermore, when the monitored water quality parameters and / or equipment operating parameters exceed preset ranges, an alarm is triggered and preset corrective measures are automatically implemented. Alarms can be communicated to operators through various means, such as audible and visual alarms, text message notifications, and email notifications. The alarm mechanism also records the specific parameter value and time of the out-of-range condition to facilitate subsequent analysis and processing. When the wastewater flow rate exceeds the normal range, the system can adjust the pump speed to restore the wastewater flow rate to a stable state. For example, if the flow rate is too low, the system can increase the pump speed; if the flow rate is too high, the system can reduce the pump speed. When the wastewater pressure or flow rate exceeds the normal range, the system can adjust the valve opening to restore normality. For example, if the pressure is too high, the system can reduce the valve opening; if the pressure is too low, the system can increase the valve opening. When the reagents in the wastewater are unevenly mixed, the system can improve mixing by adjusting the agitator's operating time or speed. For example, if the mixing is uneven, the system can increase the agitator's operating time or speed. When the dissolved oxygen content in the wastewater exceeds the normal range, the system can adjust the aeration rate to restore the dissolved oxygen balance. For example, if the dissolved oxygen content is too low, the system can increase the aeration rate; if the dissolved oxygen content is too high, the system can reduce the aeration rate. When the concentration of certain harmful substances in the wastewater exceeds the normal range, the system can quickly remove these harmful substances by adjusting the dosage. For example, if the organic matter concentration is too high, the system can increase the dosage; if the organic matter concentration is too low, the system can reduce the dosage.

[0079] Furthermore, the collected water quality index parameters and equipment operating parameters are stored in the database for subsequent historical data analysis and model optimization.

[0080] By storing collected water quality indicators and equipment operating parameters in a database, a rich data resource is provided for real-time system control and subsequent historical data analysis. Historical data analysis can identify potential system issues and areas for improvement. Model optimization can further improve the efficiency and effectiveness of wastewater treatment, reducing resource waste and treatment costs. Data visualization allows operators and managers to intuitively understand the system's operating status, promptly identify and address issues, and enhance the system's intelligence and management efficiency. These measures not only improve the system's responsiveness and treatment effectiveness, but also provide a solid foundation for continuous optimization and improvement, ensuring the system's stability and reliability over the long term.

[0081] Example 3:

[0082] like Figure 2 As shown, the present invention provides a technical solution:

[0083] An industrial wastewater treatment control device, comprising:

[0084] Data acquisition module 1, which is used to collect water quality index parameters and equipment operating parameters of wastewater treatment equipment in real time during industrial wastewater treatment;

[0085] A data preprocessing module 2, wherein the data preprocessing module 2 performs a preprocessing operation on the collected water quality index parameters, and the preprocessing operation includes cleaning and normalization processing;

[0086] Model training module 3, said model training module 3 is based on historical equipment operating parameters and historical water quality index parameters to train a wastewater treatment control model;

[0087] A control instruction generation module 4, which inputs the pre-treated water quality index parameters into the trained wastewater treatment control model, dynamically calculates the optimal values ​​of the equipment operating parameters, and generates control instructions;

[0088] The equipment control module 5 sends the control instructions to the wastewater treatment equipment, adjusts the equipment operating parameters of the wastewater treatment equipment in real time, and optimizes the industrial wastewater treatment process.

[0089] Example 4:

[0090] The present invention provides a technical solution:

[0091] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the aforementioned industrial wastewater treatment control method when executing the computer program.

[0092] In this embodiment, the computer system suitable for implementing the electronic device of the embodiment of the present invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) or the program loaded from the storage portion into the random access memory (RAM), such as the method described in the above embodiment. Various programs and data required for system operation are also stored in the RAM. The CPU, ROM, and RAM are connected to each other via a bus. The input / output (I / O) interface is also connected to the bus.

[0093] The following components are connected to the I / O interface: an input section including a keyboard, mouse, etc.; an output section including a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section including a hard disk; and a communication section including a network interface card such as a LAN (Local Area Network) card and a modem. The communication section performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as needed. Removable media such as magnetic disks, optical disks, magneto-optical disks, semiconductor memories, etc. are installed in the drive as needed so that computer programs read from them can be installed in the storage section as needed.

[0094] Example 5:

[0095] The present invention provides a technical solution:

[0096] A computer-readable storage medium storing a computer program executable by an electronic device. When the computer program is executed on the electronic device, the electronic device executes the steps of the aforementioned industrial wastewater treatment control method. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device.

[0097] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. There may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some communication interface, indirect coupling or communication connection of devices or units, which may be electrical, mechanical or other forms.

[0098] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0099] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0100] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely illustrative and are not intended to limit the scope of the present application. Various changes and modifications may be made therein by those skilled in the art without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0101] Similarly, it should be understood that in order to streamline the present application and aid in understanding one or more of the various application aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this approach of the present application should not be interpreted as reflecting the intention that the claimed application requires more features than those explicitly recited in each claim. More precisely, as reflected in the corresponding claims, the point of the application is that the corresponding technical problem can be solved with fewer features than all the features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present application.

[0102] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of this application and to form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

[0103] It should be noted that the above embodiments are illustrative rather than limiting of the present application, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The use of the words first, second, and third, etc., does not denote any order. These words may be interpreted as designations.

Claims

1. A method for controlling industrial wastewater treatment, characterized in that: The following steps are involved: Real-time collection of water quality index parameters and equipment operating parameters of wastewater treatment equipment during industrial wastewater treatment; Performing a preprocessing operation on the collected water quality index parameters, wherein the preprocessing operation includes cleaning and normalization processing; Based on historical equipment operating parameters and historical water quality index parameters, a wastewater treatment control model is trained; Inputting the pretreated water quality index parameters into the trained wastewater treatment control model, dynamically calculating the optimal values ​​of the equipment operating parameters, and generating control instructions; The control instructions are sent to the wastewater treatment equipment to adjust the equipment operating parameters of the wastewater treatment equipment in real time and optimize the industrial wastewater treatment process.

2. The industrial wastewater treatment control method according to claim 1, characterized in that: The water quality index parameters include heavy metal ion concentration, organic matter concentration, pH value, turbidity, and dissolved oxygen content.

3. The industrial wastewater treatment control method according to claim 1, characterized in that: The data cleaning includes removing null values, abnormal values ​​and duplicate values ​​in the collected water quality index parameters, and the normalization processing includes converting the collected water quality index parameters to a range between 0 and 1.

4. The industrial wastewater treatment and control method according to claim 1, characterized in that: The training process of the wastewater treatment control model includes: Collect historical equipment operating parameters X and historical water quality index parameters Y, where X is an n×p matrix, and each sample contains p equipment operating parameters; Y is an n×q matrix, and each sample contains q water quality index parameters; Construct a multi-layer feedforward neural network model, which consists of L layers, where the input layer is the first layer, the output layer is the Lth layer, and the middle layer is the hidden layer; The number of nodes in the input layer is p, the number of nodes in the output layer is q, and the number of nodes in each hidden layer is h; The forward propagation calculation formula of the model is: Z (l) =W (l) A (-1) +b (l) A (l) =σ(Z (l) ; Where Z(l) is the linear combination output of layer l, A(l) is the activation output of layer l, W(l) is the weight matrix of layer l, b(l) is the bias vector of layer l, and σ is the activation function; Use mean square error (MSE) as the loss function to calculate the difference between the model's predicted value Y^ and the actual value Y; Among them, yij is the actual value of the j-th water quality index parameter of the i-th sample, is the predicted value of the jth water quality index parameter of the i-th sample, n is the number of samples, and q is the number of water quality index parameters; Use the gradient descent method to optimize the model parameters. The update rules are as follows: Among them, α is the learning rate, which controls the step size of parameter update; and are the partial derivatives of the loss function with respect to the weights and biases of the lth layer, respectively, used to update the model parameters; Divide the preprocessed data X and Y into training sets and validation sets; Use the training set data for multiple rounds of iterative training. In each round of iteration, calculate the forward propagation output Calculating the loss function Calculating gradients and Update the model parameters W(l) and b(l). After each training cycle, use the validation set data to evaluate the model performance and finally select the model parameters with the best performance.

5. The industrial wastewater treatment and control method according to claim 1, characterized in that: The wastewater treatment equipment includes a pump, a valve, a stirrer, an aerator and a dosing mechanism.

6. The industrial wastewater treatment and control method according to claim 1, characterized in that: When the monitored water quality index parameters or the equipment operating parameters exceed the preset range, an alarm is triggered and preset corrective measures are automatically taken.

7. The industrial wastewater treatment and control method according to claim 1, characterized in that: The collected water quality index parameters and equipment operating parameters are stored in the database for subsequent historical data analysis and model optimization.

8. An industrial wastewater treatment control device, characterized in that: The industrial wastewater treatment control device includes: A data acquisition module, which is used to collect water quality index parameters and equipment operating parameters of wastewater treatment equipment in real time during industrial wastewater treatment; A data preprocessing module, wherein the data preprocessing module performs preprocessing operations on the collected water quality index parameters, and the preprocessing operations include cleaning and normalization processing; A model training module, wherein the model training module trains a wastewater treatment control model based on historical equipment operating parameters and historical water quality index parameters; A control instruction generation module, which inputs the pre-treated water quality index parameters into the trained wastewater treatment control model, dynamically calculates the optimal values ​​of the equipment operating parameters, and generates control instructions; The equipment control module sends the control instructions to the wastewater treatment equipment, adjusts the equipment operating parameters of the wastewater treatment equipment in real time, and optimizes the industrial wastewater treatment process.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and is characterized in that when the processor executes the computer program, the steps of the industrial wastewater treatment control method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program that can be executed by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the industrial wastewater treatment control method described in any one of claims 1 to 7.

Images