Water treatment automatic matching pump intelligent control method and system

Abstract

The application provides a water treatment automatic matching pump intelligent control method and system, relates to the technical field of automatic water pump control, and comprises the following steps: collecting setting distribution information of a water treatment pump group, determining a plurality of configuration control nodes, then constructing a pump group topology structure, collecting energy consumption data, obtaining a plurality of sets of energy consumption data sets under a plurality of sample scenes, then jointly mapping training, acquiring an adaptive control model, acquiring water treatment request task information, then performing task decomposition, determining task characteristic information of the configuration control nodes, acquiring a control strategy through the model, and performing automatic pump matching and parameter control. The application mainly solves the problem that automatic adjustment cannot be realized, the operation state of the pump does not match the actual demand due to the dependence on manual operation, manual operation cannot realize real-time monitoring and adjustment, the error is large, and the energy consumption is high. Through the automatic pump matching method, the appropriate pump type and quantity can be automatically selected according to the actual demand, so that the optimal energy consumption performance is achieved.

Description

Technical Field

[0001] This application relates to the field of automatic pump control technology, specifically to an intelligent control method and system for automatic pump allocation in water treatment. Background Technology

[0002] Water treatment systems require various devices to ensure water quality and quantity, and these devices consume electrical energy to operate. However, traditional water treatment systems often lack comprehensive consideration of energy consumption, leading to energy waste and low operating efficiency. With the continuous development of automation technology and intelligent control theory, automatic pump allocation methods in water treatment are gradually being widely applied. This method can automatically adjust the pump's operating status according to actual needs by monitoring and controlling system parameters in real time, achieving efficient energy utilization and stable system operation.

[0003] In traditional water treatment systems, pump configuration and operation often rely on manual operation and experience-based judgment. However, this approach has several problems. First, manual operation can easily lead to inappropriate pump configuration, resulting in high system energy consumption. Second, manual operation makes it difficult to achieve real-time monitoring and adjustment of the pumps, leading to system instability.

[0004] However, in the process of implementing the technical solution of the invention in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems:

[0005] The inability to achieve automated adjustment and reliance on manual operation leads to a mismatch between the pump's operating status and actual needs. Furthermore, manual operation cannot achieve real-time monitoring and adjustment, resulting in large errors and high energy consumption. Summary of the Invention

[0006] This application mainly addresses the problem that the inability to achieve automated adjustment and reliance on manual operation lead to a mismatch between the pump's operating status and actual needs. Furthermore, manual operation cannot achieve real-time monitoring and adjustment, resulting in large errors and high energy consumption.

[0007] In view of the above problems, this application provides an intelligent control method and system for automatic pump allocation in water treatment. In a first aspect, this application provides an intelligent control method for automatic pump allocation in water treatment, the method comprising: collecting the setting and distribution information of water treatment pump sets to determine multiple configuration control nodes; constructing a pump set topology based on the equipment basic parameters, setting locations, and connection relationships of the multiple configuration control nodes; collecting energy consumption data from the multiple configuration control nodes to obtain multiple sets of energy consumption datasets under multiple sample scenarios; performing joint mapping training based on the pump set topology and the multiple sets of energy consumption datasets to obtain an adaptive control model; acquiring water treatment request task information, and extracting task processing volume and process execution pump information based on the water treatment request task information; decomposing the task based on the task processing volume and process execution pump information to determine the task feature information of each configuration control node; inputting the task feature information of each configuration control node into the adaptive control model for optimization to obtain a control strategy, wherein the control strategy includes control parameters of the multiple configuration control nodes; automatically allocating pumps according to the control strategy, and controlling the execution parameters of each pump according to the control parameters.

[0008] Secondly, this application provides an automatic pump distribution intelligent control system for water treatment. The system includes: a configuration control node determination module, which collects the setting and distribution information of water treatment pump sets and determines multiple configuration control nodes; a pump set topology construction module, which constructs a pump set topology based on the equipment basic parameters, setting locations, and connection relationships of the multiple configuration control nodes; an energy consumption dataset acquisition module, which collects energy consumption data according to the multiple configuration control nodes to obtain multiple sets of energy consumption datasets under multiple sample scenarios; and an adaptive control model acquisition module, which performs joint mapping training based on the pump set topology and the multiple sets of energy consumption datasets to obtain... An adaptive control model; a task request information acquisition module, which acquires water treatment task request information and extracts task processing volume and process execution pump information based on the water treatment task request information; a task decomposition module, which decomposes the task based on the task processing volume and process execution pump information to determine the task characteristic information of each configured control node; a control strategy acquisition module, which inputs the task characteristic information of each configured control node into the adaptive control model for optimization to obtain a control strategy, wherein the control strategy includes control parameters for multiple configured control nodes; and a parameter control module, which automatically allocates pumps according to the control strategy and controls the execution parameters of each pump according to the control parameters.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] This application provides an intelligent control method and system for automatic pump allocation in water treatment, relating to the field of automatic pump control technology. The method includes: collecting the setting and distribution information of water treatment pump groups, determining multiple configuration control nodes, constructing the pump group topology, collecting energy consumption data, obtaining multiple sets of energy consumption datasets under multiple sample scenarios, jointly mapping and training to obtain an adaptive control model, obtaining water treatment request task information, performing task decomposition, determining the task feature information of each configuration control node, obtaining a control strategy through the model, and performing automatic pump allocation and parameter control.

[0011] This application primarily addresses the problem of reliance on manual operation leading to a mismatch between pump operating status and actual needs, as automated adjustment is impossible. Furthermore, manual operation lacks real-time monitoring and adjustment capabilities, resulting in significant errors and high energy consumption. The automatic pump matching method can automatically select the appropriate pump type and quantity based on actual needs to achieve optimal energy efficiency.

[0012] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0014] Figure 1 A schematic flowchart of an automatic pump distribution and intelligent control method for water treatment is provided for embodiments of this application;

[0015] Figure 2 This application provides a schematic flowchart of the method for constructing a training dataset in the intelligent control method for automatic pump distribution in water treatment.

[0016] Figure 3 This application provides a schematic flowchart of the adaptive adjustment method in the automatic pump distribution intelligent control method for water treatment.

[0017] Figure 4 A schematic diagram of the structure of an automatic pump control system for water treatment is provided for the embodiments of this application.

[0018] Explanation of reference numerals in the attached diagram: Module 10 for determining the configuration control node, Module 20 for constructing the pump group topology, Module 30 for acquiring the energy consumption dataset, Module 40 for acquiring the adaptive control model, Module 50 for acquiring the request task information, Module 60 for decomposing the task, Module 70 for acquiring the control strategy, and Module 80 for controlling the parameters. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] This application primarily addresses the problem of reliance on manual operation leading to a mismatch between pump operating status and actual needs, as automated adjustment is impossible. Furthermore, manual operation lacks real-time monitoring and adjustment capabilities, resulting in significant errors and high energy consumption. The automatic pump matching method can automatically select the appropriate pump type and quantity based on actual needs to achieve optimal energy efficiency.

[0021] To better understand the above technical solution, the following will provide a detailed description of the solution in conjunction with the accompanying drawings and specific implementation methods:

[0022] Example 1

[0023] like Figure 1 The water treatment automatic pump distribution intelligent control method shown includes:

[0024] Collect information on the location and distribution of water treatment pump sets to determine multiple configuration control nodes;

[0025] Specifically, the first step is to collect various data about the water treatment pump set, including pump type, specifications, quantity, and layout. This data can be obtained from equipment lists, design drawings, and site surveys. Next, control nodes are identified: based on the collected data, multiple configuration control nodes can be determined. These nodes can be for pump start-up and shutdown control, flow control, pressure control, etc. When determining control nodes, factors such as the pump set's operating mode, process flow, and safety and reliability need to be considered. Through these steps, the layout and distribution information of the water treatment pump set can be collected, and multiple configuration control nodes can be identified. This information will help in designing an efficient and reliable water treatment pump set control system.

[0026] Based on the device basic parameters, settings, and connection relationships of the multiple configuration control nodes, a pump group topology is constructed.

[0027] Specifically, a water treatment pump set topology can be constructed based on the basic equipment parameters, installation locations, and connection relationships of multiple configuration control nodes. First, the basic equipment parameters of each configuration control node are collected, such as pump type, specifications, rated power, flow rate, and head. These parameters will be used to construct the pump set topology. Next, the installation locations are determined: based on the collected installation distribution information, the location of each configuration control node can be determined. These locations can be physical locations or logical locations (such as node numbers in the system). Then, connection relationships are established: according to the pump set layout and control requirements, connection relationships can be established between the configuration control nodes. These connections can be physical connections, such as cables or pipes, or logical connections, such as communication protocols or data flows. Finally, the pump set topology is constructed: combining the basic equipment parameters, installation locations, and connection relationships, the water treatment pump set topology can be constructed. This structure can be represented as a topology graph, where each configuration control node is represented as a node, and the connections between nodes are represented as edges. Through these steps, a water treatment pump set topology can be constructed based on the basic equipment parameters, installation locations, and connection relationships of multiple configuration control nodes and applied in practical engineering. This structure will help improve the efficiency and reliability of pump unit operation, while also facilitating its monitoring and management.

[0028] Energy consumption data is collected from the multiple configured control nodes to obtain multiple sets of energy consumption datasets under multiple sample scenarios.

[0029] Specifically, by collecting energy consumption data from multiple configuration control nodes, multiple sets of energy consumption datasets can be obtained under multiple sample scenarios. The process involves: 1. Determining the configuration control nodes: Based on the collected basic equipment parameters, setting locations, and connection relationships, the location and function of each configuration control node can be determined. These nodes can be for pump start / stop control, flow control, pressure control, etc. 2. Energy consumption data collection: For each configuration control node, appropriate measuring devices (such as power meters, flow meters, etc.) are selected to collect energy consumption data. These devices should be able to accurately measure and record the energy consumption of each node. 3. Sample scenario setting: To obtain multiple sets of energy consumption datasets under multiple sample scenarios, different operating scenarios need to be set. These scenarios can include normal operation, light load operation, heavy load operation, etc. For each state, the corresponding equipment operating parameters and control strategies need to be recorded. 4. Data collection and recording: Under different sample scenarios, energy consumption data is collected and recorded according to the set time intervals or event triggering methods. This data should include information such as the energy consumption value, equipment status, and control commands of each configuration control node. By following the steps above, energy consumption data can be collected from multiple configured control nodes, resulting in multiple sets of energy consumption datasets for various sample scenarios. These datasets can be used for energy efficiency assessment, optimization, and control system improvement, helping to improve the operating efficiency of water treatment pump sets and save energy consumption.

[0030] An adaptive control model is obtained by jointly mapping and training the pump group topology and the multiple energy consumption datasets.

[0031] Specifically, an adaptive control model can be obtained by jointly mapping and training the pump group topology and multiple energy consumption datasets. The collected energy consumption datasets undergo preprocessing, including data cleaning, standardization, and normalization, to eliminate outliers and noise and convert the data to a uniform scale. Feature extraction: Energy-related features are extracted from the pump group topology. These features may include pump type, specifications, quantity, and connection relationships. For each configured control node, corresponding basic equipment parameters and operating status can be extracted as features. Constructing the adaptive control model: Machine learning or deep learning algorithms are used to jointly map and train the pump group topology and multiple energy consumption datasets. Suitable adaptive control models include neural networks, support vector machines, and decision trees. Model training: The adaptive control model is trained using the preprocessed and feature-extracted data as input. During training, techniques such as cross-validation and grid search can be used to optimize model parameters and evaluate model performance. Through these steps, an adaptive control model can be obtained by jointly mapping and training the pump group topology and multiple energy consumption datasets. This model can be used to monitor and control the operating status of water treatment pump sets in real time, thereby improving the efficiency and stability of the entire system.

[0032] Obtain water treatment request task information, and extract task processing volume and process execution pump information based on the water treatment request task information;

[0033] Specifically, the process involves acquiring water treatment request task information and extracting the task processing volume and process execution pump information based on this information. Acquiring water treatment request task information can be achieved through methods such as manual input, sensor data, or interface calls from other systems. Parsing the water treatment request task information involves parsing it to extract the task processing volume and process execution pump information. For example, the acquired data may need to be cleaned, preprocessed, and analyzed to obtain the specific information required. Extracting the task processing volume involves extracting the task processing volume from the parsed water treatment request task information. This may include parameters such as the amount of wastewater to be treated, the treatment rate, and the treatment efficiency. Extracting the process execution pump information involves extracting the process execution pump information from the parsed water treatment request task information. This may include parameters such as the pump type, quantity, operating status, and location.

[0034] Based on the task processing volume and process execution pump information, the task is decomposed to determine the task characteristic information of each configured control node.

[0035] Specifically, task decomposition based on task throughput and process execution pump information allows for the determination of task characteristic information for each configuration control node. Based on the task throughput and process execution pump information, a corresponding task decomposition strategy is formulated. This includes prioritizing tasks, segmenting them according to resource allocation requirements, or decomposing them according to process steps. The process involves: determining configuration control nodes: based on previously collected equipment basic parameters, setup locations, and connection relationships, the location and function of each configuration control node can be determined. These nodes can be pump start / stop control, flow control, pressure control, etc. Determining task characteristic information: for each configuration control node, based on the task decomposition strategy and its function, corresponding task characteristic information can be determined. This may include parameters such as task type, throughput, processing time, and operating status. Task characteristic information mapping: the task characteristic information of each configuration control node is mapped to corresponding control commands. This includes further processing and analysis of the task characteristic information, such as adjusting the pump operating status based on throughput and performing start / stop control according to time schedules. Task scheduling and allocation: based on the results of the task decomposition strategy and task characteristic information mapping, tasks are scheduled and allocated. This includes sorting, grouping, or packaging tasks, and allocating them based on the capabilities and priorities of the configured control nodes. Through these steps, tasks can be decomposed based on task throughput and process flow pump information, and the task characteristics of each configured control node can be determined. This information can be used to monitor and control the operating status of the water treatment pump set in real time, thereby improving the efficiency and stability of the entire system.

[0036] The task feature information of each configured control node is input into the adaptive control model for optimization to obtain a control strategy, wherein the control strategy includes control parameters of multiple configured control nodes;

[0037] Specifically, by inputting the task characteristic information of each configured control node into the adaptive control model for optimization, a control strategy can be obtained. This control strategy includes control parameters for multiple configured control nodes. Input Task Characteristic Information: The previously determined task characteristic information of each configured control node is input into the adaptive control model. This information serves as input to the model for optimizing the control strategy. Model Optimization: The adaptive control model is used to optimize the input task characteristic information. This includes adjusting model parameters, improving the model architecture, or using other optimization algorithms to find better control strategies. Obtaining Control Strategies: After optimization, the adaptive control model can output one or more control strategies. These strategies, derived from the input task characteristic information, can guide the operation and control of the water treatment pump set. Through these steps, by inputting the task characteristic information of each configured control node into the adaptive control model for optimization, control strategies for multiple configured control nodes can be obtained, and corresponding control parameters can be extracted to guide the real-time operation of the water treatment pump set. These strategies and parameters can be adjusted and optimized according to actual operating conditions to improve the efficiency and stability of the entire water treatment system.

[0038] Automatic pump allocation is performed using the control strategy described above, and the execution parameters of each pump are controlled using the control parameters described above.

[0039] Specifically, by using the obtained control strategy for automatic pump allocation and controlling the execution parameters of each pump with the aforementioned control parameters, automated and optimized control of the water treatment pump set can be achieved. Automatic pump allocation: Based on the control strategy and actual operational needs, suitable pumps are automatically selected for pairing. This includes evaluating the pump type, specifications, and operating status, as well as considering parameters such as system load and throughput to ensure efficient operation of the pump set. Control parameter setting: Based on the extracted control parameters, the execution parameters of each pump are controlled. This includes setting and controlling parameters such as pump start / stop status, flow rate, and pressure to ensure the pump set operates as expected. Real-time monitoring and adjustment: After automatic pump allocation and control parameter setting, the actual operating situation is monitored in real time and adjustments are made as needed. This includes real-time monitoring of pump operating status, handling of abnormal situations, and evaluation and feedback of pump set operating performance. Through these steps, by using the obtained control strategy for automatic pump allocation and controlling the execution parameters of each pump with the aforementioned control parameters, automated and optimized control of the water treatment pump set can be achieved. This helps improve the efficiency and stability of the entire system and reduce operating costs. At the same time, it is necessary to pay attention to the regular maintenance and inspection of the system to ensure its normal operation and reliability.

[0040] Furthermore, the method of this application constructs a pump group topology based on the device basic parameters, setting positions, and connection relationships of the multiple configuration control nodes, including:

[0041] Based on the multiple configuration control nodes, determine the node hierarchy;

[0042] Based on the basic parameters of the equipment, determine the equipment function information and equipment energy consumption information;

[0043] Based on the specified location settings, determine the connection distances between each device;

[0044] Based on the node hierarchy and the connection distance, a pump group hierarchical topology framework is constructed.

[0045] The device function information, device energy consumption information, and connection distance are added to the pump group hierarchical topology framework to construct the pump group topology structure.

[0046] Specifically, based on the structure and operational characteristics of the water treatment system, the hierarchical relationship of multiple configuration control nodes can be determined. For example, based on the pump type and operating characteristics, nodes such as pump start-up / shutdown control, flow control, and pressure control can be divided into different levels. Determine basic equipment parameters: Collect basic parameters such as the type, specifications, and performance of each piece of equipment to further determine its functional and energy consumption information. These basic parameters may include the equipment model, rated power, flow rate, and head, which helps in evaluating the equipment's operating characteristics and energy consumption. Determine equipment functional information: Based on the basic parameters and actual operational needs, the functional information of each piece of equipment can be determined. This includes evaluating the equipment's operating mode, control method, and processing capacity to better understand the equipment's role and function in the water treatment system. Determine equipment energy consumption information: By measuring or calculating the energy consumption data of each piece of equipment, its energy consumption information can be determined. This may include parameters such as power consumption, energy consumption, and efficiency, which helps in assessing the equipment's energy consumption level and energy-saving potential. Determine connection distances: Based on the installation location and connection relationships of each piece of equipment, the connection distances between each piece of equipment can be determined. This helps to better understand the signal transmission and data interaction relationships between devices, as well as the connection methods between devices and control nodes. Based on the structure and operating characteristics of the water treatment system, the hierarchical relationship of multiple configuration control nodes can be determined. For example, based on the pump type and operating characteristics, nodes for pump start-up / shutdown control, flow control, and pressure control can be divided into different levels. This helps to better understand and analyze the operating status and energy consumption of the pump set. Determining connection distances: Based on the installation location and connection relationships of each device, the connection distances between devices can be determined. This helps to better understand the signal transmission and data interaction relationships between devices, as well as the connection methods between devices and control nodes. Building a pump set hierarchical topology framework: Based on the node hierarchical relationship and connection distance, a pump set hierarchical topology framework can be built. This framework can display the hierarchical and connection relationships between each configuration control node and device, helping to better understand the operating characteristics and topology of the pump set. Constructing the pump set topology structure: Adding data such as device function information, device energy consumption information, and connection distances to the pump set hierarchical topology framework constructs a complete pump set topology structure. This structure can contain detailed information about each configuration control node and device, as well as their connection relationships and operating parameters, which helps to better analyze and optimize the pump set's operating status and energy consumption. Through the above steps, the node hierarchy can be determined based on multiple configuration control nodes, the device function information and energy consumption information can be determined based on the device's basic parameters, the connection distances between each device can be determined based on the setting location, and a pump set hierarchical topology framework can be built based on the node hierarchy and connection distances. The device function information, device energy consumption information, and connection distances are then added to the pump set hierarchical topology framework to construct the pump set topology structure.This information can be used to further analyze and optimize the operating status and energy consumption of the water treatment system.

[0047] Furthermore, such as Figure 2 As shown, the method of this application, based on the pump group topology and the multiple sets of energy consumption datasets, performs joint mapping training to obtain an adaptive control model, including:

[0048] Based on the pump set topology, analyze the equipment performance loss and node transmission distance loss to determine the pump set connection energy consumption relationship and the corresponding influence coefficient.

[0049] Based on the multiple sets of energy consumption datasets, determine the adjustable energy consumption parameters for each pump;

[0050] Based on the pump correspondence, the adjustable energy consumption parameters, the pump group connection energy consumption relationship and the corresponding influence coefficients are mapped to construct a training dataset;

[0051] The adaptive control model is obtained by performing adaptive training using the training dataset.

[0052] Specifically, based on the pump set topology and actual operating conditions, the performance losses of each device can be analyzed. This includes: evaluating parameters such as power consumption, energy consumption, and efficiency of the equipment to understand its performance under different operating conditions; analyzing node transmission distance loss: based on the pump set topology and connection distances, the transmission distance loss between each node can be analyzed. This helps to understand the energy consumption and latency during signal transmission and data interaction, providing a reference for optimizing network structure and reducing energy consumption; determining the energy consumption relationship of pump set connections and the corresponding influence coefficients: by analyzing the equipment performance losses and node transmission distance losses, the relationship of pump set connection energy consumption and its corresponding influence coefficients can be determined. This helps to further understand the energy consumption distribution and mutual influence during pump set operation; determining the adjustable energy consumption parameters of each pump: based on actual operating requirements and multiple sets of energy consumption datasets, the adjustable energy consumption parameters of each pump can be determined. These parameters may include pump power settings, flow regulation, pressure adjustment, etc., used to achieve energy-saving control and optimized operation of the pumps. Constructing a training dataset: Based on the pump correspondence, adjustable energy consumption parameters, pump group connection energy consumption relationships, and corresponding influence coefficients are mapped to construct a training dataset. This dataset can contain information such as the operating status, energy consumption parameters, and connection relationships of each pump, used to train the adaptive control model. Adaptive training using the training dataset: Adaptive training can be performed using the constructed training dataset to obtain the adaptive control model. This can be achieved by employing appropriate machine learning algorithms or model training methods, such as neural networks, support vector machines, and decision trees. Through the above steps, an adaptive control model can be obtained based on the pump group topology through analysis and training. This model can predict and control based on actual operating conditions to improve the efficiency and stability of the entire water treatment system. Simultaneously, it is necessary to continuously evaluate and optimize the model to adapt to different operating environments and meet ever-changing needs.

[0053] Furthermore, the method of this application, based on the multiple sets of energy consumption datasets, determines the adjustable energy consumption parameters of each pump, including:

[0054] Based on the multiple sets of energy consumption datasets, extract the first energy consumption dataset of the first node, the second energy consumption dataset of the second node, ... up to the Nth energy consumption dataset of the Nth node, where N is a positive integer;

[0055] Energy consumption decomposition is performed on the first energy consumption dataset, the second energy consumption dataset, and the Nth energy consumption dataset to determine the constrained fixed energy consumption and the controllable dynamic energy consumption.

[0056] Based on the controllable dynamic energy consumption, parameter analysis is performed to determine the adjustable energy consumption parameters of each pump.

[0057] Specifically, based on multiple sets of energy consumption datasets, energy consumption datasets for each node can be extracted separately. These datasets may include data on parameters such as power consumption, energy consumption, and efficiency of the equipment, used for further analysis of the energy consumption of each device. Energy Consumption Decomposition: The energy consumption dataset of each node is decomposed into two parts: constrained fixed energy consumption and controllable dynamic energy consumption. Constrained fixed energy consumption refers to energy consumption that cannot be changed or adjusted during equipment operation, such as energy consumption determined by the pump model and specifications; controllable dynamic energy consumption refers to energy consumption that can be changed through control strategies or parameter adjustments, such as pump flow rate and pressure parameters. Determining Adjustable Energy Consumption Parameters for Each Pump: Based on parameter analysis of controllable dynamic energy consumption, the adjustable energy consumption parameters for each pump can be determined. These parameters may include pump power settings, flow rate regulation, and pressure adjustment, used to achieve energy-saving control and optimized operation of the pumps. Constructing a Training Dataset: Based on the adjustable energy consumption parameters of each node and pump and the corresponding energy consumption dataset, a training dataset can be constructed. This dataset can contain information such as the operating status, energy consumption parameters, and connection relationships of each pump, which is used to train the adaptive control model. Adaptive training is then performed using the constructed training dataset to obtain the adaptive control model. This can be achieved by employing appropriate machine learning algorithms or model training methods, such as neural networks, support vector machines, and decision trees. Through the above steps, energy consumption can be decomposed based on multiple sets of energy consumption datasets, and the adjustable energy consumption parameters of each pump can be analyzed. Then, these parameters are used to construct a training dataset and train the adaptive control model. This model can predict and control based on actual operating conditions to improve the efficiency and stability of the entire water treatment system. Simultaneously, continuous evaluation and optimization of the model are necessary to adapt to different operating environments and meet ever-changing needs.

[0058] Furthermore, the method of this application, which uses the training dataset for adaptive training to obtain the adaptive control model, includes:

[0059] Based on the adjustable energy consumption parameters, the energy consumption relationship of the pump group connection and the corresponding influence coefficients, energy consumption-related variables are extracted.

[0060] Based on the energy consumption-related variables, the energy consumption relationship of each variable is fitted using the training dataset to determine the energy consumption relationship parameters;

[0061] A fitness function is constructed using the energy consumption-related variables and their corresponding energy consumption relationship parameters;

[0062] Based on the fitness function, the energy consumption control strategy is optimized to minimize the target energy consumption, thereby obtaining the adaptive control model.

[0063] Specifically, the process involves: extracting energy-related variables: Based on the adjustable energy consumption parameters, the energy consumption relationship of the pump group connections, and the corresponding influence coefficients, energy-related variables can be extracted. These variables may include parameters such as the power settings, flow regulation, and pressure adjustment of each pump, as well as the connection distance between nodes and equipment performance parameters. Energy consumption relationship fitting: Using a training dataset, the extracted energy-related variables can be fitted with energy consumption relationships. This can be achieved using regression analysis, machine learning, and other methods to determine the energy consumption relationship parameters between the variables. Constructing a fitness function: Based on the energy-related variables and their corresponding energy consumption relationship parameters, a fitness function can be constructed. This function measures the impact of the control strategy on the target energy consumption, providing an optimization direction for minimizing the target energy consumption. Optimizing the energy consumption control strategy: Based on the fitness function, optimization algorithms can be used to optimize the energy consumption control strategy. This can be achieved by solving for the extreme value of the fitness function or finding the optimal solution to obtain the control strategy that minimizes the target energy consumption. Obtaining an adaptive control model: Through the above steps, an adaptive control model can be obtained. This model predicts and controls based on actual operating conditions to achieve the optimization goal of minimizing the target energy consumption. Through the above steps, a training dataset can be constructed based on the adjustable energy consumption parameters, the energy consumption relationship of the pump group connection, and the corresponding influence coefficients. This training dataset is then used to fit the energy consumption relationships of each variable, construct a fitness function, and optimize the energy consumption control strategy, ultimately obtaining an adaptive control model. This model can predict and control based on actual operating conditions to reduce the energy consumption of the entire water treatment system and improve its operating efficiency.

[0064] Furthermore, the method of this application extracts energy-related variables based on the adjustable energy consumption parameters, the energy consumption relationship of the pump group connection, and the corresponding influence coefficients, including:

[0065] Based on the energy consumption relationship of the pump set connection and the corresponding influence coefficient, the energy consumption relationship of the pump set connection that meets the preset threshold is selected.

[0066] Based on the energy consumption relationship of the pump group connection, task processing parameters are extracted to obtain the variables affecting task characteristics;

[0067] Based on the energy consumption relationship of the pump set connection, the energy consumption relationship of the equipment basic parameters is extracted to determine the variables affecting equipment control;

[0068] Based on the task characteristic influencing variables and equipment control influencing variables, the energy consumption related variables are obtained;

[0069] Based on the energy consumption relationship of the pump group connection, the node transmission distance loss relationship is extracted, the distance energy consumption influence coefficient of the process node is determined, and it is determined whether the distance energy consumption influence coefficient reaches the preset threshold. When it is satisfied, the process node distance is added as a relevant variable to the energy consumption related variables.

[0070] Specifically, the process involves: screening pump group connection energy consumption relationships that meet preset thresholds: Based on the pump group connection energy consumption relationships and their corresponding influence coefficients, pump group connection energy consumption relationships with influence coefficients meeting preset thresholds can be screened. Extracting task characteristic influencing variables: Based on the screened pump group connection energy consumption relationships, task processing parameters can be further extracted to obtain task characteristic influencing variables. These variables may include parameters such as the workload, running time, and flow rate of each pump, used to reflect the energy consumption characteristics during task processing. Extracting equipment control influencing variables: Based on the pump group connection energy consumption relationships, the energy consumption relationships of basic equipment parameters can be extracted to determine equipment control influencing variables. These variables may include parameters such as the power consumption, energy consumption, and efficiency of each piece of equipment, used to reflect the energy consumption characteristics during equipment operation. Constructing energy consumption-related variables: Combining the task characteristic influencing variables and equipment control influencing variables yields the energy consumption-related variables. These variables may include parameters such as the pump's workload, running time, and flow rate, as well as parameters such as the equipment's power consumption, energy consumption, and efficiency, used to describe the energy consumption of the entire water treatment system. Extracting Node Transmission Distance Loss Relationships: Based on the pump set topology and connection distances, the node transmission distance loss relationships can be extracted, and the distance energy consumption impact coefficient of the process nodes can be determined. This coefficient reflects the energy consumption during signal transmission and data interaction between nodes. Determining if the Distance Energy Consumption Impact Coefficient Meets a Preset Threshold: The extracted distance energy consumption impact coefficients are judged. When they meet a preset threshold, the process node distance is added as a relevant variable to the energy consumption-related variables. This helps to more comprehensively consider the energy consumption influencing factors in the water treatment system. Through the above steps, relevant energy consumption variables can be screened, extracted, and constructed based on the pump set connection energy consumption relationships and corresponding impact coefficients to obtain a more accurate energy consumption model. This model can be used to predict and control the energy consumption of the water treatment system to achieve optimization goals. Simultaneously, the model can be continuously adjusted and optimized according to actual conditions to meet different needs and improve system operating efficiency.

[0071] Furthermore, such as Figure 3 As shown, the method of this application involves inputting the task characteristic information of each configured control node into the adaptive control model for optimization, including:

[0072] Based on the task feature information of each configured control node, obtain the matching constraint feature information and matching controllable feature information of each node;

[0073] The matching constraint feature information and matching controllable feature information of each node are used to randomly extract the energy consumption control strategy of each node, and the random strategy is evaluated by the fitness function.

[0074] Using the aforementioned adaptive control model, based on stochastic policy evaluation information, each configured control node is adaptively adjusted to obtain the control policy that minimizes the total target energy consumption and output it.

[0075] Specifically, the process involves: acquiring matching constraint and controllable matching feature information for each node: Based on the task feature information of each configured control node, matching constraint and controllable matching feature information can be obtained for each node. This information includes the constraints and adjustable parameters of each node during task processing, which are used for the formulation and optimization of subsequent energy consumption control strategies. Random extraction of energy consumption control strategies: Using the matching constraint and controllable matching feature information of each node, energy consumption control strategies for each node can be randomly extracted. These strategies may include various parameter adjustment schemes, power on / off schemes, etc., used to achieve energy consumption control for each node. Fitness function evaluation: The randomly extracted energy consumption control strategies are evaluated using a fitness function. The fitness function measures the merits of each strategy in minimizing the target energy consumption, providing a basis for subsequent adaptive adjustments. Adaptive adjustment: Using the adaptive control model and based on the random strategy evaluation information, adaptive adjustments can be made to each configured control node. This process can be implemented through iterative calculations, optimization algorithms, etc., to obtain the control strategy that minimizes the total target energy consumption. Control Strategy Output: After adaptive adjustment, the control strategy that minimizes the total target energy consumption can be obtained and output. This strategy can guide energy consumption control operations in actual operation to achieve efficient and energy-saving operation of the entire water treatment system. Through the above steps, energy consumption control strategies can be formulated and optimized based on the task characteristic information, matching constraint characteristic information, and matching controllable characteristic information of each configured control node. By extracting random strategies and evaluating fitness functions, the control strategy that minimizes the target energy consumption can be found. Further adaptive adjustment using the adaptive control model can further improve the operating efficiency and stability of the entire water treatment system.

[0076] Furthermore, the method of this application utilizes the aforementioned adaptive control model to adaptively adjust each configured control node based on stochastic policy evaluation information, including:

[0077] Set an adaptive adjustment step size, which is the magnitude of each optimization adjustment;

[0078] Based on the randomly extracted control strategy and the adaptive adjustment step size, a second control strategy is obtained. The second control strategy is evaluated by the fitness function to obtain the evaluation information of the second strategy. The current optimal strategy is obtained from the evaluation information of the random strategy and the evaluation information of the second strategy. This process is repeated to find the optimal control strategy of a preset number of first nodes.

[0079] Repeat the optimization steps to obtain the preferred control strategy for the second node and the preferred control strategy for the Nth node in sequence;

[0080] Based on the task characteristic information, set the mandatory constraint coefficients for each task, and perform full-cycle adaptive optimization based on the mandatory constraint coefficients, the preferred control strategy of the first node, and the preferred control strategy up to the Nth node to obtain the control strategy of each node with the minimum total energy consumption over the entire cycle.

[0081] Specifically, the process involves several steps: First, setting an adaptive adjustment step size: The adaptive adjustment step size is set according to the actual situation. This step size represents the magnitude of each optimization adjustment. This step size can be adjusted according to actual needs to control the convergence speed and optimization accuracy of the optimization algorithm. Second, obtaining a second control strategy based on a randomly extracted control strategy and the adaptive adjustment step size: A second control strategy can be obtained based on the randomly extracted control strategy and the adaptive adjustment step size. This strategy may be a fine-tuning of the random strategy or a completely new control scheme. Evaluation of the second control strategy: The second control strategy is evaluated using a fitness function. The fitness function can be designed based on minimizing energy consumption or other optimization objectives to measure the quality of the control strategy. Obtaining the current optimal strategy: The current optimal control strategy is selected from the evaluation information of the random strategy and the evaluation information of the second strategy. Repeating the optimization steps: Following the above steps, the optimization search is repeated to obtain a preset number of preferred control strategies for the first node. Then, the preferred control strategies for the second node and the Nth node are obtained sequentially. Setting mandatory constraint coefficients for each task: Mandatory constraint coefficients are set for each task based on the task characteristic information. These coefficients can reflect the task's priority, timing requirements, or other constraints. Full-cycle adaptive optimization: Based on the mandatory constraint coefficients, the optimal control strategy for the first node, and the optimal control strategy up to the Nth node, full-cycle adaptive optimization is performed. This can be achieved through iterative calculations and optimization algorithms to obtain the control strategies for each node that minimize the total energy consumption over the entire cycle. Through these steps, the control strategies for each node can be adaptively optimized throughout the entire cycle, taking into account task characteristics and mandatory constraint coefficients. This helps to obtain a more comprehensive and accurate energy consumption optimization scheme, improving the operating efficiency and stability of the entire water treatment system. Simultaneously, the algorithm parameters can be continuously adjusted and optimized according to actual conditions to meet different needs and improve system performance.

[0082] Furthermore, in the method of this application, the adaptive control model expression is:

[0083] The model converges by minimizing the total energy consumption, where C Q (x) represents the total energy consumption of all configured control nodes, δ represents the forced constraint coefficient of each node, and Q(x) represents the total energy consumption of all configured control nodes. i') represents the preset energy consumption x corresponding to the i-th node. i ',Q(x i Let be the energy consumption corresponding to the i-th node.

[0084] Specifically, the goal is to minimize the total energy consumption to bring the model to convergence: find a control strategy that minimizes the total energy consumption of the entire water treatment system. This total energy consumption is the sum of the energy consumption of all configured control nodes in the system. The total energy consumption of each configured control node is calculated by summing the energy consumption of each node. The mandatory constraint coefficients for each node are set based on the task characteristics of each node, reflecting task priority, timing requirements, or other constraints. These coefficients will be used as constraints during optimization. A preset energy consumption value is set for each node, reflecting its normal operating energy consumption. The actual energy consumption of the i-th node is represented by the value of the control strategy and other factors. The objective is to minimize the total energy consumption of the system while satisfying the mandatory constraint coefficients for each node.

[0085] Example 2

[0086] Based on the same inventive concept as the water treatment automatic pump distribution intelligent control method described in the foregoing embodiments, such as Figure 4 As shown, this application provides an automatic pump distribution intelligent control system for water treatment, the system comprising:

[0087] The configuration control node determination module 10 is used to collect the setting and distribution information of the water treatment pump set and determine multiple configuration control nodes.

[0088] Pump group topology construction module 20, which constructs the pump group topology based on the basic equipment parameters, setting positions and connection relationships of the multiple configuration control nodes;

[0089] Energy consumption dataset acquisition module 30 is used to collect energy consumption data according to the multiple configured control nodes to obtain multiple sets of energy consumption datasets under multiple sample scenarios.

[0090] Adaptive control model acquisition module 40 is used to perform joint mapping training based on the pump group topology and the multiple sets of energy consumption datasets to obtain an adaptive control model.

[0091] The request task information acquisition module 50 is used to acquire water treatment request task information and extract task processing volume and process execution pump information based on the water treatment request task information.

[0092] The task decomposition module 60 decomposes tasks based on the task processing volume and process execution pump information, and determines the task characteristic information of each configuration control node.

[0093] The control strategy acquisition module 70 is used to input the task feature information of each configured control node into the adaptive control model for optimization to obtain a control strategy, wherein the control strategy includes control parameters of multiple configured control nodes.

[0094] The parameter control module 80 is used to automatically allocate pumps according to the control strategy and to control the execution parameters of each pump according to the control parameters.

[0095] Furthermore, the system also includes:

[0096] The topology framework acquisition module determines the node hierarchy based on the multiple configuration control nodes; determines the device function information and device energy consumption information based on the device basic parameters; determines the connection distance of each device based on the set location; builds a pump group hierarchical topology framework based on the node hierarchy and the connection distance; and adds the device function information, device energy consumption information, and connection distance to the pump group hierarchical topology framework to construct the pump group topology structure.

[0097] Furthermore, the system also includes:

[0098] The adaptive control model acquisition module is used to analyze equipment performance loss and node transmission distance loss based on the pump group topology, determine the energy consumption relationship of pump group connection and the corresponding influence coefficient; determine the adjustable energy consumption parameters of each pump based on the multiple sets of energy consumption datasets; map the adjustable energy consumption parameters, pump group connection energy consumption relationship and corresponding influence coefficient based on the pump correspondence to construct a training dataset; and use the training dataset for adaptive training to obtain the adaptive control model.

[0099] Furthermore, the system also includes:

[0100] The controllable energy consumption parameter determination module is used to extract the first energy consumption dataset of the first node, the second energy consumption dataset of the second node, ... up to the Nth energy consumption dataset of the Nth node, where N is a positive integer, based on the multiple sets of energy consumption datasets; perform energy consumption decomposition on the first energy consumption dataset, the second energy consumption dataset, and the Nth energy consumption dataset respectively to determine the constrained fixed energy consumption and the controllable dynamic energy consumption; and perform parameter analysis based on the controllable dynamic energy consumption to determine the adjustable energy consumption parameters of each pump.

[0101] Furthermore, the system also includes:

[0102] The control strategy optimization module extracts energy-related variables based on the adjustable energy consumption parameters, pump group connection energy consumption relationships, and corresponding influence coefficients; it then uses the training dataset to fit the energy consumption relationships of each variable to determine energy consumption relationship parameters; it constructs a fitness function using the energy-related variables and corresponding energy consumption relationship parameters; and it optimizes the energy consumption control strategy based on the fitness function with the goal of minimizing target energy consumption, thereby obtaining the adaptive control model.

[0103] Furthermore, the system also includes:

[0104] The influence coefficient determination module is used to: filter pump group connection energy consumption relationships whose influence coefficients meet a preset threshold based on the pump group connection energy consumption relationship and the corresponding influence coefficient; extract task processing parameters based on the pump group connection energy consumption relationship to obtain task feature influence variables; extract equipment basic parameter energy consumption relationships based on the pump group connection energy consumption relationship to determine equipment control influence variables; obtain the energy consumption related variables based on the task feature influence variables and equipment control influence variables; extract node transmission distance loss relationships based on the pump group connection energy consumption relationship to determine the distance energy consumption influence coefficient of the process node; determine whether the distance energy consumption influence coefficient reaches the preset threshold; and if it does, add the process node distance as a related variable to the energy consumption related variables.

[0105] Furthermore, the system also includes:

[0106] The adaptive adjustment module is used to obtain the matching constraint feature information and matching controllable feature information of each node based on the task feature information of each configured control node; to randomly extract the energy consumption control strategy of each node using the matching constraint feature information and matching controllable feature information of each node, and to evaluate the random strategy through a fitness function; and to adaptively adjust each configured control node based on the random strategy evaluation information using the adaptive control model, and to output the control strategy that minimizes the total target energy consumption.

[0107] Furthermore, the system also includes:

[0108] The energy-minimum control strategy acquisition module is used to set an adaptive adjustment step size, which is the magnitude of each optimization adjustment; based on the randomly extracted control strategy and the adaptive adjustment step size, a second control strategy is acquired; the second control strategy is evaluated through a fitness function to obtain second strategy evaluation information; the current optimal strategy is obtained from the random strategy evaluation information and the second strategy evaluation information, and so on, to iteratively optimize and select a preset number of preferred control strategies for the first node; the optimization steps are repeated to sequentially acquire the preferred control strategies for the second node and the Nth node; the mandatory constraint coefficients for each task are set according to the task characteristic information; and full-cycle adaptive optimization is performed based on the mandatory constraint coefficients, the preferred control strategies for the first node, and so on up to the preferred control strategies for the Nth node to obtain the control strategies for each node with the minimum total energy consumption over the entire cycle.

[0109] Furthermore, the system also includes:

[0110] The corresponding energy consumption acquisition module includes The model converges by minimizing the total energy consumption, where C Q (x) represents the total energy consumption of all configured control nodes, δ represents the forced constraint coefficient of each node, and Q(x) represents the total energy consumption of all configured control nodes. i ') represents the preset energy consumption x corresponding to the i-th node. i ',Q(x i Let be the energy consumption corresponding to the i-th node.

[0111] Through the detailed description of the aforementioned water treatment automatic pump allocation intelligent control method, those skilled in the art can clearly understand the water treatment automatic pump allocation intelligent control protection system in this embodiment. As the system disclosed in the embodiment corresponds to the device disclosed in the embodiment, the description is relatively simple, and relevant parts can be referred to the method section.

[0112] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An automatic pump distribution intelligent control method for water treatment, characterized in that, include: Collect information on the location and distribution of water treatment pump sets to determine multiple configuration control nodes; Based on the device basic parameters, settings, and connection relationships of the multiple configuration control nodes, a pump group topology is constructed. Energy consumption data is collected from the multiple configured control nodes to obtain multiple sets of energy consumption datasets under multiple sample scenarios. An adaptive control model is obtained by jointly mapping and training the pump group topology and the multiple energy consumption datasets. Obtain water treatment request task information, and extract task processing volume and process execution pump information based on the water treatment request task information; Based on the task processing volume and process execution pump information, the task is decomposed to determine the task characteristic information of each configured control node. The task feature information of each configured control node is input into the adaptive control model for optimization to obtain a control strategy, wherein the control strategy includes control parameters of multiple configured control nodes; Automatic pump allocation is performed using the aforementioned control strategy, and the execution parameters of each pump are controlled using the aforementioned control parameters. An adaptive control model is obtained by jointly mapping and training the pump group topology and the multiple energy consumption datasets, including: Based on the pump set topology, analyze the equipment performance loss and node transmission distance loss to determine the pump set connection energy consumption relationship and the corresponding influence coefficient. Based on the multiple sets of energy consumption datasets, determine the adjustable energy consumption parameters for each pump; Based on the pump correspondence, the adjustable energy consumption parameters, the pump group connection energy consumption relationship and the corresponding influence coefficients are mapped to construct a training dataset; The adaptive control model is obtained by performing adaptive training using the training dataset. The adaptive control model is obtained by adaptively training using the training dataset, including: Based on the adjustable energy consumption parameters, the energy consumption relationship of the pump group connection and the corresponding influence coefficients, energy consumption-related variables are extracted. Based on the energy consumption-related variables, the energy consumption relationship of each variable is fitted using the training dataset to determine the energy consumption relationship parameters; A fitness function is constructed using the energy consumption-related variables and their corresponding energy consumption relationship parameters; Based on the fitness function, the energy consumption control strategy is optimized to minimize the target energy consumption, thereby obtaining the adaptive control model.

2. The method as described in claim 1, characterized in that, Based on the basic device parameters, settings, and connection relationships of the multiple configuration control nodes, a pump group topology is constructed, including: Based on the multiple configuration control nodes, determine the node hierarchy; Based on the basic parameters of the equipment, determine the equipment function information and equipment energy consumption information; Based on the specified location settings, determine the connection distances between each device; Based on the node hierarchy and the connection distance, a pump group hierarchical topology framework is constructed. The device function information, device energy consumption information, and connection distance are added to the pump group hierarchical topology framework to construct the pump group topology structure.

3. The method as described in claim 1, characterized in that, Based on the aforementioned multiple sets of energy consumption datasets, the adjustable energy consumption parameters for each pump are determined, including: Based on the multiple sets of energy consumption datasets, extract the first energy consumption dataset of the first node, the second energy consumption dataset of the second node, ... up to the Nth energy consumption dataset of the Nth node, where N is a positive integer; Energy consumption decomposition is performed on the first energy consumption dataset, the second energy consumption dataset, and the Nth energy consumption dataset to determine the constrained fixed energy consumption and the controllable dynamic energy consumption. Based on the controllable dynamic energy consumption, parameter analysis is performed to determine the adjustable energy consumption parameters of each pump.

4. The method as described in claim 1, characterized in that, Based on the adjustable energy consumption parameters, the energy consumption relationship of the pump set connection, and the corresponding influence coefficients, energy consumption-related variables are extracted, including: Based on the energy consumption relationship of the pump set connection and the corresponding influence coefficient, the energy consumption relationship of the pump set connection that meets the preset threshold is selected. Based on the energy consumption relationship of the pump group connection, task processing parameters are extracted to obtain the variables affecting task characteristics; Based on the energy consumption relationship of the pump set connection, the energy consumption relationship of the equipment basic parameters is extracted to determine the variables affecting equipment control; Based on the task characteristic influencing variables and equipment control influencing variables, the energy consumption related variables are obtained; Based on the energy consumption relationship of the pump group connection, the node transmission distance loss relationship is extracted, the distance energy consumption influence coefficient of the process node is determined, and it is determined whether the distance energy consumption influence coefficient reaches the preset threshold. When it is satisfied, the process node distance is added as a relevant variable to the energy consumption related variables.

5. The method as described in claim 4, characterized in that, The task characteristic information of each configured control node is input into the adaptive control model for optimization, including: Based on the task feature information of each configured control node, obtain the matching constraint feature information and matching controllable feature information of each node; The matching constraint feature information and matching controllable feature information of each node are used to randomly extract the energy consumption control strategy of each node, and the random strategy is evaluated by the fitness function. Using the aforementioned adaptive control model, based on stochastic policy evaluation information, each configured control node is adaptively adjusted to obtain the control policy that minimizes the total target energy consumption and output it.

6. The method as described in claim 5, characterized in that, Using the aforementioned adaptive control model, and based on stochastic policy evaluation information, adaptive adjustments are made to each configured control node, including: Set an adaptive adjustment step size, which is the magnitude of each optimization adjustment; Based on the randomly extracted control strategy and the adaptive adjustment step size, a second control strategy is obtained. The second control strategy is evaluated by the fitness function to obtain the evaluation information of the second strategy. The current optimal strategy is obtained from the evaluation information of the random strategy and the evaluation information of the second strategy. This process is repeated to find the optimal control strategy of a preset number of first nodes. Repeat the optimization steps to obtain the preferred control strategy for the second node and the preferred control strategy for the Nth node in sequence; Based on the task characteristic information, set the mandatory constraint coefficients for each task, and perform full-cycle adaptive optimization based on the mandatory constraint coefficients, the preferred control strategy of the first node, and the preferred control strategy up to the Nth node to obtain the control strategy of each node with the minimum total energy consumption over the entire cycle.

7. The method as described in claim 6, characterized in that, The adaptive control model expression is: The goal is to minimize the total energy consumption to bring the model to a convergent state, where... The total energy consumption of each configured control node. These are the mandatory constraint coefficients for each node. The preset energy consumption corresponding to the i-th node , Let be the energy consumption corresponding to the i-th node.

8. A water treatment automatic pump distribution intelligent control system, characterized in that, The steps for implementing the water treatment automatic pump distribution intelligent control method according to any one of claims 1 to 7 include: A configuration control node determination module is used to collect the setting and distribution information of water treatment pump sets and determine multiple configuration control nodes. A pump group topology construction module, which constructs the pump group topology based on the basic equipment parameters, settings, and connection relationships of the multiple configuration control nodes; An energy consumption dataset acquisition module is used to collect energy consumption data according to the multiple configured control nodes to obtain multiple sets of energy consumption datasets under multiple sample scenarios. An adaptive control model acquisition module is used to perform joint mapping training based on the pump group topology and the multiple sets of energy consumption datasets to obtain an adaptive control model. The request task information acquisition module is used to acquire water treatment request task information and extract task processing volume and process execution pump information based on the water treatment request task information. The task decomposition module decomposes tasks based on the task processing volume and process execution pump information, and determines the task characteristic information of each configuration control node. A control strategy acquisition module is used to input the task feature information of each configured control node into the adaptive control model for optimization to obtain a control strategy, wherein the control strategy includes control parameters of multiple configured control nodes. A parameter control module is used to automatically allocate pumps according to the control strategy and to control the execution parameters of each pump according to the control parameters.

Images