Flow adaptive regulation method and system based on solenoid valve

Abstract

The present invention discloses a flow adaptive adjustment method and system based on a solenoid valve, which belongs to the field of fluid control, wherein the method includes: determining a target solenoid valve, deploying a sensor group based on the target solenoid valve, and processing data based on flow information; establishing an initial intelligent control strategy model; supervising and training the initial intelligent control strategy model based on historical data to obtain an intelligent control strategy model; constructing an adaptive optimization space; performing real-time flow monitoring of the target solenoid valve based on the sensor group, and adjusting the target solenoid valve based on the adjustment strategy; building a feedback management and maintenance center, performing real-time monitoring of the target solenoid valve, and providing feedback on the monitoring results. The method solves the technical problems that the existing solenoid valve cannot achieve accurate control of the flow through real-time monitoring and automatic adjustment, and the stability and reliability of the system are low.

Description

Technical Field

[0001] The present invention relates to the field of fluid control, and in particular to a flow adaptive regulation method and system based on a solenoid valve. Background Art

[0002] In many industrial processes, accurate control of flow is crucial to product quality, production efficiency and system safety. For example, in chemical production, the flow of raw materials at different reaction stages needs to be accurately controlled to ensure the smooth progress of the reaction and the stability of product quality. A solenoid valve is a device that uses electromagnetic force to control the on and off of fluids (such as liquids, gases, etc.). It usually consists of an electromagnet and a valve body. The electromagnet generates electromagnetic force to control the opening and closing of the valve core, thereby controlling the flow of the fluid.

[0003] In traditional flow control methods, manual adjustment valves or fixed-opening solenoid valves are usually used to control flow. This method has limitations such as slow response speed, low control accuracy, and inflexible adjustment, which makes it difficult to meet the high requirements of modern industry for flow control. The present application overcomes these limitations, achieves precise control of flow through real-time monitoring and automatic adjustment, and improves the stability and reliability of the system. Summary of the invention

[0004] The present application provides a solenoid valve-based flow adaptive regulation method and system, aiming to solve the technical problems that the existing solenoid valves cannot achieve precise control of the flow through real-time monitoring and automatic regulation, and the system has low stability and reliability.

[0005] In view of the above problems, the present application provides a flow adaptive regulation method and system based on a solenoid valve.

[0006] The first aspect disclosed in the present application provides a flow adaptive regulation method based on a solenoid valve, the method comprising determining a target solenoid valve, arranging a sensor group based on the target solenoid valve, the sensor group comprising a temperature sensor, a pressure sensor, a flow sensor and a position sensor; performing data processing based on flow information, and converting the flow information into an electrical signal; establishing an initial intelligent control strategy model, the input data of the initial intelligent control strategy model being the electrical signal, and the output data being the adjustment strategy of the target solenoid valve; collecting historical data, and performing supervised training on the initial intelligent control strategy model based on the historical data to obtain an intelligent control strategy model; Construct an adaptive optimization space, wherein the adaptive optimization space includes a plurality of optimization control strategy particles, wherein the plurality of optimization control strategy particles are jointly determined by temperature information, pressure information, and position information, and the adaptive optimization space is embedded in an intelligent control strategy model; perform real-time flow monitoring of the target solenoid valve based on the sensor group, input the real-time flow into the intelligent control strategy model to obtain the adjustment strategy, and the target solenoid valve is adjusted based on the adjustment strategy; build a feedback management and maintenance center, wherein the feedback management and maintenance center is embedded in the control center, performs real-time monitoring of the target solenoid valve, obtains monitoring results, and provides feedback on the monitoring results.

[0007] Another aspect disclosed in the present application provides a flow adaptive regulation system based on a solenoid valve, the system including a sensor group layout module: used to determine a target solenoid valve, and to layout a sensor group based on the target solenoid valve, wherein the sensor group includes a temperature sensor, a pressure sensor, a flow sensor, and a position sensor; a flow signal conversion module: used to perform data processing based on flow information, and to convert the flow information into an electrical signal; an initial model construction module: used to establish an initial intelligent control strategy model, wherein the input data of the initial intelligent control strategy model is the electrical signal, and the output data is the adjustment strategy of the target solenoid valve; a control strategy model acquisition module: used to collect historical data, and to perform supervised training on the initial intelligent control strategy model based on the historical data, and to acquire intelligent Control strategy model; Optimization space construction module: used to construct an adaptive optimization space, the adaptive optimization space includes multiple optimization control strategy particles, the multiple optimization control strategy particles are jointly determined by temperature information, pressure information and position information, and the adaptive optimization space is embedded in the intelligent control strategy model; Acquisition adjustment strategy module: used to perform real-time flow monitoring of the target solenoid valve based on the sensor group, input the real-time flow into the intelligent control strategy model to obtain the adjustment strategy, and the target solenoid valve is adjusted based on the adjustment strategy; Monitoring result feedback module: used to build a feedback management and maintenance center, the feedback management and maintenance center is embedded in the control center, real-time monitoring of the target solenoid valve, obtain monitoring results, and feedback the monitoring results.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] By deploying a sensor group including temperature, pressure, flow and position, the working data of the solenoid valve is collected and processed in real time. Using these data, an intelligent control strategy model is established, and supervised training is performed through historical data to optimize the control strategy. At the same time, an adaptive optimization space is constructed, which can dynamically adjust the control strategy to adapt to environmental changes. The feedback management and maintenance center is embedded in the control center, which monitors the status of the solenoid valve in real time and provides feedback to ensure stable operation of the system. It solves the technical problems that the existing solenoid valve cannot achieve accurate control of the flow through real-time monitoring and automatic adjustment, and the stability and reliability of the system are low. It not only improves the working efficiency and safety of the solenoid valve, but also reduces the maintenance cost through intelligent and automated means.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A flow chart of a flow adaptive regulation method based on a solenoid valve is provided for an embodiment of the present application;

[0012] Figure 2 A structural schematic diagram of a flow adaptive regulation system based on a solenoid valve is provided for an embodiment of the present application.

[0013] Explanation of the accompanying drawings: 11 is a sensor group layout module, 12 is a flow signal conversion module, 13 is an initial model construction module, 14 is a control strategy model acquisition module, 15 is an optimization space construction module, 16 is an adjustment strategy acquisition module, and 17 is a monitoring result feedback module. DETAILED DESCRIPTION

[0014] The overall idea of ​​the technical solution provided by this application is as follows:

[0015] The embodiment of the present application provides a flow adaptive regulation method and system based on a solenoid valve. It aims to realize intelligent control and maintenance of the target solenoid valve. First, by deploying a sensor group including temperature, pressure, flow and position sensors, the state of the solenoid valve is monitored in real time. Then, the flow information is converted into an electrical signal and input into the initial intelligent control strategy model to obtain an adjustment strategy. The model is supervised and trained using historical data to obtain a more accurate intelligent control strategy model. At the same time, an adaptive optimization space is constructed and embedded in the model to cope with environmental changes. Finally, the state of the solenoid valve is monitored in real time through the feedback management and maintenance center, and the monitoring results are fed back to ensure stable operation of the system.

[0016] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the embodiment of the present application provides a flow adaptive regulation method based on a solenoid valve, the method comprising:

[0019] Step S100: determining a target solenoid valve, and deploying a sensor group based on the target solenoid valve, wherein the sensor group includes a temperature sensor, a pressure sensor, a flow sensor, and a position sensor.

[0020] Specifically: First, it is necessary to determine the target solenoid valve for adaptive flow regulation. The solenoid valve can be used in various fluid control systems, such as water treatment systems, chemical pipeline systems, etc. Then, the sensor group is arranged based on the target solenoid valve. The sensor group includes a temperature sensor, a pressure sensor, a flow sensor and a position sensor, wherein the temperature sensor is arranged at a representative position near the solenoid valve to accurately reflect the temperature of the solenoid valve and its surrounding environment. The pressure sensor is arranged at the inlet and outlet of the solenoid valve to measure the pressure difference when the fluid passes through the solenoid valve. The flow sensor is arranged at the inlet and outlet of the solenoid valve to directly measure the flow of the fluid through the solenoid valve. The position sensor is arranged on the valve stem or valve core of the solenoid valve to monitor the position change of the valve core. It is used to monitor key parameters such as temperature, pressure, flow and valve core position around the target solenoid valve in real time.

[0021] Among them, the temperature sensor is used to monitor the temperature change of the solenoid valve in real time. When the temperature exceeds the safe range, an alarm can be issued and the machine can be automatically shut down to protect the solenoid valve and peripheral equipment. The pressure sensor is used to monitor the pressure of the gas and liquid circuits controlled by the solenoid valve. If the pressure is abnormal, an alarm will be issued and the machine will be shut down to avoid equipment damage or production accidents caused by excessive or insufficient pressure. The flow sensor is used to monitor the flow of liquid or gas around the solenoid valve. When the flow is too large or too small, an alarm and shutdown will be triggered to avoid production failures and equipment damage caused by abnormal flow. The position sensor is used to monitor the opening and closing status of the solenoid valve. When an abnormality occurs, it will be judged and fed back to the control system in a timely manner to avoid equipment failures and production accidents caused by the solenoid valve being stuck or damaged.

[0022] After the sensor group is installed, the integration and calibration of the sensors is completed. This includes connecting the output signals of each sensor to the data acquisition system and calibrating the sensors to ensure the accuracy of the measurement results. In addition, it is necessary to ensure that the connection between the sensor group and the solenoid valve is firm and reliable to avoid measurement errors or failures caused by connection problems. Based on this step, a complete sensor group can be installed for the target solenoid valve, providing accurate and reliable data support for subsequent flow adaptive regulation.

[0023] Step S200: Perform data processing based on the flow information and convert the flow information into an electrical signal.

[0024] Specifically: The flow sensor collects the flow information through the target solenoid valve in real time. The collected flow information is processed, including amplification, filtering, digitization and other steps to improve the accuracy and reliability of the data. Amplification refers to amplifying the weak signal output by the sensor for subsequent processing; filtering is to use a low-pass filter to remove high-frequency noise and retain the effective flow signal; denoising is to reduce the random noise in the signal through average filtering or other denoising algorithms. The processed flow information is converted into an electrical signal through an analog-to-digital converter (ADC) for subsequent data processing and intelligent control. The digital signal is standardized to unify the dimension and range of the signal to adapt it to the input requirements of the intelligent control strategy model.

[0025] This step improves the accuracy and real-time performance of flow information through data processing and conversion, providing a reliable data foundation for intelligent control strategies.

[0026] Step S300: establishing an initial intelligent control strategy model, wherein the input data of the initial intelligent control strategy model is the electrical signal, and the output data is the adjustment strategy of the target solenoid valve.

[0027] Specifically: First, determine the model input and output. Input: electrical signals, which represent the data collected by sensors such as flow, temperature, and pressure, and are converted into numerical forms that the model can understand after preprocessing. Output the adjustment strategy of the target solenoid valve, which usually includes the switch state, opening size, etc. According to the complexity of the problem and the characteristics of the data, select a suitable model architecture, such as neural network (such as multi-layer perceptron, convolutional neural network, recurrent neural network, etc.), decision tree, random forest, support vector machine, etc. Set the model's hyperparameters, such as learning rate, number of iterations, batch size, number of hidden layers, and number of neurons.

[0028] This step improves the accuracy and response speed of solenoid valve flow regulation by establishing and optimizing the intelligent control strategy model, providing technical support for achieving efficient and stable fluid control.

[0029] Step S400: Collect historical data, and perform supervised training on the initial intelligent control strategy model based on the historical data to obtain an intelligent control strategy model.

[0030] Specifically: Collect data related to the target solenoid valve adjustment strategy from sources such as sensor history, experimental data, and system logs.

[0031] Then, the historical data is preprocessed. The preprocessed historical data is divided into a training set and a validation set, and the initial intelligent control strategy model is trained using the training set data. The performance of the model is evaluated on the validation set. After training and validation, the final intelligent control strategy model can accurately output the adjustment strategy of the target solenoid valve according to the input electrical signal (i.e., flow information).

[0032] Step S500: construct an adaptive optimization space, wherein the adaptive optimization space includes a plurality of optimization control strategy particles, wherein the plurality of optimization control strategy particles are jointly determined by temperature information, pressure information and position information, and the adaptive optimization space is embedded in an intelligent control strategy model.

[0033] Specifically, the adaptive optimization space can receive real-time information from sensors and other data sources, such as temperature, pressure, flow, etc., which directly reflects the real-time status of the system. Based on these real-time data, the adaptive optimization space can dynamically evaluate the effectiveness of the current control strategy and optimize and adjust the control strategy through internal algorithms and logic. This real-time optimization can ensure that the control system always runs in the optimal state and improve the performance and stability of the system.

[0034] The adaptive optimization space includes multiple optimization control strategy particles, which are jointly determined by temperature information, pressure information and position information, which can directly or indirectly reflect the state and performance of the solenoid valve or other control elements. The adaptive optimization space is embedded in the intelligent control strategy model.

[0035] Based on this, an adaptive optimization space containing multiple optimization control strategy particles can be constructed and embedded in the intelligent control strategy model. It can receive data from sensors in real time and dynamically adjust and optimize the control strategy based on these data to achieve higher system performance and better adaptability.

[0036] Step S600: performing real-time flow monitoring of the target solenoid valve based on the sensor group, inputting the real-time flow into the intelligent control strategy model to obtain the adjustment strategy, and adjusting the target solenoid valve based on the adjustment strategy.

[0037] Specifically: Based on the sensor group, the real-time flow rate of the target solenoid valve is monitored to obtain real-time flow rate, temperature, pressure and position information. The real-time flow rate is input into the intelligent control strategy model, and the model outputs the corresponding adjustment strategy according to the optimized control strategy particles in the adaptive optimization space. The target solenoid valve is adjusted in real time according to the output adjustment strategy, including the opening adjustment of the solenoid valve, the switch state switching, etc. The adjustment strategy is converted into an executable control signal and sent to the target solenoid valve through the control system. After receiving the control signal, the target solenoid valve makes corresponding adjustments according to the adjustment strategy to achieve real-time flow control.

[0038] Based on this step, the real-time flow monitoring of the target solenoid valve can be realized based on the sensor group, and the adjustment strategy can be obtained through the intelligent control strategy model, so as to realize the real-time flow control of the target solenoid valve. It can not only improve the performance and stability of the system, but also reduce energy consumption and maintenance costs, and improve the intelligence level of the entire system.

[0039] Step S700: Building a feedback management and maintenance center, which is embedded in the control center, monitors the target solenoid valve in real time, obtains monitoring results, and provides feedback on the monitoring results.

[0040] Specifically: Build a feedback management and maintenance center, which is embedded in the control center and is used to monitor and manage the target solenoid valve in real time. The feedback management and maintenance center receives real-time data from the sensor group, processes and analyzes the data, and generates monitoring results. Based on the monitoring results, the center can remotely control and adjust the target solenoid valve, or issue alarms and notifications to promptly discover and solve problems. In addition, the feedback management and maintenance center can also continuously optimize and maintain the intelligent control strategy model to adapt to the ever-changing working environment and needs.

[0041] Furthermore, in step S200 of the present application, data processing is performed based on the flow information, and the flow information is converted into an electrical signal, including: monitoring the flow of the target solenoid valve based on the flow sensor to obtain flow information; performing data preprocessing on the flow information to obtain flow processing information; and converting the flow processing information through D / A conversion to obtain an electrical signal.

[0042] Specifically: install a flow sensor at the target solenoid valve to ensure that flow data can be collected in real time when the fluid passes through. The flow sensor monitors the flow information of the fluid flowing through the solenoid valve in real time, and the flow information includes but is not limited to parameters such as flow size, flow velocity, change rate, and flow distribution.

[0043] Perform data preprocessing on the acquired flow information, including: data cleaning, removing outliers, noise or invalid data, ensuring data accuracy and reliability. Check data integrity to ensure no data is lost or omitted. Calibrate flow data to eliminate the impact of sensor errors or environmental factors on measurement results. Convert flow data to a unified unit of measurement or range for subsequent data analysis and processing.

[0044] Finally, the standardized flow processing information is converted into an analog electrical signal through a digital / analog (D / A) converter. The output voltage or current of the D / A converter is proportional to the flow processing information. The converted analog electrical signal is amplified for subsequent processing and transmission.

[0045] This step obtains high-quality flow processing information through real-time monitoring and data preprocessing of the flow sensor, and converts it into electrical signals through D / A conversion, providing accurate data input for the intelligent control strategy model, thereby optimizing the control strategy of the solenoid valve and improving the stability and operating efficiency of the fluid control system.

[0046] Furthermore, in step S300 of the present application, an initial intelligent control strategy model is established, including: clarifying the function and control objectives of the target solenoid valve; selecting a BP neural network for model structure design, determining input data and output data; initializing model parameters, and obtaining an initial intelligent control strategy model.

[0047] Specifically: Analyze the specific functions of the target solenoid valve in the fluid control system, such as regulating flow, controlling pressure, etc. Clarify the control objectives of the solenoid valve, such as keeping the flow stable at the set value, and adaptively adjusting according to temperature and pressure changes.

[0048] Select the input data required for solenoid valve control, including electrical signals such as flow, temperature, and pressure.

[0049] Determine the output data of the model, that is, the adjustment strategy of the solenoid valve, such as the opening degree and switch state of the solenoid valve. Select the BP neural network as the initial intelligent control strategy model and design its structure, including the number of nodes in the input layer, hidden layer and output layer. Generally speaking, the number of nodes in the hidden layer can be determined through experiments and experience to balance the complexity and generalization ability of the model. The BP (Back Propagation) neural network is a multi-layer feedforward neural network that trains the network through the back propagation algorithm so that the output value of the network gradually approaches the expected value. It can handle complex nonlinear relationships and is suitable for control strategy modeling.

[0050] Initialize the model parameters, including weight initialization: Weights are key parameters in neural networks and affect the output of the network. During initialization, you can use random values, small values, or specific initialization methods (such as He initialization, Xavier initialization, etc.) to set the weights. Bias initialization: Bias is another important parameter of neurons, which is used to adjust the output of neurons. During initialization, the bias can be set to 0 or a small value close to 0. Activation function selection: Select a suitable activation function, such as ReLU, Sigmoid, or Tanh. The activation function determines the output range and nonlinear characteristics of the neuron.

[0051] This step ensures that the design of the intelligent control strategy model meets actual needs and can effectively solve practical problems by clarifying the function and control objectives of the target solenoid valve. By selecting the BP neural network and performing a reasonable model structure design, the initial intelligent control strategy model established has strong nonlinear mapping and self-learning capabilities. Through appropriate parameter initialization methods, the initial performance of the model is improved, the effect and convergence speed of subsequent training are ensured, and a good foundation is laid for the efficient control of the solenoid valve.

[0052] Furthermore, step S400 of the present application includes: collecting historical data, extracting samples from the historical data, and obtaining a sample data set; obtaining a preset data division ratio, and dividing the sample data set into a training data set and a verification data set according to the preset data division ratio; performing supervised training on the initial intelligent control strategy model through the training data set, and when the model output result tends to converge, verifying the output result of the initial intelligent control strategy model through the verification data set; obtaining a preset model verification accuracy index, and when the output result accuracy of the initial intelligent control strategy model meets the preset model verification accuracy index, the intelligent control strategy model is obtained.

[0053] Specifically: First, collect historical data from the control system of the target solenoid valve. These data should include electrical signals (i.e. analog signals of flow information) and corresponding solenoid valve adjustment strategies (such as opening, switch status, etc.).

[0054] Perform necessary preprocessing on historical data, including cleaning, sorting, format conversion, etc., to ensure data accuracy and consistency. Extract representative samples from the preprocessed historical data to form a sample data set. The selection of samples should cover different flow conditions, solenoid valve adjustment strategies, and existing noise and abnormal conditions.

[0055] According to the preset data division ratio (such as 70% for training and 30% for verification), the sample data set is divided into a training data set and a verification data set. Ensure that the two data sets are as consistent as possible in data distribution. Use the training data set to supervise the initial intelligent control strategy model. Calculate the output of the model through forward propagation, and then use the back propagation algorithm to adjust the parameters (weights and biases) of the model so that the output of the model gradually approaches the desired adjustment strategy. During the training process, monitor the model's loss function value (such as mean square error, cross entropy, etc.) and indicators such as the accuracy of the model on the training data set to evaluate the training effect of the model.

[0056] When the loss function value of the model on the training data set gradually decreases and tends to be stable, and indicators such as accuracy no longer increase significantly, the model can be considered to have converged. Use the validation data set to verify the output results of the model and evaluate the generalization ability of the model on unseen data.

[0057] A model verification accuracy index is preset, which should be set according to the actual application requirements and data characteristics. If the accuracy of the model on the verification data set meets the preset index, then the model can be considered to have been trained successfully and can be used as an intelligent control strategy model.

[0058] Deploy the trained intelligent control strategy model to the actual control system to achieve real-time flow monitoring and intelligent control. After the model is deployed, it is continuously optimized and adjusted according to the actual operation situation to adapt to environmental changes and improve the accuracy of control.

[0059] Furthermore, in step S500 of the present application, constructing an adaptive optimization space includes: building an adaptive optimization space and determining three dimensions of the adaptive optimization space, wherein each of the three dimensions corresponds to an attribute; presetting standard thresholds for the three dimensions, and using the standard thresholds as boundary conditions for the three dimensions; designing a dynamic adjustment mechanism to adjust the boundaries of the adaptive optimization space when the specifications of the target solenoid valve change; integrating the adaptive optimization space as a component of the intelligent control strategy model, and when the model is running, calling the adaptive optimization space to generate an adjustment strategy.

[0060] Specifically: construct an adaptive optimization space and determine its three dimensions, select three key dimensions, corresponding to temperature information, pressure information and position information respectively. Each dimension is quantified through real-time data collected by sensors to construct a three-dimensional adaptive optimization space.

[0061] Dimension 1: Temperature. This dimension represents the temperature information in the working environment of the solenoid valve. Temperature changes affect the performance, sealing and response time of the solenoid valve. By optimizing the temperature dimension, it can ensure that the solenoid valve works within the optimal temperature range, thereby improving its working efficiency and reliability.

[0062] The second dimension is pressure, which reflects the pressure information that the solenoid valve is subjected to. Changes in pressure affect the flow, sealing and service life of the solenoid valve. By optimizing the pressure dimension, it can be ensured that the solenoid valve works at the appropriate pressure, thereby avoiding performance degradation or damage caused by overpressure or underpressure.

[0063] Dimension three, position, represents the flow or opening position information of the solenoid valve. Changes in flow directly affect the performance and response speed of the system. By optimizing the flow / position dimension, it is possible to ensure that the solenoid valve accurately adjusts the flow according to system requirements, thereby optimizing the overall performance of the system.

[0064] According to the system design requirements and historical data analysis, preset standard thresholds for each dimension. For the temperature dimension, set the minimum and maximum temperature thresholds to ensure that the solenoid valve works within the appropriate temperature range. For the pressure dimension, set the minimum and maximum pressure thresholds to prevent the solenoid valve from being subjected to excessive or insufficient pressure. For the position dimension, set the minimum and maximum flow / opening position thresholds to ensure that the solenoid valve can accurately adjust the flow according to system requirements. According to the preset standard thresholds, set reasonable boundary conditions for each dimension to ensure that the strategies in the optimization space are safe and effective in actual applications.

[0065] Design a dynamic adjustment mechanism for the adaptive optimization space so that it can be adjusted according to the specification changes of the target solenoid valve. The specific method includes: using sensors or other monitoring means to detect in real time whether the specifications of the target solenoid valve have changed, such as replacing a different type of solenoid valve. When the solenoid valve specification changes are detected, the boundary conditions of the adaptive optimization space are dynamically adjusted according to the new specifications and system requirements. This can be achieved by updating the preset threshold.

[0066] The adaptive optimization space is integrated as a key component of the intelligent control strategy model. During the design and implementation of the model, ensure that the adaptive optimization space can work with other parts of the model (such as data preprocessing, D / A conversion, BP neural network, etc.). When the model is running, the adaptive optimization space is called to generate the corresponding adjustment strategy based on the real-time monitored temperature information, pressure information and position information. This can be achieved by searching for the optimal particle in the adaptive optimization space or selecting the closest particle based on the current state.

[0067] This step improves the flexibility and response speed of the solenoid valve control strategy by constructing a three-dimensional adaptive optimization space containing temperature, pressure and position information and designing a dynamic adjustment mechanism. Integrating the optimization space into the intelligent control strategy model enables it to generate optimized adjustment strategies in real time during actual operation, providing technical support for the efficient and stable operation of the fluid control system.

[0068] Furthermore, in step S700 of the present application, a feedback management and maintenance center is established, and the feedback management and maintenance center is embedded in the control center to perform real-time monitoring of the target solenoid valve, obtain monitoring results, and provide feedback on the monitoring results. It also includes: designing a feedback management and maintenance center, and the feedback management and maintenance center is used to exchange data with the control center; presetting a monitoring frequency, monitoring the target solenoid valve based on the monitoring frequency, and obtaining monitoring results; establishing an alarm database based on the historical data, and inputting the monitoring results into the alarm database for judgment; if the monitoring results exist, triggering the early warning system, and sending an early warning message to the operator.

[0069] Specifically: Design a feedback management and maintenance center that can monitor the status and performance parameters of the target solenoid valve in real time. Receive instructions from the control center and adjust monitoring parameters or perform other operations based on the instructions. Integrate and analyze monitoring data to provide feedback and decision support.

[0070] Establish an efficient data exchange channel with the control center to ensure the real-time and accuracy of the data. The control center is a central management system or platform responsible for monitoring, controlling and managing a series of equipment, systems or processes, with real-time monitoring, data analysis, remote control, alarm management, data storage and reporting, user interface, system integration and other functions. Use standard data interfaces and protocols such as API, MQTT, OPC UA, etc. when establishing the connection to facilitate data exchange and integration.

[0071] According to the importance and usage scenarios of the target solenoid valve, preset the appropriate monitoring frequency. The frequency can be set to a fixed value, such as monitoring once per second, or it can be dynamically adjusted according to actual needs. Ensure the real-time and integrity of the data. Based on the preset monitoring frequency, use the sensor group to monitor the target solenoid valve in real time to obtain monitoring results such as temperature, pressure, flow and position.

[0072] Use historical data and empirical rules to build an alarm database and define the normal operating parameter range and abnormal parameter threshold. Store key information such as alarm threshold, alarm type, and alarm time. Input real-time monitoring results into the alarm database for data comparison and abnormal judgment to determine whether there are abnormal conditions.

[0073] Design an early warning system, including the generation, storage and sending mechanism of early warning information. Early warning information can include key contents such as alarm type, alarm time, target solenoid valve information, etc. Be able to respond in time when there are abnormalities in the monitoring results. Once the alarm database determines that there are abnormalities in the monitoring results, the early warning system is immediately triggered to send early warning information to the operator, including the abnormality type, specific parameters and impact, etc.

[0074] This step realizes data synchronization and sharing between the feedback management and maintenance center and the control center through efficient data collection, transmission, processing and feedback mechanisms. Through two-way data interaction and system stability design, the reliability and response speed of the fluid control system are improved, providing technical support for the precise control of the solenoid valve and the optimized operation of the system.

[0075] Furthermore, the method described in the present application also includes: if the monitoring result does not exist, the monitoring result is marked and transmitted to the control center for re-judgment; if normal, the target solenoid valve operates normally; if abnormal, a secondary warning message is generated, and the operator is quickly notified to perform manual repairs.

[0076] Specifically: If the monitoring results of the target solenoid valve cannot be successfully obtained due to some reasons (such as sensor failure, data transmission problems, etc.), the system should mark this. The marking information includes timestamp, sensor ID, current status, etc. The monitoring results marked as non-existent are transmitted to the control center. After the control center receives the non-existent monitoring results, it will make a re-judgment. Involving checking the sensor status, data transmission channel, etc., to determine the problem. Based on the results of the re-judgment, the control center will take appropriate measures, such as replacing the sensor, repairing the data transmission channel, etc., to ensure that the monitoring results can be successfully obtained again.

[0077] When the system confirms that the monitoring results show that all parameters of the target solenoid valve are within the normal range, the target solenoid valve continues to operate normally according to the current state. The system continues to monitor the target solenoid valve in real time according to the preset monitoring frequency.

[0078] When the monitoring results are abnormal, the system generates new warning information according to the abnormal degree of the monitoring results. The warning information should contain specific abnormal parameters, abnormal degree, possible causes and other information. The system quickly sends the new warning information to the operator so that the abnormal situation can be understood and handled in time. After receiving the warning information, the operator will immediately carry out manual repairs. According to the prompts in the warning information, the target solenoid valve is inspected, repaired or adjusted to restore its normal operating state. After completing the repair, the operator should record the processing process and results and report to the relevant departments or personnel. This will help the subsequent analysis and handling of similar problems.

[0079] The feedback management and maintenance center can process the monitoring results of the target solenoid valve more comprehensively, ensuring that abnormal situations are discovered and handled in a timely manner, thereby ensuring the stable operation of the system.

[0080] In summary, the flow adaptive regulation method based on the solenoid valve provided in the embodiment of the present application has the following technical effects:

[0081] 1. By deploying a sensor group including temperature, pressure, flow and position, the working data of the solenoid valve is collected and processed in real time. Using this data, an intelligent control strategy model is established, and supervised training is performed through historical data to optimize the control strategy. At the same time, an adaptive optimization space is constructed to dynamically adjust the control strategy to adapt to environmental changes. The feedback management and maintenance center is embedded in the control center, which monitors the status of the solenoid valve in real time and provides feedback to ensure stable operation of the system. This solution not only improves the working efficiency and safety of the solenoid valve, but also reduces maintenance costs through intelligent and automated means.

[0082] 2. By clarifying the function and control objectives of the target solenoid valve, ensure that the design of the intelligent control strategy model meets actual needs and can effectively solve practical problems. By selecting the BP neural network and performing a reasonable model structure design, the established initial intelligent control strategy model has strong nonlinear mapping and self-learning capabilities. Through appropriate parameter initialization methods, the initial performance of the model is improved, the effect and convergence speed of subsequent training are ensured, and a good foundation is laid for the efficient control of the solenoid valve.

[0083] 3. Through efficient data collection, transmission, processing and feedback mechanisms, data synchronization and sharing between the feedback management and maintenance center and the control center are realized. Through two-way data interaction and system stability design, the reliability and response speed of the fluid control system are improved, providing technical support for the precise control of the solenoid valve and the optimized operation of the system.

[0084] Embodiment 2

[0085] Based on the same inventive concept as the flow adaptive regulation method based on the solenoid valve in the aforementioned embodiment, Figure 2 As shown, the embodiment of the present application provides a flow adaptive regulation system based on a solenoid valve, the system comprising:

[0086] The sensor group layout module 11 is used to determine a target solenoid valve and to layout a sensor group based on the target solenoid valve. The sensor group includes a temperature sensor, a pressure sensor, a flow sensor and a position sensor.

[0087] The flow signal conversion module 12 is used to perform data processing based on the flow information and convert the flow information into an electrical signal;

[0088] An initial model building module 13 is used to build an initial intelligent control strategy model, wherein the input data of the initial intelligent control strategy model is the electrical signal, and the output data is the adjustment strategy of the target solenoid valve;

[0089] The control strategy model acquisition module 14 is used to collect historical data, perform supervised training on the initial intelligent control strategy model based on the historical data, and acquire the intelligent control strategy model;

[0090] Optimization space construction module 15: used to construct an adaptive optimization space, the adaptive optimization space includes a plurality of optimization control strategy particles, the plurality of optimization control strategy particles are jointly determined by temperature information, pressure information and position information, and the adaptive optimization space is embedded in the intelligent control strategy model;

[0091] An adjustment strategy acquisition module 16 is used to monitor the real-time flow of the target solenoid valve based on the sensor group, input the real-time flow into the intelligent control strategy model to acquire the adjustment strategy, and the target solenoid valve is adjusted based on the adjustment strategy;

[0092] Monitoring result feedback module 17: used to build a feedback management and maintenance center, which is embedded in the control center, monitors the target solenoid valve in real time, obtains monitoring results, and provides feedback on the monitoring results.

[0093] Furthermore, the system is also used for:

[0094] Based on the flow sensor, the flow of the target solenoid valve is monitored to obtain flow information;

[0095] Performing data preprocessing on the flow information to obtain flow processing information;

[0096] The flow processing information is converted through D / A to obtain an electrical signal.

[0097] Furthermore, the system is also used for:

[0098] Clarify the function and control target of the target solenoid valve;

[0099] Select BP neural network to design the model structure and determine the input data and output data;

[0100] Initialize the model parameters to obtain the initial intelligent control strategy model.

[0101] Furthermore, the system is also used for:

[0102] Collect historical data, extract samples from the historical data, and obtain a sample data set;

[0103] Obtaining a preset data division ratio, and dividing the sample data set into a training data set and a verification data set according to the preset data division ratio;

[0104] Performing supervised training on the initial intelligent control strategy model through the training data set, and when the output result of the model tends to converge, verifying the output result of the initial intelligent control strategy model through the verification data set;

[0105] A preset model verification accuracy index is obtained, and when the accuracy of the output result of the initial intelligent control strategy model meets the preset model verification accuracy index, the intelligent control strategy model is obtained.

[0106] Furthermore, the system is also used for:

[0107] Building an adaptive optimization space, and determining three dimensions of the adaptive optimization space, wherein each of the three dimensions corresponds to an attribute;

[0108] Presetting standard thresholds for the three dimensions respectively, and using the standard thresholds as boundary conditions for the three dimensions;

[0109] Designing a dynamic adjustment mechanism to adjust the boundary of the adaptive optimization space when the specification of the target solenoid valve changes;

[0110] The adaptive optimization space is integrated as a component of the intelligent control strategy model. When the model is running, the adaptive optimization space will be called to generate the adjustment strategy.

[0111] Furthermore, the system is also used for:

[0112] Design a feedback management and maintenance center, which is used to interact with the control center for data;

[0113] Preset a monitoring frequency, monitor the target solenoid valve based on the monitoring frequency, and obtain a monitoring result;

[0114] Building an alarm database based on the historical data, and inputting the monitoring results into the alarm database for judgment;

[0115] If the monitoring results exist, the early warning system will be triggered and a warning message will be sent to the operator.

[0116] Furthermore, the system is also used for:

[0117] If the monitoring result does not exist, the monitoring result is marked and transmitted to the control center for re-judgment;

[0118] If normal, the target solenoid valve operates normally;

[0119] If it is abnormal, a secondary warning message is generated and the operator is notified to perform manual repairs.

[0120] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0121] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A flow adaptive regulation method based on a solenoid valve, characterized in that: include: Determine a target solenoid valve, and arrange a sensor group based on the target solenoid valve, wherein the sensor group includes a temperature sensor, a pressure sensor, a flow sensor, and a position sensor; Performing data processing based on flow information and converting the flow information into an electrical signal; Establishing an initial intelligent control strategy model, wherein the input data of the initial intelligent control strategy model is the electrical signal, and the output data is the adjustment strategy of the target solenoid valve; Collecting historical data, and performing supervised training on the initial intelligent control strategy model based on the historical data to obtain an intelligent control strategy model; Constructing an adaptive optimization space, wherein the adaptive optimization space includes a plurality of optimization control strategy particles, wherein the plurality of optimization control strategy particles are jointly determined by temperature information, pressure information, and position information, and the adaptive optimization space is embedded in an intelligent control strategy model; Based on the sensor group, real-time flow monitoring of the target solenoid valve is performed, the real-time flow is input into the intelligent control strategy model to obtain the adjustment strategy, and the target solenoid valve is adjusted based on the adjustment strategy; Building a feedback management and maintenance center, which is embedded in the control center, to monitor the target solenoid valve in real time, obtain monitoring results, and provide feedback on the monitoring results; The establishing of the initial intelligent control strategy model comprises: Clarify the function and control target of the target solenoid valve; Select BP neural network to design the model structure and determine the input data and output data; Initialize the model parameters to obtain the initial intelligent control strategy model; The collecting of historical data, and performing supervised training on the initial intelligent control strategy model based on the historical data to obtain the intelligent control strategy model include: Collect historical data, extract samples from the historical data, and obtain a sample data set; Obtaining a preset data division ratio, and dividing the sample data set into a training data set and a verification data set according to the preset data division ratio; Performing supervised training on the initial intelligent control strategy model through the training data set, and when the model output result tends to converge, verifying the output result of the initial intelligent control strategy model through the verification data set; Obtaining a preset model verification accuracy index, and when the accuracy of the output result of the initial intelligent control strategy model meets the preset model verification accuracy index, obtaining the intelligent control strategy model; The constructing of the adaptive optimization space comprises: Building an adaptive optimization space, and determining three dimensions of the adaptive optimization space, wherein each of the three dimensions corresponds to an attribute; Presetting standard thresholds for the three dimensions respectively, and using the standard thresholds as boundary conditions for the three dimensions; Designing a dynamic adjustment mechanism to adjust the boundary of the adaptive optimization space when the specification of the target solenoid valve changes; The adaptive optimization space is integrated as a component of the intelligent control strategy model. When the model is running, the adaptive optimization space will be called to generate the adjustment strategy.

2. The method according to claim 1, characterized in that The data processing based on the flow information and converting the flow information into an electrical signal includes: Based on the flow sensor, the flow of the target solenoid valve is monitored to obtain flow information; Performing data preprocessing on the flow information to obtain flow processing information; The flow processing information is converted through D / A to obtain an electrical signal.

3. The method according to claim 1, characterized in that The feedback management and maintenance center is built, and the feedback management and maintenance center is embedded in the control center, performs real-time monitoring on the target solenoid valve, obtains monitoring results, and provides feedback on the monitoring results, including: Design a feedback management and maintenance center, which is used to interact with the control center for data; Preset a monitoring frequency, monitor the target solenoid valve based on the monitoring frequency, and obtain a monitoring result; An alarm database is built based on the historical data, and the monitoring results are input into the alarm database for judgment. If the monitoring results exist, the early warning system is triggered to send early warning information to the operator.

4. The method according to claim 3, characterized in that The inputting the monitoring results into the alarm database for judgment also includes: If the monitoring result does not exist, the monitoring result is marked and transmitted to the control center for re-judgment; If normal, the target solenoid valve operates normally; If it is abnormal, a secondary warning message is generated and the operator is notified to perform manual repairs.

5. The flow adaptive regulation system based on solenoid valve is characterized by: For executing the method according to any one of claims 1 to 4, the system comprises: A sensor group layout module: used to determine a target solenoid valve and to layout a sensor group based on the target solenoid valve, wherein the sensor group includes a temperature sensor, a pressure sensor, a flow sensor and a position sensor; Flow signal conversion module: used for performing data processing based on flow information and converting the flow information into electrical signals; An initial model building module is used to build an initial intelligent control strategy model, wherein the input data of the initial intelligent control strategy model is the electrical signal, and the output data is the adjustment strategy of the target solenoid valve; Acquisition control strategy model module: used for collecting historical data, performing supervised training on the initial intelligent control strategy model based on the historical data, and acquiring the intelligent control strategy model; Optimization space construction module: used to construct an adaptive optimization space, the adaptive optimization space includes a plurality of optimization control strategy particles, the plurality of optimization control strategy particles are jointly determined by temperature information, pressure information and position information, and the adaptive optimization space is embedded in the intelligent control strategy model; An adjustment strategy acquisition module is used to monitor the real-time flow of the target solenoid valve based on the sensor group, input the real-time flow into the intelligent control strategy model to acquire the adjustment strategy, and the target solenoid valve is adjusted based on the adjustment strategy; Monitoring result feedback module: used to build a feedback management and maintenance center, which is embedded in the control center, monitors the target solenoid valve in real time, obtains monitoring results, and provides feedback on the monitoring results.

Images