Reverse flow valve intelligent adjusting method based on self-adaptive control algorithm

Abstract

The invention relates to an intelligent reflux valve adjusting method based on a self-adaptive control algorithm, and aims to improve the accuracy and response efficiency of fluid adjustment. The method comprises the steps that fluid flow, pressure, temperature and flow direction data collected by sensors installed at an inlet and an outlet of the reflux valve are obtained, and the initial target valve opening degree under the current fluid working condition is calculated through a working condition opening degree prediction model in combination with structural parameters of the reflux valve; based on the relation among the flow, the pressure and the valve opening, the initial target valve opening is adjusted through a fuzzy rule base, so that the final target valve opening is obtained, and therefore the dynamic change of the complex fluid working condition is adapted; according to the final target valve opening degree, an execution mechanism is controlled to adjust the operation state of the reflux valve, and precise adjustment is achieved; working condition prediction and fuzzy control are combined, the adjusting precision and stability of the reflux valve are improved, and the method is particularly suitable for fluid conveying systems with large flow and pressure fluctuation and has wide application prospects in the industries of energy, chemical engineering, environmental protection and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of reverse flow valve control, and in particular to an intelligent regulation method of a reverse flow valve based on an adaptive control algorithm. Background Art

[0002] Reverse flow valves are widely used in fluid pipeline systems to control the flow direction and flow rate of fluids to ensure stable operation of the system. Traditional reverse flow valve adjustment methods usually rely on preset control logic or simple PID control strategies to set fixed control rules based on flow, pressure or opening. In industrial applications, some systems combine sensor data for closed-loop control to improve the accuracy of fluid regulation. Due to the complexity and real-time variability of fluid operating conditions, existing control methods have certain limitations when dealing with nonlinear characteristics, operating condition fluctuations and external interference.

[0003] The main problem with existing technologies is that fixed rules or simple control algorithms are difficult to adapt to the dynamic changes of fluid conditions, resulting in limited regulation accuracy. At the same time, control methods that lack adaptive regulation capabilities may cause valve over- or under-regulation, affecting the stability of fluid delivery. In addition, in complex fluid environments, due to the lack of intelligent prediction mechanisms, existing methods are difficult to adapt to flow fluctuations in advance, which in turn affects the response speed and energy efficiency of the overall control.

[0004] Therefore, it is necessary to develop an intelligent adjustment method for reverse flow valve based on adaptive control algorithm. Summary of the invention

[0005] The present application provides an intelligent regulation method for a reverse flow valve based on an adaptive control algorithm to improve the regulation accuracy and stability of the reverse flow valve.

[0006] The present application provides a reverse flow valve intelligent adjustment method based on an adaptive control algorithm, comprising: Obtaining fluid flow, pressure, temperature and flow direction data collected by sensors installed at the inlet and outlet of the reverse flow valve; Based on the acquired fluid data and the structural parameters of the reverse flow valve, the initial target valve opening under the current fluid working condition is predicted using the working condition opening prediction model; Using a fuzzy rule base based on the relationship between flow, pressure and valve opening, the initial target valve opening is adjusted in real time to obtain a final target valve opening; According to the final target valve opening, the actuator is controlled to adjust the operating state of the reverse flow valve.

[0007] The beneficial effects of the technical solution provided by this application include: (1) By combining the operating condition opening prediction model with the structural parameters of the reverse flow valve, the target opening can be accurately predicted according to different fluid operating conditions, and the fuzzy rule base can be adjusted in real time to keep the valve at the optimal opening in a dynamic environment, thereby improving the regulation accuracy and adaptability. (2) The fuzzy rule base is used for real-time adjustment, so that the system can maintain stable operation under large flow and pressure fluctuations, avoiding the problem that traditional PID control is easily affected by changes in operating conditions, and improving the robustness and anti-interference ability of the regulation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is a flow chart of a reverse flow valve intelligent adjustment method based on an adaptive control algorithm provided in the first embodiment of the present application. DETAILED DESCRIPTION

[0009] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0010] The first embodiment of the present application provides a reverse flow valve intelligent adjustment method based on an adaptive control algorithm. Figure 1 , which is a schematic diagram of the first embodiment of the present application. Figure 1 A first embodiment of the present application provides a method for intelligently adjusting a reverse flow valve based on an adaptive control algorithm and is described in detail.

[0011] Step S101: Obtain fluid flow, pressure, temperature and flow direction data collected by sensors installed at the inlet and outlet of the reverse flow valve.

[0012] In step S101, firstly, sensors of appropriate types are arranged at the inlet and outlet of the counter-flow valve to obtain the key parameters of the fluid. The flow rate can be measured by a differential pressure flowmeter, an electromagnetic flowmeter or an ultrasonic flowmeter, and the specific selection can be determined according to the physical properties of the pipeline medium, the pipe diameter and the measurement accuracy requirements. For example, for conductive fluids, an electromagnetic flowmeter can be used, while for non-conductive fluids, such as gas or certain oil fluids, an ultrasonic flowmeter or a mass flowmeter can be used. The pressure sensor can be a piezoresistive, strain gauge or capacitive pressure sensor, and it should be ensured that it can withstand the maximum pressure within the working range of the counter-flow valve to avoid sensor damage or excessive measurement errors. The temperature sensor can be selected from thermocouples or thermistors to ensure stable measurement under high or low temperature conditions. The acquisition of flow direction data can be achieved through the bidirectional measurement function of the flowmeter, or by arranging multiple flow sensors at different positions and inferring the flow direction by comparing the flow velocity directions of the inlet and outlet.

[0013] The installation of the sensor must ensure that it is coaxial with the pipeline and avoid bubbles or sediments affecting the measurement accuracy. The flange, insert or clamp type can be used for installation. The appropriate installation method should be selected according to the pipeline material and the site environment. In addition, to ensure the reliability of data acquisition, the sensor needs to be calibrated regularly, especially after long-term operation, which may cause measurement errors to increase due to factors such as temperature drift and mechanical wear. During the data acquisition process, data filtering and outlier removal methods should be combined to avoid the influence of instantaneous pulsation, flow fluctuation or pressure pulse on the control accuracy of the system. Signal processing methods such as median filtering, mean filtering or Kalman filtering can be used to improve the stability and credibility of the data.

[0014] The frequency of data collection should be set according to the dynamic response requirements of the reverse flow valve. Generally, the update frequency of the fluid control system can be set between 50 ms and 1 s to ensure that the data can reflect the changes in the working conditions of the fluid in real time. The collected flow, pressure, temperature and flow direction data can be transmitted to the host computer or controller via fieldbus (such as Modbus, CAN, etc.) or wireless communication (such as LoRa, NB-IoT, etc.) for subsequent valve opening calculation and adjustment.

[0015] During data transmission, appropriate communication protocols and error detection mechanisms should be adopted to ensure data integrity and accuracy. For example, the CRC (cyclic redundancy check) method can be used to verify the transmitted data to prevent error control caused by transmission errors. In addition, to ensure the real-time and stability of the system, edge computing methods can be used to perform preliminary data processing at the data acquisition end close to the sensor, such as filtering, data fusion, and feature extraction, to reduce communication delays and computing burdens and improve data processing efficiency.

[0016] Through the above steps, the fluid flow, pressure, temperature and flow direction data of the inlet and outlet of the reverse flow valve can be accurately and real-time obtained, providing accurate and reliable basic data for subsequent valve opening prediction and intelligent adjustment.

[0017] Furthermore, the step of obtaining the fluid flow rate, pressure, temperature and flow direction data collected by sensors disposed at the inlet and outlet of the reverse flow valve includes: Dynamically adjust the data acquisition frequency of the sensor according to the change rate of flow and pressure. When the change rate exceeds the set threshold, the acquisition frequency is increased; when the change rate is lower than the set threshold, the acquisition frequency is reduced; Store a predetermined amount of historical flow, pressure, temperature and flow direction data, and compare it with the historical data every time new data is collected. When the new data deviates from the set range of historical data, it is marked as abnormal data and the data is corrected; Based on the structural parameters and historical data of the reverse flow valve, the flow direction data is compensated. When the flow direction data changes suddenly and the valve opening changes significantly, the compensation factor is calculated and the current flow direction data is adjusted to improve the accuracy of flow direction detection.

[0018] In the process of obtaining the fluid flow, pressure, temperature and flow direction data collected by sensors at the inlet and outlet of the reverse flow valve, in order to ensure the accuracy, stability and real-time nature of the data, it is necessary to adopt methods of dynamic acquisition frequency adjustment, historical data storage and comparison, abnormal data correction and flow direction data compensation to adapt to changes in fluid conditions and provide reliable data input.

[0019] When collecting data, the system needs to first set the initial acquisition frequency of the sensor, which can be set according to the operating requirements of the system, the characteristics of the fluid in the pipeline, and the response time of the reverse flow valve. Generally, the initial sampling frequency should ensure that sufficient fluid state information can be provided under stable conditions, while avoiding the data processing burden caused by oversampling. During the operation of the system, the flow rate change rate and pressure change rate per unit time are calculated in real time. When the change rate of any parameter exceeds the set upper threshold, such as detecting a sharp increase or decrease in the flow rate in a short period of time, or a large pressure fluctuation, the system automatically increases the sampling frequency of the sensor to shorten the sampling interval in order to finely capture the rapid changes in the fluid state. In this process, the system can adopt a hierarchical adjustment method to determine the adjustment range of the sampling frequency according to the size of the change rate. For example, when the flow rate or pressure change rate exceeds the first set threshold but does not exceed the second set threshold, the sampling frequency is increased to 1.5 times the initial frequency, and when the change rate exceeds the second set threshold, the sampling frequency is increased to 2 times or more to ensure data integrity under sudden conditions. On the contrary, when the rate of change of flow and pressure is lower than the preset lower threshold, it indicates that the system is in a stable working condition and the continuous data collected by the sensor changes little. At this time, the sampling frequency is reduced to reduce data redundancy, improve system computing efficiency, and reduce the energy consumption of the sensor.

[0020] In order to ensure the integrity and continuity of the data, each new data collected needs to be compared with the historical data, and a certain amount of historical data needs to be stored to detect whether there is abnormal data. The data storage adopts a sliding window mechanism. The size of the window is determined by the number of historical data points, and should be dynamically adjusted according to the changes in the fluid working conditions to ensure that the historical data can effectively reflect the current working condition trend. When new data is written into the storage window, the system needs to calculate the mean and variance of all flow, pressure, temperature and flow direction data in the current window, and compare the mean deviation of the new data with the historical data. When the newly collected data value deviates from the historical mean by more than the set threshold, or its change trend is obviously inconsistent with the historical trend, for example, multiple consecutive data points are beyond the normal fluctuation range, the data is marked as abnormal data and anomaly correction is performed. The correction method of abnormal data needs to be selected in combination with the abnormal type. When the data only mutates in a single sampling cycle but returns to normal in the next sampling, linear interpolation or historical mean can be used for correction so that it will not interfere with the overall trend during data processing. If the abnormal data deviates from the normal range in multiple consecutive sampling cycles, it is necessary to further determine whether it is caused by sensor drift, environmental interference or system failure. For example, when judging sensor drift, the data of multiple sensors can be compared, such as whether the measured value of the flow sensor is consistent with the theoretical flow calculated by the pressure sensor, and combined with other stored historical data, Kalman filtering or dynamic offset compensation methods can be used to correct the abnormal data to ensure data reliability and consistency.

[0021] In the process of processing flow direction data, since the movement state of the fluid may be affected by the change of the opening of the reverse flow valve, the flow direction data collected by the sensor alone may not accurately reflect the real direction of the fluid. In order to improve the accuracy of flow direction detection, the system needs to compensate the flow direction data in combination with the structural parameters and historical data of the reverse flow valve. When the flow direction sensor detects a sudden change in the flow direction data, and the system records that the valve opening has been significantly adjusted in the same time period, the flow direction compensation factor needs to be calculated and the current flow direction data needs to be corrected based on the factor. The calculation of the flow direction compensation factor is based on the change amplitude of the valve opening, the fluid inertia and the historical flow direction data. Specifically, when the valve is opened or closed quickly, the inertia of the fluid may cause abnormal fluctuations in the flow direction data in a short period of time. For example, the reverse flow may be generated in a short period of time due to the backflow of the pipeline when the reverse flow valve is closed, and the flow direction sensor will detect an abnormal reverse flow signal. At this time, the system needs to combine the flow direction change trend before and after the valve opening adjustment, calculate the inertia effect in a short period of time, and correct the flow direction data to reflect the real flow state of the fluid. For different fluid media, due to different parameters such as viscosity and density, the calculation method of the compensation factor can be adjusted based on experimental data to adapt to different types of fluid working conditions.

[0022] Through the above method, the system can ensure the integrity and accuracy of the data while adjusting the sensor sampling frequency in real time, and effectively correct data anomalies caused by sudden working conditions, sensor drift or valve opening changes, so that the acquired fluid parameters more accurately reflect the actual working conditions and provide reliable data support for subsequent valve adjustments.

[0023] Furthermore, the predetermined amount of historical flow, pressure, temperature and flow direction data is stored, and each time new data is collected, it is compared with the historical data. When the new data deviates from the set range of the historical data, it is marked as abnormal data and the data is corrected, including: Preset data storage window. During each data collection, the latest flow, pressure, temperature and flow direction data are stored in the window. The window length is set according to time or data capacity so that the data in the window can reflect the current working condition trend. Calculate data distribution characteristics based on historical data in the storage window, including data mean, variance and change trend. When the deviation of the newly collected data value from the mean of historical data exceeds the set threshold, or the data change trend is significantly inconsistent with the historical trend, mark the data as abnormal data. Correct the data marked as abnormal. When the abnormal data is in a short-term mutation state and no continuous abnormality occurs, use interpolation or historical mean to correct it. When the abnormal data shows a continuous deviation trend, determine whether it is caused by sensor drift or environmental influence, and compensate based on the related data of multiple sensors to ensure that the corrected data can accurately reflect the actual fluid conditions.

[0024] In the process of storing and processing historical flow, pressure, temperature and flow direction data, in order to ensure that the system can accurately detect abnormal data and make effective corrections, it is necessary to first set a data storage window to retain historical data for a period of time. The size of the storage window can be set according to time or data capacity so that it can accommodate a sufficient number of data points to provide an effective reference for the current working conditions. Every time new data is collected, the system will store the latest flow, pressure, temperature and flow direction data in the storage window and delete the earliest data to maintain a fixed size of the storage window, thereby ensuring that the data in the window can always reflect the recent working condition change trend. The length of the storage window can be set according to the response speed of the system, the stability of the fluid working condition and the data calculation ability. For example, under rapidly changing working conditions, a shorter window length can be set to capture the data change trend more quickly, while under relatively stable working conditions, a longer window can be set to enhance the robustness of data analysis.

[0025] After the data is stored, it is necessary to perform statistical analysis on the data in the storage window to calculate the distribution characteristics of the data and determine whether the newly collected data is abnormal data based on these characteristics. The system will calculate the mean, variance and change trend of all historical data in the storage window in each sampling period as a benchmark for judging the rationality of new data. The data mean is used to represent the central trend of flow, pressure, temperature and flow direction, the variance is used to measure the discreteness of the data, and the change trend is used to identify the fluctuation pattern of the data in a short period of time. When the deviation between the newly collected data value and the historical mean in the storage window exceeds the set threshold, or the change trend of the new data is significantly inconsistent with the historical trend, such as excessive flow or pressure changes in a short period of time, and the historical data shows that the working condition is usually stable, the data is marked as abnormal data to prevent the abnormal data from misleading the system control. The threshold for abnormal judgment can be set according to the standard deviation of the historical data. For example, when the data deviates from the mean by more than a certain multiple of the standard deviation, it is regarded as abnormal data. This method can adaptively adjust the judgment criteria according to the fluctuation of different fluid working conditions to improve the accuracy of abnormal detection.

[0026] For data marked as abnormal, it is necessary to make corresponding corrections according to its characteristics to ensure the continuity and accuracy of the data. When the abnormal data is in a short-term mutation state and similar abnormalities do not appear in multiple consecutive sampling periods, interpolation or historical mean can be used for correction. For example, if the flow data in a certain sampling period suddenly deviates greatly, and the data before and after remain stable, linear interpolation can be used to calculate a reasonable correction value based on the data before and after to replace the abnormal data and make the data series smoother. If the abnormal data shows a trend of continuous deviation, such as the pressure data gradually deviates from the normal range in multiple consecutive sampling periods, it is necessary to further analyze the cause of the abnormality and determine whether it is caused by sensor drift or environmental influence. In this case, the measurement data of multiple sensors can be combined for correlation analysis, such as comparing the flow and pressure data collected by different sensors to check whether there is a consistent deviation pattern, or introducing redundant sensor data as a control to identify the specific source of the abnormality.

[0027] If it is determined that the abnormal data is caused by sensor drift, a dynamic compensation method based on historical data can be used for correction, such as using long-term trend analysis to identify sensor drift deviations and automatically correct them in subsequent measurement data. If the abnormal data may be caused by environmental factors, such as the temperature sensor being disturbed by an external heat source, resulting in measurement errors, compensation can be combined with ambient temperature data to ensure the reliability of the measurement data. In this way, the impact of sensor errors and environmental interference on the data can be effectively filtered, allowing the system to more accurately perceive fluid conditions and provide reliable data support for subsequent valve control.

[0028] Step S102: Based on the acquired fluid data and in combination with the structural parameters of the reverse flow valve, an initial target valve opening under the current fluid working condition is predicted using an operating condition opening prediction model.

[0029] In step S102, firstly, the fluid flow, pressure, temperature and flow direction data collected in step S101 need to be used in combination with the structural parameters of the counterflow valve to establish a working condition opening prediction model. The establishment of the working condition opening prediction model is based on the principles of fluid mechanics and the working characteristics of the counterflow valve, and needs to consider the fluid flow state in the pipeline, pressure loss, the effect of temperature on fluid viscosity, and the nonlinear relationship between valve opening and flow.

[0030] When calculating the initial target valve opening, the fluid data needs to be preprocessed first. Flow, pressure and temperature data may be affected by sensor noise, short-term fluctuations or environmental interference, so data filtering techniques such as sliding average filtering, median filtering or Kalman filtering are needed to improve the stability and reliability of the data. In addition, for flow direction data, it can be judged based on the flow sensor readings at the inlet and outlet of the reverse flow valve. If the inlet flow is greater than the outlet flow, there may be a risk of backflow, and the valve opening needs to be adjusted appropriately to prevent backflow.

[0031] After data preprocessing is completed, preliminary calculations are required based on the structural parameters of the reverse flow valve. These structural parameters include but are not limited to the nominal diameter of the valve, valve body material, valve disc type, flow capacity coefficient (Cv value or Kv value), flow resistance coefficient, etc. These parameters can be obtained through the data sheet provided by the manufacturer or actual testing, and are used to correct the fluid flow characteristics during the calculation process. Based on fluid mechanics equations, such as the Bernoulli equation, the continuity equation, and the flow resistance calculation formula, the relationship between the target flow rate and the valve opening under specific fluid conditions can be calculated.

[0032] To improve the prediction accuracy, an opening prediction method based on machine learning or data regression can be used. For example, a regression model trained based on historical operating data, such as polynomial regression, support vector machine regression (SVR), or a neural network model, can accurately predict the optimal opening of the valve under different fluid conditions. In addition, if the system has strong nonlinear characteristics, an adaptive neural fuzzy inference system (ANFIS) can be used for modeling to enhance the generalization ability of the model.

[0033] When calculating the initial target valve opening, the flow and pressure data can be used to determine the flow state of the fluid, such as laminar flow, transitional flow, or turbulent flow. If the fluid is in a laminar state, the target valve opening can be calculated based on the Poiseuille flow equation; if the fluid is in a turbulent state, it can be corrected based on empirical formulas or experimental data. For operating conditions with higher or lower temperatures, the effect of temperature on fluid viscosity must also be considered and the calculation formula must be adjusted.

[0034] After calculating the initial target opening, it is also necessary to check its rationality. For example, the calculated valve opening can be compared with the mechanical limit of the valve. If it exceeds the allowable range, it needs to be corrected. In addition, the trend of the calculation results can be compared based on historical operating data. If there is a large deviation between the current calculated opening and the opening under similar historical operating conditions, it may be necessary to readjust the calculation parameters or update the model.

[0035] Through the above steps, the initial target valve opening under the current fluid working conditions can be obtained, providing basic data for subsequent real-time adjustment and optimization control.

[0036] Furthermore, the operating condition opening prediction model includes a data preprocessing module, a feature extraction module, an opening calculation module and an adaptive correction module; The data preprocessing module is used to receive flow, pressure, temperature and flow direction data, and normalize the data in combination with the structural parameters of the reverse flow valve, remove abnormal values, smooth the data through a filtering algorithm, and output optimized working condition data; The feature extraction module receives the output of the data preprocessing module, and calculates the flow-pressure change rate ratio, the fluid pressure drop gradient and the flow direction stability to construct a feature vector reflecting the current working condition, and outputs the feature vector to the opening calculation module; The opening calculation module calculates the preliminary target opening based on the output of the feature extraction module by using historical data regression analysis and real-time fluid simulation methods, wherein the historical data regression analysis is used for short-term trend prediction, and the real-time fluid simulation is combined with the reverse flow valve structural parameters to correct the predicted opening, and the calculated preliminary target opening is output to the adaptive correction module; The adaptive correction module receives the output of the opening calculation module and calculates the prediction error based on the real-time feedback data. When the error exceeds the set threshold, the parameters of the opening calculation module are adjusted and the preliminary target opening is corrected to obtain the final predicted initial target valve opening.

[0037] In the process of implementing the operating condition opening prediction model, the flow, pressure, temperature and flow direction data must first be processed through the data preprocessing module to ensure the stability and reliability of the input data. This module receives the raw data from the sensors at the inlet and outlet of the counterflow valve, and normalizes the data in combination with the structural parameters of the counterflow valve to make the numerical range of each physical quantity consistent, so as to avoid the influence of different dimensions on the calculation. In addition, in order to reduce the interference of measurement errors on subsequent calculations, the data needs to be removed and filtered. When it is detected that the data deviates from the historical operating condition mean by more than the set threshold, and the deviation lasts for multiple sampling cycles, the data is marked as an outlier and replaced by historical trend interpolation or predicted values ​​calculated based on the physical model. In addition, in order to reduce the influence of high-frequency noise, the adaptive low-pass filtering method is used to smooth the data so that the data is more in line with the actual change trend of the fluid working condition, thereby improving the input data quality of the feature extraction module.

[0038] After data preprocessing is completed, the feature extraction module calculates the optimized operating data to extract key characteristic parameters that can accurately characterize the current fluid state. First, by calculating the ratio of the flow rate and pressure change rate in continuous time steps, the flow-pressure change rate ratio is obtained. This ratio can reflect the dynamic change of fluid resistance and is used to evaluate the sensitivity of valve regulation. Secondly, the fluid pressure drop gradient is calculated, that is, the pressure drop rate between different measurement points. This parameter can quantify the throttling effect of the reverse flow valve on the fluid flow and serve as an important basis for predicting the valve opening. In addition, the flow direction data is analyzed in multiple time steps, and the flow direction stability is calculated to evaluate whether the fluid is in a steady state or unstable states such as turbulence. The output of the feature extraction module is a feature vector containing multiple operating condition characteristic parameters. This feature vector is used as the input of the opening calculation module to ensure that the prediction model can calculate the target valve opening based on complete operating condition information.

[0039] After receiving the output of the feature extraction module, the opening calculation module combines historical data regression analysis with real-time fluid simulation methods to calculate the preliminary target opening. In the process of historical data regression analysis, based on the stored past operating data, the most likely opening trend in the short term is predicted by the time series regression method. For example, the weighted moving average method is used to calculate the optimal opening after the recent operating conditions are adjusted, and the exponential smoothing method is combined to predict the short-term trend, so that the calculated opening value can adapt to the changes in historical operating conditions. In addition, in order to avoid the predicted value relying only on historical trends and being unable to adapt to the complex dynamic changes of the current operating conditions, it is further combined with the real-time fluid simulation method for correction. This simulation method is based on the structural parameters of the reverse flow valve, the current fluid characteristics and the operating characteristic parameters, and uses a numerical calculation method to simulate the fluid state of the valve at different openings, and optimizes the predicted preliminary target opening by calculating physical quantities such as pressure loss and flow velocity distribution. Finally, the output of the opening calculation module is a preliminary target opening value, which will be further optimized in the subsequent adaptive correction module.

[0040] The adaptive correction module receives the output of the opening calculation module and calculates the prediction error through real-time feedback data. When there is a significant deviation between the actual fluid operating conditions after the valve is adjusted and the predicted results, the module analyzes the source of the error and adjusts the parameters of the opening calculation module. For example, when the system detects that the prediction error is continuously too large or too small, it may mean that the historical data regression model fails to fully consider the changes in the current working conditions. Therefore, the regression weight is adjusted to reduce the influence of historical data and increase the weight of real-time fluid simulation. In addition, if the error mainly comes from parameter mismatch in fluid simulation calculations, such as changes in fluid viscosity or pipeline roughness leading to deviations in simulation results, the fluid characteristic parameters in the simulation model are updated through feedback data to improve the accuracy of the simulation calculation. Finally, the module calculates the final initial target valve opening based on the prediction results after error adjustment, and uses this value to control the actuator to adjust the operating state of the reverse flow valve.

[0041] The entire prediction model realizes accurate prediction from sensor data to the final target valve opening through the serial processing of four modules: data preprocessing, feature extraction, opening calculation and adaptive correction. The output of each module is used as the input of the next module in turn, ensuring that the prediction results can take into account historical trends and can be optimized in real time according to the current fluid conditions, so that the reverse flow valve can adapt to different conditions and achieve precise control.

[0042] Furthermore, the feature extraction module includes a data conversion unit, a feature calculation unit and a dynamic feature optimization unit; The data conversion unit is used to receive the output of the data preprocessing module, and perform nonlinear transformation on the normalized flow, pressure, temperature and flow direction data to enhance the data differentiation, wherein, for flow and pressure data, a piecewise logarithmic mapping function is used to differentially scale data in different ranges so that it has a higher resolution in the low value interval, and for temperature data, an exponential smoothing method is used to reduce the impact of transient changes, thereby obtaining converted data for feature calculation; The characteristic calculation unit receives the output of the data conversion unit and calculates key characteristics of the working condition, including flow-pressure change rate ratio, fluid pressure drop gradient and flow direction stability, wherein the flow-pressure change rate ratio is obtained by calculating the ratio of flow rate and pressure change rate in continuous time steps to measure the dynamic response characteristics of the fluid working condition, the fluid pressure drop gradient is calculated based on the flow rate and pipeline resistance parameters to quantify the influence of valve opening on fluid pressure, and the flow direction stability is obtained by calculating the variance of flow direction data in multiple time steps to evaluate the stability of fluid flow, and the calculated characteristic parameters are combined into a characteristic vector; The dynamic feature optimization unit is used to receive the output of the feature calculation unit and adaptively adjust the feature weight according to the historical operating data. Based on the historical operating data of the reverse flow valve, the weighted sliding average method is used to calculate the long-term change trend of each feature, and the weight of each feature in the feature vector is adjusted according to the feature change trend to enhance the characterization ability of key influencing factors, so that the generated feature vector is more suitable for the current working condition, and the optimized feature vector is output to the opening calculation module.

[0043] In the specific implementation process of the feature extraction module, the data conversion unit first receives the output of the data preprocessing module, including the normalized flow, pressure, temperature and flow direction data. Since the numerical range and change trend of different physical quantities may be quite different, directly using normalized data may cause some features to have too small weights in the calculation process, thus affecting the prediction accuracy of the model. In order to enhance the discrimination of the data, it is necessary to perform nonlinear transformation on the input data so that the key operating parameters maintain sufficient resolution in different value ranges. In the conversion process of flow and pressure data, the piecewise logarithmic mapping function is used to adjust the data so that it has higher resolution in the low value interval and changes more slowly in the high value interval, thereby improving the perception of small flow and pressure fluctuations and avoiding being ignored due to too small values ​​in low flow rate or low pressure. For temperature data, since transient temperature changes may introduce noise or short-term anomalies, in order to reduce the interference of temperature data on the prediction model, the exponential smoothing method is used to process the temperature series data, so that the weight of the newer data is higher and the influence of historical data gradually decays, thereby obtaining stable temperature input data to improve the robustness of the overall feature. After being processed by the data conversion unit, the converted data is used as the input of the feature calculation unit to further calculate the key features.

[0044] The feature calculation unit receives the output data of the data conversion unit and extracts the key features of the working condition to construct a feature vector for predicting the valve opening. First, the flow-pressure change rate ratio is calculated to measure the dynamic response characteristics of the fluid system. The change rates of flow and pressure are calculated in each time step, and the ratio of the two is obtained. If the ratio changes greatly, it means that the system responds quickly and may require more precise valve control. When the ratio changes less, it indicates that the system tends to be stable and the adjustment frequency can be appropriately reduced. Secondly, the fluid pressure drop gradient is calculated to quantify the effect of valve opening on fluid pressure. This parameter measures the pressure change at different positions in the pipeline and calculates the pressure drop rate per unit length of the pipeline in combination with the current flow rate, thereby characterizing the regulating effect of the reverse flow valve. When the pressure drop gradient is too large, it may mean that the valve opening is insufficient and the opening needs to be appropriately increased. When the pressure drop gradient is too small, it may indicate that the valve opening is too large, resulting in reduced system efficiency. Finally, the flow stability is calculated to evaluate the stability of fluid flow. The changing trend of flow direction data can be measured by calculating the variance of flow direction data in multiple consecutive time steps. When the flow direction variance is small, it means that the fluid flow is relatively stable, while when the flow direction variance is large, it may indicate that the fluid is disturbed or instantaneously reversed, and the valve opening needs to be adjusted to improve the flow state. After these characteristic parameters are calculated, they are combined into a feature vector, and the feature vector is passed to the dynamic feature optimization unit to further optimize the feature weight and improve the adaptability of the prediction model.

[0045] The dynamic feature optimization unit receives the feature vector output by the feature calculation unit, and adaptively adjusts the feature weight in combination with the historical operating data. Since the influence of each feature on the opening prediction is different under different operating conditions, the use of fixed weights may lead to a decrease in prediction accuracy under specific operating conditions. Therefore, it is necessary to dynamically optimize the feature weight based on historical operating data. First, the long-term change trend of each feature is calculated using the weighted moving average method to identify which features have a greater impact on the valve opening in different time periods. Then, according to the historical changes of these features, the weights of each feature in the feature vector are adjusted. For example, when the flow stability changes greatly over a period of time, while the flow-pressure change rate ratio and the fluid pressure drop gradient are relatively stable, it means that the flow fluctuation is the main factor affecting the current operating conditions. Therefore, the weight of the flow stability is appropriately increased, while the weights of other features are reduced, so that the prediction model pays more attention to the impact of flow changes. On the contrary, when the flow-pressure change rate ratio changes significantly, while the flow stability remains stable, the weight of the flow-pressure change rate ratio should be increased, so that the prediction model pays more attention to the dynamic response characteristics of the system. The optimized feature vector can more accurately characterize the current working state and adapt to different fluid changes, thereby improving the robustness of the prediction model. Finally, the optimized feature vector is output to the opening calculation module as the key input for calculating the target valve opening, so that the prediction model can maintain high-precision prediction capabilities under different working conditions.

[0046] Furthermore, the opening calculation module includes a short-term trend prediction unit, a real-time fluid simulation unit and an opening correction unit; The short-term trend prediction unit is used to analyze the change trend of historical flow, pressure, temperature and flow direction data based on the output of the feature extraction module using a multi-order regression model, and calculate the target opening within a short time scale; by constructing a recursive linear regression or exponential smoothing regression method, the trend curve is fitted using the data of multiple time steps in the past to predict the optimal opening at the current moment; The real-time fluid simulation unit is used to receive the target opening calculated by the short-term trend prediction unit, and in combination with the structural parameters of the reverse flow valve and the real-time operating data, correct the target opening through the numerical simulation calculation method; the numerical solution method based on the finite volume method or the finite difference method is used to simulate the fluid flow characteristics under different openings, and calculate the key parameters of fluid flow, pressure drop, and turbulence intensity to determine whether the preliminary predicted opening meets the current operating conditions; when the simulation results show that the predicted target opening may cause flow overshoot or excessive pressure drop, the opening value is adjusted to meet the physical constraints to ensure the rationality of the prediction; The opening correction unit is used to receive the corrected target opening output by the real-time fluid simulation unit, and fine-tune the opening in combination with the stability factor of the current working condition to improve the adjustment accuracy; by calculating the stability index of the working condition characteristic vector, the change amplitude of the current fluid state is judged. When the working condition changes drastically, the method of decreasing the adjustment step size is adopted to avoid the impact of the sudden change in the predicted opening on the system; when the working condition tends to be stable, a weighted smoothing adjustment strategy is adopted to make the final target opening more in line with the natural adjustment trend of the fluid; the output preliminary target opening is used for the subsequent adaptive correction module to achieve more precise valve control.

[0047] In the specific implementation process of the opening calculation module, the historical flow, pressure, temperature and flow direction data are first analyzed by the short-term trend prediction unit to calculate the target opening within a short time scale. This unit receives the feature vector output by the feature extraction module and uses a multi-order regression model to analyze the change trend of the data to ensure that the prediction result can reflect the dynamic characteristics of the system. The historical data regression analysis uses recursive linear regression or exponential smoothing regression methods to fit the data in multiple time steps, construct a trend curve, and then predict the optimal opening value at the current moment. For example, in the recursive linear regression process, based on the flow and pressure change trends in the past several time steps, the influence coefficients of each variable on the valve opening are calculated, and a regression equation is established to calculate the optimal opening setting value at the current moment. In the exponential smoothing regression method, recent data points are given higher weights, so that the prediction results can quickly adapt to the short-term changes in fluid conditions and improve the responsiveness to the dynamic characteristics of the fluid. After determining the preliminary target opening, the value is passed as input to the real-time fluid simulation unit to further optimize the prediction results.

[0048] The real-time fluid simulation unit is used to receive the target opening calculated by the short-term trend prediction unit, and to modify the target opening through the numerical simulation calculation method in combination with the structural parameters of the reverse flow valve and the real-time operating data. The unit simulates the fluid flow characteristics under different openings based on the numerical calculation method of the finite volume method or the finite difference method, and calculates the key operating parameters, including fluid flow, pressure drop and turbulence intensity, to determine whether the predicted opening value is reasonable. In the simulation calculation process, a discretized mathematical model of fluid flow is first established, and the fluid motion equation is solved under the structural boundary conditions of the reverse flow valve to simulate the changes in fluid parameters under different valve openings. For example, under a given opening value, the flow velocity distribution of the pipe section per unit time is calculated, and the corresponding pressure loss and turbulence degree are evaluated. If the simulation results show that the predicted target opening may cause the system flow to overshoot, the pressure drop to be too large, or the turbulence intensity to exceed the preset threshold, the system needs to modify the target opening to ensure that it meets the physical constraints. The correction strategy can adjust the opening change range according to the fluid load in the simulation results. For example, when the fluid pressure drop is too large, the opening is appropriately increased to reduce the resistance loss, and when the turbulence intensity is too high, the opening is reduced to improve the flow stability. Finally, the corrected target opening calculated by the unit is passed as input to the opening correction unit to further optimize the accuracy of the opening adjustment.

[0049] The opening correction unit is used to receive the corrected target opening calculated by the real-time fluid simulation unit, and fine-tune the opening value in combination with the stability factor of the current working condition to improve the control accuracy and reduce the impact effect during the valve adjustment process. The unit calculates the stability index of the working condition characteristic vector to determine the change amplitude of the current fluid state, and determines the opening adjustment strategy accordingly. When the working condition changes drastically, such as the fluctuation of flow or pressure in a short period of time exceeds the set threshold, the system adopts a method of decreasing the adjustment step to make the opening adjustment process smoother, thereby avoiding oscillation or over-adjustment of the system due to the predicted sudden change of the opening. When the working condition tends to be stable, that is, the fluctuation amplitude of the fluid parameters is within the normal range, the system adopts a weighted smoothing adjustment strategy to gradually reduce the adjustment amplitude of the target opening, so that it is more in line with the natural adjustment trend of the fluid system. For example, during the valve adjustment process, if it is detected that the fluid state has tended to be stable, the opening adjustment amplitude is exponentially attenuated to make the final output target opening smoother, so as to reduce the mechanical loss caused by frequent adjustments. After the above optimization, the preliminary target opening output by the unit is used as the final prediction value and passed to the adaptive correction module to further improve the prediction accuracy and achieve more precise valve control.

[0050] Furthermore, the adaptive correction module includes an error calculation unit, a weight optimization unit and a dynamic compensation unit; The error calculation unit is used to receive the output of the opening calculation module, and obtain the actual valve opening and fluid condition feedback data, and calculate the prediction error; the error calculation includes opening deviation, flow error and pressure error, wherein the opening deviation is calculated by comparing the target opening with the actual opening, and the flow error and pressure error are evaluated based on the deviation between the real-time collected data and the calculated value of the prediction model, and the error index is calculated by comprehensive weighting as the input for subsequent optimization; The weight optimization unit is used to adaptively adjust the weights of various calculation methods in the opening calculation module based on the error index; when the flow error and pressure error are large, the weight of the real-time fluid simulation method is increased to enhance the adaptability to the current working conditions; when the opening deviation is mainly caused by the instability of the short-term trend prediction, the weight of the historical data regression analysis is increased to optimize the accuracy of the trend prediction, thereby realizing dynamic adjustment of the weight based on the error distribution; The dynamic compensation unit is used to correct the preliminary target opening according to the optimized weight and generate the final valve opening prediction value; when the error index continuously exceeds the set threshold, an adaptive step adjustment strategy is adopted to avoid large-scale adjustments that cause system oscillations; when the error index tends to be stable, the adjustment amplitude is gradually converged to make the predicted opening change smoothly.

[0051] In the process of implementing the adaptive correction module, the error calculation unit first receives the preliminary target opening generated by the opening calculation module, and obtains the valve opening after the actual adjustment of the actuator and the real-time collected fluid working condition feedback data, including flow and pressure. In order to accurately measure the prediction error, the unit calculates the opening deviation, flow error and pressure error respectively. The opening deviation is determined by comparing the numerical difference between the target opening and the actual execution opening, and is used to evaluate the consistency between the predicted value and the execution value. The flow error and pressure error are calculated based on the deviation between the data collected by the real-time sensor and the predicted value calculated by the opening calculation module. Specifically, the difference between the measured flow and the predicted flow per unit time is calculated, and the deviation between the measured pressure and the predicted pressure is also calculated. In order to improve the integrity of the error evaluation, the error index is comprehensively calculated, and the opening deviation, flow error and pressure error are weighted and combined, so that the influence weight of different error factors on the overall correction can be dynamically adjusted according to the actual operating status, and the error index is used as the input for subsequent optimization.

[0052] After the error calculation is completed, the weight optimization unit adaptively adjusts the weights of each calculation method in the opening calculation module based on the size and distribution of the error index. When the flow error and pressure error are large, it means that the fluid working condition may undergo a sudden change or nonlinear change. At this time, it is necessary to enhance the influence of the real-time fluid simulation method, increase the weight of the simulation model, and make the calculation result more dependent on the physical constraints of the current working condition to improve the prediction accuracy and avoid the accumulation of errors caused by changes in working conditions. On the contrary, when the main error comes from the opening deviation and the flow and pressure errors are small, it means that there is a large instability in the short-term trend prediction. At this time, the weight of the historical data regression analysis is increased to make the prediction more dependent on the past working condition change trend to optimize the short-term prediction accuracy. The weight optimization process is dynamic. The system will recalculate the error index in each calculation cycle and adjust the weight distribution according to the distribution of the error, so as to ensure that the prediction method can be adaptively optimized with the changes in the fluid working condition and achieve the gradual convergence of the prediction error.

[0053] After the weight optimization is completed, the dynamic compensation unit corrects the preliminary target opening according to the optimized weight to generate the final valve opening prediction value. The correction process is based on the changing trend of the error index. When the error index exceeds the set threshold in multiple continuous calculation cycles, it indicates that the current prediction model cannot effectively follow the changes in working conditions. At this time, the adaptive step adjustment strategy is adopted to increase the correction amplitude to speed up the adjustment of the target opening so as to converge to a reasonable range as soon as possible and avoid the system being in a deviation state for a long time and affecting the fluid regulation accuracy. On the contrary, when the error index tends to be stable, it means that the prediction model has basically adapted to the current working conditions. At this time, the adjustment amplitude is gradually converged to make the change of the opening correction smoother, reduce the system oscillation caused by frequent adjustments, and improve the stability of valve control. Finally, the unit outputs the optimized target opening and transmits it to the valve actuator to achieve precise adjustment of the reverse flow valve, so that the valve opening adjustment process not only considers the historical trend, but also can dynamically adapt to the changes in real-time working conditions, thereby improving the overall control accuracy and stability of the system.

[0054] Step S103: using a fuzzy rule base based on the relationship between flow, pressure and valve opening, the initial target valve opening is adjusted in real time to obtain a final target valve opening.

[0055] In step S103, the initial target valve opening calculated in step S102 needs to be further adjusted in real time to adapt to the dynamic changes of complex working conditions and improve the accuracy and stability of valve regulation. This adjustment process relies on a fuzzy rule base, which is established based on the relationship between flow, pressure and valve opening, and can comprehensively consider multiple factors and perform adaptive optimization adjustments. The fuzzy control method has a good effect in processing nonlinear and highly uncertain systems, and is particularly suitable for reverse flow valve control scenarios with large fluctuations in fluid working conditions.

[0056] First, according to the real-time data input from the sensor, the collected fluid flow, pressure and current valve opening are used as input variables of the fuzzy control system. In order to improve the response speed and robustness of the system, all input variables need to be normalized to meet the calculation requirements of fuzzy control. For example, a standardized interval can be defined for flow, pressure and opening respectively, and the raw data can be mapped to the range required by the fuzzy control rule base through linear transformation or empirical formula. In addition, in order to prevent the influence of data jitter or short-term outliers on control decisions, sliding mean filtering, median filtering or exponential weighted filtering can be used to smooth the input data, thereby enhancing the stability of control.

[0057] After the input variables are processed, it is necessary to define fuzzy membership functions to represent the semantic relationship between different fluid parameters in the control system. For example, flow can be divided into three levels: "low", "medium", and "high", pressure can be divided into three levels: "low pressure", "normal", and "high pressure", and valve opening can be divided into four levels: "closed", "small opening", "medium opening", and "large opening". The fuzzy membership of each input variable is determined by the set membership function. Common membership function types include triangular function, Gaussian function, and trapezoidal function. The specific selection can be optimized based on empirical data or experimental tests.

[0058] In the process of building a fuzzy rule base, it is necessary to set a set of control rules in combination with fluid dynamics characteristics and practical application experience. For example, when the flow rate is high and the pressure is in the normal range, the system may need to increase the valve opening appropriately to reduce flow resistance, while when the flow rate is low and the pressure is high, the opening may need to be reduced to avoid fluid backflow. The construction of the rule base can adopt the expert system method, that is, experienced engineers set rules based on experimental data and practical experience, or adopt a data-driven method to train the fuzzy inference system through historical operation data to automatically optimize the fuzzy rule set.

[0059] In the fuzzy reasoning process, fuzzy logic operations are used to perform fuzzy reasoning calculations on the input variables to obtain the adjusted opening adjustment amount. Common reasoning methods include Mamdani-type reasoning and Sugeno-type reasoning. Mamdani-type reasoning obtains output results through fuzzy set operations and is more suitable for control systems that require strong interpretability, while Sugeno-type reasoning is suitable for scenarios with large computational complexity and high real-time requirements. The calculated opening adjustment amount is usually a fuzzy value and needs to be defuzzified to obtain the specific final target valve opening. Defuzzification methods include the maximum membership method, the weighted average method, and the center average method. The weighted average method is more commonly used and can comprehensively consider the influence of all fuzzy outputs, making the final opening adjustment smoother and more stable.

[0060] After the final target valve opening is calculated, the adjustment result needs to be constrained to ensure the stability of the control system. For example, if the change in the valve opening after adjustment exceeds the preset safety range, a gradual adjustment method can be used to limit the maximum step size of a single adjustment to prevent the system from oscillating or overshooting. In addition, an adaptive adjustment mechanism can be introduced to dynamically optimize the fuzzy rule base based on historical control effects to improve control accuracy and response speed.

[0061] The specific implementation steps of step S103 are described below by way of example: In an industrial fluid pipeline system, the reverse flow valve is responsible for controlling the flow and preventing backflow. The system's goal is to maintain the outlet flow at 500 L / min while ensuring that the downstream pressure is stable at 0.8 MPa. To achieve this goal, the sensor collects the flow, pressure, temperature and flow direction data of the fluid in real time, and calculates the initial target valve opening through the previous step. For example, under the current fluid working conditions, the prediction model calculates the initial target opening to be 60%. However, since the fluid system may be disturbed by factors such as upstream flow fluctuations, pipeline pressure changes, or temperature affecting viscosity, directly executing according to the initial target opening may cause flow or pressure overshoot, so further real-time adjustments are required to ensure optimal control of the valve.

[0062] When the system detects that the outlet flow is 480 L / min, which is lower than the target value, and the downstream pressure is 0.85 MPa, which is higher than the set 0.8 MPa, the valve opening needs to be corrected. According to the control strategy, when the flow is low but the pressure is high, it may mean that the current valve opening is too small, and the opening needs to be increased to increase the flow. At the same time, fluctuations caused by excessive pressure should be avoided, so the adjustment range cannot be too large. The fuzzy rule base will give adjustment suggestions based on this situation. For example, under the current conditions, a moderate increase in the opening can improve the problem of insufficient flow without causing a sharp increase in downstream pressure. After calculation, it was finally decided to increase the valve opening from 60% to 63%. After this adjustment is completed, the system continuously monitors the changes in flow and pressure. If it still deviates from the target value, it will continue to optimize in the next adjustment so that the system will eventually stabilize within the target flow and pressure range.

[0063] During the entire adjustment process, the control system will continuously calculate the error based on the real-time data of the sensor, and dynamically optimize it in combination with fuzzy rules, so that the valve opening gradually tends to the optimal value. As the flow and pressure change, the system continues to adjust to ensure the stability and precise control of the fluid delivery process, and avoid shock or delay caused by excessive adjustment. In this way, the reverse flow valve can adapt to different fluid conditions, automatically adapt to changes in the external environment, improve the adjustment accuracy, and ensure the reliable operation of the system.

[0064] Furthermore, the fuzzy rule base based on the relationship between flow, pressure and valve opening is used to adjust the initial target valve opening in real time to obtain the final target valve opening, including: Construct a fuzzy rule base, establish the corresponding relationship between flow, pressure and valve opening according to historical operating data, and set fuzzy input variables, including flow deviation, pressure deviation and opening change rate, to define control rules under different operating conditions; The membership degree is calculated based on the current working condition data, the input variables are fuzzified by fuzzy reasoning method, and the fuzzy membership degree of flow, pressure and opening is calculated to determine the matching degree of the input variables in the fuzzy rule base, and the fuzzy control output is calculated; Perform real-time adjustment, calculate the adjusted target opening through the defuzzification method, and optimize the adjustment range in combination with the valve response characteristics. When the fluid operating conditions fluctuate slightly, a smooth adjustment strategy is adopted to ensure stability. When the operating conditions change drastically, adaptive gain adjustment is adopted to enhance the adjustment accuracy. Finally, the optimized final target valve opening is output to ensure that the valve adjustment effect is accurately matched with the fluid operating conditions.

[0065] In the process of using the fuzzy rule base based on the relationship between flow, pressure and valve opening to adjust the initial target valve opening in real time to obtain the final target valve opening, it is necessary to first establish a complete fuzzy control system to adapt to the dynamic changes under different fluid working conditions. The core of the system is the fuzzy rule base, which is built based on historical working condition data and experimental data. By long-term monitoring of the opening response characteristics of the reverse flow valve under different flow, pressure and temperature conditions, the nonlinear relationship between fluid characteristic changes and valve regulation is analyzed. On this basis, fuzzy input variables are defined, including flow deviation, pressure deviation and opening change rate, and these input variables are divided into different fuzzy sets, such as "low", "medium", "high" or "negative large", "negative small", "zero", "positive small", "positive large", to more accurately describe the mapping relationship between fluid working conditions and valve adjustment. Subsequently, based on experimental analysis and empirical rules, fuzzy control rules between input variables and opening adjustment are formulated to ensure that the control system can adapt to the dynamic changes of fluid working conditions.

[0066] In the real-time adjustment process, it is first necessary to calculate the membership of the current operating condition data in the fuzzy rule base, that is, to fuzzify the flow deviation, pressure deviation and opening change rate so that the corresponding membership values ​​in the fuzzy set can be used for fuzzy reasoning calculation. The flow deviation is calculated by measuring the difference between the current flow value and the target flow value. If the deviation is large, the system should make corresponding adjustments to reduce the error between the valve opening and the target opening. The pressure deviation is calculated in a similar way, that is, by measuring the deviation between the current pressure value and the predicted pressure value, it is determined whether the current operating condition is in a stable state. The calculation of the opening change rate is based on the change amplitude of the current opening compared with the previous time step. If the change rate is too fast, it may be necessary to reduce the adjustment amplitude to prevent system oscillation. When the change rate is low or the system responds slowly, it may be necessary to increase the adjustment intensity to speed up the convergence speed. After the fuzzification results of these input variables are input into the fuzzy reasoning system, the system performs reasoning calculations based on the fuzzy rule base, comprehensively calculates the influence weights of different input variables, and outputs the fuzzy control adjustment amount to obtain the fuzzy control output result.

[0067] After obtaining the fuzzy control output, real-time adjustment needs to be performed to obtain the final target valve opening. The defuzzification method is used to convert the fuzzy control output value into a specific numerical adjustment amount, and the adjustment strategy is optimized in combination with the dynamic response characteristics of the valve. The defuzzification method can adopt the weighted average defuzzification method, that is, the target adjustment value is weighted and calculated according to the membership of different fuzzy rules to ensure that the adjusted opening change meets the fluid working condition requirements. When performing adjustments, it is necessary to consider the optimization adjustment strategy under different working conditions. For example, when the system detects that the fluid working condition fluctuates slightly, in order to maintain the stability of the valve, a smooth adjustment strategy is adopted to make the valve adjustment process more gentle to reduce unnecessary fluctuations. When the system detects that the fluid working condition has changed dramatically, such as a sharp increase or decrease in flow or pressure in a short period of time, an adaptive gain adjustment strategy is adopted to dynamically adjust the valve response rate to ensure that the regulation system can quickly adapt to sudden changes and improve the regulation accuracy. In addition, during the real-time adjustment process, the control signal of the valve actuator needs to be dynamically optimized to ensure the smoothness of the valve adjustment action, prevent overshoot or system oscillation, and ultimately achieve precise valve opening control, so that the valve adjustment effect is accurately matched with the fluid working conditions, and improve the overall stability and response speed of the system.

[0068] Step S104: According to the final target valve opening, controlling the actuator to adjust the operating state of the reverse flow valve.

[0069] In step S104, the actuator needs to be precisely controlled based on the final target valve opening to adjust the operating state of the reverse flow valve so as to achieve the expected fluid regulation effect. The actuator, as a driving device for the valve, may include electric actuators, pneumatic actuators or hydraulic actuators, and the specific selection depends on the application scenario and control requirements. For electric actuators, stepper motors or servo motors are generally used to adjust the angle or linear displacement of the valve by receiving control signals. Pneumatic actuators usually drive pistons through compressed air to open and close or precisely adjust the valve, while hydraulic actuators use liquid pressure to control the valve opening, which is suitable for high-pressure conditions or fine adjustment of large-diameter valves.

[0070] When controlling an actuator, the final target valve opening must first be converted into a control signal suitable for the actuator. For electric actuators, the control signal is usually a pulse signal or an analog voltage signal. The pulse signal is used to drive a stepper motor or servo motor, and the analog voltage signal is used to control the linear change of the opening. For pneumatic actuators, the control signal is generally adjusted by an electrical proportional valve to control the air pressure and achieve precise opening control. Hydraulic actuators usually adjust the hydraulic pressure through a proportional solenoid valve or a servo valve to accurately control the change in valve opening.

[0071] In the process of executing the control signal, the response characteristics of the actuator and the inertia characteristics of the valve need to be considered to avoid oscillation or overshoot problems during the adjustment process. For example, the stepper motor of the electric actuator may be affected by load changes during the driving process, and an acceleration and deceleration strategy needs to be adopted during the control process to smoothly adjust the opening. For pneumatic actuators, due to the compressibility of compressed air, hysteresis may occur during rapid response, so the control accuracy can be improved by introducing feedback control or pressure compensation mechanism. For hydraulic actuators, hydraulic shock needs to be avoided to prevent the valve from vibrating violently during high-speed adjustment. Buffer circuits or flow control valves can be used to optimize hydraulic flow.

[0072] In the process of valve adjustment, feedback control is an important means to ensure execution accuracy and stability. The actuator is generally equipped with a position sensor or opening feedback device, such as a potentiometer, optical encoder or LVDT displacement sensor, to monitor the actual opening of the valve in real time, and compare the measured opening value with the target opening. If there is a deviation, the output of the actuator is adjusted through closed-loop control to gradually approach the target opening. The closed-loop control strategy can adopt PID control, and the optimization of PID parameters can be combined with an adaptive adjustment algorithm to adapt to different working conditions and ensure that the valve can still maintain precise control in a dynamic environment.

[0073] In the process of adjusting the valve opening by the actuator, the influence of external environmental factors on the control effect also needs to be considered. For example, in high or low temperature environments, the mechanical part of the actuator may affect the control accuracy due to thermal expansion and contraction, the pneumatic system may affect the action sensitivity due to the accumulation of condensed water due to excessive air humidity, and the hydraulic system may affect the response speed due to changes in oil viscosity due to temperature changes. Therefore, in practical applications, the temperature and humidity can be monitored through environmental sensors, and compensation mechanisms can be introduced into the control algorithm to optimize the control effect.

[0074] In order to further improve the reliability of valve regulation, fault detection and protection mechanisms can also be introduced. For example, when an actuator abnormality is detected, such as motor stalling, insufficient air source pressure, or hydraulic system leakage, the system can automatically adjust the control strategy and enter a safe mode to prevent valve malfunction or abnormal operation of the fluid system due to control failure. In addition, redundant control units or dual sensors can be integrated on the actuator to provide backup control paths and improve the overall reliability of the system.

[0075] During the entire control process, by converting the final target valve opening into the control signal of the actuator, combined with closed-loop feedback control and fault detection protection mechanism, precise adjustment of the reverse flow valve can be achieved to ensure stable operation of the fluid system and meet the adjustment requirements under different working conditions.

[0076] Furthermore, controlling the actuator to adjust the operating state of the reverse flow valve according to the final target valve opening includes: Analyze the final target valve opening, and calculate the control signal of the actuator according to the target opening value and the current valve state, including the valve opening change, execution time and execution rate, to ensure that the control signal meets the physical constraints of the valve and is optimally adjusted within the control range; Dynamically compensate execution error. Based on the real-time feedback of valve opening position, actuator operation response and fluid working condition changes, the actual execution error is calculated. When the error exceeds the set threshold, the execution signal is adjusted, including compensating for execution time deviation and optimizing execution torque to ensure the accuracy of valve opening adjustment. Optimize the control response strategy, combine the historical data of valve opening adjustment, adaptively adjust the amplitude and response time of the control signal, when the fluid working condition is stable, adopt a smooth adjustment strategy to reduce system impact, when the working condition fluctuates greatly, improve the execution response rate, enhance the system's rapid adjustment ability, and ensure the operating stability and adjustment accuracy of the reverse flow valve under different working conditions.

[0077] In the process of controlling the actuator to adjust the operating state of the reverse flow valve according to the final target valve opening, it is first necessary to analyze the final target valve opening to generate a control signal suitable for the actuator. The calculation of the control signal not only needs to consider the target opening value, but also needs to be combined with the actual state of the current valve to ensure that the adjustment process meets the physical constraints of the valve and avoid exceeding the mechanical limit of the valve or causing control instability. The main parameters of the control signal include the change in valve opening, execution time, and execution rate. The change in valve opening determines the current adjustment range of the opening, the execution time is used to control the duration of the actuator's action, and the execution rate affects the speed of the valve response. When the difference between the target opening and the current opening is small, in order to maintain the smooth operation of the fluid system, a small step and low rate adjustment strategy should be adopted to make the valve gradually approach the target opening; when the difference between the target opening and the current opening is large, it is necessary to combine the working conditions and increase the execution rate under the premise of ensuring system stability to ensure that the fluid working conditions can adapt to the adjusted valve state in time.

[0078] During the valve execution process, due to the nonlinear characteristics of the actuator and the dynamic changes of the fluid environment, execution errors may occur, that is, there is a deviation between the actual adjusted valve opening and the expected opening. Therefore, it is necessary to calculate and compensate for the execution error based on the real-time feedback of the valve opening position, the operating response of the actuator, and the changes in the fluid working conditions. When it is detected that the execution error exceeds the set threshold, the system needs to adjust the control signal to compensate for the execution time deviation and optimize the execution torque so that the valve can reach the target opening more accurately. For example, when the actuator lags in opening adjustment due to inertia, the execution time can be increased or the signal amplitude can be adjusted to make the actuator more responsive; if the valve adjustment amplitude is too large due to fluid impact, the gain of the execution signal can be reduced and the execution torque can be optimized to prevent overshoot and ensure the accuracy of the valve opening adjustment.

[0079] When controlling the actuator to adjust the operating state of the reverse flow valve, it is also necessary to optimize the control response strategy to ensure the stability and efficiency of the valve adjustment process. The system needs to combine the historical data of valve opening adjustment and adaptively adjust the amplitude and response time of the control signal according to different working conditions. When the fluid working condition is relatively stable, a smooth adjustment strategy should be adopted to make the valve adjustment process as smooth as possible to reduce the impact of drastic changes on the system; when the working condition fluctuates violently, it is necessary to increase the execution response rate so that the valve can quickly adapt to the new fluid state. For example, when the flow or pressure changes suddenly, the system should speed up the valve adjustment speed so that the fluid state can return to stability as soon as possible; when the flow and pressure fluctuations are small, the adjustment rate can be appropriately reduced to reduce the load of the actuator and extend the service life of the equipment. Finally, by optimizing the control response strategy, the reverse flow valve can maintain stable operation under different fluid working conditions and have strong adaptive ability, thereby improving the overall adjustment accuracy and ensuring the operation stability of the fluid system.

[0080] Furthermore, the reverse flow valve intelligent adjustment method based on the adaptive control algorithm further includes: Within a preset time period after the valve opening is adjusted, the flow, pressure and temperature data at the inlet and outlet of the counterflow valve are continuously collected, and the actual working condition changes are compared with the predicted working condition data in real time to calculate the working condition error; based on the working condition error, the actual control effect of the real-time adjustment of the valve opening is determined, and the rule entries corresponding to the current working condition in the fuzzy rule library and their adjustment strategies are identified to be reasonable; When the operating error exceeds the preset threshold, the corresponding control rules of the fuzzy rule base are modified to optimize the subsequent real-time adjustment strategy of the valve opening.

[0081] In this embodiment, after implementing the real-time adjustment of the reverse flow valve opening, it is necessary to further conduct refined tracking evaluation and dynamic optimization of the control effect to ensure long-term high-precision control performance. Specifically, after the actuator completes the real-time adjustment of the valve opening according to the final target valve opening, it enters a continuous data monitoring stage, which has a pre-set fixed time period, such as 5 seconds, 10 seconds or other cycle lengths suitable for specific application scenarios. During this preset time period, the system needs to continuously collect the actual flow, pressure and temperature data of the current fluid in real time through sensors installed at the inlet and outlet of the reverse flow valve, and record the collected data in the real-time data storage unit to ensure the continuity and integrity of data collection.

[0082] After collecting the above-mentioned real-time operating data, the system also needs to use the predicted operating data calculated by the above-mentioned operating condition opening prediction model to perform synchronous point-by-point real-time comparison. Specifically, the system will perform difference calculations on the recorded actual flow, pressure and temperature data with the initial predicted operating condition data (or the ideal operating condition data predicted by the previous adjustment), such as calculating the numerical values ​​of flow error, pressure error and temperature error, and evaluating the degree of fit between the prediction and the actual through the error size, so as to obtain the real-time error parameters of the current control condition. The specific calculation of the operating condition error can be performed by relative error, absolute error or root mean square error (RMSE) and other methods. For example, the flow error can be expressed as (predicted flow-actual flow) / predicted flow×100%. Through these error values, it is possible to intuitively judge the pros and cons of the real-time adjustment of the current valve opening on the improvement of the actual operating condition. The smaller the error, the better the control effect.

[0083] After obtaining the above-mentioned working condition error value, the system further evaluates the control effect, that is, through a pre-set evaluation index system, the actual control effect of the real-time adjustment of the valve opening is clarified. The control effect evaluation index may include multi-dimensional parameters such as flow stability, pressure fluctuation amplitude, and system response speed. By comparing with the predicted data, the system can clarify whether the rule items and adjustment strategies corresponding to this working condition adjustment in the currently used fuzzy rule library are reasonable and effective. For example, if the actual measured flow deviates significantly from the target value and the pressure fluctuation increases significantly after the valve opening of a certain rule is increased, it can be inferred that the adjustment strategy corresponding to the rule may be defective or need to be corrected; on the contrary, if the flow and pressure quickly approach the target value and remain stable, the rule item can remain unchanged and continue to be applied.

[0084] When the evaluation result of the above working condition error shows that the error exceeds the preset threshold set by the system (for example, the relative error exceeds the set 5% or other specific thresholds), it means that the relevant rule entries in the fuzzy rule base can no longer meet the current working condition requirements, and there may be problems such as too large or too small adjustment range. In this case, the system automatically enters the rule base correction program, and appropriately corrects or optimizes the fuzzy set, membership function shape, rule reasoning weight or adjustment range parameters of the rule output of the corresponding rule entry in the rule base to improve the adaptability of the rule base to the actual working condition. The specific implementation of the rule base correction can adopt the method of adding, deleting or adjusting the weight of fuzzy control rules. For example, for the rules that cause excessive opening adjustment, reduce the rule output; for the rules with insignificant adjustment effect, the output can be appropriately increased or the coverage of the membership function can be adjusted to improve the overall adaptability and control accuracy of the system.

[0085] After the above rule base is corrected, the system automatically updates and reloads the corrected fuzzy rule base for the next round of real-time adjustment of the valve opening, thereby continuously iterating and optimizing to achieve dynamic, long-term, stable and accurate control of the reverse flow valve operation state. The method of the present invention continuously improves the valve adjustment accuracy and adaptive ability through the closed-loop feedback mechanism of the above working condition tracking, real-time error evaluation and dynamic rule correction, and ultimately achieves a more accurate and reliable fluid control effect.

[0086] Furthermore, when the operating error exceeds a preset threshold, the corresponding control rule of the fuzzy rule base is modified to optimize the subsequent real-time adjustment strategy of the valve opening, including: Based on historical operating condition data, by establishing an operating condition change trend identification model, the correlation between the operating condition change trend and the effectiveness of rule adjustment within a certain time window is calculated, and a rule adjustment factor is dynamically generated according to the correlation; wherein the rule adjustment factor is determined by the following formula 1: ; in, is the rule adjustment factor; The total number of data points for historical operating condition data analysis; Respectively represent the history The difference between the flow rate, pressure, temperature and their respective target values ​​at each data point; For the history The difference between the actual adjustment amount of the valve opening corresponding to the data point and the predicted adjustment amount; Respectively represent the weighted coefficients of flow, pressure, and temperature for the overall operating conditions, satisfying ; is a very small positive constant to prevent the denominator from being zero; When the rule adjustment factor If it is greater than the preset threshold, it indicates that the current fuzzy rule has obvious deviations in actual control. The output amplitude or rule confidence of the corresponding rule in the fuzzy rule base is updated to make the next valve opening adjustment closer to the actual working conditions.

[0087] In this embodiment, the control rules of the fuzzy rule base need to be optimized to adapt to the changes in real-time working conditions and improve the adjustment accuracy. Specifically, when the calculated working condition error exceeds the preset threshold, it is necessary to first build a working condition change trend recognition model through historical working condition data, and use mathematical analysis methods to calculate the correlation between the working condition change trend and the effectiveness of rule adjustment within a certain time window. This correlation is used to generate the rule adjustment factor , thereby deciding whether the fuzzy rule base needs to be modified. The rule adjustment factor is calculated using formula (1): ; The formula is used to measure the influence of various working parameters in historical data on the door opening adjustment, and the calculated Evaluate the effectiveness of the current fuzzy rule base to decide whether to modify it.

[0088] In formula (1), the rule adjustment factor It reflects whether the trend of valve opening adjustment in historical data points is consistent with the change of operating parameters. Significant deviation from 1 (e.g. is greater than the preset threshold 2), which means that the valve opening adjustment strategy may not match the actual working conditions, so the rule base needs to be adjusted to optimize the subsequent control strategy.

[0089] parameter Represents the total number of data points for historical data analysis. It is usually set by the system as a fixed window, such as 100 or 500, to ensure the stability of statistical analysis. The choice of window size needs to balance real-time and data volume. Smaller window sizes are more suitable. It can improve the response speed, but may cause larger fluctuations. This can enhance robustness but may delay the triggering of adjustments.

[0090] variable Respectively represent The error change of flow, pressure and temperature of each historical data point is calculated as follows: ; in, Respectively The actual flow, pressure and temperature collected from historical data points, is the target value under this condition, which can be set according to empirical data or specific reverse flow valve adjustment requirements. The above calculation results in the deviation of each data point relative to the target value. The size and direction of the deviation are used to measure the degree of deviation of the system operation status.

[0091] variable Representative The valve opening adjustment error for each data point is calculated as follows: ; in, is the actual valve opening of the data point. is the target opening given by the prediction model under this condition. If it is too large, it means that the adjustment strategy of the control actuator fails to accurately match the system requirements, and the control rules may need to be optimized.

[0092] variable is the weighted coefficient of the importance of the operating parameters, which is used to measure the influence of flow, pressure and temperature on the valve opening adjustment under the current operating conditions. Their sum always satisfies: ; The specific value of the weighting coefficient can be set based on experience. For example, in a system where flow control is the main goal, can be set to 0.5, while the weights of pressure and temperature can be set to 0.3 and 0.2 respectively. If the system is mainly affected by pressure fluctuations, you can increase The value of .

[0093] The sum of squares term in the denominator: ; Used to normalize the error margin to prevent a certain variable from having an extreme impact on the calculation result. Similarly, another square root term: ; The calculation denominator used to prevent valve adjustment errors is zero, where is a very small positive number (e.g. ) to avoid division by zero errors in mathematical calculations.

[0094] when The calculated value of is significantly greater than 1 (for example When it is greater than the preset threshold 2), it indicates that the valve opening after the system adjustment deviates greatly from the target operating condition, and the control strategy fails to accurately match the actual demand, so the fuzzy rule base needs to be adjusted. The adjustment method includes increasing or decreasing the output amplitude of the rule, or adjusting the confidence of the rule. For example, if the adjustment of a certain rule causes flow overshoot, the output amplitude of the rule can be reduced to reduce the radical degree of the opening adjustment; if the adjustment of a certain rule is not enough to correct the deviation, the output weight of the rule can be increased to make it play a greater role in the control strategy.

[0095] During the next operating condition adjustment, the system uses the updated fuzzy rule base for control, so that the valve opening adjustment is more in line with the actual needs of the fluid working conditions, thereby optimizing the regulation accuracy of flow, pressure and temperature, and improving the long-term stability of the system.

[0096] A second embodiment of the present application provides an electronic device, the electronic device comprising: processor; The memory is used to store a program. When the program is read and executed by the processor, it executes an intelligent adjustment method for a reverse flow valve based on an adaptive control algorithm provided in the first embodiment of the present application.

[0097] The third embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, an intelligent adjustment method for a reverse flow valve based on an adaptive control algorithm provided in the first embodiment of the present application is executed.

[0098] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. A reverse flow valve intelligent adjustment method based on an adaptive control algorithm, characterized in that: include: Obtaining fluid flow, pressure, temperature and flow direction data collected by sensors installed at the inlet and outlet of the reverse flow valve; Based on the acquired fluid data and the structural parameters of the reverse flow valve, the initial target valve opening under the current fluid working condition is predicted using the working condition opening prediction model; Using a fuzzy rule base based on the relationship between flow, pressure and valve opening, the initial target valve opening is adjusted in real time to obtain a final target valve opening; According to the final target valve opening, the actuator is controlled to adjust the operating state of the reverse flow valve.

2. The intelligent adjustment method of reverse flow valve based on adaptive control algorithm according to claim 1 is characterized in that: Also includes: Within the preset time period after the valve opening is adjusted, the flow, pressure and temperature data at the inlet and outlet of the counter-flow valve are continuously collected, and the actual working condition changes are compared with the predicted working condition data in real time to calculate the working condition error; According to the working condition error, determine the actual control effect of the real-time adjustment of the valve opening, and identify whether the rule entry corresponding to the current working condition and its adjustment strategy in the fuzzy rule base are reasonable; When the operating condition error exceeds the preset threshold, the corresponding control rules of the fuzzy rule base are modified to optimize the subsequent real-time adjustment strategy of the valve opening.

3. The intelligent adjustment method of reverse flow valve based on adaptive control algorithm according to claim 1 is characterized in that: The method of obtaining the fluid flow rate, pressure, temperature and flow direction data collected by sensors disposed at the inlet and outlet of the reverse flow valve includes: Dynamically adjust the data acquisition frequency of the sensor according to the change rate of flow and pressure. When the change rate exceeds the set threshold, the acquisition frequency is increased; when the change rate is lower than the set threshold, the acquisition frequency is reduced; Store a predetermined amount of historical flow, pressure, temperature and flow direction data, and compare it with the historical data every time new data is collected. When the new data deviates from the set range of historical data, it is marked as abnormal data and the data is corrected; Based on the structural parameters and historical data of the reverse flow valve, the flow direction data is compensated. When the flow direction data changes suddenly and is accompanied by a significant change in the valve opening, the compensation factor is calculated and the current flow direction data is adjusted.

4. The intelligent adjustment method of reverse flow valve based on adaptive control algorithm according to claim 3 is characterized in that: The method stores a predetermined amount of historical flow, pressure, temperature and flow direction data, and compares the data with the historical data each time new data is collected. When the new data deviates from the set range of the historical data, it is marked as abnormal data and the data is corrected, including: Preset data storage window. During each data collection, the latest flow, pressure, temperature and flow direction data are stored in the window. The window length is set according to time or data capacity so that the data in the window can reflect the current working condition trend. Calculate data distribution characteristics based on historical data in the storage window, including data mean, variance and change trend. When the deviation of the newly collected data value from the mean of historical data exceeds the set threshold, or the data change trend is significantly inconsistent with the historical trend, mark the data as abnormal data. Correct the data marked as abnormal. When the abnormal data is in a short-term mutation state and no continuous abnormality occurs, use interpolation or historical mean to correct it. When the abnormal data shows a continuous deviation trend, determine whether it is caused by sensor drift or environmental influence, and compensate based on the related data of multiple sensors.

5. The intelligent adjustment method of reverse flow valve based on adaptive control algorithm according to claim 1 is characterized in that: The operating condition opening prediction model includes a data preprocessing module, a feature extraction module, an opening calculation module and an adaptive correction module; The data preprocessing module is used to receive flow, pressure, temperature and flow direction data, and normalize the data in combination with the structural parameters of the reverse flow valve, remove abnormal values, smooth the data through a filtering algorithm, and output optimized working condition data; The feature extraction module receives the output of the data preprocessing module, and calculates the flow-pressure change rate ratio, the fluid pressure drop gradient and the flow direction stability to construct a feature vector reflecting the current working condition, and outputs the feature vector to the opening calculation module; The opening calculation module calculates the preliminary target opening based on the output of the feature extraction module by using historical data regression analysis and real-time fluid simulation methods, wherein the historical data regression analysis is used for short-term trend prediction, and the real-time fluid simulation is combined with the reverse flow valve structural parameters to correct the predicted opening, and the calculated preliminary target opening is output to the adaptive correction module; The adaptive correction module receives the output of the opening calculation module and calculates the prediction error based on the real-time feedback data. When the error exceeds the set threshold, the parameters of the opening calculation module are adjusted and the preliminary target opening is corrected to obtain the final predicted initial target valve opening.

6. The intelligent adjustment method of reverse flow valve based on adaptive control algorithm according to claim 5 is characterized in that: The feature extraction module includes a data conversion unit, a feature calculation unit and a dynamic feature optimization unit; The data conversion unit is used to receive the output of the data preprocessing module, and perform nonlinear transformation on the normalized flow, pressure, temperature and flow direction data to enhance the data differentiation, wherein, for flow and pressure data, a piecewise logarithmic mapping function is used to differentially scale data in different ranges so that it has a higher resolution in the low value interval, and for temperature data, an exponential smoothing method is used to reduce the impact of transient changes, thereby obtaining converted data for feature calculation; The characteristic calculation unit receives the output of the data conversion unit and calculates key characteristics of the working condition, including flow-pressure change rate ratio, fluid pressure drop gradient and flow direction stability, wherein the flow-pressure change rate ratio is obtained by calculating the ratio of flow rate and pressure change rate in continuous time steps to measure the dynamic response characteristics of the fluid working condition, the fluid pressure drop gradient is calculated based on the flow rate and pipeline resistance parameters to quantify the influence of valve opening on fluid pressure, and the flow direction stability is obtained by calculating the variance of flow direction data in multiple time steps to evaluate the stability of fluid flow, and the calculated characteristic parameters are combined into a characteristic vector; The dynamic feature optimization unit is used to receive the output of the feature calculation unit and adaptively adjust the feature weight according to the historical operating data. Based on the historical operating data of the reverse flow valve, the weighted sliding average method is used to calculate the long-term change trend of each feature, and the weight of each feature in the feature vector is adjusted according to the feature change trend to enhance the characterization ability of key influencing factors, so that the generated feature vector is more suitable for the current working condition, and the optimized feature vector is output to the opening calculation module.

7. The intelligent adjustment method of reverse flow valve based on adaptive control algorithm according to claim 5 is characterized in that: The opening calculation module includes a short-term trend prediction unit, a real-time fluid simulation unit and an opening correction unit; The short-term trend prediction unit is used to analyze the change trend of historical flow, pressure, temperature and flow direction data based on the output of the feature extraction module using a multi-order regression model, and calculate the target opening within a short time scale; by constructing a recursive linear regression or exponential smoothing regression method, the trend curve is fitted using the data of multiple time steps in the past to predict the optimal opening at the current moment; The real-time fluid simulation unit is used to receive the target opening calculated by the short-term trend prediction unit, and in combination with the structural parameters of the reverse flow valve and the real-time operating data, correct the target opening through the numerical simulation calculation method; a numerical solution method based on the finite volume method or the finite difference method is used to simulate the fluid flow characteristics under different openings, and calculate the key parameters of fluid flow, pressure drop, and turbulence intensity to determine whether the preliminary predicted opening meets the current operating conditions; when the simulation results show that the predicted target opening may cause flow overshoot or excessive pressure drop, the opening value is adjusted to meet the physical constraints; The opening correction unit is used to receive the corrected target opening output by the real-time fluid simulation unit, and fine-tune the opening in combination with the stability factor of the current operating condition to improve the adjustment accuracy; by calculating the stability index of the operating condition characteristic vector, the change amplitude of the current fluid state is judged. When the operating condition changes drastically, the method of decreasing the adjustment step size is adopted to avoid the impact of the sudden change in the predicted opening on the system; when the operating condition tends to be stable, a weighted smoothing adjustment strategy is adopted to make the final target opening more in line with the natural adjustment trend of the fluid; the output preliminary target opening is used for the subsequent adaptive correction module.

8. The intelligent adjustment method of reverse flow valve based on adaptive control algorithm according to claim 5 is characterized in that: The adaptive correction module includes an error calculation unit, a weight optimization unit and a dynamic compensation unit; The error calculation unit is used to receive the output of the opening calculation module, and obtain the actual valve opening and fluid condition feedback data, and calculate the prediction error; the error calculation includes opening deviation, flow error and pressure error, wherein the opening deviation is calculated by comparing the target opening with the actual opening, and the flow error and pressure error are evaluated based on the deviation between the real-time collected data and the calculated value of the prediction model, and the error index is calculated by comprehensive weighting as the input for subsequent optimization; The weight optimization unit is used to adaptively adjust the weights of various calculation methods in the opening calculation module based on the error index; when the flow error and pressure error are large, the weight of the real-time fluid simulation method is increased to enhance the adaptability to the current working conditions; when the opening deviation is mainly caused by the instability of the short-term trend prediction, the weight of the historical data regression analysis is increased to optimize the accuracy of the trend prediction; The dynamic compensation unit is used to correct the preliminary target opening according to the optimized weight and generate the final valve opening prediction value; when the error index continuously exceeds the set threshold, an adaptive step adjustment strategy is adopted to avoid large-scale adjustments causing system oscillations; when the error index tends to be stable, the adjustment amplitude is gradually converged.

9. The intelligent adjustment method of reverse flow valve based on adaptive control algorithm according to claim 1, characterized in that: The method adopts a fuzzy rule base based on the relationship between flow, pressure and valve opening to adjust the initial target valve opening in real time to obtain the final target valve opening, including: Construct a fuzzy rule base, establish the corresponding relationship between flow, pressure and valve opening according to historical operating data, and set fuzzy input variables, including flow deviation, pressure deviation and opening change rate, to define control rules under different operating conditions; The membership degree is calculated based on the current working condition data, the input variables are fuzzified by fuzzy reasoning method, and the fuzzy membership degree of flow, pressure and opening is calculated to determine the matching degree of the input variables in the fuzzy rule base, and the fuzzy control output is calculated; Perform real-time adjustment, calculate the adjusted target opening through the defuzzification method, and optimize the adjustment range in combination with the valve response characteristics. When the fluid operating conditions fluctuate slightly, a smooth adjustment strategy is adopted to ensure stability. When the operating conditions change drastically, adaptive gain adjustment is used to enhance the adjustment accuracy, and finally the optimized final target valve opening is output.

10. The intelligent adjustment method of reverse flow valve based on adaptive control algorithm according to claim 1, characterized in that: According to the final target valve opening, controlling the actuator to adjust the operating state of the reverse flow valve includes: Analyze the final target valve opening, and calculate the control signal of the actuator according to the target opening value and the current valve state, including the valve opening change, execution time and execution rate, to ensure that the control signal meets the physical constraints of the valve and is optimally adjusted within the control range; Dynamically compensate execution error. Based on the real-time feedback of valve opening position, actuator operation response and fluid working condition changes, the actual execution error is calculated. When the error exceeds the set threshold, the execution signal is adjusted, including compensating for execution time deviation and optimizing execution torque. Optimize the control response strategy, combine the historical data of valve opening adjustment, adaptively adjust the amplitude and response time of the control signal, when the fluid working condition is stable, adopt a smooth adjustment strategy to reduce system impact, when the working condition fluctuates greatly, increase the execution response rate and enhance the system's rapid adjustment capability.

Images