Precise control method of solenoid valve based on dynamic flow regulation

Abstract

The present invention provides a precise control method for a solenoid valve based on dynamic flow regulation. The working parameters are collected in real time by sensors, the real-time working condition data of the solenoid valve is obtained, and the data is pre-processed by noise reduction and normalization to generate a comprehensive working condition feature vector. Based on the feature vector and the target output parameter, the flow, temperature and outlet pressure values ​​of the future working condition are calculated by a prediction algorithm. Combined with the calculated future working condition and real-time working condition data, an optimized control signal is generated to dynamically adjust the opening of the solenoid valve to achieve preliminary dynamic control of the flow and pressure. The outlet pressure and flow are monitored in real time through high-frequency sampling, the deviation between the actual output and the target value is calculated, and the control signal is corrected based on the deviation. The present invention is suitable for high-precision flow and pressure regulation of solenoid valves under complex working conditions, has the characteristics of fast response and high regulation accuracy, and can be widely used in the fields of environmental protection, industrial automation and fluid control.

Description

Technical Field

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

[0002] In the prior art, solenoid valves, as core components of fluid control, are widely used in the fields of industrial automation, fluid control, and environmental protection equipment. Traditional solenoid valve control methods usually rely on open-loop or closed-loop control systems with fixed parameters. These systems adjust the valve opening through simple proportional control or preset programs to achieve basic regulation of flow and pressure. At the same time, some improved schemes combine PID control algorithms to improve the adaptability to complex working conditions to a certain extent. However, most of these methods are based on the assumption of static working conditions, and the control effect under dynamic working conditions is limited.

[0003] The main problem in the existing technology is that the solenoid valve control system under dynamic and complex working conditions cannot accurately respond to rapid changes in flow and pressure. This deficiency is manifested in control delays, reduced accuracy, and poor robustness to uncertain factors. In addition, due to the lack of the ability to predict future working conditions, existing methods usually rely on real-time feedback signals for adjustment, which is difficult to meet the needs of high-frequency changing working conditions, resulting in low control efficiency and even system instability.

[0004] In order to solve the above problems, the present invention proposes a new solenoid valve control method. Summary of the invention

[0005] The present application provides a solenoid valve precise control method based on dynamic flow regulation to improve the regulation accuracy of the solenoid valve.

[0006] The present application provides a solenoid valve precise control method based on dynamic flow regulation, comprising:

[0007] The solenoid valve working parameters including ambient pressure, solenoid valve outlet pressure, flow rate and temperature are collected in real time through sensors to obtain the real-time working condition data of the solenoid valve;

[0008] Performing preprocessing including data noise reduction and normalization on the real-time operating condition data to obtain a comprehensive operating condition feature vector;

[0009] According to the comprehensive operating condition characteristic vector and the preset target output pressure value and flow value, the flow rate, temperature and outlet pressure value of the future operating condition are calculated by a prediction algorithm;

[0010] Based on the calculated flow, temperature and outlet pressure values ​​of future working conditions, combined with the real-time working condition characteristic vector, the proportional parameters, integral parameters and differential parameters of the PID control algorithm are adaptively adjusted to generate an optimized solenoid valve control signal;

[0011] Applying the optimized solenoid valve control signal to the solenoid valve to dynamically adjust the opening of the solenoid valve, thereby preliminarily realizing dynamic control of flow and pressure;

[0012] The flow and pressure at the outlet of the solenoid valve are monitored in real time through high-frequency sampling, and the actual output value monitored is compared with the target output value to calculate the control deviation;

[0013] Based on the control deviation, the control signal of the solenoid valve is corrected to accurately match the working condition requirements, thereby achieving precise dynamic control of flow and pressure.

[0014] The beneficial effects of the technical solution provided by this application include:

[0015] (1) By collecting environmental pressure, solenoid valve outlet pressure, flow rate and temperature in real time, and combining the prediction algorithm to predict future working conditions, this method can quickly adjust the control signal of the solenoid valve, significantly improving the response speed and control accuracy of the solenoid valve under complex dynamic working conditions. (2) This method uses the real-time working condition feature vector and the future working condition prediction results to adaptively adjust the proportional, integral and differential parameters of the PID control algorithm, thereby realizing accurate dynamic adjustment of the solenoid valve opening, which is suitable for complex working conditions with large uncertainty and volatility. (3) Dynamic adjustment and precise control avoid the energy waste caused by control delay and over-adjustment in traditional control methods, realize the efficient operation of the solenoid valve, help save energy and improve the overall efficiency of the system. (4) Through high-frequency sampling to monitor the actual flow rate and pressure of the solenoid valve in real time, and dynamically correct the control signal based on the control deviation, this method can effectively reduce the control error and prevent system oscillation, significantly improving the stability and long-term reliability of the control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of a solenoid valve precise control method based on dynamic flow regulation provided in the first embodiment of the present application. DETAILED DESCRIPTION

[0017] 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.

[0018] The first embodiment of the present application provides a solenoid valve precise control method based on dynamic flow regulation. 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 solenoid valve precise control method based on dynamic flow regulation and is described in detail.

[0019] Step S101: The solenoid valve operating parameters including ambient pressure, solenoid valve outlet pressure, flow rate and temperature are collected in real time by sensors to obtain real-time operating data of the solenoid valve.

[0020] In step S101, the solenoid valve operating parameters including ambient pressure, solenoid valve outlet pressure, flow rate and temperature are collected in real time by sensors to obtain real-time operating data of the solenoid valve.

[0021] First, an environmental pressure sensor and an outlet pressure sensor are arranged at the inlet and outlet of the solenoid valve respectively. The environmental pressure sensor is installed at the inlet of the solenoid valve to monitor the possible impact of the external environment on the operation of the solenoid valve. The outlet pressure sensor is installed at the outlet of the solenoid valve to measure the fluid pressure after the solenoid valve is adjusted and provide dynamic pressure data. In order to ensure the stability and accuracy of the collected data, the installation of these sensors must avoid the influence of fluid turbulence, which can be achieved by setting a pressure stabilization device before and after the sensor.

[0022] Secondly, arrange the flow sensor on the fluid channel of the solenoid valve. The flow sensor needs to have high sensitivity and low latency performance to monitor the flow changes through the solenoid valve in real time. When installing the flow sensor, ensure that it is aligned with the fluid channel to reduce fluid interference and improve measurement accuracy.

[0023] Then, place temperature sensors on or around the solenoid valve to measure the temperature changes of the fluid or working environment in real time. The temperature sensor needs to maintain good thermal contact with the fluid while avoiding the influence of external interference. The layout of the sensor needs to be combined with the actual working conditions to ensure that the temperature data can truly reflect the thermodynamic state of the fluid.

[0024] The above sensors transmit the collected ambient pressure, solenoid valve outlet pressure, flow rate and temperature data to the data acquisition device by wired or wireless means. During the data acquisition process, it is necessary to ensure that the data sampling frequency of each sensor is consistent to avoid data timing misalignment. The data acquisition device performs preliminary digital processing on the signals transmitted by the sensor, including sampling, quantization and filtering steps, to ensure that the acquired working condition data is clear and accurate.

[0025] Finally, the preliminarily processed data is output as time series data, including operating parameters such as ambient pressure, solenoid valve outlet pressure, flow rate and temperature, and each set of data is marked with a corresponding timestamp. This time series data is the real-time operating data of the solenoid valve for use in subsequent steps.

[0026] Furthermore, the solenoid valve operating parameters including ambient pressure, solenoid valve outlet pressure, flow rate and temperature are collected in real time by the sensor to obtain real-time operating data of the solenoid valve, including:

[0027] A pressure sensor is installed at the inlet of the solenoid valve to collect ambient pressure data, and a pressure sensor and a temperature sensor are installed at the outlet to collect outlet pressure and temperature data respectively;

[0028] A flow sensor is installed on the flow channel of the solenoid valve to collect real-time flow data, and the data collected by all sensors are transmitted to the data processing device through wired or wireless signals;

[0029] The ambient pressure, solenoid valve outlet pressure, flow rate and temperature data are synchronized and cleaned to generate accurate real-time operating data for subsequent steps.

[0030] First, install a pressure sensor at the inlet of the solenoid valve to collect ambient pressure data. The pressure sensor should have high sensitivity and stability, and be able to accurately reflect the ambient pressure at the inlet. The installation of the sensor needs to avoid the influence of fluid turbulence or external interference. It is recommended to set up a pressure stabilization device around the sensor, such as a pressure buffer chamber, to reduce the influence of fluid pulsation on the collection accuracy.

[0031] At the same time, a pressure sensor and a temperature sensor are installed at the outlet of the solenoid valve. The outlet pressure sensor is used to monitor the pressure changes at the outlet of the solenoid valve in real time, while the temperature sensor is used to measure the temperature of the outlet fluid. The positions of these sensors need to be accurately calibrated to ensure that the measurement data can truly reflect the actual state of the outlet fluid. The contact surface between the temperature sensor and the outlet fluid should have high thermal conductivity, and interference from external heat sources should be prevented to ensure measurement accuracy.

[0032] In addition, a flow sensor is installed on the flow channel of the solenoid valve to collect real-time flow data. The flow sensor should be well aligned with the channel to avoid improper installation that may cause fluid flow obstruction or turbulence, thereby affecting the reliability of the measurement results. For scenarios that require high-precision flow control, a differential pressure flow meter or ultrasonic flow meter can be selected to meet the requirements of real-time performance and accuracy.

[0033] All data collected by sensors are transmitted to data processing devices via wired or wireless means. The transmission path needs to ensure signal integrity, such as adding a signal amplifier in long-distance transmission, or using shielded cables with strong anti-interference capabilities to reduce noise interference. Wireless transmission needs to ensure data encryption and signal stability to avoid data loss or interference.

[0034] In the data processing device, the data collected by all sensors are first time-synchronized to align the differences in sampling time of different sensors. Time synchronization can be achieved through a unified time reference or a high-precision clock signal to ensure that all data can be compared and analyzed at the same time point.

[0035] After that, the collected ambient pressure, solenoid valve outlet pressure, flow rate and temperature data are cleaned to remove invalid data points caused by sensor errors, environmental interference or transient anomalies. Data cleaning can be achieved through simple threshold filtering, sliding average filtering or statistical methods (such as removing outliers) to ensure the smoothness and accuracy of the data.

[0036] After time synchronization and data cleaning, the data is integrated into a set of real-time operating data, including dynamic change information of ambient pressure, solenoid valve outlet pressure, flow rate and temperature. These data have time series characteristics and can provide a reliable basis for subsequent control and optimization steps.

[0037] Furthermore, the real-time acquisition of solenoid valve operating parameters including ambient pressure, solenoid valve outlet pressure, flow rate and temperature by sensors to obtain real-time operating data of the solenoid valve also includes:

[0038] The collected ambient pressure, solenoid valve outlet pressure, flow rate and temperature data are combined into real-time operating data with consistent time series, and a timestamp is added to each data point to ensure the accuracy and integrity of the data.

[0039] After collecting the ambient pressure, solenoid valve outlet pressure, flow rate and temperature data in real time, these data need to be further processed to ensure that they can accurately reflect the real-time working conditions of the solenoid valve. First, the data collected by all sensors need to be sorted and integrated according to the time series. These data come from different types of sensors. Since there may be differences in sampling frequency and data transmission, the data must be time-aligned. Time alignment is achieved through a unified time reference, such as a standard clock signal provided by the data processing system, to ensure that the data sampling time of all sensors corresponds to the same time point.

[0040] After completing the time alignment, the data of ambient pressure, solenoid valve outlet pressure, flow rate and temperature are combined into a unified data set to form a set of real-time operating data with consistent time sequence. These data are represented in the form of a matrix or time series, and each set of data points includes the values ​​of the above four physical quantities. For example, at a certain point in time, the ambient pressure recorded in the data set may be 50 kPa, the outlet pressure is 45 kPa, the flow rate is 12 cubic meters per hour, and the temperature is 25 degrees Celsius.

[0041] To ensure the accuracy and completeness of the data, each data point also needs to be marked with a timestamp. The timestamp is generated based on a unified time base and is used to record the acquisition time of each set of data. This process can be completed automatically by a data processing device, and the accuracy of the timestamp should meet the requirements of the sampling frequency. For example, if the sampling frequency is 100 Hz, the timestamp should be accurate to the millisecond level.

[0042] The introduction of timestamps can not only ensure the consistency of data, but also be used to track the dynamic changes of data in the subsequent analysis process. For example, by comparing data at different time points, the trend of the working condition of the solenoid valve can be intuitively observed, and whether the operating status of the system is stable or abnormal can be judged.

[0043] The integrated time series data also needs to undergo a simple check to ensure the integrity of each set of data. For example, check whether all data points contain the values ​​of ambient pressure, outlet pressure, flow rate and temperature, and whether the timestamps are continuous. If missing data or unreasonable time intervals are found, they can be repaired by interpolation or removal of abnormal points to ensure data quality.

[0044] Through this method, the collected ambient pressure, solenoid valve outlet pressure, flow rate and temperature data can be organized into a real-time operating condition data set with a clear structure and consistent time sequence, providing reliable input for subsequent dynamic control and optimization steps.

[0045] Step S102: preprocessing the real-time operating condition data including data noise reduction and normalization to obtain a comprehensive operating condition feature vector.

[0046] In step S102, the real-time operating condition data obtained in step S101 needs to be preprocessed, including data noise reduction and normalization, to generate a comprehensive operating condition feature vector that can characterize the current operating condition state. The specific implementation is as follows.

[0047] First, the ambient pressure, solenoid valve outlet pressure, flow rate, and temperature data collected from the sensor are subjected to noise reduction processing. The collected raw data may contain noise caused by sensor sensitivity, environmental interference, or data transmission delay. The noise reduction process uses a simple sliding average method to average multiple data points sampled continuously to filter out high-frequency noise. The size of the sliding window is set according to the sampling frequency and the dynamic response requirements of the solenoid valve. For example, when the sampling frequency is 100 Hz, 10 data points can be selected as the window length. Through sliding average, the data curve can be effectively smoothed, the main trend information can be retained, and sharp fluctuations can be eliminated.

[0048] Secondly, the data after noise reduction needs to be normalized so that the subsequent algorithms can uniformly process different physical quantities. Normalization is achieved by mapping each data to a unified numerical interval (such as between 0 and 1). Taking flow data as an example, assuming that the flow measurement range of the sensor is 0 to 100 cubic meters per hour, the current flow value is mapped to the normalized interval according to this range through linear transformation. Similarly, pressure and temperature data are mapped according to their corresponding maximum and minimum value ranges to ensure that all data have the same numerical scale. This process ensures that in the subsequent feature extraction or calculation process, the contribution of each physical quantity to the comprehensive feature will not be unbalanced due to dimensional differences.

[0049] Finally, the denoised and normalized data are combined into a multidimensional vector in the order of ambient pressure, solenoid valve outlet pressure, flow rate, and temperature, namely the comprehensive operating condition feature vector. Each dimension of the comprehensive feature vector represents the normalized value of a physical parameter and is recorded in time series to form a dynamic feature that can continuously reflect the changes in operating conditions. The feature vector is the direct input of the subsequent prediction algorithm, so it is necessary to ensure the temporal consistency and integrity of the data.

[0050] In this way, a clear and usable comprehensive operating condition feature vector can be extracted from the real-time operating condition data, laying the foundation for the subsequent precise control of the solenoid valve.

[0051] Furthermore, the real-time operating condition data is preprocessed including data noise reduction and normalization to obtain a comprehensive operating condition feature vector, including:

[0052] The real-time collected environmental pressure, solenoid valve outlet pressure, flow rate and temperature data are subjected to noise filtering, and the sliding window method is used to remove instantaneous outliers and high-frequency interference in the data to ensure the smoothness of the data;

[0053] The noise-reduced data is normalized according to the standard range set by the system, and the ambient pressure, solenoid valve outlet pressure, flow rate and temperature values ​​are mapped to the same dimension range to facilitate comparison and fusion between different physical quantities;

[0054] The multidimensional data after noise reduction and normalization are integrated into a comprehensive operating condition feature vector in chronological order, wherein the comprehensive operating condition feature vector includes real-time status values ​​of ambient pressure, solenoid valve outlet pressure, flow rate and temperature.

[0055] After collecting the raw data of ambient pressure, solenoid valve outlet pressure, flow rate and temperature in real time, these data need to be processed for noise filtering to remove possible instantaneous outliers and high-frequency interference. The noise filtering adopts the sliding window method, taking several continuously sampled data points as a window, and smoothing the data curve by calculating the average or median of the data in the window. The size of the sliding window is determined according to the dynamic response requirements of the system. For example, if the sampling frequency is 100 Hz, 10 data points can be selected as the window length, so as to maintain a sensitive response to dynamic changes while ensuring data accuracy. In this way, high-frequency sharp fluctuations and instantaneous abnormal data points are effectively smoothed or filtered, so that the processed data can better reflect the actual working conditions.

[0056] After noise reduction, the data needs to be normalized. Normalization is achieved by mapping the data of different physical quantities to the same numerical range. For example, the ambient pressure, solenoid valve outlet pressure, flow rate and temperature values ​​are all normalized to the range between 0 and 1. The normalization process requires a linear transformation based on the actual measurement range of each physical quantity and the standard range of the system. For example, assuming that the measurement range of the ambient pressure is 0 to 100 kPa, after normalization, the normalized value corresponding to 50 kPa is 0.5. Similarly, the flow rate, temperature and outlet pressure are also linearly mapped according to their respective measurement ranges. This normalization method ensures that physical quantities of different dimensions have consistent numerical weights in subsequent processing steps, avoiding deviations caused by dimensional differences.

[0057] The denoised and normalized data are integrated into a multi-dimensional comprehensive operating condition feature vector in chronological order. Each dimension of the feature vector corresponds to a physical quantity, such as the real-time state value of ambient pressure, solenoid valve outlet pressure, flow rate and temperature. The time sequence of the feature vector is consistent with the sampling time to reflect the dynamic changes of the operating condition parameters over time. For each time point, the comprehensive operating condition feature vector completely records all the physical quantity information at that time, providing high-quality input for subsequent steps.

[0058] Through the above method, the present invention can be effectively implemented to ensure that the real-time working condition data has smoothness and consistency after preprocessing, and at the same time provide a comprehensive working condition feature vector with a clear structure, laying a solid data foundation for further dynamic control and optimization of the system. According to specific application requirements, the size of the sliding window, the normalization range, and the organization of the feature vector can be flexibly adjusted to adapt to different practical scenarios.

[0059] Furthermore, the real-time operating condition data is preprocessed including data noise reduction and normalization to obtain a comprehensive operating condition feature vector, including:

[0060] Perform anomaly detection on the real-time collected ambient pressure, solenoid valve outlet pressure, flow rate and temperature data, remove abnormal data points below or above the set threshold, and interpolate and complete the detected missing data;

[0061] The data after the abnormalities are removed are normalized using a standardization method. Based on the historical average and variance of each operating condition parameter, the ambient pressure, solenoid valve outlet pressure, flow rate and temperature are converted into dimensionless standardized values ​​to ensure that the contribution weight of each parameter to the feature vector is consistent.

[0062] The normalized ambient pressure, solenoid valve outlet pressure, flow rate and temperature data are combined into a comprehensive operating condition feature vector.

[0063] After collecting the raw data of ambient pressure, solenoid valve outlet pressure, flow rate and temperature in real time, anomaly detection is first required to identify and eliminate possible abnormal data points. These abnormal data may be caused by sensor failure, external interference or data transmission problems, and usually appear as extreme values ​​far away from the normal value range. By setting upper and lower thresholds, it is determined whether each data point is within a reasonable range. For example, the reasonable range of ambient pressure may be 0 to 100 kPa. If a data point exceeds this range, it is judged as abnormal data. Similarly, the reasonable range of flow rate, temperature and outlet pressure can also be set according to system design and actual operating conditions.

[0064] For the detected abnormal data, it is necessary to remove it from the data sequence to avoid interference with subsequent processing. If the abnormal data causes missing points in the data sequence, the missing data needs to be supplemented by interpolation methods. The interpolation method can be linear interpolation, that is, the approximate value of the missing point is calculated based on the difference between the two normal data points before and after, or a more complex interpolation method such as polynomial interpolation or spline interpolation can be selected. The specific method can be determined according to the dynamic characteristics of the working conditions and computing resources. Through interpolation completion, the integrity of the data sequence can be ensured, providing continuous input for subsequent processing.

[0065] After anomaly detection and data completion, the data enters the normalization processing stage. Normalization adopts a standardized method, that is, the data is converted into a dimensionless standardized value based on the historical mean and variance of each operating condition parameter. Specifically, for the current data point of a physical quantity, the difference between it and the historical average value is calculated and divided by the historical standard deviation to normalize it to a dimensionless numerical range. Such processing can eliminate the problem of uneven weights caused by dimensional differences between different physical quantities, so that the ambient pressure, outlet pressure, flow rate and temperature have consistent contribution weights in the subsequent calculation of the comprehensive operating condition characteristic vector.

[0066] The normalized data are combined into a comprehensive working condition feature vector in chronological order. Each dimension of the feature vector corresponds to a physical quantity, including the standardized values ​​of ambient pressure, solenoid valve outlet pressure, flow rate and temperature. By integrating the standardized values ​​of these physical quantities into feature vectors, the overall working condition of the solenoid valve at a certain point in time can be accurately reflected. At the same time, these feature vectors can also form a dynamic feature change sequence as the time series progresses, providing accurate input for subsequent control algorithms.

[0067] Through anomaly detection, interpolation completion and standardization processing, the accuracy, consistency and completeness of the data are ensured. In addition, the threshold range of anomaly detection, interpolation method and calculation method of standardization parameters can be adjusted according to specific needs to adapt to data processing requirements under different working conditions. In this way, the generated comprehensive working condition feature vector has good robustness and applicability, providing a solid foundation for the efficient operation of subsequent control algorithms.

[0068] Step S103: Calculate the flow rate, temperature and outlet pressure value of the future working condition through a prediction algorithm according to the comprehensive working condition characteristic vector and the preset target output pressure value and flow rate value.

[0069] In step S103, the flow rate, temperature and outlet pressure value of the future working condition need to be calculated by a prediction algorithm according to the comprehensive working condition characteristic vector and the preset target output pressure value and flow rate value. The specific implementation method of this process is as follows.

[0070] First, the comprehensive working condition feature vector processed by step S102 is obtained, which contains the normalized values ​​of ambient pressure, solenoid valve outlet pressure, flow rate and temperature, and has a continuous time series structure. These data can reflect the dynamic change trend of the current working condition and provide a basis for comparative analysis with the target output parameters.

[0071] Next, the target output parameters are introduced, including the target output pressure value and the target flow value. These target parameters are usually set according to system requirements, such as the flow demand in industrial processes or the outlet pressure range of system design. During implementation, the target parameters need to be consistent with the timestamp of the feature vector to ensure the timeliness of the prediction results.

[0072] Then, the comprehensive working condition feature vector and the target output parameters are input into the prediction algorithm. The prediction algorithm can use the linear extrapolation method based on historical trends. By analyzing the rate of change of each parameter in the comprehensive feature vector over time, the pressure, flow and temperature change trends in the short future time are derived. For example, the outlet pressure change rate at the last few time points is calculated, and the pressure value at a specific time point in the future is predicted based on the change rate. For complex working conditions, the multi-parameter correlation of historical data can also be used to estimate the future multi-parameter working conditions by combining the change trends of flow, pressure and temperature.

[0073] In the prediction process, in order to ensure the accuracy and robustness of the results, a weighted method can be used to highlight the importance of the data at the most recent time point. For example, the closer the parameter is to the current time point, the greater the weight it has for future predictions, ensuring that the prediction results can reflect the latest dynamics of the actual working conditions in a timely manner. At the same time, for parameters with strong correlations such as temperature and pressure, a collaborative analysis strategy can be introduced to deduce the trend of another parameter based on the change of one parameter, further improving the reliability of the prediction results.

[0074] Finally, the prediction algorithm outputs the flow, temperature, and outlet pressure values ​​at a specific time point in the future. These predicted values, combined with the target parameters, provide a basis for predicting the working conditions for subsequent control steps. This step uses the linear trend method and a simple weighting strategy to meet the needs of most working conditions. If the actual working conditions are more complex, higher-order algorithms can be introduced on this basis, such as multivariate regression or machine learning models based on historical data, to further improve the prediction performance.

[0075] Furthermore, the flow rate, temperature and outlet pressure value of the future working condition are calculated by a prediction algorithm according to the comprehensive working condition characteristic vector and the preset target output pressure value and flow rate value, including:

[0076] According to the following formula 1, the historical operating condition characteristic matrix is ​​constructed :

[0077] ;

[0078] in, is the number of historical sampling points; Indicates The outlet pressure value at a historical time point is obtained through the recorded historical collection data; Indicates The temperature value at a historical time point is obtained through the recorded historical collection data; Indicates The flow value at a historical time point is obtained through the recorded historical collection data; It represents the working condition correlation characteristics and is calculated by the following formula 2:

[0079] ;

[0080] in, is the time interval of historical sampling; Indicates The flow value at a historical time point; Indicates The outlet pressure value at a historical time point; Indicates the The temperature value at a historical time point;

[0081] For the historical operating condition feature matrix Middle The historical feature points composed of rows are calculated according to the following formula 3 to calculate their nonlinear weights :

[0082] ;

[0083] in, Indicates the timestamp corresponding to each feature point, ; is the time decay factor; is the working condition correlation coefficient;

[0084] According to the following formula 4, the future flow rate, temperature and outlet pressure values ​​are predicted:

[0085] ;

[0086] in, is the predicted value of outlet pressure at the future moment; The temperature prediction value for the future time; The traffic forecast value for the future time; and is the nonlinear regression coefficient matrix, obtained by least squares fitting based on historical data; is the bias term, which is calculated and determined based on historical data; is a nonlinear weight matrix, expressed by the following formula 5:

[0087] ;

[0088] Among them, the nonlinear weight matrix is a diagonal matrix with is the nonlinear weight obtained according to formula (3); is the number of historical sampling points.

[0089] First, construct the historical operating condition feature matrix matrix It consists of data from each historical sampling point. Each row represents the comprehensive operating characteristics of a historical time point, including the outlet pressure ,temperature ,flow , and working condition related features These data are from the historical collection values ​​recorded by the system and are arranged in chronological order.

[0090] In formula 1, Indicates the current time of the system, for example, it is a certain second (such as 12:00:05). It is dynamic and changes with the monitoring and analysis of real-time working conditions. will be updated to indicate the base time of sampling.

[0091] Used to represent data at a certain moment in the past, where is the serial number of the historical point, is the time interval for historical sampling. For example:

[0092] when When, the time point is , means before the current time Seconds of data.

[0093] when When, the time point is , means before the current time Seconds of data.

[0094] Therefore, the matrix Each row in corresponds to a different historical time point, and It is the basis for calculations at these historical time points.

[0095] for , which means that The outlet pressure value at a historical time point is obtained through the data collected and recorded by the sensor. is the temperature at that time point, is the flow rate value at that time point.

[0096] Secondly, calculate the working condition related characteristics , which is used to quantify the dynamic coupling between different physical quantities. According to formula (2), the operating condition correlation characteristics are calculated by the product and sum of the change rates of outlet pressure, flow rate and temperature. Among them, the change rate of flow rate is defined as the difference between the flow rate at the target moment and the flow rate at the previous moment divided by the time interval , For example:

[0097] ;

[0098] Similarly, the rate of change of outlet pressure and temperature is obtained by corresponding calculation. For example, if at a certain time point Cubic meters per hour, cubic meters per hour, and seconds, the flow rate change rate is 2 cubic meters per hour per second. By substituting these change rates into formula (2), we can calculate The value of .

[0099] Then, according to formula (3), the nonlinear weight of each historical feature point is calculated . Weight The influence of time decay and working condition association is taken into account, and its value is determined by the time decay factor Correlation coefficient with working condition For example, when Closer to the current time When the time decay factor makes the corresponding is larger, reflecting the more important influence of more recent time points on future forecasts. When it is larger, the weight will also increase, indicating that the working condition of this point is more strongly correlated and contributes more significantly to the prediction.

[0100] Next, the nonlinear weights Composition weight matrix According to formula (5), the weight matrix Is a diagonal matrix, and the elements on the diagonal correspond to the nonlinear weights of each feature point. , then the weight matrix may be:

[0101] ;

[0102] in They are calculated according to formula (3) respectively.

[0103] Finally, the outlet pressure, temperature and flow rate of future working conditions are predicted using formula (4). The prediction process is based on a nonlinear regression model, where the matrix and It is the nonlinear regression coefficient matrix obtained by fitting historical data through the least squares method. are fixed parameters of the regression model, which are determined by fitting optimization. right The weighting of reflects the comprehensive influence of historical feature points. Through the activation function tanh, the weighted features are transformed nonlinearly, so that the model can capture complex dynamic relationships. For example, when and They are and The matrix, is the number of hidden layer features, and the output prediction result is:

[0104] ;

[0105] The predicted future values ​​are directly used to control the process and provide data support for the dynamic regulation of electromagnetics.

[0106] Step S104: Based on the calculated flow, temperature and outlet pressure values ​​of the future operating conditions, combined with the real-time operating condition characteristic vector, the proportional parameter, integral parameter and differential parameter of the PID control algorithm are adaptively adjusted to generate an optimized solenoid valve control signal.

[0107] In step S104, based on the calculated flow, temperature and outlet pressure values ​​of the future working condition, combined with the real-time working condition characteristic vector, the proportional parameter, integral parameter and differential parameter of the PID control algorithm need to be adaptively adjusted to generate an optimized solenoid valve control signal. This process is specifically implemented as follows.

[0108] First, the future operating parameters obtained in step S103, including future flow, temperature and outlet pressure values, are matched and compared with the real-time operating characteristic vector. The real-time operating characteristic vector includes data such as the current ambient pressure, solenoid valve outlet pressure, flow and temperature. The combination of the two can provide the overall status of the current and future operating conditions, which is used to guide the direction of PID parameter adjustment.

[0109] Next, analyze the differences between future and current operating conditions, such as whether the future outlet pressure value is lower than the current value and the deviation from the target value, or whether the future flow needs to be significantly increased or decreased. These differences are used to determine whether the system needs faster response, smoother regulation, or higher error tolerance, and adjust the proportional, integral, and differential parameters of the PID controller accordingly. The proportional parameter is used to directly adjust the amplitude of the response, the integral parameter is used to correct the long-term accumulated deviation, and the differential parameter is used to predict trends and optimize dynamic responses.

[0110] Next, based on the results of the above analysis, the parameters of the PID controller are dynamically adjusted. For example, when the future outlet pressure is predicted to drop significantly, the value of the proportional parameter can be appropriately increased to enhance the response strength, while the differential parameter can be increased to respond to trend changes more quickly; when the predicted future flow rate deviates slightly from the current target value, the proportional parameter can be reduced to reduce the sensitivity of the controller to improve the stability of the system. This parameter adjustment can be achieved through simple preset rules or response curves to ensure that the adjustment process is both fast and reliable.

[0111] Finally, the adjusted proportional, integral and differential parameters are input into the PID controller to generate an optimized control signal based on the real-time error and deviation trend. This control signal is used as the driving instruction of the solenoid valve to guide the displacement of the valve core and adjust the opening of the solenoid valve to meet the target flow and pressure requirements.

[0112] Through the above method, dynamic adjustment of PID controller parameters can be achieved, the control signal of the solenoid valve can be effectively optimized, and the rapid response and stable control of the system under complex dynamic conditions can be ensured.

[0113] Furthermore, the proportional parameter, integral parameter and differential parameter of the PID control algorithm are adaptively adjusted based on the calculated flow rate, temperature and outlet pressure values ​​of the future working condition, combined with the real-time working condition characteristic vector, to generate an optimized solenoid valve control signal, including:

[0114] According to the following formula (6), the adjusted proportional parameter is calculated :

[0115] ;

[0116] in, is the initial value of the proportional parameter, which is set according to the initial adjustment requirements of flow and pressure; is the future outlet pressure value obtained by the prediction algorithm; It is the outlet pressure value of the solenoid valve monitored in real time; is the target outlet pressure value, which is determined by the system setting requirements; is the future flow value obtained by the prediction algorithm; is the flow value monitored in real time; is the target flow value, which is determined by the system setting requirements; is the flow change per unit time sampled in real time; is the outlet pressure change per unit time sampled in real time; , and is the weight coefficient;

[0117] According to the following formula (7), the adjusted integral parameter is calculated: :

[0118] ;

[0119] in, is the initial value of the integral parameter, which is set by the response time requirement of the solenoid valve; is the current time point, and the initial time point is the start time of the solenoid valve; is the target outlet pressure value, which is determined by the system setting requirements; Indicates at time Real-time outlet pressure value; is the future flow value obtained by the prediction algorithm; is the flow value monitored in real time; is the target flow value, which is determined by the system setting requirements; is the outlet pressure change per unit time sampled in real time; , and is the weight coefficient;

[0120] According to the following formula (8), the adjusted integral parameter is calculated: :

[0121] ;

[0122] in, The initial value of the derivative parameter is set by the dynamic stability requirements of the system; is the flow rate change rate per unit time; is the outlet pressure change rate per unit time; is the future temperature obtained by the prediction algorithm; is the current temperature; and is the weight coefficient.

[0123] According to the calculated adjusted scale parameter , adjusted integral parameters And the adjusted integral parameter , using the following formula (9), the optimal control signal of the solenoid valve is generated :

[0124] ;

[0125] in, is the real-time deviation, defined as ; is the target outlet pressure value, which is determined by the system setting requirements; Indicates the current time Real-time outlet pressure value; is the future outlet pressure value obtained by the prediction algorithm; It is the outlet pressure value of the solenoid valve monitored in real time; is the future flow value obtained by the prediction algorithm; is the flow value monitored in real time; is the target flow value, which is determined by the system setting requirements; and is the weight coefficient.

[0126] First, the adjusted proportional parameter is calculated by formula (6): . Scale parameter Initial value of It is set according to the initial adjustment requirements of the solenoid valve. For example, when the solenoid valve needs to respond sensitively to the outlet pressure, Take larger values ​​to increase the amplitude of the control signal.

[0127] In formula (6), is the future outlet pressure value calculated by the prediction algorithm, is the outlet pressure value monitored in real time, and the difference between the two reflects the pressure difference between the current working condition and the future demand. Similarly, the future forecast value of the flow With real-time value The difference reflects the regulation requirements on the flow. These difference values ​​are normalized and divided by the target value and , making it dimensionless and convenient for subsequent calculations.

[0128] In addition, the real-time sampling flow rate change per unit time and pressure change For example, if the current flow rate is 10 cubic meters per hour, the flow rate at the previous moment is 9 cubic meters per hour, and the sampling interval is 1 second, then Cubic meters per hour per second. Weight factor , and It is used to adjust the contribution of each parameter to the proportionality parameter. The specific value can be set according to the response requirements of the system. Formula (6) combines the comprehensive information of future prediction value and real-time change rate, so that It has higher adaptability under dynamic conditions.

[0129] Next, the adjusted integral parameter is calculated by formula (7): . Initial value of the integration parameter It is set according to the solenoid valve response time requirement, which usually depends on the system's ability to correct long-term deviations. For example, a slow-response system requires a smaller To avoid over-regulation. The deviation term in the integral formula The target pressure and the real-time pressure are The difference in the predicted future flow can be accumulated by integrating the deviation over time. and real-time pressure change rate The normalized value of is introduced into the formula to enhance the responsiveness to changes in operating conditions. and Controls the effect of these terms on the integration parameters.

[0130] Then, the adjusted differential parameter is calculated by formula (8): . Initial value of the derivative parameter It is set according to the dynamic stability requirements of the system and is used to respond to rapidly changing deviations.

[0131] In the formula and Respectively represent the flow rate and pressure change rate per unit time, which can be calculated from the continuously sampled flow and pressure values. For example, if the flow rate changes from 8 cubic meters per hour to 10 cubic meters per hour in 1 second, then Cubic meters per hour per second. Future temperature prediction With current temperature The difference reflects the influence of temperature on dynamic stability through normalization. Weight coefficient and Used to adjust different pairs of items contribution.

[0132] Finally, the optimized electromagnetic control signal is generated by formula (9): The control signal consists of three parts: proportional control term , integral control term and the derivative control term Among them, the deviation It is defined as the difference between the target pressure and the current pressure, that is, . Future predicted pressure and flow differences and By weighting factor and The introduction of control signals further enhances the predictive capability of control.

[0133] Through the above method, the optimized control signal can dynamically respond to the complex working conditions of the system and ensure the precise adjustment of the solenoid valve.

[0134] Step S105: applying the optimized solenoid valve control signal to the solenoid valve to dynamically adjust the opening of the solenoid valve, thereby preliminarily achieving dynamic control of flow and pressure.

[0135] In step S105, the optimized solenoid valve control signal is applied to the solenoid valve to dynamically adjust the opening of the solenoid valve, thereby preliminarily realizing dynamic control of flow and pressure.

[0136] First, the optimized solenoid valve control signal generated by step S104 is obtained, which includes the solenoid valve drive parameters adjusted based on real-time and future working conditions. The optimized signal is transmitted to the actuator of the solenoid valve through the digital signal transmission system. In this process, in order to ensure the accuracy and integrity of signal transmission, a digital-to-analog conversion method can be used to convert the digital control signal into an analog signal for driving the coil of the solenoid valve.

[0137] Next, the control signal acts on the solenoid valve coil to adjust the current intensity in the coil. When the solenoid valve coil receives currents of different intensities, it will generate a magnetic field of corresponding intensity, which drives the movement of the valve core, thereby changing the position of the valve core and the opening of the solenoid valve. By accurately controlling the current, the displacement of the valve core can be accurately adjusted, so that the opening of the solenoid valve can change according to the instructions of the optimized control signal.

[0138] During the movement of the valve core, the opening of the solenoid valve directly affects the flow rate and outlet pressure through the valve. When the valve core displacement increases, the valve opening increases, the flow rate increases, and the outlet pressure may decrease; when the valve core displacement decreases, the valve opening decreases, the flow rate decreases, and the outlet pressure may increase. This dynamic adjustment ensures that the solenoid valve can respond to changes in working conditions in a timely manner according to the needs of optimizing the control signal, thereby achieving preliminary control of flow and pressure.

[0139] Finally, to ensure the stability of the regulation effect, the feedback signal of the valve core displacement and opening change can be monitored to verify whether the actual execution result matches the control signal. If deviation is found, the control signal can be further corrected in the subsequent steps to achieve more accurate dynamic control.

[0140] Through the above method, the process of the control signal acting on the solenoid valve can be efficiently realized, and the requirements for dynamic regulation of flow and pressure under complex working conditions can be met through real-time adjustment of the solenoid valve opening.

[0141] Furthermore, the optimized solenoid valve control signal is applied to the solenoid valve to dynamically adjust the opening of the solenoid valve, thereby preliminarily realizing dynamic control of flow and pressure, including:

[0142] The optimized solenoid valve control signal is converted into a driving current signal of the electromagnetic coil through a driving signal conversion unit, and the amplitude and frequency of the driving current signal are dynamically adjusted according to the strength of the optimized signal and the adjustment requirements;

[0143] The solenoid valve coil receives the driving current signal and controls the displacement of the valve core according to the magnetic field strength of the coil. The size of the valve core displacement directly adjusts the opening of the solenoid valve, thereby changing the flow rate and outlet pressure;

[0144] Real-time monitoring of the impact of changes in the solenoid valve opening on the outlet flow and pressure ensures that the displacement of the valve core and the actual opening of the solenoid valve can accurately respond to the optimized control signal, thereby dynamically balancing the flow and pressure requirements.

[0145] First, the optimized solenoid valve control signal is converted into a drive current signal. The optimized control signal is a dynamic variable, which is generated according to the current system conditions and expected goals, and contains the intensity and frequency information of the solenoid valve operation. The function of the drive signal conversion unit is to convert the optimized signal into a current signal that can directly drive the solenoid valve coil. This conversion process includes adjusting the amplitude of the optimized signal to match the input requirements of the solenoid coil, while ensuring that the signal frequency can reflect the rapidity of dynamic adjustment. For example, when the optimized signal indicates that a larger adjustment is required, the intensity of the drive current increases, and the frequency may also increase accordingly to quickly respond to system requirements.

[0146] Next, the solenoid valve coil receives the drive current signal and generates a magnetic field through the principle of electromagnetic induction. The strength of the magnetic field is directly related to the amplitude of the input current signal. The change in the magnetic field in the coil drives the movement of the valve core, and the displacement of the valve core determines the opening of the solenoid valve. For example, when the drive current increases, the magnetic field strength increases, the valve core is further pulled, and the valve opening increases, thereby increasing the flow rate and possibly reducing the outlet pressure. Conversely, reducing the drive current will weaken the magnetic field, causing the valve core to return to its original position or close the valve, reducing the flow rate and possibly increasing the pressure.

[0147] In order to ensure that the valve core displacement is consistent with the control signal, it is very important to monitor the opening change of the solenoid valve in real time. Through the displacement sensor installed inside or outside the solenoid valve, the current position and movement range of the valve core can be accurately measured and compared with the optimized control signal. For example, if the optimization signal requires the valve core to move 2 mm to achieve the desired flow rate, but the actual displacement is only 1.8 mm, this deviation can be compensated by increasing the drive current. Similarly, if the valve core displacement is too large, it is corrected by reducing the drive current.

[0148] In addition, the impact of opening changes on outlet flow and pressure needs to be monitored dynamically. This is usually done by collecting pressure and flow data at the outlet in real time through pressure sensors and flow sensors to form a closed-loop feedback system. The feedback data can be used in conjunction with the optimized control signal to ensure that the system always operates in a dynamic balance state. For example, when the outlet flow exceeds the target value, the control system will automatically reduce the opening of the solenoid valve to restore balance by reducing the flow; and when the outlet pressure is lower than the set range, the system will increase the opening to increase the flow and adjust the pressure.

[0149] Through the above method, the precise dynamic adjustment of the solenoid valve opening by optimizing the control signal can be achieved, ensuring that the operation of the solenoid valve can quickly respond to complex working conditions and maintain a stable dynamic balance between flow and pressure. This method is highly flexible and feasible, and is suitable for industrial automation and complex fluid control scenarios.

[0150] Step S106: monitor the flow rate and pressure at the outlet of the solenoid valve in real time through high-frequency sampling, compare the monitored actual output value with the target output value, and calculate the control deviation.

[0151] In step S106, the flow rate and pressure at the outlet of the solenoid valve are monitored in real time through high-frequency sampling, the monitored actual output value is compared with the target output value, and the control deviation is calculated. This process is specifically implemented as follows.

[0152] First, a high-frequency sampling device is set up to monitor the flow rate and pressure at the outlet of the solenoid valve in real time. The flow sensor and pressure sensor are installed in the outlet channel of the solenoid valve respectively to collect the instantaneous flow rate and outlet pressure data of the fluid after it flows through the solenoid valve. The sampling frequency of the high-frequency sampling device is set according to the system response time and dynamic adjustment requirements, such as 100 Hz or higher, to ensure that the monitoring data can accurately capture dynamic changes.

[0153] The collected flow and pressure data are immediately transmitted to the data processing unit for real-time analysis. In the data processing unit, the actual flow and pressure values ​​at each sampling point are compared with the preset target output values ​​one by one. The target output values ​​are the pressure and flow parameters set according to the working conditions during system design, usually based on the ideal values ​​for steady-state operation. In actual operation, these target values ​​may be dynamically adjusted according to process requirements.

[0154] Then, the deviation value of each sampling point is calculated, that is, the difference between the actual flow and pressure values ​​and the target output value. These deviation values ​​can reflect the degree of match between the current working conditions and the target requirements. If the actual value deviates from the target value, the deviation value will be recorded and used for subsequent control adjustments. In order to facilitate dynamic monitoring and analysis, these deviation values ​​are usually stored in the form of time series to form a dynamic deviation curve that reflects the changes in working conditions.

[0155] In the whole process, to ensure the accuracy and consistency of the data, denoising technology can be used to filter the sampled data preliminarily, such as removing abnormal values ​​or short-term extreme fluctuations. The processed deviation value can more accurately reflect the real state of the system, thus providing a reliable basis for subsequent control signal correction.

[0156] Furthermore, the flow rate and pressure at the outlet of the solenoid valve are monitored in real time by high-frequency sampling, the monitored actual output value is compared with the target output value, and the control deviation is calculated, including:

[0157] Using the pressure sensor and flow sensor installed at the outlet of the solenoid valve, the outlet pressure and flow are monitored in real time with a fixed high-frequency sampling period, and the collected data are stored as continuous time series data;

[0158] Real-time analysis of the pressure and flow data obtained by high-frequency sampling is performed to ensure the stability and reliability of the data by removing mutation values ​​or noise points, and the data is compared with the target pressure value and target flow value one by one to calculate the actual output deviation at the current time point;

[0159] The calculated pressure deviation and flow deviation are recorded in chronological order as a dynamic deviation sequence, and the real-time regulation effect of the solenoid valve is evaluated through the sequence to provide feedback basis for the subsequent adjustment of the control signal.

[0160] Pressure sensors and flow sensors are installed at the outlet of the solenoid valve. The function of these sensors is to collect pressure and flow data at the outlet of the solenoid valve in real time. The setting of the high-frequency sampling period needs to comprehensively consider the dynamic response requirements of the system and the technical specifications of the sensor. For example, the sampling period can be set to 100 times per second (i.e., the sampling frequency is 100 Hz) to capture rapidly changing fluid characteristics. The data collected by the sensor is stored in the form of a time series, and each data point is accompanied by an accurate timestamp to mark the time point of data collection. The storage of time series data can be completed by a data processing device, usually using a circular buffer or a real-time database to ensure the efficiency and continuity of data storage.

[0161] After completing data acquisition, real-time analysis of the pressure and flow data obtained by high-frequency sampling is a key step. The raw data may contain noise or mutation values ​​due to sensor accuracy limitations or external interference. These abnormal data points will mislead the deviation calculation and system evaluation. Therefore, in the data analysis stage, the raw data must first be cleaned and filtered. The sliding window averaging method or median filtering method can be used to remove noise points. For example, the average value of multiple consecutive sampling points can be calculated to smooth the data curve, or abnormal points with excessive fluctuations in a short period of time can be removed. Through these processes, the stability and reliability of the input data are ensured.

[0162] After data cleaning is completed, the pressure and flow data at each time point are compared with the target value, and the deviation between the actual output value and the target output value is calculated. The pressure deviation is defined as the difference between the actual outlet pressure value and the target outlet pressure value, while the flow deviation is defined as the difference between the actual flow value and the target flow value. For example, if the target outlet pressure value is 50 kPa and the current actual outlet pressure is 48 kPa, the pressure deviation is -2 kPa. Similarly, if the target flow is 20 cubic meters per hour and the current flow is 22 cubic meters per hour, the flow deviation is 2 cubic meters per hour. Through such a one-by-one comparison, a deviation value reflecting the current system status can be generated.

[0163] The calculated pressure deviation and flow deviation are recorded in chronological order as a dynamic deviation sequence. The dynamic deviation sequence can not only reflect the real-time status of the system, but also show the trend of deviation changes over time. For example, if the deviation sequence shows that the pressure deviation continues to increase, it may mean that the control system fails to respond to the change in working conditions in a timely manner, and needs to be corrected by adjusting the control signal. In addition, the dynamic deviation sequence can also be used to evaluate the regulation effect of the solenoid valve. For example, when the deviation sequence tends to zero or fluctuates within a reasonable range, it can be considered that the solenoid valve regulation effect is good.

[0164] Through high-frequency sampling, real-time data analysis and deviation calculation, this method can be effectively implemented to ensure the dynamic control accuracy of the solenoid valve under complex working conditions. The generation of dynamic deviation sequence not only provides a closed-loop feedback mechanism for the system, but also provides a solid data foundation for the subsequent optimization and adjustment of control signals.

[0165] Step S107: Based on the control deviation, the control signal of the solenoid valve is corrected to accurately match the working condition requirements, thereby achieving precise dynamic control of flow and pressure.

[0166] In step S107, based on the control deviation, the control signal of the solenoid valve is corrected to accurately match the working condition requirements, thereby achieving precise dynamic control of flow and pressure. This process requires a close combination of the relationship between the deviation data and the solenoid valve control signal to ensure the accuracy and real-time performance of the dynamic correction.

[0167] First, the calculated control deviation is obtained from step S106, which includes the difference between the actual output flow rate and outlet pressure and the target value. The adjustment requirements of the current working condition are judged according to the size and direction of the deviation. For example, when the actual flow rate is lower than the target value, the system needs to increase the opening of the solenoid valve, and when the outlet pressure is high, the opening of the solenoid valve needs to be reduced. This adjustment requirement is directly reflected by the positive and negative values ​​and amplitude of the deviation data.

[0168] Next, the control deviation is input into the correction algorithm. The correction algorithm dynamically adjusts the control signal of the solenoid valve according to the deviation, for example, by increasing or decreasing the amplitude of the control signal to correspond to a larger valve core displacement. The simplest correction method is direct proportional adjustment. The larger the deviation, the larger the correction amplitude, so as to quickly respond to changes in operating conditions. To prevent over-adjustment and system oscillation, a limiting mechanism can be introduced during the correction process, such as setting the maximum and minimum correction value range of the control signal to ensure that the adjustment amplitude is within a reasonable range.

[0169] Subsequently, the generated correction control signal is directly applied to the solenoid valve drive system to adjust the current intensity of the solenoid coil, thereby changing the movement distance of the valve core and the opening size of the solenoid valve. This real-time correction ensures that the dynamic response of the solenoid valve can quickly adapt to the current working conditions, reduce deviations and gradually adjust the system flow and pressure to the target value.

[0170] During this process, to ensure the accuracy of the correction, the system can continuously monitor the actual output value after the correction. If it is found that the correction effect fails to significantly reduce the deviation, the correction algorithm can be further iterated, for example, by increasing the adjustment amplitude in small steps, so that the system gradually approaches the target value.

[0171] Through the above methods, the solenoid valve control signal can be dynamically corrected to accurately match the actual working conditions, thereby achieving precise control of flow and pressure under complex and dynamically changing working conditions.

[0172] Furthermore, based on the control deviation, the control signal of the solenoid valve is corrected to accurately match the working condition requirements to achieve precise dynamic control of flow and pressure, including:

[0173] According to the calculated pressure deviation and flow deviation, they are input into the dynamic adjustment module, and the adjustment direction of the working condition is determined by the deviation classification, including four main situations: flow increase, flow decrease, pressure increase or pressure decrease;

[0174] According to the determined adjustment direction, combined with the historical deviation trend and the current deviation change rate, the control signal amplitude and frequency of the solenoid valve are dynamically adjusted to accurately control the driving current of the solenoid coil, thereby adjusting the valve core displacement;

[0175] Through real-time feedback monitoring of the adjusted flow and pressure changes, verify whether the correction result of the control signal reaches the target value range. If there is still a deviation, repeat the correction process until the deviation meets the accuracy requirements, thereby achieving precise dynamic control of flow and pressure.

[0176] After obtaining the pressure deviation and flow deviation, these deviation values ​​are input into the dynamic adjustment module for classification analysis. The purpose of deviation classification is to determine the adjustment direction required for the current working conditions, which mainly includes four situations: flow increase, flow decrease, pressure increase or pressure decrease. For example, when the pressure deviation is positive (that is, the actual outlet pressure is lower than the target value), it indicates that the system needs to increase the pressure; and when the flow deviation is negative (that is, the actual flow is higher than the target value), it indicates that the system needs to reduce the flow. These classifications are made based on the sign and size of the deviation, which can provide clear direction guidance for subsequent control signal adjustments.

[0177] After the classification is completed, the control signal of the solenoid valve is dynamically adjusted according to the adjustment direction, the historical deviation trend and the current deviation change rate. The historical deviation trend is determined by analyzing the deviation changes over a period of time in the past. For example, if the past deviation shows a trend of gradual decrease, the current adjustment amplitude can be appropriately reduced to avoid over-adjustment; on the contrary, if the deviation does not decrease or even increases, the strength of the control signal needs to be significantly increased. The current deviation change rate is calculated by comparing the deviation change of two consecutive sampling points. For example, if the current deviation change rate is large, it means that the system needs a faster response, and the frequency of the control signal can be appropriately increased. The dynamic adjustment of the control signal includes the comprehensive optimization of amplitude and frequency, which is specifically manifested in the synchronous adjustment of the current size and change speed of the driving electromagnetic coil.

[0178] The adjusted control signal acts on the electromagnetic coil, driving the displacement of the valve core, thereby changing the opening of the electromagnetic valve. The displacement of the valve core directly affects the flow and pressure. For example, increasing the drive current will increase the magnetic field strength, thereby pulling the valve core, increasing the valve opening, increasing the flow, and possibly reducing the pressure. On the contrary, reducing the drive current will reduce the magnetic field strength, reduce the displacement of the valve core, thereby reducing the valve opening, reducing the flow, and possibly increasing the pressure.

[0179] After the adjustment is completed, the changes in the outlet flow and pressure are monitored in real time to verify whether the correction of the control signal reaches the target value range. If the actual flow and pressure still do not meet the target value, the deviation is re-evaluated and the correction process is repeated. For example, if the target outlet pressure is 50 kPa, and the actual pressure after adjustment is only 48 kPa, the system will further increase the control signal amplitude to increase the pressure. This closed-loop process continues until the deviation converges to the set accuracy range, ensuring that the solenoid valve can achieve accurate dynamic control of flow and pressure.

[0180] Through the above method, the solenoid valve control signal can be efficiently and dynamically corrected according to the changes in the working conditions, ensuring that the system can respond quickly and maintain the stability of the working conditions.

[0181] A second embodiment of the present application provides an electronic device, the electronic device comprising:

[0182] processor;

[0183] The memory is used to store a program. When the program is read and executed by the processor, it executes a solenoid valve precise control method based on dynamic flow regulation provided in the first embodiment of the present application.

[0184] 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, a solenoid valve precise control method based on dynamic flow regulation provided in the first embodiment of the present application is executed.

[0185] 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 solenoid valve precise control method based on dynamic flow regulation, characterized in that: include: The solenoid valve working parameters including ambient pressure, solenoid valve outlet pressure, flow rate and temperature are collected in real time through sensors to obtain the real-time working condition data of the solenoid valve; Performing preprocessing including data noise reduction and normalization on the real-time operating condition data to obtain a comprehensive operating condition feature vector; According to the comprehensive operating condition characteristic vector and the preset target output pressure value and flow value, the flow rate, temperature and outlet pressure value of the future operating condition are calculated by a prediction algorithm; Based on the calculated flow, temperature and outlet pressure values ​​of future working conditions, combined with the real-time working condition characteristic vector, the proportional parameters, integral parameters and differential parameters of the PID control algorithm are adaptively adjusted to generate an optimized solenoid valve control signal; Applying the optimized solenoid valve control signal to the solenoid valve to dynamically adjust the opening of the solenoid valve, thereby preliminarily realizing dynamic control of flow and pressure; The flow and pressure at the outlet of the solenoid valve are monitored in real time through high-frequency sampling, and the actual output value monitored is compared with the target output value to calculate the control deviation; Based on the control deviation, the control signal of the solenoid valve is corrected to accurately match the working condition requirements, thereby achieving precise dynamic control of flow and pressure; The flow rate, temperature and outlet pressure value of the future working condition are calculated by a prediction algorithm according to the comprehensive working condition characteristic vector and the preset target output pressure value and flow rate value, including: According to the following formula 1, the historical operating condition characteristic matrix is ​​constructed : ； in, is the current time point; is the number of historical sampling points; Indicates The outlet pressure value at a historical time point is obtained through the recorded historical collection data; Indicates The temperature value at a historical time point is obtained through the recorded historical collection data; Indicates The flow value at a historical time point is obtained through the recorded historical collection data; It represents the working condition correlation characteristics and is calculated by the following formula 2: ； in, is the time interval of historical sampling; Indicates The flow value at a historical time point; Indicates The outlet pressure value at a historical time point; Indicates the The temperature value at a historical time point; For the historical operating condition feature matrix Middle The historical feature points composed of rows are calculated according to the following formula 3 to calculate their nonlinear weights : ； in, Indicates the timestamp corresponding to each feature point, ; is the time decay factor; is the working condition correlation coefficient; According to the following formula 4, the future flow rate, temperature and outlet pressure values ​​are predicted: ； in, is the predicted value of outlet pressure at the future moment; The temperature prediction value for the future time; The traffic forecast value for the future time; and is the nonlinear regression coefficient matrix, obtained by least squares fitting based on historical data; is the bias term, which is calculated and determined based on historical data; is a nonlinear weight matrix, expressed by the following formula 5: ； Among them, the nonlinear weight matrix is a diagonal matrix with is the nonlinear weight obtained according to formula (3); is the number of historical sampling points; The method of adaptively adjusting the proportional parameter, integral parameter and differential parameter of the PID control algorithm based on the calculated flow rate, temperature and outlet pressure value of the future working condition and combining the real-time working condition characteristic vector to generate an optimized solenoid valve control signal includes: According to the following formula (6), the adjusted proportional parameter is calculated : ； in, It is the initial value of the proportional parameter, which is set according to the initial adjustment requirements of flow and pressure; is the future outlet pressure value obtained by the prediction algorithm; It is the outlet pressure value of the solenoid valve monitored in real time; is the target outlet pressure value, which is determined by the system setting requirements; is the future flow value obtained by the prediction algorithm; is the flow value monitored in real time; is the target flow value, which is determined by the system setting requirements; is the flow change per unit time sampled in real time; is the outlet pressure change per unit time sampled in real time; , and is the weight coefficient; According to the following formula (7), the adjusted integral parameter is calculated: : ； in, is the initial value of the integral parameter, which is set by the response time requirement of the solenoid valve; is the current time point, and the initial time point is the start time of the solenoid valve; is the target outlet pressure value, which is determined by the system setting requirements; Indicates at time Real-time outlet pressure value; is the future flow value obtained by the prediction algorithm; is the flow value monitored in real time; is the target flow value, which is determined by the system setting requirements; is the outlet pressure change per unit time sampled in real time; , and is the weight coefficient; According to the following formula (8), the adjusted integral parameter is calculated: : ； in, The initial value of the derivative parameter is set by the dynamic stability requirements of the system; is the flow rate change rate per unit time; is the outlet pressure change rate per unit time; is the future temperature obtained by the prediction algorithm; is the current temperature; and is the weight coefficient; According to the calculated adjusted scale parameter , adjusted integral parameters And the adjusted integral parameter , using the following formula (9), the optimal control signal of the solenoid valve is generated : ； in, is the real-time deviation, defined as ; is the target outlet pressure value, which is determined by the system setting requirements; Indicates the current time Real-time outlet pressure value; is the future outlet pressure value obtained by the prediction algorithm; It is the outlet pressure value of the solenoid valve monitored in real time; is the future flow value obtained by the prediction algorithm; is the flow value monitored in real time; is the target flow value, which is determined by the system setting requirements; and is the weight coefficient.

2. The solenoid valve precise control method based on flow dynamic regulation according to claim 1 is characterized in that: The solenoid valve operating parameters including ambient pressure, solenoid valve outlet pressure, flow rate and temperature are collected in real time by the sensor to obtain real-time operating data of the solenoid valve, including: A pressure sensor is installed at the inlet of the solenoid valve to collect ambient pressure data, and a pressure sensor and a temperature sensor are installed at the outlet to collect outlet pressure and temperature data respectively; A flow sensor is installed on the flow channel of the solenoid valve to collect real-time flow data, and the data collected by all sensors are transmitted to the data processing device through wired or wireless signals; The ambient pressure, solenoid valve outlet pressure, flow rate and temperature data are synchronized and cleaned to generate accurate real-time operating data for subsequent steps.

3. The solenoid valve precise control method based on flow dynamic regulation according to claim 2 is characterized in that: The method of collecting the solenoid valve working parameters including the ambient pressure, the solenoid valve outlet pressure, the flow rate and the temperature in real time through the sensor to obtain the real-time working condition data of the solenoid valve also includes: The collected ambient pressure, solenoid valve outlet pressure, flow rate and temperature data are combined into real-time operating data with consistent time series, and a timestamp is added to each data point to ensure the accuracy and integrity of the data.

4. The solenoid valve precise control method based on flow dynamic regulation according to claim 1 is characterized in that: The preprocessing of the real-time operating condition data including data noise reduction and normalization to obtain a comprehensive operating condition feature vector includes: The real-time collected environmental pressure, solenoid valve outlet pressure, flow rate and temperature data are subjected to noise filtering, and the sliding window method is used to remove instantaneous outliers and high-frequency interference in the data to ensure the smoothness of the data; The noise-reduced data is normalized according to the standard range set by the system, and the ambient pressure, solenoid valve outlet pressure, flow rate and temperature values ​​are mapped to the same dimension range to facilitate comparison and fusion between different physical quantities; The multidimensional data after noise reduction and normalization are integrated into a comprehensive operating condition feature vector in chronological order, wherein the comprehensive operating condition feature vector includes real-time status values ​​of ambient pressure, solenoid valve outlet pressure, flow rate and temperature.

5. The solenoid valve precise control method based on flow dynamic regulation according to claim 1 is characterized in that: The preprocessing of the real-time operating condition data including data noise reduction and normalization to obtain a comprehensive operating condition feature vector includes: Perform anomaly detection on the real-time collected ambient pressure, solenoid valve outlet pressure, flow rate and temperature data, remove abnormal data points below or above the set threshold, and interpolate and complete the detected missing data; The data after the abnormalities are removed are normalized using a standardization method. Based on the historical average and variance of each operating condition parameter, the ambient pressure, solenoid valve outlet pressure, flow rate and temperature are converted into dimensionless standardized values ​​to ensure that the contribution weight of each parameter to the feature vector is consistent. The normalized ambient pressure, solenoid valve outlet pressure, flow rate and temperature data are combined into a comprehensive operating condition feature vector.

6. The solenoid valve precise control method based on flow dynamic regulation according to claim 1 is characterized in that: The step of applying the optimized solenoid valve control signal to the solenoid valve to dynamically adjust the opening of the solenoid valve, thereby preliminarily realizing dynamic control of flow and pressure, includes: The optimized solenoid valve control signal is converted into a driving current signal of the electromagnetic coil through a driving signal conversion unit, and the amplitude and frequency of the driving current signal are dynamically adjusted according to the strength of the optimized signal and the adjustment requirements; The solenoid valve coil receives the driving current signal and controls the displacement of the valve core according to the magnetic field strength of the coil. The size of the valve core displacement directly adjusts the opening of the solenoid valve, thereby changing the flow rate and outlet pressure; Real-time monitoring of the impact of changes in the solenoid valve opening on the outlet flow and pressure ensures that the displacement of the valve core and the actual opening of the solenoid valve can accurately respond to the optimized control signal, thereby dynamically balancing the flow and pressure requirements.

7. The solenoid valve precise control method based on flow dynamic regulation according to claim 1 is characterized in that: The method of monitoring the flow rate and pressure of the outlet of the solenoid valve in real time through high-frequency sampling, comparing the monitored actual output value with the target output value, and calculating the control deviation includes: Using the pressure sensor and flow sensor installed at the outlet of the solenoid valve, the outlet pressure and flow are monitored in real time with a fixed high-frequency sampling period, and the collected data is stored as continuous time series data; Real-time analysis of the pressure and flow data obtained by high-frequency sampling is performed to ensure the stability and reliability of the data by removing mutation values ​​or noise points, and the data is compared with the target pressure value and target flow value one by one to calculate the actual output deviation at the current time point; The calculated pressure deviation and flow deviation are recorded in chronological order as a dynamic deviation sequence, and the real-time regulation effect of the solenoid valve is evaluated through the sequence to provide feedback basis for the subsequent adjustment of the control signal.

8. The solenoid valve precise control method based on flow dynamic regulation according to claim 1 is characterized in that: Based on the control deviation, the control signal of the solenoid valve is corrected to accurately match the working condition requirements to achieve precise dynamic control of flow and pressure, including: According to the calculated pressure deviation and flow deviation, they are input into the dynamic adjustment module, and the adjustment direction of the working condition is determined by the deviation classification, including four main situations: flow increase, flow decrease, pressure increase or pressure decrease; According to the determined adjustment direction, combined with the historical deviation trend and the current deviation change rate, the control signal amplitude and frequency of the solenoid valve are dynamically adjusted to accurately control the driving current of the solenoid coil, thereby adjusting the valve core displacement; Through real-time feedback monitoring of the adjusted flow and pressure changes, verify whether the correction result of the control signal reaches the target value range. If there is still a deviation, repeat the correction process until the deviation meets the accuracy requirements, thereby achieving precise dynamic control of flow and pressure.

Images