A high-precision control method, device, equipment and medium for a proportional valve

Abstract

The present application relates to the field of proportional valve control, and in particular to a method, device, equipment and medium for high-precision control of proportional valves. The method includes: the present application obtains the historical data of the current proportional valve, and performs time domain analysis and frequency domain analysis on the historical data, establishes a first time domain function relationship between the control data and the opening data, and a second time domain function relationship between the opening data and the flow data, judges the working state of the current proportional valve, and can adjust the control strategy in time to adapt to different operating conditions by accurately grasping the current working state, predicts the current demand of the current proportional valve using the frequency domain eigenvector matrix, determines the control data in the current cycle according to the current demand and the current working state, and controls the proportional valve according to this data, converts the prediction and analysis results into actual actions, and realizes precise control of the proportional valve.

Description

Technical Field

[0001] The present application relates to the field of proportional valve control, and in particular to a method, device, equipment and medium for high-precision control of a proportional valve. Background Art

[0002] A proportional valve is a hydraulic valve that converts an input electrical signal into force or displacement in proportion, thereby continuously controlling parameters such as pressure and flow. It plays an important role in various industrial fields, ensuring stable operation and efficient production of equipment by accurately controlling the parameters of the hydraulic system. In the proportional valve control process, the staff generally directly generates a control signal based on the predicted flow demand to control the proportional valve to a certain opening, so that water can flow out to complete the supply of water flow.

[0003] However, in the above process, since the proportional valve may produce a certain opening error due to the accuracy or wear of the proportional valve when converting the input control signal into opening data, or after the proportional valve converts the opening data into water flow, there is an error between the preset water volume corresponding to the opening data and the actual water volume, thereby causing the problem of inaccurate supply.

[0004] To address this problem, the current common practice is to rely on the staff's experience to manually adjust the control signal in an attempt to improve the control accuracy of the proportional valve. However, this experience-based adjustment method still has certain limitations and cannot effectively reduce the control accuracy of the proportional valve. Therefore, improving the accuracy of the proportional valve control process has become an urgent problem to be solved. Summary of the invention

[0005] In order to improve the accuracy of proportional valve control process, the present application provides a proportional valve high-precision control method, device, equipment and medium.

[0006] In a first aspect, the present application provides a high-precision control method for a proportional valve, which adopts the following technical solution:

[0007] A high-precision control method for a proportional valve, comprising:

[0008] Acquire historical data of the current proportional valve, wherein the historical data includes historical control data, historical opening data, and historical flow data corresponding to a historical period, and the historical control data is data for controlling parameters of the current proportional valve;

[0009] Performing time domain analysis and frequency domain analysis on the historical data to obtain a first time domain function relationship between the control data and the opening data, a second time domain function relationship between the opening data and the flow data, and a frequency domain feature vector matrix corresponding to the historical data;

[0010] Determining a current working state of the current proportional valve based on the first time domain functional relationship and the second time domain functional relationship;

[0011] Based on the frequency domain eigenvector matrix, predicting a current demand corresponding to the current proportional valve, the current demand being a demand corresponding to a current cycle;

[0012] Based on the current demand and the current working state, current control data of the current proportional valve in the current cycle is determined, and the current proportional valve is controlled according to the current control data.

[0013] By adopting the above technical solution, the historical data of the current proportional valve is obtained, including the control data, opening data and flow data in the historical period, and the historical data is analyzed in the time domain and frequency domain, and the first time domain function relationship between the control data and the opening data, and the second time domain function relationship between the opening data and the flow data are established. Based on the above functional relationship and frequency domain characteristics, the working state of the current proportional valve can be accurately judged, which is the premise for achieving precise control. By accurately grasping the current working state, the control strategy can be adjusted in time to adapt to different operating conditions. Furthermore, the frequency domain characteristic vector matrix is ​​used to predict the current demand of the current proportional valve. This process fully considers the periodicity and trend of the historical data, making the prediction result more reliable. According to the current demand and the current working state, the control data in the current period is determined, and the proportional valve is controlled according to this data, and the prediction and analysis results are transformed into actual actions, realizing the precise control of the proportional valve.

[0014] In a possible implementation, the performing of time domain analysis and frequency domain analysis on the historical data to obtain a first time domain function relationship between the control data and the opening data, a second time domain function relationship between the opening data and the flow data, and a frequency domain feature vector matrix corresponding to the historical data includes:

[0015] Acquire a first standard conversion relationship between control data and standard opening data and a second standard conversion relationship between opening data and standard flow data;

[0016] Based on the first standard conversion relationship, determine the historical standard opening data corresponding to each historical control data;

[0017] Performing time domain analysis on the historical standard opening data and the corresponding historical opening data corresponding to the historical control data in the historical data to obtain a first time domain function relationship with the historical period as the horizontal axis and the first historical difference as the vertical axis, wherein the first historical difference is the difference between the historical standard opening data and the corresponding historical opening data;

[0018] Based on the second standard conversion relationship, determine the historical standard flow data corresponding to each historical opening data;

[0019] Performing time domain analysis on the historical standard flow data corresponding to the historical opening data in the historical data and the corresponding historical flow data to obtain a second time domain function relationship with the historical period as the horizontal axis and the second historical difference as the vertical axis, wherein the second historical difference is the difference between the historical standard flow data and the corresponding historical opening data;

[0020] Performing frequency domain analysis on the historical control data, the historical opening data and the historical flow data in the historical data, respectively, to obtain a first frequency domain feature vector corresponding to the historical control data, a second frequency domain feature vector corresponding to the opening data and a third frequency domain feature vector corresponding to the historical flow data;

[0021] The first frequency domain eigenvector, the second frequency domain eigenvector and the third frequency domain eigenvector are integrated to obtain a frequency domain eigenvector matrix corresponding to the historical data.

[0022] By adopting the above technical solution and through in-depth time domain and frequency domain analysis, not only the dynamic deviation and performance of the proportional valve in the control process are revealed, but also through the extraction and integration of frequency domain feature vectors, a rich information basis is provided for subsequent precise prediction and control, providing a strong guarantee for the stable operation and efficient output of industrial production.

[0023] In a possible implementation, determining the current working state of the current proportional valve based on the first time domain function relationship and the second time domain function relationship includes:

[0024] Based on the first time-domain functional relationship, determining a first change trend between the control data and the opening data, and based on the first change trend, predicting a first characteristic value of the current proportional valve in a current cycle;

[0025] Based on the first characteristic value and the first standard conversion relationship, determining a current opening state of the current proportional valve, wherein the current opening state is used to characterize a current conversion relationship between control data and opening data of the current proportional valve in a current cycle;

[0026] Based on the second time-domain functional relationship, a second change trend between the opening data and the flow data, and based on the second change trend, predicting a second characteristic value of the current proportional valve in a current cycle;

[0027] Based on the second characteristic value and the second standard conversion relationship, a current flow state of the current proportional valve is determined, and the current flow state is used to characterize a current conversion relationship between the opening data and the flow data of the current proportional valve in a current cycle.

[0028] By adopting the above technical solution, the changing trends among control data, opening data and flow data are accurately analyzed, and the characteristic value and standard conversion relationship are used to determine the current working state of the proportional valve, which provides a scientific basis for real-time evaluation and adjustment of the performance of the proportional valve.

[0029] In a possible implementation, predicting the current demand corresponding to the current proportional valve based on the frequency domain eigenvector matrix includes:

[0030] Obtaining a historical demand corresponding to the current proportional valve, where one historical demand corresponds to one historical period, and the historical demand includes a plurality of historical sub-demands, and each historical sub-demand corresponds to a time period;

[0031] Inputting the frequency domain eigenvector matrix into a periodic cycle network model, and obtaining the sub-demand corresponding to each time period in the current cycle corresponding to the periodic cycle network model;

[0032] The sum of each of the sub-demand quantities is calculated to obtain the current demand quantity corresponding to the current proportional valve.

[0033] By adopting the above technical solution and utilizing the frequency domain eigenvector matrix and periodic cycle network model, an accurate prediction of the current proportional valve demand is achieved. This not only takes into account the periodic changes in the data, but also makes full use of historical data and model prediction capabilities, providing strong data support for flow control and system optimization in industrial production.

[0034] In a possible implementation, determining the current control data of the current proportional valve in the current cycle based on the current demand and the current working state includes:

[0035] Obtaining a historical demand corresponding to the current proportional valve, wherein the historical demand includes a historical sub-demand corresponding to each historical period;

[0036] Determine a historical duty cycle corresponding to each historical period based on each historical sub-demand of the current proportional valve and the corresponding historical flow data;

[0037] Determine the target control data corresponding to the current proportional valve in the current cycle based on the historical duty cycle corresponding to each historical cycle and the current demand;

[0038] Based on the current working state, current control data corresponding to the target control data is determined.

[0039] By adopting the above technical solution, the current proportional valve control data can be accurately determined by comprehensively considering the current demand, current working status and historical data. It not only utilizes the wisdom of historical data, but also fully considers the current actual operating conditions, providing strong technical support for flow control and system optimization in industrial production.

[0040] In a possible implementation, based on each historical sub-demand of the current proportional valve and the corresponding historical flow data, the historical duty ratio corresponding to each historical period is determined, and the process of determining the historical duty ratio corresponding to each historical period includes:

[0041] Determine a first difference threshold and a second difference threshold corresponding to each of the historical sub-demands;

[0042] Calculate the target difference between each historical sub-demand and the corresponding historical sub-flow data, and determine the target difference less than the first difference threshold as the first target difference, and determine the target difference greater than the second difference threshold as the second target difference;

[0043] Calculating a first ratio of the number of the first target difference values ​​to the number of time periods in the historical cycle to obtain a first duty cycle, and calculating a second duty cycle based on a second ratio of the number of the second target difference values ​​to the number of time periods in the historical cycle;

[0044] Based on the first duty cycle and the second duty cycle, a historical duty cycle corresponding to the historical period is obtained.

[0045] By adopting the above technical solution, the historical duty cycle corresponding to each historical period is determined by meticulously analyzing the relationship between the historical sub-demands and the corresponding historical flow data. Not only the direct difference between the demand and flow data is considered, but also the quantitative indicators reflecting the performance of the proportional valve are obtained by setting the difference threshold, quantitative analysis and statistical analysis.

[0046] In a possible implementation, determining the target control data corresponding to the current proportional valve in the current cycle based on the historical duty cycle corresponding to each historical cycle and the current demand includes:

[0047] Filtering out a target historical duty cycle from the historical duty cycles corresponding to each historical period, wherein the target historical duty cycle is a historical duty cycle in which the first duty cycle is greater than a first duty cycle threshold value and / or the second duty cycle is greater than a second duty cycle threshold value;

[0048] Determine the similarity between the historical period corresponding to each target historical duty cycle and the current period;

[0049] Based on the similarity, determine a target historical period, wherein the similarity between the target historical period and the current period is greater than a similarity threshold, and the similarity between the target historical period and the current period is greater than the similarity between other historical periods and the current period;

[0050] Based on the historical duty cycle corresponding to the target historical cycle and the sub-demand corresponding to each time period in the current cycle, the target control data corresponding to the current proportional valve in the current cycle is determined.

[0051] By adopting the above technical solution, through carefully screening the historical duty cycle, calculating the similarity between the historical cycle and the current cycle, and determining the target control data accordingly, the accurate formulation of the current proportional valve control strategy is achieved. It not only utilizes historical data, but also fully considers the current actual needs, providing strong technical support for flow control and system optimization in industrial production.

[0052] In a second aspect, the present application provides a high-precision proportional valve control device, which adopts the following technical solution:

[0053] A high-precision control device for a proportional valve, comprising:

[0054] An acquisition module, used to acquire historical data of the current proportional valve, wherein the historical data includes historical control data, historical opening data and historical flow data corresponding to a historical period, and the historical control data is data for controlling parameters of the current proportional valve;

[0055] An analysis module, used for performing time domain analysis and frequency domain analysis on the historical data to obtain a first time domain function relationship between the control data and the opening data, a second time domain function relationship between the opening data and the flow data, and a frequency domain feature vector matrix corresponding to the historical data;

[0056] A determination module, configured to determine a current working state of the current proportional valve based on the first time domain functional relationship and the second time domain functional relationship;

[0057] A prediction module, used to predict the current demand corresponding to the current proportional valve based on the frequency domain feature vector matrix, where the current demand is the demand corresponding to the current cycle;

[0058] The control module is used to determine the current control data of the current proportional valve in the current cycle based on the current demand and the current working state, and control the current proportional valve according to the current control data.

[0059] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0060] An electronic device, comprising:

[0061] at least one processor;

[0062] Memory;

[0063] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the method for high-precision control of a proportional valve described in the first aspect above.

[0064] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0065] A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the high-precision control method of a proportional valve described in the first aspect.

[0066] In summary, this application includes the following beneficial technical effects:

[0067] By adopting the above technical solution, the historical data of the current proportional valve is obtained, including the control data, opening data and flow data in the historical period, and the historical data is analyzed in the time domain and frequency domain, and the first time domain function relationship between the control data and the opening data, and the second time domain function relationship between the opening data and the flow data are established. Based on the above functional relationship and frequency domain characteristics, the working state of the current proportional valve can be accurately judged, which is the premise for achieving precise control. By accurately grasping the current working state, the control strategy can be adjusted in time to adapt to different operating conditions. Furthermore, the frequency domain characteristic vector matrix is ​​used to predict the current demand of the current proportional valve. This process fully considers the periodicity and trend of the historical data, making the prediction result more reliable. According to the current demand and the current working state, the control data in the current period is determined, and the proportional valve is controlled according to this data, and the prediction and analysis results are transformed into actual actions, realizing the precise control of the proportional valve. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 It is a flow chart of a high-precision control method of a proportional valve provided in an embodiment of the present application;

[0069] Figure 2 It is a block diagram of a high-precision control device for a proportional valve provided in an embodiment of the present application;

[0070] Figure 3 It is a schematic diagram of an electronic device provided in an embodiment of the present application.

[0071] Attached figures: 20, high-precision control device for proportional valve; 210, acquisition module; 220, analysis module; 230, determination module; 240, prediction module; 250, control module; 30, electronic device; 301, processor; 302, bus; 303, memory; 304, transceiver. DETAILED DESCRIPTION

[0072] The following is combined with Figure 1 -Attached Figure 3 This application is described in further detail.

[0073] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0074] In order to facilitate understanding of the technical solution proposed in this application, several elements introduced in the description of this application are first introduced here. It should be understood that the following introduction is only for the convenience of understanding these elements, so as to understand the content of the embodiments of this application, and does not necessarily cover all possible situations.

[0075] Proportional valve, also known as electro-hydraulic proportional valve, can convert the input electrical signal into force or displacement in proportion to achieve continuous control of parameters such as pressure and flow. There are various control methods for proportional valves. The following are some common control methods:

[0076] 1. Control method based on electrical-mechanical conversion

[0077] Electromagnetic type: Proportional electromagnet is used as the electro-mechanical conversion element. The proportional electromagnet converts the input current signal into mechanical output, that is, output force and displacement, and then controls parameters such as pressure, flow and direction.

[0078] Electric type: DC servo motor is used as the electro-mechanical conversion element. The DC servo motor converts the input electrical signal into the rotation speed of the rotational motion, and then outputs force and displacement through the reduction device and conversion mechanism such as the screw nut, gear rack or cam to control the output hydraulic parameters.

[0079] Electro-hydraulic type: uses a torque motor and a nozzle-baffle structure as the pilot control stage. Different electrical signals are input to the torque motor, and the displacement or angular displacement is output through the baffle connected to it (sometimes the armature of the torque motor is the baffle). Changing the distance between the baffle and the nozzle changes the fluid resistance of the oil sprayed from the nozzle, thereby controlling the output parameters.

[0080] 2. Control Method Based on Signal Conditioning

[0081] Voltage method: adjust the opening of the proportional valve by adjusting the control voltage.

[0082] Current method: The opening of the proportional valve is adjusted by adjusting the control current. The driving force of the electromagnetic component of the proportional valve has a good linear relationship with the current.

[0083] PWM control method: adjust the opening of the proportional valve by adjusting the PWM duty cycle.

[0084] The present application provides a high-precision control method for a proportional valve. Figure 1 As shown, the method provided in the embodiment of the present application is performed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S101 to S105, wherein:

[0085] Step S101, obtaining historical data of the current proportional valve.

[0086] Among them, the historical data includes historical control data, historical opening data and historical flow data corresponding to the historical cycle. The historical control data is the data for controlling the current proportional valve parameters, wherein one historical cycle corresponds to one historical control data, one historical opening data and one historical flow data, and one historical cycle can be one day or one time period. Specifically, the proportional valve corresponds to three data: control data, opening data and flow data. The control data is the data corresponding to the control instruction input by the staff (such as voltage or current, etc.), the opening data is the data for controlling the change of the proportional valve opening after the proportional valve receives the control data (such as the degree of opening of the valve, etc.), and the flow data is the water flow change data caused by the change of the proportional valve opening after the proportional valve receives the control data (such as the volume of fluid passing through the proportional valve valve per unit time). More specifically, the opening data can correspond to different data according to the type of proportional valve. For example, the opening data can be displacement and / or output force, etc., which is not limited in the embodiments of the present application.

[0087] The electronic device records each control instruction received by the current proportional valve, converts the control instruction into corresponding control data, obtains the opening data and flow data corresponding to the control instruction through the sensor installed on the current proportional valve, and records the control data, opening data and flow data corresponding to the control instruction and the cycle to which the control instruction belongs in the database corresponding to the current proportional valve. Among them, the sensor corresponding to the opening data is related to the model corresponding to the current proportional valve.

[0088] Specifically, the electronic device may obtain corresponding historical data from a database corresponding to the current proportional valve.

[0089] Step S102: Perform time domain analysis and frequency domain analysis on the historical data to obtain a first time domain function relationship between the control data and the opening data, a second time domain function relationship between the opening data and the flow data, and a frequency domain feature vector matrix corresponding to the historical data.

[0090] The first time-domain function relationship can represent the trend of the correlation between the control data and the opening data changing over time, and the second time-domain function relationship can represent the trend of the correlation between the opening data and the flow data changing over time.

[0091] Specifically, the process of establishing the first time domain function relationship (control data and opening data) can be: using statistical analysis methods (such as linear regression, nonlinear regression, time series analysis, etc.) to explore the relationship between the control data and the opening data. According to the analysis results, a mathematical model is fitted to describe how the control data affects the opening data, forming the first time domain function relationship.

[0092] Similarly, the process of establishing the second time domain function relationship (opening data and flow data) can be: using statistical analysis methods to analyze the relationship between the opening data and the flow data. According to the analysis results, a mathematical model describing how the opening data affects the flow data is fitted to form the second time domain function relationship.

[0093] Furthermore, the pre-processed historical data is subjected to Fourier transform (FFT), and the historical control data, historical opening data, and historical flow data corresponding to each period in the historical data are converted into frequency domain data corresponding to the historical data. In the frequency domain data, key features such as main frequency, secondary frequency, frequency distribution, amplitude, etc. are identified and extracted. The extracted frequency domain features are arranged in chronological order or specific rules to form a matrix to obtain the frequency domain feature vector matrix. Among them, each row of the frequency domain feature vector matrix represents the frequency domain feature of a time point, and each column represents a specific frequency domain feature (such as main frequency, amplitude, etc.) for subsequent prediction or analysis.

[0094] Step S103: Determine the current working state of the current proportional valve based on the first time domain function relationship and the second time domain function relationship.

[0095] The current working state includes an opening state and a flow state. The opening state may be a normal opening or an opening deviation degree, and the flow state may be a normal flow or a flow deviation degree.

[0096] After obtaining the first time domain function relationship and the second time domain function relationship, the known first time domain function relationship (the mathematical model between the control data and the opening data) can be used, and the detection control data can be input into the model. The predicted detection opening data is obtained through model calculation. The predicted detection opening data is compared with the preset normal range of opening. If the predicted detection opening data is within the normal range of opening, the opening state is "normal opening". If the predicted detection opening data exceeds the normal range of opening, the opening state is determined as "opening deviation degree" according to the degree of deviation, and the opening state is obtained using the formula opening deviation degree = (detection opening data-first target value) / (maximum value of the normal range of opening-minimum value of the normal range of opening), where the first target value is the data that is closer to the opening flow data between the maximum value of the normal range of opening and the minimum value of the normal range of opening.

[0097] Similarly, using the known second time domain function relationship (the mathematical model between the opening data and the flow data), the known detection opening data is input into the model. Through model calculation, the predicted detection flow data is obtained. The predicted detection flow data is compared with the preset normal flow range. If the predicted detection flow data is within the normal flow range, the flow state is "normal flow". If the predicted detection flow data exceeds the normal flow range, the flow state is determined as "flow deviation degree" according to the degree of deviation, and the flow state is obtained using the formula flow deviation degree = (detection flow data-second target value) / (maximum value of the normal flow range-minimum value of the normal flow range), where the second target value is the data that is closer to the detection flow data between the maximum value of the normal flow range and the minimum value of the normal flow range.

[0098] Furthermore, after the flow state and the opening state are obtained, the current working state of the current proportional valve is obtained.

[0099] Step S104: predicting the current demand corresponding to the current proportional valve based on the frequency domain eigenvector matrix.

[0100] The current demand is the demand corresponding to the current cycle, that is, the demand for liquid volume in the current cycle.

[0101] Specifically, the frequency domain feature vector matrix is ​​input into the trained deep learning model, the deep learning model is used to predict the demand of the current cycle, and the output of the deep learning model is obtained to obtain the predicted value of the demand of the current proportional valve in the current cycle, thereby obtaining the current demand corresponding to the current proportional valve. Among them, the deep learning model can be a recurrent neural network (RNN), a long short-term memory network (LSTM), a support vector machine (SVM) or a random forest, etc. The deep learning model can be trained using a large number of frequency domain feature vector sub-matrices corresponding to historical cycles and the corresponding actual historical demand.

[0102] Step S105: based on the current demand and the current working state, determine the current control data of the current proportional valve in the current cycle, and control the current proportional valve according to the current control data.

[0103] After obtaining the current demand and current working state corresponding to the current proportional valve in the current cycle, the current control data of the current proportional valve in the current cycle can be determined according to the current demand and the current working state. Specifically, when the current working state is normal, the predicted current demand is used as the current control data; when the opening state is not normal and the flow state is normal in the current working state, the current control data is obtained based on the formula current control data = current demand / (1 + opening deviation degree); when the opening state is normal and the flow state is not normal in the current working state, the current control data is obtained based on the formula current control data = current demand / (1 + flow deviation degree); when the opening state is not normal and the flow state is not normal in the current working state, the current control data is obtained based on the formula current control data = current demand / (1 + flow deviation degree + opening deviation degree).

[0104] Furthermore, after the current control data is obtained, the current control data is sent to an electronic device corresponding to a worker corresponding to the current proportional valve, so that the current proportional valve can be controlled according to the current control data.

[0105] The embodiment of the present application provides a high-precision control method for a proportional valve. By adopting the above technical solution, the historical data of the current proportional valve is obtained, including the control data, opening data and flow data in the historical period, and the historical data is analyzed in the time domain and frequency domain, and the first time domain function relationship between the control data and the opening data, and the second time domain function relationship between the opening data and the flow data are established. Based on the above functional relationship and frequency domain characteristics, the working state of the current proportional valve can be accurately judged, which is the premise for achieving precise control. By accurately grasping the current working state, the control strategy can be adjusted in time to adapt to different operating conditions. Further, the current demand of the current proportional valve is predicted using the frequency domain feature vector matrix. This process fully considers the periodicity and trend of the historical data, making the prediction result more reliable. According to the current demand and the current working state, the control data in the current period is determined, and the proportional valve is controlled according to this data, and the prediction and analysis results are converted into actual actions, realizing the precise control of the proportional valve.

[0106] A possible implementation of the embodiment of the present application is that in the above step S102, the historical data is subjected to time domain analysis and frequency domain analysis to obtain a first time domain function relationship between the control data and the opening data, a second time domain function relationship between the opening data and the flow data, and a frequency domain feature vector matrix corresponding to the historical data, which may specifically include:

[0107] Acquire a first standard conversion relationship between control data and standard opening data and a second standard conversion relationship between opening data and standard flow data;

[0108] Based on the first standard conversion relationship, determine the historical standard opening data corresponding to each historical control data;

[0109] Performing time domain analysis on the historical standard opening data and the corresponding historical opening data corresponding to the historical control data in the historical data, obtaining a first time domain function relationship with the historical period as the horizontal axis and the first historical difference as the vertical axis, wherein the first historical difference is the difference between the historical standard opening data and the corresponding historical opening data;

[0110] Based on the second standard conversion relationship, determine the historical standard flow data corresponding to each historical opening data;

[0111] Performing time domain analysis on the historical standard flow data corresponding to the historical opening data and the corresponding historical flow data in the historical data, obtaining a second time domain function relationship with the historical period as the horizontal axis and the second historical difference as the vertical axis, wherein the second historical difference is the difference between the historical standard flow data and the corresponding historical opening data;

[0112] Performing frequency domain analysis on the historical control data, the historical opening data and the historical flow data in the historical data, respectively, to obtain a first frequency domain feature vector corresponding to the historical control data, a second frequency domain feature vector corresponding to the opening data and a third frequency domain feature vector corresponding to the historical flow data;

[0113] The first frequency domain eigenvector, the second frequency domain eigenvector and the third frequency domain eigenvector are integrated to obtain a frequency domain eigenvector matrix corresponding to the historical data.

[0114] Among them, the first standard conversion relationship is the conversion relationship between control data and standard opening data, for example, the conversion relationship between voltage data and valve opening degree, and the second standard conversion relationship is the conversion relationship between opening data and standard flow data, for example, the conversion relationship between valve opening degree and the volume of liquid flowing through the valve per unit time. The first standard conversion relationship and the second standard conversion relationship corresponding to the current proportional valve are recorded in the database corresponding to the current proportional valve, and the electronic device can obtain the first standard conversion relationship and the second standard conversion relationship corresponding to the current proportional valve from the corresponding database. Among them, one control data corresponds to one standard opening data, and the standard opening data is the corresponding opening data when the current proportional valve error is ignored and there is no fault. Similarly, the standard flow data is the corresponding flow data when the current proportional valve error is ignored and there is no fault.

[0115] The establishment of the time domain function relationship can reveal the dynamic connection between the control input and output, and provide a mathematical basis for accurate prediction and control. At the same time, the frequency domain eigenvector matrix generated by the frequency domain analysis further reveals the periodicity and trend characteristics in the data, which helps to more comprehensively understand the operation law of the proportional valve. Therefore, the time domain function and the frequency domain eigenvector matrix can be established based on historical data. Specifically, for each historical period, the difference between the historical standard opening data and the corresponding historical opening data (the first historical difference) is calculated, and the first time domain function relationship diagram is drawn with these first historical differences as the vertical axis and the historical period as the horizontal axis. Similarly, for each historical period, the difference between the historical standard flow data and the corresponding historical flow data (the second historical difference) is calculated. And these second historical differences are used as the vertical axis and the historical period as the horizontal axis to draw the second time domain function relationship diagram.

[0116] Further, the historical control data, historical opening data and historical flow data corresponding to each period are respectively transformed in the frequency domain (such as Fourier transform) to obtain their representation in the frequency domain, so as to obtain the characteristic subvectors corresponding to the historical control data, historical opening data and historical flow data of each historical period, and each characteristic subvector corresponding to the historical control data is sorted in the periodic order to form a characteristic vector, so as to obtain the frequency domain characteristic vector corresponding to the historical control data. Similarly, each characteristic subvector corresponding to the historical opening data is sorted in the periodic order to form a characteristic vector, so as to obtain the frequency domain characteristic vector corresponding to the historical opening data; each characteristic subvector corresponding to the historical flow data is sorted in the periodic order to form a characteristic vector, so as to obtain the frequency domain characteristic vector corresponding to the historical flow data. Thus, the first frequency domain characteristic vector, the second frequency domain characteristic vector and the third frequency domain characteristic vector are obtained. These frequency domain characteristic vectors are arranged in the order of the data set to form a matrix, namely the frequency domain characteristic vector matrix. Among them, each row of the frequency domain characteristic vector matrix represents the frequency domain feature in a historical period, and each column represents the frequency domain feature of different data sets.

[0117] A possible implementation of the embodiment of the present application, in the above embodiment, based on the first time domain function relationship and the second time domain function relationship, determining the current working state of the current proportional valve may specifically include:

[0118] Based on the first time domain function relationship, determine a first change trend between the control data and the opening data, and based on the first change trend, predict a first characteristic value of the current proportional valve in the current cycle;

[0119] Based on the first characteristic value and the first standard conversion relationship, determining a current opening state of the current proportional valve, the current opening state being used to characterize a current conversion relationship between control data and opening data of the current proportional valve in a current cycle;

[0120] Based on the second time domain function relationship, a second change trend between the opening data and the flow data, and based on the second change trend, predicting a second characteristic value of the current proportional valve in the current cycle;

[0121] Based on the second characteristic value and the second standard conversion relationship, the current flow state of the current proportional valve is determined, and the current flow state is used to characterize the current conversion relationship between the opening data and the flow data of the current proportional valve in the current cycle.

[0122] The first characteristic value is the difference between the predicted current standard opening data and the current actual opening data, and the second characteristic value is the difference between the predicted current standard flow data and the current actual flow data.

[0123] The first time domain function relationship diagram takes the historical period as the horizontal axis and the first historical difference as the vertical axis, showing the changing trend of the difference between the control data and the standard opening data (i.e., the first historical difference) over time. The type (such as linear, nonlinear, periodic, etc.) and parameters of this changing trend can be determined by observing or fitting the trend line. Specifically, the first eigenvalue of the current cycle is predicted using the determined changing trend and the control data of the current cycle. Further, the predicted first eigenvalue is converted into an evaluation of the current opening state of the current proportional valve using the known first standard conversion relationship. The current opening state not only reflects the difference between the actual conversion relationship and the standard conversion relationship between the control data and the opening data in the current cycle, but also provides information about the degree and nature of this difference.

[0124] The second time domain function relationship diagram uses the historical cycle as the horizontal axis and the second historical difference as the vertical axis (note that the second historical difference here should be the difference between the standard flow data and the actual flow data), showing the changing trend of the difference between the opening data and the standard flow data over time. Similarly, by observing or fitting the trend line, the type and parameters of this changing trend are determined. Specifically, the second eigenvalue of the current cycle is predicted using the determined changing trend and the opening data of the current cycle. Further, using the known second standard conversion relationship, the predicted second eigenvalue is converted into an evaluation of the current flow state of the current proportional valve. The current flow state reflects the difference between the actual conversion relationship and the standard conversion relationship between the opening data and the flow data in the current cycle, and provides information about the degree and nature of this difference.

[0125] In a possible implementation of the embodiment of the present application, in the above step S104, based on the frequency domain characteristic vector matrix, predicting the current demand corresponding to the current proportional valve may specifically include:

[0126] Get the historical demand corresponding to the current proportional valve. One historical demand corresponds to one historical period. The historical demand includes multiple historical sub-demands, and each historical sub-demand corresponds to a time period.

[0127] Input the frequency domain eigenvector matrix into the periodic cycle network model, and obtain the sub-demand corresponding to each time period in the current cycle corresponding to the periodic cycle network model;

[0128] The sum of each sub-demand is calculated to obtain the current demand corresponding to the current proportional valve.

[0129] Among them, a historical cycle can be divided according to a cycle division rule to obtain multiple time periods, and the cycle division rule can be input by a staff. It is worth noting that the duration corresponding to each cycle is the same, and the cycle division rule corresponding to each cycle is the same rule.

[0130] Specifically, historical demand data corresponding to the current proportional valve is obtained from a database corresponding to the current proportional valve, wherein the historical demand data is arranged in time series, each historical demand includes multiple historical sub-demands, and each historical sub-demand corresponds to a specific time period (eg, every hour, every day, or every week).

[0131] Furthermore, the historical demand is organized into a form including a timestamp and corresponding sub-demand, and the frequency domain analysis is performed on the historical demand data through methods such as Fourier transform to extract the frequency domain feature vector matrix, wherein the frequency domain feature vector matrix contains information that can reflect different frequency components in the historical demand.

[0132] The frequency domain feature vector matrix of the current proportional valve is input into the trained periodic cycle network model, and the sub-demand forecast value of each time period in the current cycle output by the periodic cycle network model is obtained. Among them, a periodic cycle network model (such as long short-term memory network LSTM, gated recurrent unit GRU or time convolution network TCN, etc.) is selected, which is suitable for processing time series data and capturing its periodicity, and a large number of demand samples and their corresponding frequency domain feature vector matrix samples are used to train the periodic cycle network model to obtain a trained periodic cycle network model.

[0133] Furthermore, the sub-demand quantity prediction values ​​of each time period in the current cycle are added together to obtain the total demand quantity prediction value of the current proportional valve in the current cycle.

[0134] A possible implementation of the embodiment of the present application, in the above embodiment, based on the current demand and the current working state, determining the current control data of the current proportional valve in the current cycle may specifically include:

[0135] Obtain the historical demand corresponding to the current proportional valve, the historical demand includes the historical sub-demand corresponding to each historical period;

[0136] Based on each historical sub-demand of the current proportional valve and the corresponding historical flow data, determine the historical duty cycle corresponding to each historical period;

[0137] Based on the historical duty cycle corresponding to each historical cycle and the current demand, determine the target control data corresponding to the current proportional valve in the current cycle;

[0138] Based on the current working state, current control data corresponding to the target control data is determined.

[0139] The historical duty cycle is the ratio of the target number to the number of time periods in the historical cycle, where the target number is the number of times the absolute value of the difference between the historical sub-demand and historical sub-flow data is greater than a certain value. The historical duty cycle reflects the proportion of time periods with significant differences between flow and demand in the historical cycle.

[0140] Specifically, the historical demand data of the current proportional valve and the historical sub-demand corresponding to each time period in each historical cycle are obtained from the database corresponding to the current proportional valve. At the same time, the historical sub-flow data corresponding to these historical sub-demands are obtained, and the historical sub-demands and historical sub-flow data are arranged in chronological order. Among them, since the flow data is measured at a measurement moment, the historical sub-flow data corresponding to each historical sub-demand can be obtained according to the time period to which the historical moment corresponding to the historical flow data belongs.

[0141] Furthermore, for each time period in each historical cycle, the difference between the historical sub-demand and the historical sub-flow data is calculated and the absolute value is taken. Then, the number of time periods in each historical cycle whose absolute value of the difference is greater than the set threshold is counted. This number is the target number, and the target number in each historical cycle is divided by the total number of time periods in the cycle to obtain the historical duty cycle. Among them, the difference threshold is set in advance, and the difference threshold is used to determine whether the difference between the historical sub-demand and the historical sub-flow data is significant.

[0142] Furthermore, based on the time series characteristics of historical demand, a suitable forecasting method (such as time series analysis, machine learning model, etc.) is used to forecast the total demand of the current cycle, and the predicted total demand of the current cycle and the set target duty cycle are used, combined with the maximum flow capacity of the current proportional valve, to calculate the target control data of the current cycle. Among them, the target duty cycle is set in advance, and the target duty cycle can reflect the matching degree between the expected flow and demand.

[0143] Furthermore, after obtaining the target control data of the current cycle, the current control data is obtained based on the formula: current control data = target control data / (1 + flow deviation degree + opening deviation degree). When the flow state is normal, the flow deviation degree is 0; similarly, when the opening state is normal, the opening deviation degree is 0.

[0144] A possible implementation of the embodiment of the present application is that in the above embodiment, based on each historical sub-demand of the current proportional valve and the corresponding historical flow data, the historical duty ratio corresponding to each historical period is determined. The determination process of the historical duty ratio corresponding to each historical period may specifically include:

[0145] Determine a first difference threshold and a second difference threshold corresponding to each historical sub-demand;

[0146] Calculate the target difference between each historical sub-demand and the corresponding historical sub-flow data, and determine the target difference that is less than the corresponding first difference threshold as the first target difference, and determine the target difference that is greater than the corresponding second difference threshold as the second target difference;

[0147] Calculating a first ratio of the number of first target differences to the number of time periods in the historical cycle to obtain a first duty cycle, and obtaining a second duty cycle based on a second ratio of the number of second target differences to the number of time periods in the historical cycle;

[0148] Based on the first duty cycle and the second duty cycle, a historical duty cycle corresponding to the historical period is obtained.

[0149] Specifically, for each time period in the historical cycle: obtain the confidence level (such as 80%) corresponding to the current proportional valve from the database corresponding to the current proportional valve, and based on the confidence level and the historical sub-demand corresponding to the time period, obtain the demand confidence range corresponding to the historical sub-demand, and use the opposite number corresponding to the minimum value in the demand confidence range as the first difference threshold, and use the maximum value in the demand confidence range as the second difference threshold. It is worth noting that the specific process of calculating the confidence interval corresponding to a known number based on the confidence level corresponding to the number is a process well known to those skilled in the art, and will not be described in detail in the embodiments of the present application.

[0150] Furthermore, for each historical sub-demand, the difference between it and the corresponding historical sub-flow data, i.e., the target difference, is calculated. According to the first difference threshold and the second difference threshold corresponding to the historical sub-demand, the target difference is divided into two categories: the target difference less than the first difference threshold is recorded as the first target difference, and the target difference greater than the second difference threshold is recorded as the second target difference.

[0151] Further, the number of first target differences in the historical period is counted, and the ratio of this number to the total number of time periods in the historical period is calculated to obtain the first duty cycle. Similarly, the number of second target differences in the historical period is counted, and the ratio of this number to the total number of time periods in the historical period is calculated to obtain the second duty cycle. Further, the first duty cycle and the second duty cycle are used as historical duty cycles.

[0152] A possible implementation of the embodiment of the present application, in the above embodiment, based on the historical duty cycle corresponding to each historical cycle and the current demand, determining the target control data corresponding to the current proportional valve in the current cycle may specifically include:

[0153] Filtering out a target historical duty cycle from the historical duty cycles corresponding to each historical period, where the target historical duty cycle is a historical duty cycle in which the first duty cycle is greater than a first duty cycle threshold value and / or the second duty cycle is greater than a second duty cycle threshold value;

[0154] Determine the similarity between the historical period corresponding to each target historical duty cycle and the current period;

[0155] Based on the similarity, a target historical period is determined, the similarity between the target historical period and the current period is greater than a similarity threshold, and the similarity between the target historical period and the current period is greater than the similarity between other historical periods and the current period;

[0156] Based on the historical duty cycle corresponding to the target historical cycle and the sub-demand corresponding to each time period in the current cycle, the target control data corresponding to the current proportional valve in the current cycle is determined.

[0157] Specifically, all historical cycles are traversed to obtain the historical duty cycle data corresponding to each historical cycle. For each historical cycle, its historical duty cycle is checked (assuming that each cycle has two duty cycle data: the first duty cycle and the second duty cycle). If the first duty cycle is greater than the first duty cycle threshold, or the second duty cycle is greater than the second duty cycle threshold, the historical cycle and its corresponding historical duty cycle are marked as the target historical duty cycle. The first duty cycle threshold and the second duty cycle threshold can be set according to actual needs.

[0158] Furthermore, the date features of the current cycle are obtained, such as date, day of the week, month, quarter, etc., and the date features of the historical cycle corresponding to each target historical duty cycle are extracted. The matching degree between the date features of the current cycle and the date features of each historical cycle is calculated based on the cosine distance, such as the same date, the same day of the week, the same month, etc., to obtain the similarity between each target historical cycle and the current cycle. The similarity can be a value between 0 and 1, and the larger the value, the higher the similarity.

[0159] From all target historical periods, select the historical period with a similarity greater than the similarity threshold as the candidate target historical period. If there are multiple candidate target historical periods, select the historical period with the highest similarity as the target historical period. The similarity threshold is set in advance, and the similarity threshold can be set according to actual needs, such as based on the statistical results of historical data or system performance requirements, which is not limited in the embodiments of the present application.

[0160] Furthermore, the historical duty cycle corresponding to the target historical cycle is obtained, and the target control data corresponding to the current cycle is determined according to the sub-demands of each time period in the current cycle and the historical duty cycle corresponding to the target historical cycle. Specifically, the first duty cycle and the second duty cycle corresponding to the target historical cycle are obtained, the first duty cycle is compared with the second duty cycle, and the demand confidence range corresponding to each historical sub-demand is calculated. If the first duty cycle is greater than the second duty cycle, the maximum value of the demand confidence range is multiplied by the number of time periods in the current cycle to calculate the target control data corresponding to the current cycle; if the first duty cycle is less than the second duty cycle, the minimum value of the demand confidence range is multiplied by the number of time periods in the current cycle to calculate the target control data corresponding to the current cycle; if the first duty cycle is equal to the second duty cycle, the middle value of the demand confidence range is multiplied by the number of time periods in the current cycle to calculate the target control data corresponding to the current cycle.

[0161] The above embodiment introduces a high-precision control method for a proportional valve from the perspective of a method flow, and the following embodiment introduces a high-precision control device for a proportional valve from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0162] See also Figure 2 The high-precision control device 20 for a proportional valve may specifically include: an acquisition module 210, an analysis module 220, a determination module 230, a prediction module 240 and a control module 250. Specifically:

[0163] A high-precision proportional valve control device 20, comprising:

[0164] An acquisition module 210 is used to acquire historical data of the current proportional valve, the historical data including historical control data, historical opening data and historical flow data corresponding to a historical period, and the historical control data is data for controlling the parameters of the current proportional valve;

[0165] The analysis module 220 is used to perform time domain analysis and frequency domain analysis on the historical data to obtain a first time domain function relationship between the control data and the opening data, a second time domain function relationship between the opening data and the flow data, and a frequency domain feature vector matrix corresponding to the historical data;

[0166] A determination module 230, configured to determine a current working state of the current proportional valve based on the first time domain function relationship and the second time domain function relationship;

[0167] A prediction module 240 is used to predict the current demand corresponding to the current proportional valve based on the frequency domain feature vector matrix, where the current demand is the demand corresponding to the current cycle;

[0168] The control module 250 is used to determine the current control data of the current proportional valve in the current cycle based on the current demand and the current working state, and control the current proportional valve according to the current control data.

[0169] In a possible implementation of the embodiment of the present application, when the analysis module 220 performs time domain analysis and frequency domain analysis on the historical data to obtain a first time domain function relationship between the control data and the opening data, a second time domain function relationship between the opening data and the flow data, and a frequency domain feature vector matrix corresponding to the historical data, it can be specifically used to:

[0170] Acquire a first standard conversion relationship between control data and standard opening data and a second standard conversion relationship between opening data and standard flow data;

[0171] Based on the first standard conversion relationship, determine the historical standard opening data corresponding to each historical control data;

[0172] Performing time domain analysis on the historical standard opening data and the corresponding historical opening data corresponding to the historical control data in the historical data, obtaining a first time domain function relationship with the historical period as the horizontal axis and the first historical difference as the vertical axis, wherein the first historical difference is the difference between the historical standard opening data and the corresponding historical opening data;

[0173] Based on the second standard conversion relationship, determine the historical standard flow data corresponding to each historical opening data;

[0174] Performing time domain analysis on the historical standard flow data corresponding to the historical opening data and the corresponding historical flow data in the historical data, obtaining a second time domain function relationship with the historical period as the horizontal axis and the second historical difference as the vertical axis, wherein the second historical difference is the difference between the historical standard flow data and the corresponding historical opening data;

[0175] Performing frequency domain analysis on the historical control data, the historical opening data and the historical flow data in the historical data, respectively, to obtain a first frequency domain feature vector corresponding to the historical control data, a second frequency domain feature vector corresponding to the opening data and a third frequency domain feature vector corresponding to the historical flow data;

[0176] The first frequency domain eigenvector, the second frequency domain eigenvector and the third frequency domain eigenvector are integrated to obtain a frequency domain eigenvector matrix corresponding to the historical data.

[0177] In a possible implementation of the embodiment of the present application, when the determination module 230 determines the current working state of the current proportional valve based on the first time domain function relationship and the second time domain function relationship, it can be specifically used to:

[0178] Based on the first time domain function relationship, determine a first change trend between the control data and the opening data, and based on the first change trend, predict a first characteristic value of the current proportional valve in the current cycle;

[0179] Based on the first characteristic value and the first standard conversion relationship, determining a current opening state of the current proportional valve, the current opening state being used to characterize a current conversion relationship between control data and opening data of the current proportional valve in a current cycle;

[0180] Based on the second time domain function relationship, a second change trend between the opening data and the flow data, and based on the second change trend, predicting a second characteristic value of the current proportional valve in the current cycle;

[0181] Based on the second characteristic value and the second standard conversion relationship, the current flow state of the current proportional valve is determined, and the current flow state is used to characterize the current conversion relationship between the opening data and the flow data of the current proportional valve in the current cycle.

[0182] In a possible implementation of the embodiment of the present application, when the prediction module 240 predicts the current demand corresponding to the current proportional valve based on the frequency domain feature vector matrix, it can be specifically used to:

[0183] Get the historical demand corresponding to the current proportional valve. One historical demand corresponds to one historical period. The historical demand includes multiple historical sub-demands, and each historical sub-demand corresponds to a time period.

[0184] Input the frequency domain eigenvector matrix into the periodic cycle network model, and obtain the sub-demand corresponding to each time period in the current cycle corresponding to the periodic cycle network model;

[0185] The sum of each sub-demand is calculated to obtain the current demand corresponding to the current proportional valve.

[0186] In a possible implementation of the embodiment of the present application, when the control module 250 determines the current control data of the current proportional valve in the current cycle based on the current demand and the current working state, it can be specifically used to:

[0187] Obtain the historical demand corresponding to the current proportional valve, the historical demand includes the historical sub-demand corresponding to each historical period;

[0188] Based on each historical sub-demand of the current proportional valve and the corresponding historical flow data, determine the historical duty cycle corresponding to each historical period;

[0189] Based on the historical duty cycle corresponding to each historical cycle and the current demand, determine the target control data corresponding to the current proportional valve in the current cycle;

[0190] Based on the current working state, current control data corresponding to the target control data is determined.

[0191] In a possible implementation of the embodiment of the present application, when the control module 250 determines the historical duty ratio corresponding to each historical period (for each historical period) based on each historical sub-demand of the current proportional valve and the corresponding historical flow data, it can be specifically used to:

[0192] Determine a first difference threshold and a second difference threshold corresponding to each historical sub-demand;

[0193] Calculate the target difference between each historical sub-demand and the corresponding historical sub-flow data, and determine the target difference that is less than the corresponding first difference threshold as the first target difference, and determine the target difference that is greater than the corresponding second difference threshold as the second target difference;

[0194] Calculating a first ratio of the number of first target differences to the number of time periods in the historical cycle to obtain a first duty cycle, and obtaining a second duty cycle based on a second ratio of the number of second target differences to the number of time periods in the historical cycle;

[0195] Based on the first duty cycle and the second duty cycle, a historical duty cycle corresponding to the historical period is obtained.

[0196] In a possible implementation of the embodiment of the present application, when the control module 250 determines the target control data corresponding to the current proportional valve in the current cycle based on the historical duty cycle corresponding to each historical cycle and the current demand, it can be specifically used to:

[0197] Filtering out a target historical duty cycle from the historical duty cycles corresponding to each historical period, where the target historical duty cycle is a historical duty cycle in which the first duty cycle is greater than a first duty cycle threshold value and / or the second duty cycle is greater than a second duty cycle threshold value;

[0198] Determine the similarity between the historical period corresponding to each target historical duty cycle and the current period;

[0199] Based on the similarity, a target historical period is determined, the similarity between the target historical period and the current period is greater than a similarity threshold, and the similarity between the target historical period and the current period is greater than the similarity between other historical periods and the current period;

[0200] Based on the historical duty cycle corresponding to the target historical cycle and the sub-demand corresponding to each time period in the current cycle, the target control data corresponding to the current proportional valve in the current cycle is determined.

[0201] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0202] See also Figure 3 , the embodiment of the present application also introduces an electronic device from the perspective of a physical device, such as Figure 3 As shown, Figure 3 The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0203] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0204] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0205] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0206] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0207] The electronic devices include but are not limited to: mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and can also be servers, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0208] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0209] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0210] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A high-precision control method for a proportional valve, characterized in that: include: Acquire historical data of the current proportional valve, wherein the historical data includes historical control data, historical opening data, and historical flow data corresponding to a historical period, and the historical control data is data for controlling parameters of the current proportional valve; Performing time domain analysis and frequency domain analysis on the historical data to obtain a first time domain function relationship between the control data and the opening data, a second time domain function relationship between the opening data and the flow data, and a frequency domain feature vector matrix corresponding to the historical data; Determining a current working state of the current proportional valve based on the first time domain functional relationship and the second time domain functional relationship; Based on the frequency domain eigenvector matrix, predicting a current demand corresponding to the current proportional valve, the current demand being a demand corresponding to a current cycle; Based on the current demand and the current working state, current control data of the current proportional valve in the current cycle is determined, and the current proportional valve is controlled according to the current control data.

2. The high-precision control method for a proportional valve according to claim 1, characterized in that: The time domain analysis and frequency domain analysis of the historical data are performed to obtain a first time domain function relationship between the control data and the opening data, a second time domain function relationship between the opening data and the flow data, and a frequency domain feature vector matrix corresponding to the historical data, including: Acquire a first standard conversion relationship between control data and standard opening data and a second standard conversion relationship between opening data and standard flow data; Based on the first standard conversion relationship, determine the historical standard opening data corresponding to each historical control data; Performing time domain analysis on the historical standard opening data and the corresponding historical opening data corresponding to the historical control data in the historical data to obtain a first time domain function relationship with the historical period as the horizontal axis and the first historical difference as the vertical axis, wherein the first historical difference is the difference between the historical standard opening data and the corresponding historical opening data; Based on the second standard conversion relationship, determine the historical standard flow data corresponding to each historical opening data; Performing time domain analysis on the historical standard flow data corresponding to the historical opening data in the historical data and the corresponding historical flow data to obtain a second time domain function relationship with the historical period as the horizontal axis and the second historical difference as the vertical axis, wherein the second historical difference is the difference between the historical standard flow data and the corresponding historical opening data; Performing frequency domain analysis on the historical control data, the historical opening data and the historical flow data in the historical data, respectively, to obtain a first frequency domain feature vector corresponding to the historical control data, a second frequency domain feature vector corresponding to the opening data and a third frequency domain feature vector corresponding to the historical flow data; The first frequency domain eigenvector, the second frequency domain eigenvector and the third frequency domain eigenvector are integrated to obtain a frequency domain eigenvector matrix corresponding to the historical data.

3. The high-precision control method for a proportional valve according to claim 2, characterized in that: The determining the current working state of the current proportional valve based on the first time domain functional relationship and the second time domain functional relationship includes: Based on the first time-domain functional relationship, determining a first change trend between the control data and the opening data, and based on the first change trend, predicting a first characteristic value of the current proportional valve in a current cycle; Based on the first characteristic value and the first standard conversion relationship, determining a current opening state of the current proportional valve, wherein the current opening state is used to characterize a current conversion relationship between control data and opening data of the current proportional valve in a current cycle; Based on the second time-domain functional relationship, a second change trend between the opening data and the flow data, and based on the second change trend, predicting a second characteristic value of the current proportional valve in a current cycle; Based on the second characteristic value and the second standard conversion relationship, a current flow state of the current proportional valve is determined, and the current flow state is used to characterize a current conversion relationship between the opening data and the flow data of the current proportional valve in a current cycle.

4. The high-precision control method for a proportional valve according to claim 1, characterized in that: The predicting the current demand corresponding to the current proportional valve based on the frequency domain eigenvector matrix includes: Obtaining a historical demand corresponding to the current proportional valve, where one historical demand corresponds to one historical period, and the historical demand includes a plurality of historical sub-demands, and each historical sub-demand corresponds to a time period; Inputting the frequency domain eigenvector matrix into a periodic cycle network model, and obtaining the sub-demand corresponding to each time period in the current cycle corresponding to the periodic cycle network model; The sum of each of the sub-demand quantities is calculated to obtain the current demand quantity corresponding to the current proportional valve.

5. The high-precision control method for a proportional valve according to claim 4, characterized in that: The determining, based on the current demand and the current working state, current control data of the current proportional valve in the current cycle includes: Obtaining a historical demand corresponding to the current proportional valve, wherein the historical demand includes a historical sub-demand corresponding to each historical period; Determine a historical duty cycle corresponding to each historical period based on each historical sub-demand of the current proportional valve and the corresponding historical flow data; Determine the target control data corresponding to the current proportional valve in the current cycle based on the historical duty cycle corresponding to each historical cycle and the current demand; Based on the current working state, current control data corresponding to the target control data is determined.

6. The high-precision control method for a proportional valve according to claim 5, characterized in that: The process of determining the historical duty ratio corresponding to each historical period based on each historical sub-demand of the current proportional valve and the corresponding historical flow data includes: Determine a first difference threshold and a second difference threshold corresponding to each of the historical sub-demands; Calculate a target difference between each historical sub-demand and the corresponding historical sub-flow data, and determine a target difference that is less than a corresponding first difference threshold as a first target difference, and determine a target difference that is greater than a corresponding second difference threshold as a second target difference, wherein one historical sub-flow data corresponds to one time period; Calculating a first ratio of the number of the first target difference values ​​to the number of time periods in the historical cycle to obtain a first duty cycle, and calculating a second duty cycle based on a second ratio of the number of the second target difference values ​​to the number of time periods in the historical cycle; Based on the first duty cycle and the second duty cycle, a historical duty cycle corresponding to the historical period is obtained.

7. The high-precision control method for a proportional valve according to claim 6, characterized in that: The determining, based on the historical duty cycle corresponding to each historical cycle and the current demand, target control data corresponding to the current proportional valve in the current cycle includes: Filtering out a target historical duty cycle from the historical duty cycles corresponding to each historical period, wherein the target historical duty cycle is a historical duty cycle in which the first duty cycle is greater than a first duty cycle threshold value and / or the second duty cycle is greater than a second duty cycle threshold value; Determine the similarity between the historical period corresponding to each target historical duty cycle and the current period; Based on the similarity, determining a target historical period, wherein the similarity between the target historical period and the current period is greater than a similarity threshold, and the similarity between the target historical period and the current period is greater than the similarity between other historical periods and the current period; Based on the historical duty cycle corresponding to the target historical cycle and the sub-demand corresponding to each time period in the current cycle, the target control data corresponding to the current proportional valve in the current cycle is determined.

8. A high-precision control device for a proportional valve, characterized in that: include: An acquisition module, used to acquire historical data of the current proportional valve, wherein the historical data includes historical control data, historical opening data and historical flow data corresponding to a historical period, and the historical control data is data for controlling parameters of the current proportional valve; An analysis module, used for performing time domain analysis and frequency domain analysis on the historical data to obtain a first time domain function relationship between the control data and the opening data, a second time domain function relationship between the opening data and the flow data, and a frequency domain feature vector matrix corresponding to the historical data; A determination module, configured to determine a current working state of the current proportional valve based on the first time domain functional relationship and the second time domain functional relationship; A prediction module, used to predict the current demand corresponding to the current proportional valve based on the frequency domain feature vector matrix, where the current demand is the demand corresponding to the current cycle; The control module is used to determine the current control data of the current proportional valve in the current cycle based on the current demand and the current working state, and control the current proportional valve according to the current control data.

9. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the high-precision control method for a proportional valve as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the high-precision control method for a proportional valve according to any one of claims 1 to 7.

Images