A method and system for controlling the opening of a hydraulic valve

Abstract

The present invention discloses a hydraulic valve opening control method and system, which relates to the technical field related to hydraulic valves. The method includes: receiving a hydraulic drive request; performing state transfer analysis according to the driving target direction, driving target distance and driving target speed; constructing a three-constraint convergence probability function; using the oil flow channel network as the valve core area constraint, performing three-constraint optimization on the valve core position based on the three-constraint convergence probability function; and performing electromagnetic hydraulic valve control according to the valve core position optimization value. The method solves the technical problem that the existing hydraulic valve opening control can only adjust to the user's preset standard when the valve deviates, and cannot accurately analyze the user's demand information, resulting in the inability to realize the hydraulic valve's adaptive opening adjustment. The hydraulic valve opening adaptive adjustment control is realized, and the technical effect of improving the stability and reliability of the production process is achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to hydraulic valves, and in particular to a method and system for controlling the opening of a hydraulic valve. Background Art

[0002] Hydraulic valve opening control originates from the continuous development and optimization needs of industrial automation and control systems. With the continuous expansion of the industrial field, the requirements for flow and pressure control accuracy of fluid media (such as water, oil, gas, etc.) are becoming higher and higher. As a key component in the fluid control system, the accuracy and stability of hydraulic valve opening control directly affect the operating efficiency and performance of the entire system. Traditional hydraulic valve opening control methods mostly rely on mechanical or electric devices, but these methods often have problems such as slow response speed, low accuracy, and high maintenance cost. When the hydraulic valve deviates, it cannot be accurately adaptively adjusted and controlled, affecting product quality and production efficiency.

[0003] Therefore, in the current hydraulic valve opening control related technologies, there is a technical problem that when the valve deviates, it can only be adjusted to the user's preset standard, and the user's demand information cannot be accurately analyzed, resulting in the inability to achieve adaptive opening adjustment of the hydraulic valve. Summary of the invention

[0004] The present application provides a hydraulic valve opening control method and system, and adopts technical means such as state transition analysis, probability function construction, and constraint optimization to solve the technical problem that the existing hydraulic valve opening control can only adjust the valve to the user's preset standard when the valve deviates, and cannot accurately analyze user demand information, resulting in the inability to achieve adaptive opening adjustment of the hydraulic valve. The application realizes adaptive adjustment control of the hydraulic valve opening and achieves the technical effect of improving the stability and reliability of the production process.

[0005] The present application provides a method for controlling the opening of a hydraulic valve, the method comprising: receiving a hydraulic drive request, wherein the hydraulic drive request comprises a drive target direction, a drive target distance and a drive target speed; performing a state transition analysis according to the drive target direction, the drive target distance and the drive target speed to generate a desired liquid direction, a desired liquid pressure and a desired liquid flow rate; and constructing a three-constraint convergence probability function:

[0006] ;

[0007] in, Characterizes the convergence probability of the valve core at any position in the oil flow channel network, Characterizes the direction deviation distance, Characterizes the pressure deviation distance, Characterizes the flow deviation distance, , and are the allowable deviation distances for direction, pressure and flow, respectively. , and They are the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, , and are respectively the predicted liquid direction, predicted liquid pressure and predicted liquid flow of the solution, and e is a constant; according to the expected liquid direction, the expected liquid pressure and the expected liquid flow, the oil flow channel network is used as the valve core area constraint, and the valve core position is subjected to three-constraint optimization based on the three-constraint convergence probability function to generate the valve core position optimization value; the electromagnetic hydraulic valve control is performed according to the valve core position optimization value.

[0008] In a possible implementation, a state transfer analysis is performed according to the driving target direction, the driving target distance and the driving target speed to generate the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, and the following processing is performed: the driving target direction, the driving target distance and the driving target speed are dedimensionalized to construct an explicit state matrix, wherein any element position of the explicit state matrix uniquely corresponds to a driving state attribute; the explicit state matrix is ​​analyzed through a state transfer analysis network to generate an implicit state matrix, wherein any element position of the implicit state matrix uniquely corresponds to a liquid state attribute; the implicit state matrix is ​​dedimensionalized inversely to generate the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid.

[0009] In a possible implementation, the state transfer analysis network is constructed and the following processing is performed: according to the hydraulic system model, a driving direction constraint interval, a driving distance constraint interval and a driving speed constraint interval are obtained; based on the driving direction constraint interval, the driving distance constraint interval and the driving speed constraint interval, a random uniform distribution function is used to perform processing to obtain several groups of driving state information; the several groups of driving state information are traversed, and the transition probability is identified with the hydraulic system model as a constraint to generate a transition probability matrix; an explicit state training matrix set and an implicit state supervision matrix set are collected; based on the transition probability matrix, the explicit state training matrix set and the implicit state supervision matrix set are retrieved to train the state transfer analysis network, wherein the state transfer analysis network has a hidden Markov model topology.

[0010] In a possible implementation, the plurality of groups of driving state information are traversed, and transition probabilities are identified with the hydraulic system model as a constraint to generate a transition probability matrix. The following processing is also performed: a liquid state record data set is collected with the first group of driving state information and the hydraulic system model as constraints; a cluster analysis is performed on the liquid state record data set to generate multiple clusters of liquid state record data, wherein the multiple clusters of liquid state record data have multiple frequent factor identifiers; the multiple frequent factor identifiers are traversed to calculate the proportions with the liquid state record data set to generate multiple transition feature probabilities; based on the multiple transition feature probabilities, a first transition probability matrix for transferring the first group of driving state information to the multiple clusters of liquid state record data is constructed and added to the transition probability matrix.

[0011] In a possible implementation, according to the desired direction of the liquid, the desired pressure of the liquid and the desired flow rate of the liquid, the oil flow channel network is used as the valve core area constraint, and the valve core position is subjected to three-constraint optimization based on the three-constraint convergence probability function to generate a valve core position optimization value, and the following processing is also performed: according to the oil flow channel network, the valve core position is uniformly distributed to obtain a number of valve core position output values; the liquid initial pressure, the liquid initial direction and the liquid initial flow rate are obtained; the several valve core position output values ​​are traversed, and based on the liquid initial pressure, the liquid initial direction and the liquid initial flow rate, a process is executed through a liquid state mapping model to output a number of liquid direction mapping values, a number of liquid pressure mapping values ​​and a number of liquid flow mapping values; according to the three-constraint convergence probability function, the several liquid direction mapping values, the several liquid pressure mapping values ​​and the several liquid flow mapping values ​​are traversed for analysis to generate a number of three-constraint convergence probability evaluation values; when the number of the several three-constraint convergence probability evaluation values ​​equal to 1 includes at least one, the valve core position optimization value is output.

[0012] In a possible implementation, the liquid state mapping model is constructed and the following processing is also performed: a graph neural network topology is constructed based on the oil flow channel network, wherein the graph neural network topology is the same as the oil flow channel network; based on the hydraulic system model, the hydraulic valve opening control log is collected, and the graph neural network topology is trained to generate the liquid state mapping model; wherein the liquid state mapping model includes a liquid initial pressure record data set, a liquid initial direction record data set, a liquid initial flow record data set, a valve core control position record data set, a liquid direction record data set, a liquid pressure record data set and a liquid flow record data set.

[0013] In a possible implementation, three-constraint optimization is performed on the valve core position based on the three-constraint convergence probability function to generate a valve core position optimization value, and the following processing is also performed: when the number of three-constraint convergence probability evaluation values ​​equal to 1 is 0, the several valve core position output values ​​are arranged from large to small according to the convergence probability to generate a valve core position output value sequence; the first number of valve core positions of the valve core position output value sequence are taken from the head; the second number of valve core positions of the valve core position output value sequence are taken from the tail; with the first number of valve core positions as the center, a preset radius target area is constructed, the second number of valve core positions are disturbed, a number of valve core position update values ​​are generated, and a loop is executed; when the number of loops meets the preset number of times, there is still no solution with a three-constraint convergence probability evaluation value equal to 1, the optimal solution is output and set as the valve core position optimization value.

[0014] The present application also provides a hydraulic valve opening control system, comprising:

[0015] A hydraulic drive request receiving module, the hydraulic drive request receiving module is used to receive a hydraulic drive request, wherein the hydraulic drive request includes a driving target direction, a driving target distance and a driving target speed;

[0016] A state transfer analysis module, the state transfer analysis module is used to perform state transfer analysis according to the driving target direction, the driving target distance and the driving target speed, and generate a desired direction of the liquid, a desired pressure of the liquid and a desired flow rate of the liquid;

[0017] A convergence probability function establishment module, which is used to construct a three-constraint convergence probability function:

[0018] ;

[0019] in, Characterizes the convergence probability of the valve core at any position in the oil flow channel network, Characterizes the direction deviation distance, Characterizes the pressure deviation distance, Characterizes the flow deviation distance, , and are the allowable deviation distances for direction, pressure and flow, respectively. , and They are the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, , and are the predicted liquid direction, predicted liquid pressure and predicted liquid flow rate of the solution, and e is a constant;

[0020] A valve core position optimization value generation module, the valve core position optimization value generation module is used to perform three-constraint optimization on the valve core position based on the three-constraint convergence probability function according to the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, with the oil flow channel network as the valve core area constraint, to generate a valve core position optimization value;

[0021] An electromagnetic hydraulic valve control module is used to perform the electromagnetic hydraulic valve control according to the valve core position optimization value.

[0022] A hydraulic valve opening control method and system proposed in this application are intended to receive hydraulic drive requests; perform state transfer analysis based on the drive target direction, drive target distance and drive target speed; construct a three-constraint convergence probability function; use the oil flow channel network as the valve core area constraint, and perform three-constraint optimization on the valve core position based on the three-constraint convergence probability function; and perform electromagnetic hydraulic valve control according to the valve core position optimization value, thereby solving the technical problem that the existing hydraulic valve opening control can only adjust to the user's preset standard when the valve deviates, and cannot accurately analyze user demand information, resulting in the inability to achieve adaptive opening adjustment of the hydraulic valve. Adaptive adjustment control of the hydraulic valve opening is realized, and the technical effect of improving the stability and reliability of the production process is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0024] Figure 1 A schematic diagram of a flow chart of a hydraulic valve opening control method provided in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of the structure of a hydraulic valve opening control system provided in an embodiment of the present application.

[0026] Description of reference numerals: hydraulic drive request receiving module 10 , state transition analysis module 20 , convergence probability function establishment module 30 , valve core position optimization value generation module 40 , electromagnetic hydraulic valve control module 50 . DETAILED DESCRIPTION

[0027] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0028] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0029] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0030] An embodiment of the present application provides a method for controlling the opening of a hydraulic valve, which is applied to an electromagnetic hydraulic valve. The electromagnetic hydraulic valve is integrated in a hydraulic valve block. The hydraulic valve block also includes an integrated valve block body and a valve core. The valve block body includes an oil flow channel network. The electromagnetic hydraulic valve, valve block body and valve core are integrated and deployed in the hydraulic valve block, wherein the valve block body includes an oil flow channel network, which is composed of a series of interconnected channels and is precisely designed inside the valve block body to guide and control the flow of hydraulic oil. When the electromagnetic hydraulic valve is activated, the valve core will move under the action of electromagnetic force, thereby changing the channel state of the oil flow channel network, thereby controlling the flow direction and flow rate of the hydraulic oil. Specifically, the oil flow channel network may include multiple interfaces such as an oil inlet, an oil outlet, a control port, and channels connecting these interfaces. The movement of the valve core will change the opening and closing state of the channel, thereby regulating the flow of the hydraulic oil. For example, when the valve core moves to a certain position, a channel may be opened to allow the hydraulic oil to flow from the oil inlet to the oil outlet. In this way, the hydraulic valve opening control method can accurately control the flow of the hydraulic oil, thereby achieving precise control of the hydraulic system.

[0031] A method for controlling the opening of a hydraulic valve, such as Figure 1 As shown, the method includes:

[0032] Step S100, receiving a hydraulic drive request, wherein the hydraulic drive request includes a drive target direction, a drive target distance, and a drive target speed. In a hydraulic system, a controller or related equipment receives a drive instruction from another control source, requiring the hydraulic system to perform a specific action or operation, which is called a hydraulic drive request, including a drive target direction, a drive target distance, and a drive target speed. Specifically, the drive target direction refers to the direction in which the hydraulic system needs to perform an action. For example, if it is a hydraulically driven mechanical arm, the drive target direction may be upward, downward, left, right, etc. The direction instruction is usually closely related to the configuration and control logic of the valves and actuators in the hydraulic system, ensuring that the hydraulic fluid can flow in a predetermined direction, thereby driving the related components to achieve the desired direction of movement; the drive target distance refers to the distance that the hydraulic system needs to move or operate. For a hydraulic cylinder, it may be the length that the piston needs to extend or retract. For other types of hydraulic actuators, such as a hydraulic motor, it may be the number of turns or angles of its rotation; the drive target speed refers to the speed at which the hydraulic system performs an action. By adjusting the flow control valve in the hydraulic system or adjusting the speed of the pump, the control of the movement speed of the hydraulic actuator can be achieved.

[0033] Step S200, a state transition analysis is performed according to the driving target direction, the driving target distance and the driving target speed to generate the expected liquid direction, the expected liquid pressure and the expected liquid flow rate. According to the received hydraulic driving request such as the driving target direction, the driving target distance and the driving target speed, the liquid flow state that the system needs to achieve is determined through state transition analysis, including the expected liquid direction, the expected liquid pressure and the expected liquid flow rate, wherein the state transition analysis refers to the evaluation and prediction of the current and future states of the hydraulic system, and analyzes how to smoothly and efficiently transfer from the current state to the target state according to the current hydraulic pressure, flow, direction and other parameters, as well as the received driving target direction, distance and speed information. Specifically, the expected liquid direction is the expected liquid flow direction calculated according to the driving target direction. For example, if the driving target is to make the piston of the hydraulic cylinder If it moves to the right, the expected direction of the liquid is to flow to the right, which guides the control system on how to adjust the switching state of the hydraulic valve to control the flow direction of the liquid; the expected liquid pressure is the expected hydraulic pressure calculated based on the driving target distance and speed. The longer the target distance and the faster the speed, the greater the hydraulic pressure required. By adjusting the throttling degree of the hydraulic valve, the pressure in the hydraulic system can be controlled; the expected liquid flow rate is the expected liquid flow rate calculated based on the driving target speed and the characteristics of the hydraulic components. The flow rate is directly related to the speed. A larger flow rate usually has a faster action speed. By controlling the speed of the hydraulic pump or the opening of the hydraulic valve, the flow rate in the hydraulic system can be adjusted to achieve the target speed.

[0034] In a possible implementation, step S200 further includes step S210, performing dimension removal processing on the driving target direction, the driving target distance and the driving target speed to construct an explicit state matrix, wherein any element position of the explicit state matrix uniquely corresponds to a driving state attribute. The driving target direction, the driving target distance and the driving target speed have different dimensions, and dimension removal processing is to convert physical data of different dimensions into dimensionless values ​​for unified processing and comparison; the explicit state matrix is ​​a mathematical tool used to represent the state of the system. In hydraulic control, each element position of the explicit state matrix uniquely corresponds to a driving state attribute, which means that each row or column of the matrix represents a specific driving state attribute, such as direction, distance or speed. By constructing such a matrix, the relationship and change between different driving state attributes can be easily viewed and compared. It also includes step S220, performing analysis on the explicit state matrix through a state transition analysis network to generate an implicit state matrix, wherein any element position of the implicit state matrix uniquely corresponds to a liquid state attribute. The state transition analysis network is an analysis model for predicting and analyzing the behavior and response of the hydraulic system under different states. It can process the information in the explicit state matrix and predict the change trend of the state according to the dynamic characteristics of the system. The implicit state matrix is ​​an abstract and quantitative representation of the liquid state attribute. Specifically, the state transition analysis network operates and transforms the elements in the explicit state matrix to obtain the implicit state matrix. Each element position in the implicit matrix uniquely corresponds to a specific liquid state attribute, such as the pressure value at a specific position, the flow rate of a certain flow channel, etc. Through the implicit state matrix, the control system can more accurately understand the state change of the liquid in the actual flow process, so as to more accurately adjust the control strategy and achieve a more efficient and stable control effect. It also includes step S230, performing dedimensionalization reverse processing on the implicit state matrix to generate the desired direction of the liquid, the desired pressure of the liquid and the desired flow rate of the liquid. The state information in the implicit state matrix is ​​dedimensionalized and reversely processed to convert it back to a dimensional unit with actual physical meaning to generate the desired direction of the liquid, the desired pressure of the liquid and the desired flow rate of the liquid.

[0035] In a possible implementation, step S220 further includes step S221, obtaining a driving direction constraint interval, a driving distance constraint interval, and a driving speed constraint interval according to the hydraulic system model. According to the hydraulic system model, determine the effective operating range or restriction conditions of its driving direction, driving distance, and driving speed. The constraint interval is a key parameter to ensure the safe, stable, and efficient operation of the hydraulic system. Specifically, the driving direction constraint interval refers to the driving direction range that the hydraulic system can achieve. For example, some systems may only achieve unidirectional driving, while other systems may support multi-directional driving; the driving distance constraint interval refers to the driving distance range that the hydraulic system can achieve; the driving speed constraint interval refers to the driving speed range that the hydraulic system can achieve, which is affected by factors such as the output capacity of the hydraulic pump, the adjustment capacity of the hydraulic valve, and the damping characteristics of the hydraulic system. It also includes step S222, based on the driving direction constraint interval, the driving distance constraint interval, and the driving speed constraint interval, perform processing through a random uniform distribution function to obtain several groups of driving state information. According to the driving direction constraint interval, the driving distance constraint interval and the driving speed constraint interval, a plurality of groups of driving state information meeting the constraint requirements are generated by using a random uniform distribution function, wherein the random uniform distribution function is a mathematical function that generates random numbers uniformly distributed within a specified range, and is used to generate random driving state information within a known constraint interval. It also includes step S223, traversing the plurality of groups of driving state information, identifying the transition probability with the hydraulic system model as a constraint, and generating a transition probability matrix. The plurality of groups of driving state information generated are traversed, and the transition probability is identified with the hydraulic system model as a constraint. For each group of driving state information, the system calculates the probability of it transferring to other states and identifies it. After completing the calculation of the transition probability of all driving state information, the system organizes these probability values ​​into a matrix form, namely, a transition probability matrix. It also includes step S224, collecting an explicit state training matrix set and an implicit state supervision matrix set. It also includes step S225, based on the transition probability matrix, calling the explicit state training matrix set and the implicit state supervision matrix set, and training the state transition analysis network, wherein the state transition analysis network has a hidden Markov model topology.According to the transition probability matrix, the transition rules between different states are determined, and the explicit state training matrix set and the implicit state supervision matrix set are retrieved. These data are used to train the state transition analysis network. Specifically, the explicit state training matrix set and the implicit state supervision matrix set respectively contain explicit state information and implicit state information used to train the state transition analysis network. The hidden Markov model is a statistical model used to describe a Markov process with hidden variables. It is assumed that the current state of the system depends only on the previous state, and each state generates an observation. The state transition analysis network has a hidden Markov model topology, which means that the structure and characteristics of the network are similar to those of the hidden Markov model, and it can handle state transition problems containing hidden variables. Finally, a fully trained state transition analysis network is obtained, which can predict future state changes based on the current state and historical information of the system, and is helpful for the optimization control of the hydraulic control system.

[0036] In a possible implementation, step S223 further includes step S223-1, collecting a liquid state record data set with the first set of drive state information and the hydraulic system model as constraints. Under a specific hydraulic system model, the real-time state of the liquid is collected and recorded according to the first set of drive state information to form a liquid state record data set. It also includes step S223-2, performing cluster analysis on the liquid state record data set to generate multiple clusters of liquid state record data, wherein the multiple clusters of liquid state record data have multiple frequent factor identifiers. Cluster analysis divides clusters based on the similarity between data. Specifically, if the direction, pressure, and flow deviation distances are all less than the corresponding allowable deviation distances, they are clustered into a cluster. Data objects with close distances or high similarity will be divided into the same cluster, while data objects with far distances or low similarity will be assigned to different clusters. The generated multiple clusters represent different liquid state modes or categories. Frequent factor identifiers are usually used to identify features or factors that appear frequently or are representative in each cluster. It also includes step S223-3, traversing the multiple frequent factor identifiers to calculate the proportion with the liquid state record data set, and generating multiple transfer feature probabilities. For each frequent factor identifier, calculate its frequency or proportion in the liquid state record data set, and further calculate their probability as liquid state transfer features based on the proportion of frequent factor identifiers, so as to have a deeper understanding of the law and trend of liquid state transfer. It also includes step S223-4, based on the multiple transfer feature probabilities, construct a first transfer probability matrix for transferring the first group of drive state information to the multiple clusters of liquid state record data, and add it to the transfer probability matrix. What is constructed is the first transfer probability matrix for transferring the first group of drive state information to the multiple clusters of liquid state record data, which is added to the existing transfer probability matrix to obtain a transfer probability matrix containing more drive state information and liquid state transfer probabilities, which can more comprehensively describe the state transfer law of the hydraulic system.

[0037] Step S300, constructing a three-constraint convergence probability function:

[0038] ;

[0039] in, Characterizes the convergence probability of the valve core at any position in the oil flow channel network, Characterizes the direction deviation distance, Characterizes the pressure deviation distance, Characterizes the flow deviation distance, , and are the allowable deviation distances for direction, pressure and flow, respectively. , and They are the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, , and are the predicted liquid direction, predicted liquid pressure and predicted liquid flow rate of the solution respectively, and e is a constant.

[0040] Step S400, according to the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, taking the oil flow channel network as the valve core area constraint, performing three-constraint optimization on the valve core position based on the three-constraint convergence probability function, and generating an optimized value of the valve core position. According to the expected direction, expected pressure and expected flow rate of the liquid, the oil flow channel network is considered as the constraint condition of the valve core area. The oil flow channel network is the channel for the flow of liquid in the hydraulic system. The position of the valve core will directly affect the flow direction and flow rate of the liquid. When optimizing the valve core position, it is necessary to consider the layout and characteristics of the oil flow channel network to ensure that the optimized valve core position can meet the expected direction, pressure and flow rate of the liquid while not exceeding the limit range of the channel network. Specifically, the three-constraint convergence probability function is used to comprehensively consider these three constraints to perform three-constraint optimization, find an optimal valve core position within the adjustable range of the valve core, and finally generate an optimized valve core position value. The optimized valve core position value is calculated based on the constraints of the expected direction, pressure and flow rate of the liquid and the oil flow channel network. It represents the valve core position that can achieve the best system performance under the current system state.

[0041] In a possible implementation, step S400 further includes step S410, uniformly distributing the valve core position according to the oil flow channel network to obtain a number of valve core position output values. At the key positions or nodes of the oil flow channel network, a series of possible valve core positions are set according to certain rules or intervals, and the valve cores are evenly arranged throughout the network so that the flow of the liquid can be more comprehensively controlled and regulated, and a number of valve core position output values ​​are obtained, which represent the valve core installation positions that may be selected under a specific channel network. It also includes step S420, obtaining the initial pressure of the liquid, the initial direction of the liquid, and the initial flow of the liquid. It also includes step S430, traversing the several valve core position output values, and based on the initial pressure of the liquid, the initial direction of the liquid, and the initial flow of the liquid, executing the process through the liquid state mapping model, outputting a number of liquid direction mapping values, a number of liquid pressure mapping values, and a number of liquid flow mapping values. For each valve core position, we will combine the initial state information of the liquid, that is, the initial pressure, initial direction and initial flow of the liquid, to analyze and use the liquid state mapping model to execute the process. By inputting the valve core position and the initial state information of the liquid, the model can calculate the state parameters such as the direction, pressure and flow of the liquid flow at a specific valve core position, and obtain a series of output values, including a number of liquid direction mapping values, a number of liquid pressure mapping values ​​and a number of liquid flow mapping values, which represent the predicted results of the liquid flow state at different valve core positions, wherein the liquid state mapping model is a mathematical model that can predict or map the flow state of the liquid in the hydraulic system according to the position of the valve core and the initial state of the liquid. It also includes step S440, according to the three-constraint convergence probability function, traverse the several liquid direction mapping values, the several liquid pressure mapping values ​​and the several liquid flow mapping values ​​for analysis, and generate several three-constraint convergence probability evaluation values. The convergence probability of different mapping value combinations is evaluated by analyzing a number of liquid direction mapping values, a number of liquid pressure mapping values, and a number of liquid flow mapping values ​​using a three-constraint convergence probability function, which reflects the degree of matching between the current mapping value combination and the desired state. By traversing all mapping value combinations, we can obtain a number of three-constraint convergence probability evaluation values, each of which corresponds to a specific valve core position and its corresponding liquid state mapping value. It also includes step S450, when the number of the three-constraint convergence probability evaluation values ​​equal to 1 includes at least one, the valve core position optimization value is output. After analyzing the three-constraint convergence probability evaluation values ​​of all valve core positions, if it is found that the three-constraint convergence probability evaluation value of at least one valve core position reaches the maximum value of 1, it is considered that this valve core position fully meets the requirements of the desired liquid direction, the desired liquid pressure, and the desired liquid flow, and is an ideal valve core position selection, and the valve core position optimization value is output.

[0042] In one possible implementation, step S430 further includes step S431, building a graph neural network topology based on the oil flow channel network, wherein the graph neural network topology is the same as the oil flow channel network. The graph neural network topology built based on the oil flow channel network means mapping each channel in the oil flow channel network to a node in the graph neural network, and establishing connections between nodes based on the actual flow relationship of the liquid between the channels. The graph neural network topology can accurately reflect the structure and flow characteristics of the oil flow channel network. It also includes step S432, collecting the hydraulic valve opening control log based on the hydraulic system model, training the graph neural network topology, and generating the liquid state mapping model. According to the model of the hydraulic system, the hydraulic valve opening control log is collected. The hydraulic valve opening control log records the opening changes of the hydraulic valve during the actual operation process and other related parameters, such as pressure, flow, etc. The graph neural network topology is trained using the collected hydraulic valve opening control log data. The trained graph neural network will generate a liquid state mapping model, which can predict the corresponding liquid state, including direction, pressure and flow, etc., according to the given valve opening information. It also includes step S433, wherein the liquid state mapping model includes a liquid initial pressure record data set, a liquid initial direction record data set, a liquid initial flow record data set, a valve core control position record data set, a liquid direction record data set, a liquid pressure record data set and a liquid flow record data set.

[0043] In a possible implementation, step S400 further includes step S460, when the number of three-constraint convergence probability evaluation values ​​equal to 1 is 0, the plurality of valve core position output values ​​are arranged from large to small according to the convergence probability, and a valve core position output value sequence is generated. When the number of three-constraint convergence probability evaluation values ​​equal to 1 is 0, it means that among all valve core positions, no position can fully meet all the constraints of the expected direction of the liquid, the expected pressure of the liquid, and the expected flow rate of the liquid. The system will arrange the plurality of valve core position output values ​​from large to small according to their corresponding three-constraint convergence probability evaluation values, and generate a valve core position output value sequence, which reflects the pros and cons of different valve core positions in meeting the constraints. The valve core positions at the front of the sequence have higher convergence probability evaluation values, which means that they are closer to the expected liquid state; while the valve core positions at the back of the sequence have lower convergence probability evaluation values, and the degree of matching with the expected state is poor. It also includes step S470, which starts with the first number of valve core positions in the valve core position output value sequence. The valve core position with the largest convergence probability evaluation value is taken as the first number of valve core positions. It also includes step S480, taking the second number of valve core positions of the valve core position output value sequence from the end. The valve core position with the smallest convergence probability evaluation value is taken as the second number of valve core positions. It also includes step S490, constructing a preset radius target area with the first number of valve core positions as the center, perturbing the second number of valve core positions, generating several valve core position update values, and executing a loop. Construct a target area with a preset radius with the first number of valve core positions as the center, perturbing the second number of valve core positions, that is, making small adjustments or changes to these positions to explore possible better solutions in the target area, and generating several valve core position update values, which represent the new valve core position candidate set after the perturbation, and cyclically performing the above perturbation and evaluation process to gradually find a better valve core position. The number of cycles can be set as needed until a certain stop condition is met, for example, the maximum number of iterations is reached, the convergence probability evaluation value reaches a preset threshold, etc. The method further includes step S4100, when the number of cycles meets the preset number of times, and there is still no solution with the three-constraint convergence probability evaluation value equal to 1, the optimal solution is output and set as the valve core position optimization value. After the specified number of iterations, if the system still does not find a valve core position solution that fully meets all the constraints (i.e., the three-constraint convergence probability evaluation value is equal to 1), then according to the existing evaluation results, the optimal solution under the current conditions is selected as the output and set as the valve core position optimization value.

[0044] Step S500, executing the electromagnetic hydraulic valve control according to the valve core position optimization value. The obtained valve core position optimization value is applied to the actual control of the electromagnetic hydraulic valve. Specifically, the control system converts the optimized valve core position information into a specific control instruction for the electromagnetic hydraulic valve, and sends it to the electromagnetic part of the electromagnetic hydraulic valve, and changes the position of the valve core by controlling the current of the electromagnet. In this way, the flow, pressure and other parameters of the hydraulic system can be accurately adjusted as needed, thereby realizing the automation and efficient operation of the hydraulic system.

[0045] In the above, refer to Figure 1 A method for controlling the opening degree of a hydraulic valve according to an embodiment of the present invention is described in detail. Figure 2 A hydraulic valve opening control system according to an embodiment of the present invention is described.

[0046] A hydraulic valve opening control system according to an embodiment of the present invention is used to solve the technical problem that the existing hydraulic valve opening control can only adjust to the user's preset standard when the valve deviates, and cannot accurately analyze the user's demand information, resulting in the inability to realize the hydraulic valve's adaptive opening adjustment. It realizes the hydraulic valve opening adaptive adjustment control and achieves the technical effect of improving the stability and reliability of the production process. A hydraulic valve opening control system includes: a hydraulic drive request receiving module 10, a state transition analysis module 20, a convergence probability function establishment module 30, a valve core position optimization value generation module 40, and an electromagnetic hydraulic valve control module 50.

[0047] A hydraulic drive request receiving module 10, wherein the hydraulic drive request receiving module 10 is used to receive a hydraulic drive request, wherein the hydraulic drive request includes a driving target direction, a driving target distance, and a driving target speed;

[0048] A state transfer analysis module 20, the state transfer analysis module 20 is used to perform state transfer analysis according to the driving target direction, the driving target distance and the driving target speed, and generate a desired direction of the liquid, a desired pressure of the liquid and a desired flow rate of the liquid;

[0049] The convergence probability function establishment module 30 is used to construct a three-constraint convergence probability function:

[0050] ;

[0051] in, Characterizes the convergence probability of the valve core at any position in the oil flow channel network, Characterizes the direction deviation distance, Characterizes the pressure deviation distance, Characterizes the flow deviation distance, , and are the allowable deviation distances for direction, pressure and flow, respectively. , and They are the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, , and are the predicted liquid direction, predicted liquid pressure and predicted liquid flow rate of the solution, and e is a constant;

[0052] A valve core position optimization value generation module 40, the valve core position optimization value generation module 40 is used to perform three-constraint optimization on the valve core position based on the three-constraint convergence probability function according to the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, with the oil flow channel network as the valve core area constraint, to generate a valve core position optimization value;

[0053] The electromagnetic hydraulic valve control module 50 is used to execute the electromagnetic hydraulic valve control according to the valve core position optimization value.

[0054] The specific configuration of the state transfer analysis module 20 will be described in detail below. The state transfer analysis module 20 further includes: performing dimensionless processing on the driving target direction, the driving target distance and the driving target speed to construct an explicit state matrix, wherein any element position of the explicit state matrix uniquely corresponds to a driving state attribute; performing analysis on the explicit state matrix through a state transfer analysis network to generate an implicit state matrix, wherein any element position of the implicit state matrix uniquely corresponds to a liquid state attribute; performing dimensionless reverse processing on the implicit state matrix to generate the desired direction of the liquid, the desired pressure of the liquid and the desired flow rate of the liquid.

[0055] The specific configuration of the state transfer analysis module 20 will be described in detail below. The state transfer analysis module 20 may further include: obtaining a driving direction constraint interval, a driving distance constraint interval, and a driving speed constraint interval according to the hydraulic system model; performing processing through a random uniform distribution function based on the driving direction constraint interval, the driving distance constraint interval, and the driving speed constraint interval to obtain several groups of driving state information; traversing the several groups of driving state information, using the hydraulic system model as a constraint to identify the transition probability, and generating a transition probability matrix; collecting an explicit state training matrix set and an implicit state supervision matrix set; based on the transition probability matrix, calling the explicit state training matrix set and the implicit state supervision matrix set to train the state transfer analysis network, wherein the state transfer analysis network has a hidden Markov model topology.

[0056] The specific configuration of the state transfer analysis module 20 will be described in detail below. The state transfer analysis module 20 may further include: collecting a liquid state record data set with the first set of driving state information and the hydraulic system model as constraints; performing cluster analysis on the liquid state record data set to generate multiple clusters of liquid state record data, wherein the multiple clusters of liquid state record data have multiple frequent factor identifiers; traversing the multiple frequent factor identifiers to calculate the proportion of the liquid state record data set to generate multiple transfer feature probabilities; constructing a first transfer probability matrix for transferring the first set of driving state information to the multiple clusters of liquid state record data based on the multiple transfer feature probabilities, and adding it to the transfer probability matrix.

[0057] The specific configuration of the valve core position optimization value generation module 40 will be described in detail below. The valve core position optimization value generation module 40 further includes: according to the oil flow channel network, the valve core position is evenly distributed to obtain a number of valve core position output values; the initial pressure of the liquid, the initial direction of the liquid and the initial flow of the liquid are obtained; the several valve core position output values ​​are traversed, and based on the initial pressure of the liquid, the initial direction of the liquid and the initial flow of the liquid, a process is executed through the liquid state mapping model to output a number of liquid direction mapping values, a number of liquid pressure mapping values ​​and a number of liquid flow mapping values; according to the three-constraint convergence probability function, the several liquid direction mapping values, the several liquid pressure mapping values ​​and the several liquid flow mapping values ​​are traversed for analysis to generate a number of three-constraint convergence probability evaluation values; when the number of the three-constraint convergence probability evaluation values ​​equal to 1 includes at least one, the valve core position optimization value is output.

[0058] The specific configuration of the valve core position optimization value generation module 40 will be described in detail below. The valve core position optimization value generation module 40 further includes: building a graph neural network topology based on the oil flow channel network, wherein the graph neural network topology is the same as the oil flow channel network; based on the hydraulic system model, collecting the hydraulic valve opening control log, training the graph neural network topology, and generating the liquid state mapping model; wherein the liquid state mapping model includes a liquid initial pressure record data set, a liquid initial direction record data set, a liquid initial flow record data set, a valve core control position record data set, a liquid direction record data set, a liquid pressure record data set, and a liquid flow record data set.

[0059] The specific configuration of the valve core position optimization value generation module 40 will be described in detail below. The valve core position optimization value generation module 40 may further include: when the number of three-constraint convergence probability evaluation values ​​equal to 1 is 0, the valve core position output values ​​are arranged from large to small according to the convergence probability to generate a valve core position output value sequence; the first number of valve core positions of the valve core position output value sequence is taken from the beginning; the second number of valve core positions of the valve core position output value sequence is taken from the end; with the first number of valve core positions as the center, a preset radius target area is constructed, the second number of valve core positions is disturbed, a number of valve core position update values ​​are generated, and a loop is executed; when the number of loops meets the preset number, there is still no solution with a three-constraint convergence probability evaluation value equal to 1, the optimal solution is output and set as the valve core position optimization value.

[0060] A hydraulic valve opening control system provided in an embodiment of the present invention can execute a hydraulic valve opening control method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0061] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0062] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for controlling the opening of a hydraulic valve, characterized in that: Applied to an electromagnetic hydraulic valve, the electromagnetic hydraulic valve is integrated and deployed in a hydraulic valve block, the hydraulic valve block also includes an integrated valve block body and a valve core, the valve block body includes an oil flow channel network, including: receiving a hydraulic driving request, wherein the hydraulic driving request includes a driving target direction, a driving target distance, and a driving target speed; Performing state transition analysis according to the driving target direction, the driving target distance and the driving target speed to generate a desired direction of the liquid, a desired pressure of the liquid and a desired flow rate of the liquid; Construct a three-constrained convergence probability function: ； in, Characterizes the convergence probability of the valve core at any position in the oil flow channel network, Characterizes the direction deviation distance, Characterizes the pressure deviation distance, Characterizes the flow deviation distance, , and are the allowable deviation distances for direction, pressure and flow, respectively. , and They are the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, , and are the predicted liquid direction, predicted liquid pressure and predicted liquid flow rate of the solution, e is a constant, and the parameters , , Respectively represent the weight coefficients of direction deviation distance, pressure deviation distance and flow deviation distance; According to the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, taking the oil flow channel network as the valve core area constraint, performing three-constraint optimization on the valve core position based on the three-constraint convergence probability function to generate an optimized value of the valve core position; The electromagnetic hydraulic valve control is performed according to the valve core position optimization value.

2. A method for controlling the opening of a hydraulic valve according to claim 1, characterized in that: Performing state transition analysis according to the driving target direction, the driving target distance, and the driving target speed to generate a desired direction of the liquid, a desired pressure of the liquid, and a desired flow rate of the liquid, including: De-dimensionalizing the driving target direction, the driving target distance, and the driving target speed to construct an explicit state matrix, wherein any element position of the explicit state matrix uniquely corresponds to a driving state attribute; By means of a state transition analysis network, the explicit state matrix is ​​analyzed to generate an implicit state matrix, wherein any element position of the implicit state matrix uniquely corresponds to a liquid state attribute; The implicit state matrix is ​​dedimensionalized and reversely processed to generate the desired direction of the liquid, the desired pressure of the liquid and the desired flow rate of the liquid.

3. A method for controlling the opening of a hydraulic valve according to claim 2, characterized in that: The state transfer analysis network construction step includes: According to the hydraulic system model, a driving direction constraint interval, a driving distance constraint interval and a driving speed constraint interval are obtained; Based on the driving direction constraint interval, the driving distance constraint interval and the driving speed constraint interval, performing processing by a random uniform distribution function to obtain several sets of driving state information; Traversing the plurality of sets of driving state information, performing transition probability identification with the hydraulic system model as a constraint, and generating a transition probability matrix; Collect explicit state training matrix set and implicit state supervision matrix set; Based on the transition probability matrix, the explicit state training matrix set and the implicit state supervision matrix set are retrieved to train the state transition analysis network, wherein the state transition analysis network has a hidden Markov model topology.

4. A method for controlling the opening of a hydraulic valve according to claim 3, characterized in that: Traversing the plurality of sets of driving state information, performing transition probability identification with the hydraulic system model as a constraint, and generating a transition probability matrix, including: Collecting a liquid state record data set with the first set of driving state information and the hydraulic system model as constraints; Performing cluster analysis on the liquid state record data set to generate multiple clusters of liquid state record data, wherein the multiple clusters of liquid state record data have multiple frequent factor identifiers; Traversing the multiple frequent factor identifiers to calculate the proportion of the liquid state record data set, and generating multiple transfer feature probabilities; A first transfer probability matrix for transferring the first group of driving state information to the multiple clusters of liquid state record data is constructed based on the multiple transfer feature probabilities and added into the transfer probability matrix.

5. A hydraulic valve opening control method as claimed in claim 1, characterized in that: According to the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, the oil flow channel network is used as the valve core area constraint, and the valve core position is subjected to three-constraint optimization based on the three-constraint convergence probability function to generate the valve core position optimization value, including: The valve core positions are evenly distributed according to the oil flow channel network to obtain a plurality of valve core position output values; Obtaining the initial pressure of the liquid, the initial direction of the liquid and the initial flow rate of the liquid; Traversing the plurality of valve core position output values, and based on the liquid initial pressure, the liquid initial direction, and the liquid initial flow rate, executing a process through a liquid state mapping model, outputting a plurality of liquid direction mapping values, a plurality of liquid pressure mapping values, and a plurality of liquid flow mapping values; According to the three-constraint convergence probability function, the plurality of liquid direction mapping values, the plurality of liquid pressure mapping values ​​and the plurality of liquid flow mapping values ​​are traversed for analysis to generate a plurality of three-constraint convergence probability evaluation values; When at least one of the plurality of three-constraint convergence probability evaluation values ​​is equal to 1, the valve core position optimization value is output.

6. A method for controlling the opening of a hydraulic valve according to claim 5, characterized in that: The liquid state mapping model construction step comprises: According to the oil flow channel network, a graph neural network topology is constructed, wherein the graph neural network topology is the same as the oil flow channel network; Based on the hydraulic system model, the hydraulic valve opening control log is collected, the graph neural network topology is trained, and the liquid state mapping model is generated; The liquid state mapping model includes a liquid initial pressure record data set, a liquid initial direction record data set, a liquid initial flow record data set, a valve core control position record data set, a liquid direction record data set, a liquid pressure record data set and a liquid flow record data set.

7. A method for controlling the opening of a hydraulic valve according to claim 5, characterized in that: Also includes: When the number of three-constraint convergence probability evaluation values ​​equal to 1 is 0, the plurality of valve core position output values ​​are arranged from large to small according to the convergence probability to generate a valve core position output value sequence; Taking a first number of valve core positions of the valve core position output value sequence from the beginning; Taking a second number of valve core positions of the valve core position output value sequence from the end; Taking the first number of valve core positions as the center, constructing a preset radius target area, disturbing the second number of valve core positions, generating a plurality of valve core position update values, and executing a loop; When the number of cycles meets the preset number of times, and a solution whose three-constraint convergence probability evaluation value is equal to 1 still does not appear, the optimal solution is output and set as the valve core position optimization value.

8. A hydraulic valve opening control system, characterized in that: The system is used to implement a hydraulic valve opening control method according to any one of claims 1 to 7, and the system comprises: A hydraulic drive request receiving module, the hydraulic drive request receiving module is used to receive a hydraulic drive request, wherein the hydraulic drive request includes a driving target direction, a driving target distance and a driving target speed; A state transfer analysis module, the state transfer analysis module is used to perform state transfer analysis according to the driving target direction, the driving target distance and the driving target speed, and generate a desired direction of the liquid, a desired pressure of the liquid and a desired flow rate of the liquid; A convergence probability function establishment module, which is used to construct a three-constraint convergence probability function: ； in, Characterizes the convergence probability of the valve core at any position in the oil flow channel network, Characterizes the direction deviation distance, Characterizes the pressure deviation distance, Characterizes the flow deviation distance, , and are the allowable deviation distances for direction, pressure and flow, respectively. , and The expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid are respectively , and are the predicted liquid direction, predicted liquid pressure and predicted liquid flow rate of the solution, e is a constant, and the parameters , , Respectively represent the weight coefficients of direction deviation distance, pressure deviation distance and flow deviation distance; A valve core position optimization value generation module, the valve core position optimization value generation module is used to perform three-constraint optimization on the valve core position based on the three-constraint convergence probability function according to the expected direction of the liquid, the expected pressure of the liquid and the expected flow rate of the liquid, with the oil flow channel network as the valve core area constraint, to generate a valve core position optimization value; An electromagnetic hydraulic valve control module is used to perform the electromagnetic hydraulic valve control according to the valve core position optimization value.

Images