Method, device, electronic equipment and excavator for constructing hydraulic control model

Abstract

The embodiment of the present application provides a method, device, electronic device and excavator for constructing a hydraulic control model, the method comprising: according to the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, and the second input data of at least one second component at a preset time, identifying the parameters in the model to be identified, and obtaining the hydraulic control model of the first component; the preset time is a time adjacent to the current time and before the current time, the first component is controlled by the hydraulic control system, and the pressure output by the first component during operation is suppressed by the operation of the second component; the model to be identified is a Hammerstein model including a coupling term, and the coupling term is determined based on the second input data of the second component at the preset time. The method provided in the embodiment of the present application constructs a hydraulic control model with a simple structure and fast calculation speed, which meets the requirements of the hydraulic control system for motion control.

Description

Technical Field

[0001] The present application belongs to the technical field of engineering machinery, and in particular, relates to a method, device, electronic equipment and excavator for constructing a hydraulic control model. Background Art

[0002] The hydraulic control system on construction machinery is a complex nonlinear system. The system is powered by an electric motor, uses a hydraulic pump to convert mechanical energy into pressure, pushes the hydraulic oil, and changes the flow direction of the hydraulic oil by controlling various valves, thereby pushing the hydraulic cylinder to make different strokes and directions to complete the different action needs of various equipment. The model of this system is directly related to the operating stability and operation quality of the main machine's actuators. Therefore, it is very necessary to identify the model of the hydraulic control system.

[0003] In existing hydraulic control systems, extreme learning machine models or particle swarm algorithms are generally used. Among them, the extreme learning machine model is a type of neural network, and its model structure is relatively complex; the particle swarm algorithm is initialized as a group of random particles (random solutions), and then finds the optimal solution through iteration.

[0004] Since the model structure of the extreme learning machine model is relatively complex, it is not conducive to the development of the control algorithm when controlling the model later; the particle swarm algorithm finds the optimal solution through iteration, and the calculation speed is slow. The working scene of construction machinery is constantly changing, which causes the dynamic characteristics of the hydraulic system to change with the changes in the external environment, which is not conducive to the subsequent promotion of online identification. Therefore, the above two models cannot meet the motion control requirements of the hydraulic control system. Summary of the invention

[0005] The embodiments of the present application provide a method, device, electronic device and excavator for constructing a hydraulic control model, which can construct a hydraulic control model with a simple structure and fast calculation speed to meet the motion control requirements of the hydraulic control system.

[0006] According to a first aspect of an embodiment of the present application, a method for constructing a hydraulic control model is provided, the method comprising:

[0007] S1, obtain data and the model to be identified:

[0008] Acquire first input data and first output data of a first component at a preset time, second output data of the first component at a current time, second input data of at least one second component at a preset time, and acquire a model to be identified; the preset time is a time adjacent to and before the current time, the first component is controlled by a hydraulic control system, and the pressure output by the first component during operation is suppressed by the operation of the second component;

[0009] S2, build hydraulic control model:

[0010] According to the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, and the second input data of at least one second component at a preset time, the parameters in the model to be identified are identified to obtain the hydraulic control model of the first component;

[0011] The model to be identified in S1 is a Hammerstein model including a coupling term, and the coupling term is determined based on the second input data of the second component at a preset time.

[0012] In one embodiment, before obtaining the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, the second input data of at least one second component at a preset time, and the model to be identified, that is, before step S1, the method further includes:

[0013] S10, obtain pressure data:

[0014] Each third component and the first component of the plurality of components are respectively regarded as a group of components, and each component in each group of components is controlled to operate according to at least one preset operation sequence, so as to obtain pressure data output by each component in each group of components;

[0015] S11, determine the second component:

[0016] According to the pressure data output by each component in each group of components, the component that suppresses the pressure output by the first component among the multiple components is determined, and the component that suppresses the pressure output by the first component among the multiple components is used as the second component.

[0017] In one embodiment, after determining the component that suppresses the pressure output by the first component among the multiple components according to the pressure data output by each component in each group of components, and using the component that suppresses the pressure output by the first component among the multiple components as the second component, that is, after step S11, the method further includes:

[0018] S20, get the Hammerstein model:

[0019] The Hammerstein model includes a first input item and a first output item of the first component at a preset time, and a second output item of the first component at a current time;

[0020] S21, component model to be identified:

[0021] The product of the second input item of the second component at the preset time and the preset parameter is taken as a coupling item and added to the Hammerstein model to obtain the model to be identified.

[0022] In one embodiment, obtaining first input data and first output data of a first component at a preset time, second output data of the first component at the current time, and second input data of at least one second component at a preset time, that is, step S1, includes:

[0023] Obtaining input data and output data of a first component and input data of at least one second component;

[0024] Synchronize the time axis of the input data and output data of the first component and the input data of at least one second component according to the timestamp of the input data and the timestamp of the output data of the first component and the timestamp of the input data of at least one second component, and obtain the input data and output data of the first component, the data of the input data of at least one second component at a preset time, and the data of the output data of the first component at a current time;

[0025] A preset filtering method is used to filter the data at the preset moment and the data at the current moment to obtain the first input data and the first output data of the first component at the preset moment, the second output data of the first component at the current moment, and the second input data of at least one second component at the preset moment.

[0026] In one embodiment, the preset filtering method includes at least one of low-pass filtering or mean filtering.

[0027] In one embodiment, according to the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, and the second input data of at least one second component at a preset time, the parameters in the model to be identified are identified to obtain the hydraulic control model of the first component, that is, step S2, including:

[0028] Constructing a loss function according to first input data and first output data of the first component at a preset time, second output data of the first component at the current time, and second input data of at least one second component at a preset time; the loss function includes a ridge parameter and a parameter in the model to be identified;

[0029] Solve the loss function to get the value of the parameter;

[0030] Substituting the first input data, the first output data, the second output data, the second input data and the numerical values ​​of the parameters into the model to be identified to obtain an estimated value of the output of the model to be identified;

[0031] Determine data corresponding to the regression evaluation index of the model to be identified according to the estimated value and the second output data;

[0032] When the data corresponding to the regression evaluation index of the model to be identified meets the preset conditions, the model to be identified with the numerical values ​​of the parameters substituted is used as the hydraulic control model of the first component.

[0033] In one embodiment, the regression evaluation metric includes at least one of error or goodness of fit.

[0034] According to a second aspect of an embodiment of the present application, a device for constructing a hydraulic control model is provided, the device comprising:

[0035] an acquisition module, used to acquire first input data and first output data of a first component at a preset time, second output data of the first component at a current time, second input data of at least one second component at a preset time, and a model to be identified; the preset time is a time adjacent to the current time and before the current time, the first component is controlled by a hydraulic control system, and the pressure output by the first component during operation is suppressed by the operation of the second component;

[0036] an identification module, used to identify parameters in the model to be identified according to first input data and first output data of the first component at a preset time, second output data of the first component at a current time, and second input data of at least one second component at a preset time, so as to obtain a hydraulic control model of the first component;

[0037] The model to be identified is a Hammerstein model including a coupling term, and the coupling term is determined based on second input data of the second component at a preset time.

[0038] According to a third aspect of an embodiment of the present application, there is provided an electronic device, the device comprising: a processor and a memory storing computer program instructions;

[0039] When the processor executes the computer program instructions, the first aspect or any one of the methods for constructing a hydraulic control model of the first aspect is implemented.

[0040] According to a fourth aspect of the embodiments of the present application, an excavator is provided, and the excavator includes the electronic device according to the third aspect of the embodiments of the present application.

[0041] According to the fifth aspect of the embodiment of the present application, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method for constructing a hydraulic control model as described in the first aspect or any one of the first aspects is implemented.

[0042] The embodiment of the present application provides a method, device, electronic device and excavator for constructing a hydraulic control model, which uses a Hammerstein model including input data and output data of a first component and input data of a second component that suppresses the first component, identifies the parameters of each item in the Hammerstein model, and obtains a hydraulic control model of the first component. The Hammerstein model has a simple structure, and the amount of calculation when using the Hammerstein model is small, so the calculation speed is fast. The hydraulic control model with a simple structure and fast calculation speed meets the requirements of the hydraulic control system for motion control. Moreover, the Hammerstein model constructed in the embodiment of the present application includes coupling terms, which reduces the dependence of the output of the model at the current moment on the output data of the first component at the moment before the current moment, thereby improving the goodness of fit of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0044] Figure 1 A schematic diagram of an implementation environment involved in an embodiment of the present application.

[0045] Figure 2 A flow chart of a method for constructing a hydraulic control model provided in an embodiment of the present application.

[0046] Figure 3 A schematic diagram of the operation timing of a first component and a third component provided in an embodiment of the present application.

[0047] Figure 4 A schematic diagram of pressure data output by a first component and a third component provided in an embodiment of the present application.

[0048] Figure 5 A schematic diagram of the structure of a device for constructing a hydraulic control model provided in an embodiment of the present application.

[0049] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only 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.

[0051] The hydraulic control system on construction machinery is a complex nonlinear system. The system is powered by an electric motor, and uses a hydraulic pump to convert mechanical energy into pressure to push the hydraulic oil. By controlling various valves to change the flow direction of the hydraulic oil, the hydraulic cylinder is pushed to make different strokes and different directions to complete the different action needs of various equipment. The model of this system is directly related to the operating stability and operation quality of the main actuator. Therefore, it is very necessary to identify the model of the hydraulic control system. In the existing hydraulic control system, the extreme learning machine model or the particle swarm algorithm is generally used. Among them, the extreme learning machine model is a kind of neural network, and its model structure is relatively complex; the particle swarm algorithm is initialized as a group of random particles (random solution), and then finds the optimal solution through iteration. Due to the complex model structure of the extreme learning machine model, it is not conducive to the development of the control algorithm when the model is controlled in the future; the particle swarm algorithm finds the optimal solution through iteration, and the calculation speed is slow. The working scene of the construction machinery is constantly changing, resulting in the dynamic characteristics of the hydraulic system changing with the changes in the external environment, which is not conducive to the subsequent promotion of online identification. Therefore, the above two models cannot meet the needs of the hydraulic control system for motion control.

[0052] Exemplary Implementation Environment

[0053] like Figure 1 As shown, Figure 1 It is a schematic diagram of an implementation environment involved in the present application.

[0054] In the actual loading work of the excavator, the current data obtained by the controller and sensor on the excavator is used as input data and brought into the model of the hydraulic main controller system to predict the output data of the hydraulic main controller at the next moment and at a later moment, providing the necessary state information and output data for the motion control algorithm. The more accurate the state information and output data, the higher the accuracy of the motion control algorithm, providing strong support for the stable operation and operation quality of the components under the action of the motion control algorithm.

[0055] The execution subject of the method provided in the embodiment of the present application is a device with data processing function, such as a computer, a server, etc.

[0056] Exemplary Methods

[0057] In some embodiments, a method for constructing a hydraulic control model provided in an embodiment of the present application is as follows: Figure 2 As shown, the following steps may be included:

[0058] S1, obtain data and the model to be identified:

[0059] The first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, the second input data of at least one second component at a preset time, and the model to be identified are obtained.

[0060] Some engineering machinery (such as excavators) include a hydraulic control system. The first component is any component in the engineering machinery that is controlled by the hydraulic control system, and the pressure output by the first component during operation is suppressed by the operation of at least one second component in the engineering machinery. The controller, sensors and other equipment on the engineering machinery collect input data of the first component and the second component, as well as output data of the first component.

[0061] The first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, and the second input data of at least one second component at a preset time are extracted from the above data, and a model to be identified is pre-built.

[0062] Among them, the preset moment is a moment adjacent to the current moment and before the current moment. The preset moment may include one or more moments. When the preset moment includes one moment, the preset moment is a moment adjacent to the current moment and before the current moment; when the preset moment includes multiple moments, the preset moment is before the current moment, and is multiple consecutive moments starting from a moment adjacent to the current moment.

[0063] The Hammerstein model is a nonlinear system with memory composed of a nonlinear subsystem without memory and a linear subsystem in series. In the prior art, in the Hammerstein model used to fit the input data and output data of the first component, the output data of the first component at the current moment is determined by the input data and output data of the first component at the preset moment.

[0064] In one example, the preset time includes a time that is adjacent to the current time and before the current time, and the Hammerstein model for fitting the input data and output data of the first component is as follows:

[0065] y(t)=θ1·y(t-1)+θ2·u(t-1)

[0066] Among them, t represents the current moment, t-1 represents the moment before the current moment, y(t) represents the output item of the first component of the model output at the current moment, y(t-1) represents the first output item of the first component at the moment t-1, θ1 represents the parameter of the first output item, u(t-1) represents the first input item of the first component at the moment t-1, and θ2 represents the parameter of the first input item.

[0067] Since there is a pressure priority mechanism between some components of the hydraulic system of engineering machinery, that is, when multiple components are operating at the same time, the operating requirements of one of the components are met first, so the output pressure of other components may be reduced, that is, the output pressure is suppressed. If the output pressure of the first component is suppressed by other components when it is operating, then when constructing the hydraulic control model of the first component, it is difficult to construct a hydraulic control model with better fitting effect based only on the input data and output data of the first component.

[0068] Based on the above problems, the embodiment of the present application improves the existing Hammerstein model by adding a coupling term to the Hammerstein model. The coupling term is determined based on the second input data of the second component at a preset time. The second component refers to the component that suppresses the pressure output by the first component during operation. The Hammerstein model including the coupling term is used as the model to be identified.

[0069] In one example, the preset moment is a moment adjacent to the current moment and before the current moment, and the Hammerstein model including the coupling term includes a coupling term, and the Hammerstein model including the coupling term is as follows:

[0070] y(t)=θ1·y(t-1)+θ2·u1(t-1)+θ3·u2(t-1)

[0071] Among them, t represents the current moment, t-1 represents the moment before the current moment, y(t) represents the output item of the first component of the model output at the current moment, y(t-1) represents the first output item of the first component at the moment t-1, θ1 represents the parameter of the first output item, u1(t-1) represents the first input item of the first component at the moment t-1, θ2 represents the parameter of the first input item, u2(y-1) represents the second input item of the second component at the moment t-1, that is, it represents the coupling item, and θ3 represents the parameter of the coupling item.

[0072] When the output pressure of the first component is not suppressed by the operation of any component, the parameter of the coupling term is 0.

[0073] In one example, the first input data and the second input data are handle signals of an excavator, and the first output data and the second output data are pilot pressures output by a first component of the excavator at a preset time and at a current time, respectively.

[0074] S2, build hydraulic control model:

[0075] According to the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, and the second input data of at least one second component at a preset time, the parameters in the model to be identified are identified to obtain the hydraulic control model of the first component.

[0076] The first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, and the second input data of at least one second component at a preset time are substituted into the model to be identified, and the parameters in the model to be identified are solved, that is, the parameters in the Hammerstein model with coupling terms are solved to obtain the numerical values ​​of the parameters, and the numerical values ​​of the parameters are substituted into the Hammerstein model with coupling terms to obtain the hydraulic control model of the first component.

[0077] In one embodiment, the recursive least square method is used to solve the parameters in the model to be identified.

[0078] The recursive least squares method is a method for estimating the actual output at the current moment based on the data generated by the system's past operation. Since the algorithm does not need to find the inverse of a large matrix during the model identification process, the amount of calculation is greatly reduced. At the same time, it can converge quickly and has a fast identification speed.

[0079] In another embodiment, a particle swarm algorithm is used to solve the parameters in the model to be identified.

[0080] The particle swarm algorithm is a random search algorithm based on group collaboration developed by simulating the foraging behavior of bird flocks. Assuming that there is only one piece of food in the area (that is, the optimal solution in the usual optimization problem), the task of the bird flock is to find this food source. During the entire search process, the bird flock transmits each other's information to let other birds know their position. Through such collaboration, they can determine whether they have found the optimal solution, and at the same time, they also transmit the information of the optimal solution to the entire bird flock. Finally, the entire bird flock can gather around the food source, that is, they have found the optimal solution.

[0081] In another embodiment, a hybrid frog leaping algorithm is used to solve the parameters in the model to be identified.

[0082] The hybrid frog leaping algorithm simulates the foraging process of frogs in a pond. Each frog in the population changes its position by jumping in the pond and approaches food by communicating with each other. Assume that there is a group of frogs living in a pond with many scattered stones. Frogs can jump between the scattered stones to find food, but the food in the pond is limited. Each frog has its own thoughts and can communicate with its fellow frogs around it. Through the exchange of information, it strives to get more food. The total frog population is divided into several sub-populations. The frogs in the sub-population can change their jumping direction by communicating with their peers in the same sub-population during the jumping process, and can also affect the jumping direction of their peers. The evolution of the sub-population position is processed according to the memetic algorithm. After the evolution iteration of the sub-population is completed, the sub-populations must also communicate information, that is, the hybrid operation between the sub-populations, so as to achieve a balance between local search and global search. In the calculation process, local search and global search are repeated and performed alternately until the most food in the pond is found. The hybrid frog leaping algorithm has the ability to balance local optimization and global optimization. When the algorithm falls into the local optimum, it can jump out of the unnecessary cycle in time and move quickly towards the global optimum.

[0083] The method for constructing a hydraulic control model provided in the embodiment of the present application adopts a Hammerstein model including input data and output data of a first component and input data of a second component that suppresses the first component, identifies the parameters of each item in the Hammerstein model, and obtains a hydraulic control model of the first component. The Hammerstein model has a simple structure, and the amount of calculation when using the Hammerstein model is small, so the calculation speed is fast, and a hydraulic control model with a simple structure and fast calculation speed is constructed, which meets the requirements of the hydraulic control system for motion control. Moreover, the Hammerstein model constructed in the embodiment of the present application includes a coupling term, which reduces the dependence of the output data of the model at the current moment on the output data of the first component at the previous moment, and improves the goodness of fit of the model.

[0084] In some embodiments, before S1: obtaining the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, the second input data of at least one second component at a preset time, and the model to be identified, the method may further include the following steps:

[0085] S10, obtain pressure data:

[0086] Each component in the plurality of components and the first component are respectively regarded as a group of components, and each component in each group of components is controlled to operate according to at least one preset operation sequence to obtain pressure data output by each component in each group of components.

[0087] The hydraulic control system of the same engineering machinery where the first component is located may also include multiple components other than the first component. Each of the multiple components and the first component are respectively regarded as a group of components, and at least one operation sequence is pre-set. According to each operation sequence, each component in each group of components is controlled to operate, and the pressure data output by each component in each group of components is recorded.

[0088] In one embodiment, at least one preset operation sequence may include at least one of synchronous action of the first component and another component in the same group, the first component acts first and stops first, the first component acts first and then exits, the first component acts later and then exits, and the first component acts later and then exits.

[0089] In one example, at least one preset operation sequence includes a first component acting first and then exiting, then the operation sequence of the first component and another component in the same group is as follows: Figure 3 As shown in FIG. 1 , the first component starts to input signals before another component in the same group. After a period of operation, the first component stops inputting signals after another component in the same group. The pressure data output by the first component and another component in the same group are shown in FIG. Figure 4 As shown, after another component in the same group starts to input signals, the pressure output by the first component decreases, and after another component in the same group stops inputting signals, the pressure output by the first component recovers, indicating that another component in the same group suppresses the pressure output by the first component.

[0090] S11, determine the second component:

[0091] According to the pressure data output by each component in each group of components, the component that suppresses the pressure output by the first component among the multiple components is determined, and the component that suppresses the pressure output by the first component among the multiple components is used as the second component.

[0092] The changing trend of the pressure data output by each component in each group of components is counted. If any component among the multiple components suppresses the pressure output by the first component when operating based on any one of the at least one timing sequence mentioned above, the component is used as the second component.

[0093] The method provided in the embodiment of the present application determines through experiments the second component that suppresses the pressure output by the first component, provides a coupling term for constructing a hydraulic control model, and improves the fit of the hydraulic control model.

[0094] In some embodiments, after determining, according to the pressure data output by each component in each group of components, a component that suppresses the pressure output by the first component among the multiple components, and using the component that suppresses the pressure output by the first component among the multiple components as the second component, the method may further include the following steps:

[0095] S20, get the Hammerstein model:

[0096] The Hammerstein model includes a first input item and a first output item of a first component at a preset time, and a second output item of the first component at a current time.

[0097] First, a Hammerstein model is constructed based on a first input item and a first output item of a first component at a preset time, and a second output item of the first component at a current time.

[0098] In one example, the preset time includes a time before the current time, and the Hammerstein model is as follows:

[0099] y(t)=θ1·y(t-1)+θ2·u(t-1)

[0100] Among them, t represents the current moment, t-1 represents the moment before the current moment, y(t) represents the output item of the first component of the model output at the current moment, y(t-1) represents the first output item of the first component at the moment t-1, θ1 represents the parameter of the first output item, u(t-1) represents the first input item of the first component at the moment t-1, and θ2 represents the parameter of the first input item.

[0101] S21, component model to be identified:

[0102] The product of the second input item of the second component at the preset time and the preset parameter is taken as a coupling item and added to the Hammerstein model to obtain the model to be identified.

[0103] The operation of the second component suppresses the pressure output by the first component during operation, that is, the second component affects the output of the first component. Therefore, the product of the second input item of the second component at a preset time and the preset parameter item is added to the Hammerstein model as a coupling item to obtain the model to be identified.

[0104] In one example, the preset moment includes the moment before the current moment, a coupling term is added to the Hammerstein model, and the obtained model to be identified is as follows:

[0105] y(t)=θ1·y(t-1)+θ2·u1(t-1)+θ3·u2(t-1)

[0106] Among them, t represents the current moment, t-1 represents the moment before the current moment, y(t) represents the output item of the first component of the model output at the current moment, y(t-1) represents the first output item of the first component at the moment t-1, θ1 represents the parameter of the first output item, u1(t-1) represents the first input item of the first component at the moment t-1, θ2 represents the parameter of the first input item, u2(t-1) represents the second input item of the second component at the moment t-1, that is, it represents the coupling item, and θ3 represents the preset parameter of the coupling item.

[0107] The method provided in the embodiment of the present application takes the input of the second component that affects the output of the first component as a coupling term and adds it to the Hammerstein model, taking more influencing factors into consideration, reducing the influence of the output of the first component in the model on the model output, and improving the goodness of fit of the model.

[0108] In one embodiment, in S1: obtaining the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, and the second input data of at least one second component at a preset time may include the following steps:

[0109] First, input data and output data of a first component and input data of at least one second component are acquired.

[0110] The controller, sensors and other equipment on the engineering machinery collect input data of the first component and the second component, as well as output data of the first component.

[0111] Secondly, based on the timestamp of the input data and the timestamp of the output data of the first component and the timestamp of the input data of at least one second component, the time axis of the input data and the output data of the first component and the input data of at least one second component are synchronized to obtain the input data and the output data of the first component, the data in the input data of at least one second component at a preset time, and the data in the output data of the first component at the current time.

[0112] Since controllers, sensors and other devices on engineering machinery collect a large number of variables, there may be a problem of time asynchrony when storing data at each storage address.

[0113] Based on the timestamp of the input data and the timestamp of the output data of the first component and the timestamp of the input data of at least one second component, the time axis of the input data and the output data of the first component and the input data of at least one second component are synchronized to obtain the time-synchronized input data and the output data of the first component and the input data of at least one second component, and data at a preset moment is extracted from the time-synchronized input data and the output data of the first component and the input data of at least one second component, and data at the current moment is extracted from the output data of the first component.

[0114] Finally, a preset filtering method is used to filter the data at the preset moment and the data at the current moment to obtain the first input data and the first output data of the first component at the preset moment, the second output data of the first component at the current moment, and the second input data of at least one second component at the preset moment.

[0115] The input data and output data of components in the hydraulic control system of construction machinery are low-frequency signals. Due to the harsh working environment of construction machinery, the data collected by controllers, sensors and other equipment on the construction machinery inevitably contain high-frequency impact signals, burrs and other noises.

[0116] Using a preset filtering method, the input data and output data of the first component, the data at a preset moment and the data at the current moment in the input data of at least one second component are filtered to obtain the first input data and first output data of the first component at the preset moment, and the second output data of the first component at the current moment; the data at the preset moment in the input data of at least one second component is filtered to obtain the second input data of at least one second component at the preset moment.

[0117] The method provided in the embodiment of the present application performs time synchronization and filtering on the collected data, thereby obtaining relatively accurate data, and improving the recognition accuracy of the model to be identified when identifying the model to be identified.

[0118] In one embodiment, the preset filtering method includes at least one of low-pass filtering or mean filtering.

[0119] Low-pass filtering is a filtering method. The rule is that low-frequency signals can pass normally, while high-frequency signals exceeding the set critical value are blocked and weakened. After low-pass filtering is performed on the input data and output data of the first component and the input data of at least one second component, the high-frequency impact signals in these data are filtered out to obtain more accurate data.

[0120] Mean filtering is a typical linear filtering algorithm, which refers to giving a template to the target pixel in the image. The template includes the neighboring pixels around it (the 8 pixels around the target pixel as the center constitute a filtering template, that is, including the target pixel itself), and then replaces the original pixel value with the average value of all pixels in the template. After mean filtering, the sharp noise in the data is eliminated.

[0121] Based on the principle of mean filtering, the embodiment of the present application filters the data collected by the controller, sensor and other equipment on the engineering machinery. Specifically, based on the data collection time, starting from the earliest collection time in the same set of data (the input data of the first component, the output data of the first component or the input data of the second component), the mean of the data within the preset time length is calculated, and the data with the earliest collection time is updated to the mean; then, starting from the moment after the earliest collection time, the mean of the data within the preset time length is calculated, and the data at this moment is updated to the mean, until each set of collected data is processed as above, that is, the mean filtering is completed.

[0122] After mean filtering, the burrs in the data collected by controllers, sensors and other equipment on the construction machinery are eliminated, and the data changes are more accurate.

[0123] The filtering method provided in the embodiment of the present application filters out noise in the data collected by the controller, sensor and other equipment on the engineering machinery, thereby improving the accuracy of the data.

[0124] In one embodiment, S2: according to the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, and the second input data of at least one second component at a preset time, identifying the parameters in the model to be identified, and obtaining the hydraulic control model of the first component, may include the following steps:

[0125] First, a loss function is constructed according to first input data and first output data of a first component at a preset time, second output data of the first component at a current time, and second input data of at least one second component at a preset time.

[0126] The loss function includes the ridge parameter and the parameters in the model to be identified.

[0127] Among them, the ridge parameter is the penalty coefficient in the ridge regression algorithm, and the ridge regression algorithm is the least square method with a regular term. During the identification process, the fitting accuracy of the model can be improved by adjusting the value of the ridge parameter.

[0128] In one example, the loss function is as follows:

[0129]

[0130] Wherein, J represents the loss, y(k) represents the first output item of the first component at a preset time, represents the output item of the model to be identified, k represents the current moment, k-1 represents the moment before the current moment, y(k-1) represents the first output item of the first component at the k-1 moment, θ1 represents the parameter of the first output item, u1(k-1) represents the first input item of the first component at the k-1 moment, θ2 represents the parameter of the first input item, u2(k-1) represents the coupling item, and θ3 represents the parameter of the coupling item. λ represents the ridge parameter.

[0131] Will Substituting into the loss function, we get the following formula:

[0132]

[0133] Secondly, solve the loss function to get the value of the parameter.

[0134] The unknowns in the loss function are θ1, θ2 and θ3. The loss function is differentiated to obtain the parameters of the model to be identified.

[0135] In one example, the loss function is differentiated to obtain the following parameters:

[0136] θ=(H T H+λ·rm) -1 HY

[0137] Wherein, θ represents a column vector including θ1, θ2 and θ3, Y represents a vector obtained by concatenating the first output items of N moments before the current moment in rows, λ is a ridge parameter, the value of λ is a preset value, and rm is a column vector of λ.

[0138] Solve and obtain the values ​​of θ1, θ2, and θ3.

[0139] Again, the first input data, the first output data, the second output data, the second input data and the numerical values ​​of the parameters are substituted into the model to be identified to obtain an estimated value of the output of the model to be identified.

[0140] The first input data, the first output data, the second output data, the second input data and the parameter values ​​are substituted into the model to be identified, and the model to be identified outputs an estimated value after calculation, that is, the estimated value of the second output item of the first component at the current moment by the model to be identified.

[0141] Thirdly, according to the estimated value and the second output data, the data corresponding to the regression evaluation index of the model to be identified is determined.

[0142] The regression evaluation index represents an index for evaluating the fitting effect of the model to be identified, and is selected in advance by the technician according to the needs.

[0143] According to the estimated value of the second output item of the first component at the current moment by the model to be identified and the actual output value of the first component at the current moment, data corresponding to the regression evaluation index of the model to be identified is calculated.

[0144] Finally, when the data corresponding to the regression evaluation index of the model to be identified meets the preset conditions, the model to be identified with the numerical values ​​of the parameters substituted is used as the hydraulic control model of the first component.

[0145] Compare the data corresponding to the regression evaluation index of the model to be identified with the data in the preset conditions. When the data corresponding to the regression evaluation index of the model to be identified meets the preset conditions, the model to be identified with the numerical values ​​of the parameters substituted is used as the hydraulic control model of the first component.

[0146] The preset condition may be that the data corresponding to the regression evaluation index of the model to be identified reaches a preset threshold.

[0147] When the data corresponding to the regression evaluation index of the model to be identified does not meet the preset conditions, the value of the ridge parameter is adjusted; or the preset moment in the model to be identified is made to include more continuous moments before the current moment; or the number of coupling terms in the model to be identified is increased, that is, the number of second components is increased, and then the model to be identified is identified again until the data corresponding to the regression evaluation index of the model to be identified meets the preset conditions.

[0148] The embodiment of the present application adopts a ridge regression algorithm for model identification and introduces a ridge parameter. During the identification process, the size of the ridge parameter can be adjusted to weaken the model's dependence on the output data at the previous moment while ensuring the fitting accuracy, thereby ensuring the generalization of the model and providing a reliable model for accurately controlling the operation of the first component.

[0149] In one embodiment, the regression evaluation metric includes at least one of error or goodness of fit.

[0150] Error refers to the difference between the output data of the model and the actual collected output data.

[0151] Goodness of fit refers to the degree of fit of the model to the actual collected data. The statistic that measures goodness of fit is the coefficient of determination (also known as the coefficient of determination) R 2 . R 2 The maximum value is 1. 2 The closer the value of is to 1, the better the regression line fits the observed value; on the contrary, R 2 The smaller the value of , the worse the fit of the regression line to the observed value.

[0152] At least one of the error or goodness of fit of the model to be identified is calculated and determined based on the estimated value of the second output item of the first component at the current moment and the actual output value of the first component at the current moment.

[0153] When the regression evaluation index includes an error, the error of the model to be identified is calculated based on the estimated value of the second output item of the first component at the current moment and the actual output value of the first component at the current moment. The preset condition is that the error of the model to be identified is less than the preset error. If the calculated error of the model to be identified is less than the preset error, the model to be identified with the numerical value of the parameter substituted is used as the hydraulic control model of the first component.

[0154] When the regression evaluation index includes goodness of fit, the goodness of fit of the model to be identified is calculated and determined based on the estimated value of the second output item of the first component at the current moment of the model to be identified and the actual output value of the first component at the current moment. The preset condition is that the goodness of fit of the model to be identified reaches the preset goodness of fit. If the calculated goodness of fit of the model to be identified reaches the preset goodness of fit, the model to be identified with the numerical value of the parameter substituted is used as the hydraulic control model of the first component.

[0155] When the regression evaluation index includes error and goodness of fit, the error and goodness of fit of the model to be identified are calculated and determined according to the estimated value of the second output item of the first component at the current moment and the actual output value of the first component at the current moment of the model to be identified. The preset condition is that the error of the model to be identified is less than the preset error, and the goodness of fit of the model to be identified reaches the preset goodness of fit. If the calculated error of the model to be identified is less than the preset error, and the goodness of fit reaches the preset goodness of fit, the model to be identified with the numerical value of the parameter substituted is used as the hydraulic control model of the first component.

[0156] The method provided in the embodiment of the present application sets at least one regression index. When the data of the regression index of the model to be identified meets the preset conditions, the model to be identified with the numerical value of the parameter is substituted as the hydraulic control model of the first component, thereby ensuring that the hydraulic control model has a better fitting effect.

[0157] Exemplary Devices

[0158] The present application also provides a device for constructing a hydraulic control model. Figure 5 As shown, the apparatus 500 may include an acquisition module 510 and an identification module 520 .

[0159] The acquisition module 510 is used to acquire the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, the second input data of at least one second component at the preset time, and the model to be identified; the preset time is a time adjacent to the current time and before the current time, the first component is controlled by the hydraulic control system, and the pressure output by the first component during operation is suppressed by the operation of the second component;

[0160] An identification module 520, configured to identify parameters in the model to be identified based on first input data and first output data of the first component at a preset time, second output data of the first component at a current time, and second input data of at least one second component at a preset time, so as to obtain a hydraulic control model of the first component;

[0161] The model to be identified is a Hammerstein model including a coupling term, and the coupling term is determined based on second input data of the second component at a preset time.

[0162] The embodiment of the present application provides a device for constructing a hydraulic control model, which uses a Hammerstein model including input data and output data of a first component and input data of a second component that suppresses the first component, identifies the parameters of each item in the Hammerstein model, and obtains a hydraulic control model of the first component. The Hammerstein model has a simple structure, and the amount of calculation when using the Hammerstein model is small, so the calculation speed is fast, and a hydraulic control model with a simple structure and fast calculation speed is constructed, which meets the requirements of the hydraulic control system for motion control. In addition, the Hammerstein model constructed in the embodiment of the present application includes a coupling term, which reduces the dependence of the output of the model at the current moment on the output data of the first component at the previous moment, thereby improving the goodness of fit.

[0163] In one embodiment, the apparatus 500 may further include a control module 530 and a determination module 540 .

[0164] The control module 530 is used to respectively treat each third component and the first component of the multiple components as a group of components, control each component in each group of components to operate according to at least one preset operation sequence, and obtain pressure data output by each component in each group of components.

[0165] The determination module 540 is used to determine the component that suppresses the pressure output by the first component among the multiple components according to the pressure data output by each component in each group of components, and use the component that suppresses the pressure output by the first component among the multiple components as the second component.

[0166] The device provided in the embodiment of the present application determines through experiments the second component that suppresses the pressure output by the first component, provides a coupling term for constructing a hydraulic control model, and improves the fit of the hydraulic control model.

[0167] In some embodiments, the acquisition module 510 may also be used to acquire a Hammerstein model, where the Hammerstein model includes a first input item and a first output item of the first component at a preset time, and a second output item of the first component at a current time.

[0168] The apparatus 500 may further include an adding module 550 .

[0169] The adding module 550 is used to add the product of the second input item of the second component at the preset time and the preset parameter as a coupling item to the Hammerstein model to obtain the model to be identified.

[0170] The device provided in the embodiment of the present application takes the input of the second component that affects the output of the first component as a coupling term and adds it to the Hammerstein model, taking more influencing factors into consideration, reducing the influence of the output term of the first component in the model on the model output, and improving the goodness of fit of the model.

[0171] In one embodiment, the acquisition module 510 may be specifically used to:

[0172] Obtaining input data and output data of a first component and input data of at least one second component;

[0173] Synchronize the time axis of the input data and output data of the first component and the input data of at least one second component according to the timestamp of the input data and the timestamp of the output data of the first component and the timestamp of the input data of at least one second component, and obtain the input data and output data of the first component, the data of the input data of at least one second component at a preset time, and the data of the output data of the first component at a current time;

[0174] A preset filtering method is used to filter the data at the preset moment and the data at the current moment to obtain the first input data and the first output data of the first component at the preset moment, the second output data of the first component at the current moment, and the second input data of at least one second component at the preset moment.

[0175] The device provided in the embodiment of the present application performs time synchronization and filtering on the collected data, thereby obtaining relatively accurate data, and improving the recognition accuracy of the model to be identified when identifying the model to be identified.

[0176] In one embodiment, the preset filtering method includes at least one of low-pass filtering or mean filtering.

[0177] The filtering method provided in the embodiment of the present application filters out noise in the data collected by the controller, sensor and other equipment on the engineering machinery, thereby improving the accuracy of the data.

[0178] In one embodiment, the identification module 520 may be specifically used to:

[0179] Constructing a loss function according to first input data and first output data of the first component at a preset time, second output data of the first component at the current time, and second input data of at least one second component at a preset time; the loss function includes a ridge parameter and a parameter in the model to be identified;

[0180] Solve the loss function to get the value of the parameter;

[0181] Substituting the first input data, the first output data, the second output data, the second input data and the numerical values ​​of the parameters into the model to be identified to obtain an estimated value of the output of the model to be identified;

[0182] Determine data corresponding to the regression evaluation index of the model to be identified according to the estimated value and the second output data;

[0183] When the data corresponding to the regression evaluation index of the model to be identified meets the preset conditions, the model to be identified with the numerical values ​​of the parameters substituted is used as the hydraulic control model of the first component.

[0184] The device provided in the embodiment of the present application obtains a hydraulic control model of the first component that meets preset conditions through identification, thereby providing a reliable model for accurately controlling the operation of the first component.

[0185] In one embodiment, the regression evaluation metric includes at least one of error or goodness of fit.

[0186] The device provided in the embodiment of the present application sets at least one regression index. When the data of the regression index of the model to be identified meets the preset conditions, the model to be identified with the numerical value of the parameter is substituted as the hydraulic control model of the first component, thereby ensuring that the hydraulic control model has a better fitting effect.

[0187] The device provided in this embodiment belongs to the same application concept as the method provided in the above embodiment of this application, can execute the method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of the execution method. For the technical details not fully described in this embodiment, please refer to the specific processing content of the method provided in the above embodiment of this application, which will not be repeated here.

[0188] Exemplary Electronic Devices

[0189] Figure 6A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention is shown.

[0190] The electronic device may include a processor 601 and a memory 602 storing computer program instructions.

[0191] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0192] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 602 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.

[0193] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0194] The processor 601 implements any one of the methods for constructing a hydraulic control model in the above embodiments by reading and executing computer program instructions stored in the memory 602 .

[0195] In one example, the electronic device may further include a communication interface 603 and a bus 610. Figure 6 As shown, the processor 601, the memory 602, and the communication interface 603 are connected via a bus 610 and communicate with each other.

[0196] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiment of the present invention.

[0197] Bus 610 includes hardware, software or both, and the components of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 610 may include one or more buses. Although the embodiment of the present invention describes and shows a specific bus, the present invention considers any suitable bus or interconnection.

[0198] The electronic device can execute the method for constructing a hydraulic control model in the embodiment of the present invention, thereby realizing the combination Figure 2 A method for constructing a hydraulic control model is described.

[0199] The present application also provides an excavator, such as Figure 1 As shown, the excavator includes the electronic device provided by the embodiment of the present application.

[0200] The electronic device can execute the method for constructing a hydraulic control model in the embodiment of the present invention, thereby realizing the combination Figure 2 A method for constructing a hydraulic control model is described.

[0201] Exemplary computer program products and storage media

[0202] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps in any one of the methods for constructing a hydraulic control model in the above-mentioned embodiments of this specification.

[0203] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0204] In addition, in combination with the method for constructing a hydraulic control model in the above embodiment, the embodiment of the present invention can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the methods for constructing a hydraulic control model in the above embodiment is implemented.

[0205] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0206] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0207] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0208] The modules and sub-modules in the devices and terminals of the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0209] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0210] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0211] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0212] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0213] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0214] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0215] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for constructing a hydraulic control model, characterized in that: The method comprises: Acquire first input data and first output data of a first component at a preset time, second output data of the first component at a current time, second input data of at least one second component at the preset time, and a model to be identified; the preset time is a time adjacent to the current time and before the current time, the first component is controlled by a hydraulic control system, and the pressure output by the first component during operation is suppressed by the operation of the second component; According to the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, and the second input data of at least one second component at the preset time, the parameters in the model to be identified are identified to obtain the hydraulic control model of the first component; The model to be identified is a Hammerstein model including a coupling term, and the coupling term is determined based on second input data of the second component at the preset moment.

2. The method according to claim 1, characterized in that Before obtaining the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, the second input data of at least one second component at the preset time, and the model to be identified, the method further includes: Respectively taking each component of the plurality of components and the first component as a group of components, and controlling each component in each group of components to operate according to at least one preset operation sequence, to obtain pressure data output by each component in each group of components; According to the pressure data output by each component in each group of components, the component among the multiple components that suppresses the pressure output by the first component is determined, and the component among the multiple components that suppresses the pressure output by the first component is used as the second component.

3. The method according to claim 2, characterized in that After determining, according to the pressure data output by each component in each group of components, a component among the multiple components that suppresses the pressure output by the first component, and using the component among the multiple components that suppresses the pressure output by the first component as the second component, the method further includes: Acquire a Hammerstein model, wherein the Hammerstein model includes a first input item and a first output item of the first component at a preset time, and a second output item of the first component at a current time; The product of the second input item of the second component at the preset time and the preset parameter is taken as a coupling item and added to the Hammerstein model to obtain the model to be identified.

4. The method according to claim 1, characterized in that: The obtaining of first input data and first output data of a first component at a preset time, second output data of the first component at a current time, and second input data of at least one second component at the preset time includes: Acquiring input data and output data of the first component and input data of the at least one second component; Synchronize the time axis of the input data and output data of the first component and the input data of the at least one second component according to the timestamp of the input data and the timestamp of the output data of the first component and the timestamp of the input data of the at least one second component, and obtain the input data and output data of the first component, the data of the input data of the at least one second component at the preset time, and the data of the output data of the first component at the current time; A preset filtering method is adopted to filter the data at the preset moment and the data at the current moment to obtain the first input data and the first output data of the first component at the preset moment, the second output data of the first component at the current moment, and the second input data of the at least one second component at the preset moment.

5. The method according to claim 4, characterized in that The preset filtering method includes at least one of low-pass filtering and mean filtering.

6. The method according to claim 1, characterized in that The method of identifying the parameters in the model to be identified based on the first input data and the first output data of the first component at a preset time, the second output data of the first component at a current time, and the second input data of at least one second component at the preset time to obtain the hydraulic control model of the first component includes: Constructing a loss function according to the first input data and the first output data of the first component at a preset time, the second output data of the first component at the current time, and the second input data of the at least one second component at the preset time; the loss function includes a ridge parameter and parameters in the model to be identified; Solving the loss function to obtain the value of the parameter; Substituting the first input data, the first output data, the second output data, the second input data and the numerical values ​​of the parameters into the model to be identified to obtain an estimated value of the output of the model to be identified; Determining data corresponding to the regression evaluation index of the model to be identified according to the estimated value and the second output data; When the data corresponding to the regression evaluation index of the model to be identified meets the preset conditions, the model to be identified with the numerical values ​​of the parameters substituted is used as the hydraulic control model of the first component.

7. The method according to claim 6, characterized in that The regression evaluation index includes at least one of error or goodness of fit.

8. A device for constructing a hydraulic control model, characterized in that: The device comprises: an acquisition module, used for acquiring first input data and first output data of a first component at a preset time, second output data of the first component at a current time, second input data of at least one second component at the preset time, and a model to be identified; the preset time is a time adjacent to the current time and before the current time, the first component is controlled by a hydraulic control system, and the pressure output by the first component during operation is suppressed by the operation of the second component; an identification module, configured to identify parameters in the model to be identified based on first input data and first output data of the first component at a preset time, second output data of the first component at a current time, and second input data of at least one second component at the preset time, so as to obtain a hydraulic control model of the first component; The model to be identified is a Hammerstein model including a coupling term, and the coupling term is determined based on second input data of the second component at the preset moment.

9. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for constructing a hydraulic control model as described in any one of claims 1 to 7 is implemented.

10. An excavator, characterized in that: The excavator includes the electronic device according to claim 9.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for constructing a hydraulic control model according to any one of claims 1 to 7 is implemented.

Images