A method and device for identifying model parameters of a hydraulic system and hydraulic engineering machinery

Abstract

The present application discloses a method, device and hydraulic engineering machinery for identifying model parameters of a hydraulic system. First, a system model of the hydraulic system is constructed according to historical data of the hydraulic system. Then, according to historical control signals and the system model, predicted outputs at multiple moments are iteratively obtained, and a loss function of the system model is calculated according to the predicted outputs at multiple moments and corresponding historical execution action data. Finally, according to the loss function, the parameters of the system model are identified, that is, the parameters of the system model are obtained by optimizing and solving the loss function, which not only considers the accuracy of the predicted output at the next moment, but also considers the accuracy of the predicted output at subsequent moments, so as to ensure the authenticity and accuracy of the system model, thereby providing an accurate model basis for intelligent control.

Description

Technical Field

[0001] The present application relates to the technical field of model parameter identification of hydraulic systems, and in particular to a model parameter identification method and device for a hydraulic system and hydraulic engineering machinery. Background Art

[0002] For the hydraulic system of construction machinery, it is necessary to obtain its dynamic mathematical model in order to realize model predictive control and other intelligent control. However, due to the complexity of the internal environment of the hydraulic system and the electromagnetic hysteresis characteristics of multiple solenoid valves, the workload of modeling based on physical mechanisms is extremely large. Therefore, simulation software is usually used in the prior art to achieve this.

[0003] If predictive control of the electro-hydraulic system model is to be achieved, mathematical modeling based on data construction is the first choice, that is, by collecting the input and output of the electro-hydraulic system, the mathematical relationship between the input and output is fitted and identified through optimization methods. The current system identification technology mainly focuses on the fitting ability of the model, that is, at the current moment, the input signal that is the same as the actual system is input to the mathematical model, and the degree of similarity between the output calculated by the mathematical model and the actual output is measured at the next moment. However, for model predictive control, the predictive ability of the model is as important as the fitting ability of the model, that is, when the input signal is given, it is necessary to simultaneously measure whether the predicted output at the next few moments is consistent with the actual output. Summary of the invention

[0004] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a method and device for identifying model parameters of a hydraulic system and a hydraulic engineering machine, which solve the above technical problems.

[0005] According to one aspect of the present application, a method for identifying model parameters of a hydraulic system is provided, comprising: constructing a system model of the hydraulic system based on historical data of the hydraulic system; wherein the system model characterizes the correspondence between a control signal of the hydraulic system and execution action data of the hydraulic system, and the historical data includes historical control signals and corresponding historical execution action data; iterating to obtain predicted outputs at multiple moments based on the historical control signals and the system model; calculating a loss function of the system model based on the predicted outputs at multiple moments and the corresponding historical execution action data; and identifying parameters of the system model based on the loss function.

[0006] In one embodiment, iteratively obtaining the predicted outputs at multiple moments based on the historical control signal and the system model includes: obtaining the predicted output at the current moment based on the historical control signal at the current moment, the multiple predicted outputs before the current moment and / or the historical execution action data, and the system model.

[0007] In one embodiment, the loss function of the system model is calculated based on the predicted outputs at multiple moments and the corresponding historical execution action data, including: obtaining the loss function of the system model based on the square of the difference between the predicted outputs at multiple moments and the corresponding historical execution action data.

[0008] In one embodiment, obtaining the loss function of the system model based on the square of the difference between the predicted output at multiple moments and the corresponding historical execution action data includes: taking a weighted sum of the square of the difference between the predicted output at multiple moments and the corresponding historical execution action data to obtain the loss function of the system model.

[0009] In one embodiment, the weighted summation of the squares of the differences between the predicted outputs at multiple moments and the corresponding historical execution action data to obtain the loss function of the system model includes: setting corresponding weights for multiple moments; wherein the weight of the current moment is greater than the weight of the next moment; and weighted summation of the squares of the differences between the predicted outputs at multiple moments and the corresponding historical execution action data according to the weights to obtain the loss function of the system model.

[0010] In one embodiment, the identifying the parameters of the system model according to the loss function includes: calculating the parameters of the system model according to the loss function so that the value of the loss function is less than a preset value.

[0011] In one embodiment, constructing the system model of the hydraulic system based on the historical data of the hydraulic system includes: constructing a Hammerstein model based on the historical data of the hydraulic system; wherein the Hammerstein model includes a nonlinear part and a linear part, and the nonlinear part includes a piecewise linear function.

[0012] In one embodiment, constructing the Hammerstein model based on the historical data of the hydraulic system includes: combining the nonlinear part and the linear part into a matrix through matrix transformation, and converting the parameters of the system model into a vector.

[0013] According to another aspect of the present application, a model parameter identification device for a hydraulic system is provided, comprising: a model construction module, for constructing a system model of the hydraulic system based on historical data of the hydraulic system; wherein the system model characterizes the correspondence between the control signal of the hydraulic system and the execution action data of the hydraulic system, and the historical data includes historical control signals and corresponding historical execution action data; a prediction output module, for iteratively obtaining prediction outputs at multiple moments based on the historical control signals and the system model; a loss calculation module, for calculating a loss function of the system model based on the prediction outputs at multiple moments and the corresponding historical execution action data; and a parameter identification module, for identifying parameters of the system model based on the loss function.

[0014] According to another aspect of the present application, a hydraulic engineering machine is provided, comprising: an actuator, which is driven by hydraulic pressure to perform actions; and a model parameter identification device of the hydraulic system as described above, which is connected to the actuator.

[0015] The present application provides a method, device and hydraulic engineering machinery for identifying model parameters of a hydraulic system. First, a system model of the hydraulic system is constructed according to historical data of the hydraulic system; then, predicted outputs at multiple moments are iteratively obtained according to historical control signals and the system model, and a loss function of the system model is calculated according to the predicted outputs at multiple moments and corresponding historical execution action data; finally, parameters of the system model are identified according to the loss function; that is, an initial system model is first constructed according to historical data, and then predicted output data at multiple subsequent moments are iteratively obtained according to input data at the current moment, and a loss function is constructed according to the predicted output data and real data at the corresponding moments, and the parameters of the system model are obtained by optimizing and solving the loss function, which not only considers the accuracy of the predicted output at the next moment, but also considers the accuracy of the predicted output at the subsequent moments, so as to ensure the authenticity and accuracy of the system model, thereby providing an accurate model basis for intelligent control. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 It is a flow chart of a method for identifying model parameters of a hydraulic system provided by an exemplary embodiment of the present application.

[0018] Figure 2 It is a schematic diagram of the principle of a method for identifying model parameters of a hydraulic system provided by an exemplary embodiment of the present application.

[0019] Figure 3 It is a flow chart of a method for identifying model parameters of a hydraulic system provided by another exemplary embodiment of the present application.

[0020] Figure 4 It is a structural diagram of a Hammerstein model provided by an exemplary embodiment of the present application.

[0021] Figure 5 It is a schematic diagram of the principle of a method for calculating multiple prediction outputs provided by an exemplary embodiment of the present application.

[0022] Figure 6 It is a flow chart of a method for identifying model parameters of a hydraulic system provided by another exemplary embodiment of the present application.

[0023] Figure 7 It is a flow chart of a method for identifying model parameters of a hydraulic system provided by another exemplary embodiment of the present application.

[0024] Figure 8 It is a structural schematic diagram of a model parameter identification device for a hydraulic system provided by an exemplary embodiment of the present application.

[0025] Fig. 9 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0026] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0027] Figure 1 FIG. 1 is a flow chart of a method for identifying model parameters of a hydraulic system provided by an exemplary embodiment of the present application. Figure 1 As shown, the model parameter identification method of the hydraulic system includes the following steps:

[0028] Step 110: Construct a system model of the hydraulic system based on the historical data of the hydraulic system.

[0029] The system model represents the correspondence between the control signal of the hydraulic system and the execution action data of the hydraulic system; the historical data includes the historical control signal and the corresponding historical execution action data, that is, the input signal and output signal of the hydraulic system. For example, for an excavator, the input signal is the handle signal, and the output signal is the angular velocity of each joint of the excavator. After collecting the input signal and output signal of the excavator, the hydraulic system is modeled according to the input signal and output signal to establish the correspondence between the input signal (control signal) and the output signal (execution action data) of the hydraulic system.

[0030] Step 120: Iterate and obtain the predicted outputs at multiple moments according to the historical control signal and the system model.

[0031] Usually, the system model of the hydraulic system pays more attention to the similarity between the output data at the next moment obtained according to the input signal at the current moment and the actual output. That is to say, the usual system model determines the parameters of the system model based on the accuracy of the output data at the next moment (i.e., the next step), so that the system model pays more attention to the fitting ability. Usually, the signal input by the user (such as the handle signal) is the driver's target signal, and the target result corresponding to this target signal is usually not achieved in one step. That is to say, in order to achieve this target result, the actuator (joint) may need to perform multiple actions (corresponding to multiple moments) to achieve it. If only the action at the next moment is considered at this time, it is likely to cause the system model to only consider the next step prediction result and ignore the prediction results after multiple steps, resulting in poor prediction performance of the output result of the system model, which in turn makes it difficult for the intelligent control of the hydraulic system to meet the needs of the driver. Therefore, the present application obtains the predicted output of multiple subsequent moments by iterating the input signal at the current moment, so as to consider the prediction performance of the system model.

[0032] Step 130: Calculate the loss function of the system model based on the predicted outputs at multiple moments and the corresponding historical execution action data.

[0033] After predicting the predicted outputs at multiple subsequent moments, the loss function of the system model is calculated based on the predicted outputs at these multiple moments and the corresponding historical execution action data (i.e., the actual output), that is, the prediction results of the system model at multiple subsequent moments are considered to improve the prediction ability of the system model.

[0034] Step 140: According to the loss function, the parameters of the system model are identified.

[0035] According to the loss function, the parameters of the system model are identified and updated again, that is, the parameters of the system model are obtained by optimizing and calculating the loss function, that is, the parameters that ensure the simulation and predictability of the system model are obtained.

[0036] Specifically, Figure 2 As shown, the model parameter identification method provided by the present application mainly includes the following steps: collecting data (i.e. collecting historical data of the hydraulic system, including input signals and output signals), determining the form of the mathematical model (i.e. building a system model of the hydraulic system based on the input signals and output signals), designing a loss function (i.e. obtaining a predicted output result based on the mathematical model, and comparing it with the actual output result to obtain the loss), optimizing the loss function using a nonlinear optimization algorithm (i.e. solving the loss function through a nonlinear optimization algorithm), and obtaining a system mathematical model (i.e. solving the model parameters corresponding to the minimum loss function). Through the above steps, a model that can guarantee both fitting effect and prediction effect can be obtained.

[0037] The present application provides a method for identifying model parameters of a hydraulic system. First, a system model of the hydraulic system is constructed according to historical data of the hydraulic system; then, predicted outputs at multiple moments are iteratively obtained according to historical control signals and the system model, and a loss function of the system model is calculated according to the predicted outputs at multiple moments and corresponding historical execution action data; finally, parameters of the system model are identified according to the loss function; that is, an initial system model is first constructed according to historical data, and then predicted output data at multiple subsequent moments are iteratively obtained according to input data at the current moment, and a loss function is constructed according to the predicted output data and real data at the corresponding moments, and the parameters of the system model are obtained by optimizing and solving the loss function, which not only considers the accuracy of the predicted output at the next moment, but also considers the accuracy of the predicted output at the subsequent moments, so as to ensure the authenticity and accuracy of the system model, thereby providing an accurate model basis for intelligent control.

[0038] Figure 3 FIG. 1 is a flow chart of a method for identifying model parameters of a hydraulic system provided by another exemplary embodiment of the present application. Figure 3 As shown, the above step 110 may include:

[0039] Step 111: Construct a Hammerstein model based on the historical data of the hydraulic system.

[0040] The Hammerstein model includes a nonlinear part and a linear part. The nonlinear part includes a piecewise linear function. Since the hydraulic system itself is a nested nonlinear model, the Hammerstein model can have a good fitting effect on the nonlinear system. Specifically, the structure of the Hammerstein model is as follows: Figure 4As shown, the Hammerstein model constructed in the present application includes a nonlinear link f and a linear transfer function B / F; wherein u(k) is an input quantity, and an intermediate quantity w(k)=f(u(k)) is obtained through a nonlinear link (nonlinear part), and then a linear transfer function (linear part) is passed to obtain a final output: y(k)=B / F·w(k), wherein the specific form of the linear transfer function is as follows:

[0041]

[0042] Among them, b0, ..., b m and a1, …, a n are the coefficients of the discrete transfer function, z is the transformation variable in the Z-transform, and the orders m and n of the transfer function can be determined based on practical experience or by related parameters such as the error reduction ratio (ERR).

[0043] In the present application, the nonlinear part may be expressed in the form of a piecewise linear function, wherein the specific form of the nonlinear function f is as follows:

[0044]

[0045] Among them, c i d i For each piecewise linear parameter, q i is the breakpoint position of the segment, i = 1, 2, 3, ... For the hydraulic system, the breakpoint position in the nonlinear link is generally determined by the dead zone characteristics of the hydraulic system itself. In other words, under the premise that there is a certain amount of pilot pressure in the hydraulic system (the pilot pressure is small at this time), the end of the actuator does not move (that is, the corresponding intermediate amount changes are small). Such a nonlinear link form can better describe the dynamic characteristics of the hydraulic system. For example, c1 and d1 can be set to smaller values. When u(k)≤q1, the change in w(k) caused by the change in u(k) is small.

[0046] Specifically, after constructing the Hammerstein model, the nonlinear part and the linear part are combined into a matrix through matrix transformation, and the parameters of the system model are converted into a vector. For the above-constructed system model (Hammerstein model), the parameters that need to be identified (i.e., the parameters of the Hammerstein model) are:

[0047] θ=[c1·b0,d1·b0,c2·b0,d2·b0,...c1·b m ,d1·b m …,a1,a2,…a n ] T ;

[0048] For optimization problems, it is usually necessary to extract the parameters to be identified (i.e., separate the variables of the optimization problem into separate vectors, etc.). Therefore, the present application introduces the Kronecker product to extract the parameters to be identified, wherein the Kronecker product is defined as:

[0049]

[0050] According to the definition of Kronecker product, the prediction output of the above Hammerstein model at time k+1 can be converted into the following form:

[0051]

[0052] in, θ is the parameter to be identified.

[0053] Through the above conversion, the parameters to be identified can be extracted, so that the nonlinear part and the linear part of the Hammerstein model are combined into a matrix, and the parameters of the Hammerstein model are converted into a relatively independent vector, which is convenient for subsequent optimization calculations.

[0054] In one embodiment, the specific implementation of step 120 may be: according to the historical control signal at the current moment, multiple predicted outputs before the current moment and / or historical execution action data, and the system model, the predicted output at the current moment is obtained. Specifically, when the number of prediction steps is less than or equal to the number of predicted outputs that have been obtained (i.e., the number of predicted outputs that have been predicted at the current moment), the predicted output at the current moment is obtained according to the historical control signal at the current moment and multiple (the number corresponding to the number of prediction steps) predicted outputs before the current moment; when the number of prediction steps is greater than the number of predicted outputs that have been obtained, the real output data (i.e., the historical execution action data) is used to supplement the output results equal to the number of prediction steps, and the predicted output at the current moment is obtained according to the historical control signal at the current moment and the output results equal to the number of prediction steps.

[0055] Specific, definition To predict the output l steps later from time k, we can get the following recursive formula:

[0056]

[0057] According to the recursive formula, the calculation method of model prediction is as follows Figure 5 As shown in the figure, [y(k)…y(k-n+1)], For actual data, is the predicted value inherited by each recursion, is the predicted output of the model.

[0058] Figure 6 FIG. 1 is a flow chart of a method for identifying model parameters of a hydraulic system provided by another exemplary embodiment of the present application. Figure 6 As shown, the above step 130 may include:

[0059] Step 131: Obtain the loss function of the system model according to the square of the difference between the predicted output at multiple moments and the corresponding historical execution action data.

[0060] In one embodiment, the specific implementation of step 131 is: weighted sum of the squares of the differences between the predicted outputs at multiple moments and the corresponding historical execution action data to obtain the loss function of the system model. After the predicted outputs at multiple subsequent moments are predicted, the loss function is constructed based on the weighted sum of the squares of the differences between the predicted outputs at multiple moments and the corresponding historical execution action data (i.e., the actual value), so that the subsequent multi-step predicted outputs of the model are as similar as possible to the actual values, so as to ensure the prediction accuracy of the model. Among them, the specific expression of the loss function is:

[0061]

[0062] Among them, N1 is the number of prediction steps, N is the total amount of data, α j is the recursive factor (i.e. weight).

[0063] Since the size of the weight reflects the importance of the predicted value of the corresponding step or moment, or in other words, the size of the weight determines the accuracy of the predicted value at the corresponding moment, in order to fit the dynamic characteristics of the hydraulic system as much as possible, the present application sets the weights corresponding to multiple moments, and according to the weights, weighted sums the squares of the differences between the predicted outputs at multiple moments and the corresponding historical execution action data to obtain the loss function of the system model, so that the parameters can be identified in a targeted manner; wherein, the weight at the current moment is greater than the weight at the next moment. In order to achieve ease of control, the model structure used is as relatively simple as possible, which makes the model's fitting ability and prediction ability limited. In order to solve this problem, the present application sets different requirements for the prediction ability of the model with different step numbers (that is, different weights for ). At the same time, for model predictive control, the accuracy of the predicted value with a shorter prediction step is more important, so the recursive factor is set to decrease with the increase of the step number. Specifically, the calculation formula of the recursive factor is as follows:

[0064]

[0065] The value of the recursive factor is always positive and becomes smaller as the number of steps increases. That is, the shorter the prediction step, the more important the accuracy of the prediction value is. This ensures the compatibility with model predictive control under the condition of limited prediction ability of the model.

[0066] Figure 7 FIG. 1 is a flow chart of a method for identifying model parameters of a hydraulic system provided by another exemplary embodiment of the present application. Figure 7 As shown, the above step 140 may include:

[0067] Step 141: According to the loss function, calculate the parameters of the system model so that the value of the loss function is less than a preset value.

[0068] After setting the loss function, the mainstream nonlinear optimization algorithm can be used to identify the parameters of the model. For example, the sequential quadratic programming algorithm can be used to optimize and solve the model, that is, according to the collected real data and the loss function defined above, the model parameters corresponding to the minimum loss function value are calculated. Among them, the minimum loss function value can be set to a preset value. When the value of the loss function is less than the preset value, it is determined that the loss function has reached the minimum value. At this time, the corresponding parameter value is the optimal parameter of the model. By updating the model with this optimal parameter, a system model of the hydraulic system that takes into account both simulation performance and prediction performance can be obtained.

[0069] Figure 8 FIG. 1 is a schematic diagram of a model parameter identification device for a hydraulic system provided by an exemplary embodiment of the present application. Figure 8 As shown, the model parameter identification device 80 includes: a model construction module 81, which is used to construct a system model of the hydraulic system based on the historical data of the hydraulic system; wherein the system model represents the corresponding relationship between the control signal of the hydraulic system and the execution action data of the hydraulic system, and the historical data includes the historical control signal and the corresponding historical execution action data; a prediction output module 82, which is used to iteratively obtain the prediction output at multiple moments according to the historical control signal and the system model; a loss calculation module 83, which is used to calculate the loss function of the system model according to the prediction output at multiple moments and the corresponding historical execution action data; and a parameter identification module 84, which is used to identify the parameters of the system model according to the loss function.

[0070] The present application provides a model parameter identification device for a hydraulic system. First, a model construction module 81 constructs a system model of the hydraulic system according to historical data of the hydraulic system; then, a prediction output module 82 iterates to obtain prediction outputs at multiple moments according to historical control signals and the system model, and a loss calculation module 83 calculates a loss function of the system model according to the prediction outputs at multiple moments and corresponding historical execution action data; finally, a parameter identification module 84 identifies the parameters of the system model according to the loss function; that is, first, an initial system model is constructed according to historical data, and then, prediction output data at multiple subsequent moments are iterated according to input data at the current moment, and a loss function is constructed according to the prediction output data and the actual data at the corresponding moment, and the parameters of the system model are obtained by optimizing and solving the loss function, which not only considers the accuracy of the prediction output at the next moment, but also considers the accuracy of the prediction output at the subsequent moments, so as to ensure the authenticity and accuracy of the system model, thereby providing an accurate model basis for intelligent control.

[0071] In one embodiment, the model building module 81 can be further configured to: build a Hammerstein model based on historical data of the hydraulic system, wherein the Hammerstein model includes a nonlinear part and a linear part, and the nonlinear part includes a piecewise linear function.

[0072] In one embodiment, the model building module 81 may be further configured to: merge the nonlinear part and the linear part into one matrix through matrix transformation, and convert the parameters of the system model into a vector.

[0073] In one embodiment, the prediction output module 82 may be further configured to obtain the prediction output at the current moment according to the historical control signal at the current moment, multiple prediction outputs before the current moment and / or historical execution action data, and the system model.

[0074] In one embodiment, the loss calculation module 83 may be further configured to obtain a loss function of the system model according to the square of the difference between the predicted output at multiple moments and the corresponding historical execution action data.

[0075] In one embodiment, the loss calculation module 83 may be further configured to perform a weighted sum of the squares of the differences between the predicted outputs at multiple moments and the corresponding historical execution action data to obtain a loss function of the system model.

[0076] In one embodiment, the parameter identification module 84 may be further configured to: calculate the parameters of the system model according to the loss function so that the value of the loss function is less than a preset value.

[0077] The present application also provides a hydraulic engineering machinery, comprising: an actuator and a model parameter identification device of the hydraulic system as described above; wherein the actuator is driven by hydraulic pressure to perform actions, and the model parameter identification device of the hydraulic system is connected to the actuator.

[0078] A hydraulic engineering machinery provided by the present application first constructs a system model of the hydraulic system according to the historical data of the hydraulic system; then, according to the historical control signal and the system model, iteratively obtains the predicted output at multiple moments, and according to the predicted output at multiple moments and the corresponding historical execution action data, calculates the loss function of the system model; finally, according to the loss function, identifies the parameters of the system model; that is, first constructs an initial system model according to the historical data, then iteratively obtains the predicted output data at multiple subsequent moments according to the input data at the current moment, and constructs the loss function according to the predicted output data and the real data at the corresponding moment, and obtains the parameters of the system model by optimizing and solving the loss function, not only considering the accuracy of the predicted output at the next moment, but also considering the accuracy of the predicted output at the subsequent moments, so as to ensure the authenticity and accuracy of the system model, thereby providing an accurate model basis for intelligent control.

[0079] Below, reference Fig. 9 The electronic device according to the embodiment of the present application is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signal from them.

[0080] Fig. 9 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0081] like Fig. 9 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0082] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0083] The memory 12 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the model parameter identification method of the hydraulic system of each embodiment of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0084] In one example, the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0085] When the electronic device is a stand-alone device, the input device 13 may be a communication network connector, which is used to receive the collected input signals from the first device and the second device.

[0086] In addition, the input device 13 may also include, for example, a keyboard, a mouse, and the like.

[0087] The output device 14 can output various information to the outside, including the determined distance information, direction information, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0088] Of course, to simplify, Fig. 9 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0089] 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.

[0090] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0091] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for identifying model parameters of a hydraulic system, characterized in that: include: Constructing a system model of the hydraulic system according to the historical data of the hydraulic system; wherein the system model represents the corresponding relationship between the control signal of the hydraulic system and the execution action data of the hydraulic system, and the historical data includes the historical control signal and the corresponding historical execution action data; According to the input data at the current moment, iteratively obtain the predicted output data for multiple moments after the current moment; Calculating a loss function of the system model according to the predicted outputs at multiple moments and the corresponding historical execution action data; and According to the loss function, identifying the parameters of the system model; Wherein, the loss function is: In the formula, N is the total amount of data, N1 is the number of prediction steps, α j is the weight value corresponding to the predicted output at time k+j, is the predicted output at time k+j obtained by iterating the input signal at time k.

2. The method for model parameter identification of a hydraulic system according to claim 1, characterized in that: The step of identifying the parameters of the system model according to the loss function includes: According to the loss function, the parameters of the system model are calculated so that the value of the loss function is less than a preset value.

3. The model parameter identification method of the hydraulic system according to claim 1, characterized in that: The constructing the system model of the hydraulic system according to the historical data of the hydraulic system comprises: A Hammerstein model is constructed according to the historical data of the hydraulic system; wherein the Hammerstein model includes a nonlinear part and a linear part, and the nonlinear part includes a piecewise linear function.

4. The method for model parameter identification of a hydraulic system according to claim 3, characterized in that: The constructing of the Hammerstein model according to the historical data of the hydraulic system comprises: Through matrix transformation, the nonlinear part and the linear part are combined into one matrix, and the parameters of the system model are converted into a vector.

5. A model parameter identification device for a hydraulic system, characterized in that: include: A model building module, used to build a system model of the hydraulic system according to the historical data of the hydraulic system; wherein the system model represents the corresponding relationship between the control signal of the hydraulic system and the execution action data of the hydraulic system, and the historical data includes the historical control signal and the corresponding historical execution action data; The prediction output module is used to iteratively obtain the prediction output data of multiple moments after the current moment according to the input data of the current moment; a loss calculation module, configured to calculate a loss function of the system model based on the predicted outputs at multiple moments and the corresponding historical execution action data; and A parameter identification module, used to identify the parameters of the system model according to the loss function; Wherein, the loss function is: In the formula, N is the total amount of data, N1 is the number of prediction steps, α j is the weight value corresponding to the predicted output at time k+j, is the predicted output at time k+j obtained by iterating the input signal at time k.

6. A hydraulic engineering machine, characterized in that: include: An actuator, wherein the actuator is driven by hydraulic pressure to perform an action; as well as The model parameter identification device for a hydraulic system as claimed in claim 5, wherein the model parameter identification device for a hydraulic system is connected to the actuator.

Images