Control method and device of excavator hydraulic system, electronic equipment and medium

Abstract

The invention provides a control method and device for an excavator hydraulic system, electronic equipment and a medium, and the method comprises the steps: training a neural network model based on parameter information in the operation process of a target excavator, and obtaining a trained target excavator hydraulic system model; the target excavator hydraulic system model is used for fitting a target hydraulic system parameter relation from an input control signal of a target excavator hydraulic system to the excavator joint speed; the real-time joint expected speed of the target excavator is obtained; based on the target excavator hydraulic system model, converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system; and on the basis of the real-time input control signal, the hydraulic system of the target excavator is controlled to operate, so that the excavator hydraulic system parameter relation meeting the precision requirement can be automatically fitted, the fitting precision is high, the parameter identification work is little, and the control precision is high.

Description

Technical Field

[0001] The present application relates to the technical field of excavators, and in particular to a control method, device, electronic equipment and medium for an excavator hydraulic system. Background Art

[0002] The hydraulic system of the excavator itself cannot accept the speed command issued by the computer to achieve the corresponding action. Therefore, in order to realize the automation of the excavator and control the excavator to reach the specified speed, it is necessary to first obtain the corresponding parameter relationship between the control signal and the excavator joint speed, and then convert the target speed command into a control signal acceptable to the excavator hydraulic system according to the parameter relationship and input it into the hydraulic system of the excavator. Finally, the hydraulic system performs the corresponding action according to the input control signal to drive the excavator to reach the specified speed. However, due to the control difficulties such as strong nonlinearity, complex influencing factors, and time-varying parameters of the hydraulic system, the manually designed mathematical model is insufficient in the accuracy of fitting the parameters of the excavator hydraulic system. Secondly, in order to fit the hydraulic system parameters of the excavator well, a lot of manual parameter identification work needs to be done on the excavator, and the tedious parameter identification work needs to be repeated for different excavators, which makes it difficult to mass produce and cannot be delivered in batches. Summary of the invention

[0003] In view of this, the purpose of the present application is to provide a control method, device, electronic equipment and medium for an excavator hydraulic system, which can automatically fit the excavator hydraulic system parameter relationship that meets the accuracy requirements, has high fitting accuracy, requires less parameter identification work, and can achieve mass delivery.

[0004] In a first aspect, an embodiment of the present application provides a control method for an excavator hydraulic system, the method comprising:

[0005] A neural network model is trained based on parameter information during the operation of the target excavator to obtain a trained target excavator hydraulic system model; the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed;

[0006] Obtain the real-time joint expected speed of the target excavator;

[0007] Based on the target excavator hydraulic system model, converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system;

[0008] Based on the real-time input control signal, the operation of the hydraulic system of the target excavator is controlled.

[0009] In a second aspect, in some embodiments, a control device for an excavator hydraulic system is further provided, the device comprising:

[0010] A training module is used to train a neural network model based on parameter information during the operation of a target excavator to obtain a trained target excavator hydraulic system model; the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed;

[0011] An acquisition module, used for acquiring the real-time joint expected speed of the target excavator;

[0012] A conversion module, for converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system based on the target excavator hydraulic system model;

[0013] A control module is used to control the operation of the hydraulic system of the target excavator based on the real-time input control signal.

[0014] In the third aspect, in some embodiments, an electronic device is also provided, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory through the bus, and when the machine-readable instructions are executed by the processor, the steps of the control method of the excavator hydraulic system are executed.

[0015] In a fourth aspect, in some embodiments, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the control method of the excavator hydraulic system are executed.

[0016] In an embodiment of the present application, a control method, device, electronic device and medium for an excavator hydraulic system are provided. The method uses a neural network model for parameter fitting to better solve the difficulties of the hydraulic system such as strong nonlinearity, complex influencing factors, and time-varying parameters, thereby improving the estimation accuracy of the parameter relationship of the excavator hydraulic system; uses parameter information during the operation of the target excavator to fit the hydraulic system parameter relationship of the target excavator, and the fitting result is highly matched with the single target excavator, thereby further improving the estimation accuracy of the hydraulic system parameter relationship of the excavator; and automatically fits the neural network model to replace the process of manually designing mathematical equations for a new excavator to establish an excavator hydraulic system model and calibrate parameters each time. Only a period of excavator operation data needs to be collected, and the method can automatically fit the hydraulic system parameter relationship of the excavator for deployment, thereby enabling mass production, without the need to design new parameter equations for a new excavator each time and perform a large amount of manual parameter calibration work, thereby improving the deployment efficiency of the excavator's automated control system and reducing the labor cost required for the deployment process. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flow chart showing a control method of an excavator hydraulic system according to an embodiment of the present application;

[0019] Figure 2 A schematic diagram of the structure of the neural network model described in the embodiment of the present application is shown;

[0020] Figure 3 A schematic diagram showing the principle of the neural network model described in the embodiment of the present application is shown;

[0021] Figure 4 A flow chart of a method for training a neural network model based on parameter information during the operation of a target excavator according to an embodiment of the present application is shown;

[0022] Figure 5 A flow chart of a method for converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system according to an embodiment of the present application is shown;

[0023] Figure 6 A schematic diagram showing the structure of a control device for an excavator hydraulic system according to an embodiment of the present application is shown;

[0024] Figure 7 A schematic structural diagram of an electronic device described in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0026] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0027] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0028] The hydraulic system of the excavator itself cannot accept the speed command issued by the computer to achieve the corresponding action. Therefore, in order to realize the automation of the excavator and control the excavator to reach the specified speed, it is necessary to first obtain the corresponding parameter relationship between the control signal and the excavator joint speed, and then convert the target speed command into a control signal acceptable to the excavator hydraulic system according to the parameter relationship and input it into the hydraulic system of the excavator, generally a PWM signal. Finally, the hydraulic system performs the corresponding action according to the input control signal to drive the excavator to reach the specified speed. However, due to the control difficulties of the hydraulic system such as strong nonlinearity, complex influencing factors, and time-varying parameters, if the accuracy of the fitted parameter relationship is not enough, it will directly lead to the problem of insufficient control accuracy of the excavator. Therefore, it is necessary to quickly and accurately fit the hydraulic system parameter relationship of different excavators to improve the automatic control accuracy of the intelligent excavator.

[0029] Most existing methods are to build the hydraulic system model of the excavator by manually designing mathematical equations, but such methods are difficult to solve the difficulties of the hydraulic system such as strong nonlinearity, complex influencing factors, and time-varying parameters. First, the manually designed mathematical model is not accurate enough to fit the parameters of the excavator hydraulic system. Secondly, in order to fit the hydraulic system parameters of the excavator well, a lot of manual parameter identification work needs to be done on the excavator, and the tedious parameter identification work needs to be repeated for different excavators, which makes it difficult to mass produce and deliver in batches.

[0030] Based on this, in an embodiment of the present application, a control method, device, electronic device and medium for an excavator hydraulic system are provided, the method comprising: training a neural network model based on parameter information during the operation of a target excavator to obtain a trained target excavator hydraulic system model; the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed; obtaining the real-time joint expected speed of the target excavator; based on the target excavator hydraulic system model, converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system; based on the real-time input control signal, controlling the operation of the hydraulic system of the target excavator; in this way, through the designed neural network and the collected real excavator operation data of the target excavator, the excavator hydraulic system parameter relationship that meets the accuracy requirements of a specific target excavator is automatically fitted, so as to utilize the neural network model to achieve the desired effect. First, parameter fitting based on the model can better solve the difficulties of strong nonlinearity, complex influencing factors, and time-varying parameters of the hydraulic system, thereby improving the estimation accuracy of the parameter relationship of the excavator hydraulic system; second, the parameter information of the target excavator during operation is used to fit the hydraulic system parameter relationship of the target excavator. The fitting result is highly matched with the single target excavator, further improving the estimation accuracy of the hydraulic system parameter relationship of the excavator; third, automatic fitting through the neural network model can replace the process of manually designing mathematical equations for a new excavator to establish the excavator hydraulic system model and parameter calibration each time. It only needs to collect the excavator operation data for a period of time. Through this method, the hydraulic system parameter relationship of the excavator can be automatically fitted for deployment, so that mass production can be carried out, without the need to design new parameter equations for a new excavator each time and perform a large amount of manual parameter calibration work, thereby improving the deployment efficiency of the excavator's automated control system and reducing the manpower cost required for the deployment process.

[0031] Please refer to Figure 1 , Figure 1 A flow chart of a control method for an excavator hydraulic system according to an embodiment of the present application is shown; specifically, the control method for an excavator hydraulic system comprises the following steps S101-S104:

[0032] S101, training a neural network model based on parameter information during the operation of a target excavator to obtain a trained target excavator hydraulic system model; the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed;

[0033] S102, obtaining the real-time expected joint speed of the target excavator;

[0034] S103, based on the target excavator hydraulic system model, converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system;

[0035] S104: Control the operation of the hydraulic system of the target excavator based on the real-time input control signal.

[0036] In step S101, a neural network model is trained based on parameter information during the operation of the target excavator to obtain a trained target excavator hydraulic system model; the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed.

[0037] The target excavator is an excavator for which hydraulic system parameter relationship calibration is to be performed, and may be a new excavator, or an excavator that needs to be recalibrated after running for a period of time.

[0038] The parameter information during the operation of the target excavator represents the state of the target excavator during the operation, and also represents the corresponding relationship between the input control signal of the hydraulic system of the target excavator and the excavator joint speed during the operation of the target excavator.

[0039] Based on this, the parameter information of the target excavator during operation can be used to train the neural network model, so that the neural network learns the corresponding relationship between the input control signal of the target excavator hydraulic system and the excavator joint speed. After the training is completed, the target excavator hydraulic system model is obtained to fit the target hydraulic system parameter relationship between the input control signal of the target excavator hydraulic system and the excavator joint speed.

[0040] In the embodiment of the present application, before training the neural network, a neural network framework is designed and a neural network model is built.

[0041] In some embodiments, a multi-layer fully connected neural network is used in one embodiment, such as Figure 2 The number of network layers and dimensions of the multi-layer fully connected neural network are designed according to the number and dimensions of parameters of parameter information during the operation of the target excavator.

[0042] Specifically, the parameter information of the target excavator during operation includes: an input control signal of the hydraulic system of the excavator, state parameters of the excavator, joint speeds of the excavator at the previous moment, and joint speeds of the excavator at the next moment.

[0043] Please refer to Figure 3 , Figure 3A schematic diagram of the principle of the neural network model described in an embodiment of the present application is shown; the neural network model can predict the joint speed Vt+1 of the excavator at the next moment by inputting the control signal PWM and the excavator state S and joint speed Vt at the current moment t.

[0044] That is to say, during the training process, the input of the neural network model is the input control signal of the excavator hydraulic system, the excavator state parameters, and the joint speed of the excavator at the previous moment, and the output is the joint speed of the excavator at the next moment.

[0045] Based on this, the target excavator hydraulic system model describes the input control signal PWM of the excavator hydraulic system, the excavator state S, the joint speed Vt of the excavator at the previous moment, and the joint speed Vt of the excavator at the next moment. t+1 The functional relationship between the three t+1 =F(PWM,S,V t ).

[0046] In some embodiments, the excavator state parameter is determined based on the following method:

[0047] Analyze the influence of the operating state of the excavator and environmental factors on the relationship between the parameters of the hydraulic system respectively, and determine the operating parameters and environmental parameters of the excavator that affect the relationship between the parameters of the hydraulic system;

[0048] The excavator state parameter is determined based on the excavator operating parameter and the environmental parameter.

[0049] The operating status of an excavator directly reflects the coordinated working of its internal mechanical, hydraulic and electrical systems, and changes in these states will significantly affect the parameter relationships of the hydraulic system.

[0050] Environmental factors, as external conditions, also have an important impact on the hydraulic system parameters of the excavator. For example, a high temperature environment will increase the temperature of the hydraulic oil, reduce its viscosity, and increase leakage and wear; a low temperature environment may cause the hydraulic oil viscosity to be too high and the fluidity to be poor, affecting the startup and response speed of the system.

[0051] It should be noted that environmental factors can cause changes in operating parameters. For example, the temperature of the hydraulic oil is affected by the ambient temperature. In other words, the operating parameters can characterize the impact of environmental factors to a certain extent.

[0052] Based on this, the control method of the excavator hydraulic system described in the embodiment of the present application analyzes the influence of the excavator operating parameters and environmental parameters on the relationship between the excavator hydraulic system parameters, so as to better solve the difficulties of the hydraulic system such as strong nonlinearity, complex influencing factors, and time-varying parameters.

[0053] Specifically, in the embodiment of the present application, the excavator state parameters include: excavator operation parameters and environmental parameters;

[0054] The excavator operating parameters include solenoid valve pilot pressure P1, hydraulic cylinder output pressure P2, engine cooling water temperature W1, hydraulic oil temperature W2, and joint position J;

[0055] The environmental parameters include the ambient temperature W3.

[0056] Different excavator state parameters characterize different states of the excavator during operation. Therefore, the target excavator hydraulic system model is trained based on the parameter information of the target excavator in different states during operation, and is used to fit the target hydraulic system parameter relationship of the target excavator in different states. In this way, using the neural network model for parameter fitting can better solve the difficulties of the hydraulic system such as strong nonlinearity, complex influencing factors, and time-varying parameters.

[0057] For the target excavator, run the target excavation bureau and collect parameter information such as the input control signal PWM, solenoid valve pilot pressure P1, hydraulic cylinder output pressure P2, engine cooling water temperature W1, hydraulic oil temperature W2, ambient temperature W3, joint position J and joint speed V of the target excavator bureau.

[0058] In the embodiment of the present application, parameter information within a preset operating time of the target excavator is collected. Exemplarily, the preset operating time is 8 hours.

[0059] It should be noted that even for excavators of the same model, the excavator manufacturer cannot guarantee that the performance of their hydraulic systems is completely consistent. Therefore, in the embodiment of the present application, regardless of whether the model is the same, a new excavator needs to use the method to collect operating data (new operating data must be collected for each new excavator) and train the neural network model to obtain a matching target excavator hydraulic system model.

[0060] Please refer to Figure 4 , Figure 4 The flowchart of the method for training a neural network model based on parameter information during the operation of a target excavator according to an embodiment of the present application is shown; specifically, the training of the neural network model based on parameter information during the operation of the target excavator to obtain a trained target excavator hydraulic system model includes the following steps S401-S402:

[0061] S401, taking the input control signal, the excavator state parameter, and the joint speed of the excavator at the previous moment as the input of the neural network model, and the joint speed of the excavator at the next moment as the output of the neural network model, and training the neural network model so that the neural network model learns the target hydraulic system parameter relationship between the input control signal of the target excavator in different states and the joint speed of the excavator at the next moment; wherein the excavator state parameter and the joint speed of the excavator at the previous moment represent the state of the target excavator;

[0062] S402: When the neural network model meets the training completion condition, a trained target excavator hydraulic system model is obtained.

[0063] The training completion conditions include: reaching a preset training time, the prediction accuracy output by the neural network model meets the preset accuracy requirements, etc.

[0064] In some embodiments, in the control method of the excavator hydraulic system, when the neural network model meets the training completion condition, a trained target excavator hydraulic system model is obtained, including:

[0065] Running the target excavator and recollecting verification parameter information;

[0066] Verifying the neural network model based on the verification parameter information to determine whether the prediction accuracy output by the neural network model meets the preset accuracy requirements;

[0067] If so, it is determined that the neural network model meets the training completion condition, and a trained target excavator hydraulic system model is obtained.

[0068] Meanwhile, if not, the parameter information of the target excavator during operation is collected again, and the neural network model is continuously trained until a model that meets the requirements is obtained.

[0069] That is to say, in the embodiment of the present application, when judging whether the model meets the requirements, it is necessary to run the excavator to recollect a set of data to verify the trained model. If its prediction accuracy is lower than the set threshold, it meets the requirements and can be added to the hydraulic control system of the excavator for use. If it does not meet the requirements, repeat the data collection and training steps to retrain the model that meets the requirements.

[0070] The trained target excavator hydraulic system model described in the embodiment of the present application is mainly used to predict the size of the input control signal PWM required to achieve a specified joint speed V under different operating conditions of the excavator, thereby improving the response speed and control accuracy of the excavator's automatic control system.

[0071] After obtaining the trained target excavator hydraulic system model, the target excavator hydraulic system model is deployed to the controller of the hydraulic system.

[0072] In some embodiments, the number of the trained target excavator hydraulic system models is the same as the number of joints of the target excavator, and different target excavator hydraulic system models determine the target hydraulic system parameter relationships of different joints of the target excavator.

[0073] The excavator is a complex mechanical system, and each joint has its own motion characteristics and hydraulic characteristics. Therefore, subdividing the hydraulic system model by joints can more effectively solve the difficulties of the excavator hydraulic system, such as strong nonlinearity, complex influencing factors, and time-varying parameters. It can more accurately capture and simulate the hydraulic system parameter relationship of a specific joint, thereby improving the fitting accuracy of the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed.

[0074] In some embodiments, the method for controlling the hydraulic system of an excavator further comprises:

[0075] When the target excavator hydraulic system model of the target excavator meets a preset update condition, parameter information during the operation of the target excavator is re-collected to update the target excavator hydraulic system model based on the re-collected parameter information.

[0076] During the operation of the excavator, it will be affected by many factors, such as ambient temperature, humidity, oil contamination, mechanical wear, etc. These factors may cause changes in the hydraulic system parameters, which in turn affect the prediction accuracy of the model. Therefore, it is necessary to update the model regularly or according to specific conditions to maintain its prediction accuracy and performance, so as to more accurately control the hydraulic system and improve the overall operation efficiency and stability of the excavator.

[0077] Specifically, the preset update condition includes at least one of the following:

[0078] The prediction accuracy of the target excavator hydraulic system model does not meet the preset accuracy requirements;

[0079] The error of the execution result of the target excavator is greater than the preset error requirement;

[0080] The operating time of the target excavator reaches a preset operating time.

[0081] The prediction accuracy of the target excavator hydraulic system model does not meet the preset accuracy requirements. Specifically, after the target excavator hydraulic system model is calibrated in the target excavator, a set of data can be re-collected at regular intervals to verify the deployed target excavator hydraulic system model. If its prediction accuracy is lower than the set threshold, it meets the requirements, which means that the target excavator hydraulic system model needs to be updated.

[0082] The error of the execution result of the target excavator is greater than the preset error requirement; specifically, it can be the error between the output joint speed of the target excavator and the expected joint speed; the error of the execution result directly reflects the effect of the hydraulic system model of the target excavator in practical application. If the error is too large, it means that the target hydraulic system parameter relationship calibrated by the model is inaccurate. By updating the model, the error can be reduced and the control accuracy and efficiency can be improved.

[0083] The operating time of the target excavator is greater than the preset operating time, that is, it is updated regularly.

[0084] It should be noted that the traditional method of manually designing mathematical equations to establish the hydraulic system model of the excavator is difficult to recalibrate even if the excavator is affected by various factors during operation, resulting in changes in the hydraulic system parameters. The control method of the excavator hydraulic system described in the embodiment of the present application can automatically calibrate and update the target excavator hydraulic system model when the preset update conditions are met, thereby improving the fitting accuracy of the excavator hydraulic system parameter relationship.

[0085] In step S102, the real-time joint expected speed of the target excavator is obtained.

[0086] Real-time joint expected speed refers to the target speed that each joint (such as boom, arm, bucket, etc.) should reach in order to ensure working efficiency, stability and safety in the current working state of the excavator. These speed values ​​are calculated based on a variety of factors such as the excavator's operating requirements, working environment, and mechanical performance.

[0087] The real-time joint expected speed is the real-time joint expected speed of each joint in the target excavator.

[0088] After obtaining the expected real-time joint speed, the actual movement speed of each joint is controlled by adjusting the real-time input control signal of the hydraulic system (usually a PWM signal), so that the excavator can operate according to the expected trajectory and speed.

[0089] Therefore, it is necessary to convert the real-time joint expected speed into a real-time input control signal of the target excavator hydraulic system.

[0090] In the step S103, based on the target excavator hydraulic system model, the real-time joint expected speed is converted into a real-time input control signal for determining the target excavator hydraulic system.

[0091] Specifically, since the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship of the target excavator in different states, please refer to Figure 5 , Figure 5A flow chart of a method for converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system according to an embodiment of the present application is shown; Figure 5 As shown, based on the target excavator hydraulic system model, converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system includes the following steps S501-S503:

[0092] S501, obtaining excavator state parameters and real-time joint speed of the target excavator in real-time state;

[0093] S502, the target excavator hydraulic system model processes the excavator state parameters and real-time joint speeds in the real-time state, and fits the target hydraulic system parameter relationship of the target excavator in the real-time state;

[0094] S503: based on the fitted target hydraulic system parameter relationship of the target excavator in the real-time state, convert the real-time joint expected speed into a real-time input control signal matching the real-time state of the target excavator.

[0095] The real-time excavator state parameters include real-time excavator operating parameters and environmental parameters;

[0096] The excavator operating parameters in the real-time state include solenoid valve pilot pressure, hydraulic cylinder output pressure, engine cooling water temperature, hydraulic oil temperature, and joint position;

[0097] The environmental parameters in the real-time state include the environmental temperature.

[0098] Because the hydraulic system has strong nonlinearity, complex influencing factors, and time-varying parameters, the embodiment of the present application describes a target hydraulic system parameter relationship that is fitted under the real-time state of the target excavator, and the real-time state takes into account multiple influencing factors such as the solenoid valve pilot pressure, hydraulic cylinder output pressure, engine cooling water temperature, hydraulic oil temperature, joint position, environment, etc. The fitted target hydraulic system parameter relationship can characterize the influence of the influencing factors on the target hydraulic system parameter relationship. In addition to the real-time joint speed, the fitted target hydraulic system parameter relationship is also real-time, reducing the influence of the time-varying characteristics of the parameters on the target hydraulic system parameters, thereby improving the accuracy of converting the real-time expected joint speed into a real-time input control signal for determining the target excavator hydraulic system.

[0099] The target excavator hydraulic system model processes the excavator state parameters and real-time joint speeds in the real-time state, and fits the target hydraulic system parameter relationship of the target excavator in the real-time state, including:

[0100] inputting a reference input control signal of a target excavator hydraulic system, an excavator state parameter in the real-time state, and a real-time joint speed into a target excavator hydraulic system model;

[0101] The target excavator hydraulic system model processes the reference input control signal, the excavator state parameters in real time and the real-time joint speed, and outputs the reference joint speed corresponding to the reference input control signal; the relationship between the reference input control signal and the reference joint speed represents the relationship between the target hydraulic system parameters of the target excavator in real time.

[0102] The reference input control signal may be a preset input control signal.

[0103] That is, the target excavator hydraulic system model describes the input control signal PWM of the excavator hydraulic system, the excavator state S, the joint speed Vt of the excavator at the previous moment, and the joint speed Vt of the excavator at the next moment. t+1 The functional relationship between the three t+1 =F(PWM,S,V t ), based on the target excavator hydraulic system model, the reference input control signal, the excavator state parameters in real time and the real-time joint speed are processed, and the functional relationship is determined as the joint speed V of the excavator at the next moment t+1 The relationship between the input control signal PWM.

[0104] In this way, based on the fitted target hydraulic system parameter relationship under the real-time state of the target excavator, the real-time joint expected speed is converted into a real-time input control signal matching the real-time state of the target excavator, including:

[0105] Based on the relationship among the reference input control signal, the reference joint speed and the real-time joint expected speed, a real-time input control signal matching the real-time state of the target excavator is determined.

[0106] That is, substitute the real-time joint expected velocity into the functional relationship V t+1 =F(PWM,S,V t ), the real-time joint expected speed can be converted into a real-time input control signal that matches the real-time state of the target excavator.

[0107] As an example only, when the input control signal PWM, the excavator state S, the joint speed Vt of the excavator at the previous moment and the joint speed Vt of the excavator at the next moment are t+1 The functional relationship between the three t+1 =F(PWM,S,V t), after the excavator state S and the joint speed Vt of the excavator at the previous moment are determined, the ratio between the reference input control signal and the real-time input control signal is equal to the ratio between the reference joint speed and the real-time joint expected speed.

[0108] For example, the reference input control signal is A1, the reference joint speed is A2, and the real-time joint expected speed is 2A2. Based on the relationship between the reference input control signal, the reference joint speed and the real-time joint expected speed, the real-time input control signal that matches the real-time state of the target excavator is determined to be 2A1.

[0109] Thus, in the control method of the hydraulic system of an excavator described in the embodiment of the present application, the joint speed V of the excavator at the next moment can be established through the target excavator hydraulic system model. t+1 The hidden relationship between the input control signal PWM of the excavator hydraulic system, the current excavator state S and the joint speed Vt of the excavator at the previous moment can be used to predict the joint speed Vt of the excavator at the next moment under different states by using the target excavator hydraulic system model. t+1 The changes in the joint speed can better adjust the input control signal PWM of the excavator hydraulic system, so that the excavator can reach the specified joint speed V more quickly, thereby improving the control accuracy of the excavator's automatic control algorithm.

[0110] In the step S104, the operation of the hydraulic system of the target excavator is controlled based on the real-time input control signal.

[0111] Based on the processed control signal, the flow direction, pressure and flow rate of the oil in the hydraulic system are adjusted through hydraulic control elements such as solenoid valves and proportional valves. The precise movement of each joint of the excavator is controlled by precise control of the hydraulic elements, so that the joints of the target excavator reach the expected real-time joint speed.

[0112] Based on the same inventive concept, the embodiment of the present application also provides a control device for the excavator hydraulic system corresponding to the control method of the excavator hydraulic system. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the control method of the excavator hydraulic system in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0113] Please refer to Figure 6 , Figure 6 The schematic diagram of the structure of the control device of the hydraulic system of the excavator according to the embodiment of the present application is shown; the control device of the hydraulic system of the excavator comprises:

[0114] The training module 601 is used to train the neural network model based on the parameter information of the target excavator during operation to obtain a trained target excavator hydraulic system model; the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed;

[0115] An acquisition module 602 is used to acquire the real-time joint expected speed of the target excavator;

[0116] A conversion module 603, for converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system based on the target excavator hydraulic system model;

[0117] The control module 604 is used to control the operation of the hydraulic system of the target excavator based on the real-time input control signal.

[0118] In some embodiments, in the control device of the excavator hydraulic system, the conversion module, when converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system based on the target excavator hydraulic system model, is specifically used to:

[0119] Obtain the excavator state parameters and real-time joint speed of the target excavator in real-time state;

[0120] The target excavator hydraulic system model processes the excavator state parameters and real-time joint speeds in the real-time state, and fits the target hydraulic system parameter relationship of the target excavator in the real-time state;

[0121] Based on the fitted target hydraulic system parameter relationship of the target excavator in the real-time state, the real-time joint expected speed is converted into a real-time input control signal matching the real-time state of the target excavator.

[0122] In some embodiments, in the control device of the excavator hydraulic system, the conversion module, when the target excavator hydraulic system model processes the excavator state parameters and real-time joint speeds in the real-time state and fits the target hydraulic system parameter relationship in the real-time state of the target excavator, is specifically used to:

[0123] inputting a reference input control signal of a target excavator hydraulic system, an excavator state parameter in the real-time state, and a real-time joint speed into a target excavator hydraulic system model;

[0124] The target excavator hydraulic system model processes the reference input control signal, the excavator state parameters in real time and the real-time joint speed, and outputs the reference joint speed corresponding to the reference input control signal; the relationship between the reference input control signal and the reference joint speed represents the relationship between the target hydraulic system parameters of the target excavator in real time.

[0125] In some embodiments, in the control device of the excavator hydraulic system, the conversion module, based on the fitted target hydraulic system parameter relationship under the real-time state of the target excavator, converts the real-time joint expected speed into a real-time input control signal matching the real-time state of the target excavator, is specifically used to:

[0126] Based on the relationship among the reference input control signal, the reference joint speed and the real-time joint expected speed, a real-time input control signal matching the real-time state of the target excavator is determined.

[0127] In some embodiments, in the control device of the hydraulic system of the excavator, the excavator state parameters include: excavator operating parameters and environmental parameters;

[0128] The excavator operating parameters include solenoid valve pilot pressure, hydraulic cylinder output pressure, engine cooling water temperature, hydraulic oil temperature, and joint position;

[0129] The environmental parameters include ambient temperature.

[0130] In some embodiments, in the control device of the excavator hydraulic system, the target excavator hydraulic system model is trained based on parameter information of the target excavator in different states during operation, and is used to fit the target hydraulic system parameter relationship of the target excavator in different states.

[0131] In some embodiments, in the control device of the excavator hydraulic system, the parameter information of the target excavator during operation includes: the input control signal of the excavator hydraulic system, the excavator state parameters, the joint speed of the excavator at the previous moment and the joint speed of the excavator at the next moment.

[0132] In some embodiments, in the control device of the excavator hydraulic system, the training module, when training the neural network model based on the parameter information during the operation of the target excavator to obtain the trained target excavator hydraulic system model, is specifically used to:

[0133] The input control signal, the excavator state parameter, and the joint speed of the excavator at the previous moment are used as the input of the neural network model, and the joint speed of the excavator at the next moment is used as the output of the neural network model, and the neural network model is trained so that the neural network model learns the target hydraulic system parameter relationship between the input control signal of the target excavator in different states and the joint speed of the excavator at the next moment; wherein the excavator state parameter and the joint speed of the excavator at the previous moment represent the state of the target excavator;

[0134] When the neural network model meets the training completion condition, a trained target excavator hydraulic system model is obtained.

[0135] In some embodiments, in the control device for the excavator hydraulic system, the training module, when the neural network model meets the training completion condition, obtains the trained target excavator hydraulic system model, is specifically used to:

[0136] Running the target excavator and recollecting verification parameter information;

[0137] Verifying the neural network model based on the verification parameter information to determine whether the prediction accuracy output by the neural network model meets the preset accuracy requirements;

[0138] If so, it is determined that the neural network model meets the training completion condition, and a trained target excavator hydraulic system model is obtained.

[0139] In some embodiments, the control device of the excavator hydraulic system further includes:

[0140] An analysis module, used to respectively analyze the influence of the operating state of the excavator and environmental factors on the relationship between the parameters of the hydraulic system, and determine the operating parameters of the excavator and environmental parameters that affect the relationship between the parameters of the hydraulic system;

[0141] The excavator state parameter is determined based on the excavator operating parameter and the environmental parameter.

[0142] In some embodiments, in the control device of the excavator hydraulic system, the number of the trained target excavator hydraulic system models is the same as the number of joints of the target excavator, and different target excavator hydraulic system models determine the target hydraulic system parameter relationships of different joints of the target excavator.

[0143] In some embodiments, the control device of the excavator hydraulic system further includes:

[0144] The updating module is used for re-collecting parameter information of the target excavator during operation when the target excavator hydraulic system model of the target excavator meets a preset updating condition, so as to update the target excavator hydraulic system model based on the re-collected parameter information.

[0145] In some embodiments, in the control device of the hydraulic system of the excavator, the preset update condition includes at least one of the following:

[0146] The prediction accuracy of the target excavator hydraulic system model does not meet the preset accuracy requirements;

[0147] The error of the execution result of the target excavator is greater than the preset error requirement;

[0148] The operating time of the target excavator reaches a preset operating time.

[0149] Based on the same inventive concept, an electronic device corresponding to the control method of the excavator hydraulic system is also provided in the embodiment of the present application. Since the principle of solving the problem by the electronic device in the embodiment of the present application is similar to the control method of the excavator hydraulic system in the embodiment of the present application, the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0150] Please refer to Figure 7 , Figure 7 The schematic diagram of the structure of the electronic device described in the embodiment of the present application is shown; the electronic device 700 includes: a processor 702, a memory 701 and a bus, the memory 701 stores machine-readable instructions executable by the processor 702, when the electronic device 700 is running, the processor 702 communicates with the memory 701 through the bus, and when the machine-readable instructions are executed by the processor 702, the steps of the control method of the excavator hydraulic system are executed, which are as follows:

[0151] A neural network model is trained based on parameter information during the operation of the target excavator to obtain a trained target excavator hydraulic system model; the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed;

[0152] Obtain the real-time joint expected speed of the target excavator;

[0153] Based on the target excavator hydraulic system model, converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system;

[0154] Based on the real-time input control signal, the operation of the hydraulic system of the target excavator is controlled.

[0155] In some embodiments, when the processor executes the step of converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system based on the target excavator hydraulic system model, the processor specifically executes the following steps:

[0156] Obtain the excavator state parameters and real-time joint speed of the target excavator in real-time state;

[0157] The target excavator hydraulic system model processes the excavator state parameters and real-time joint speeds in the real-time state, and fits the target hydraulic system parameter relationship of the target excavator in the real-time state;

[0158] Based on the fitted target hydraulic system parameter relationship of the target excavator in the real-time state, the real-time joint expected speed is converted into a real-time input control signal matching the real-time state of the target excavator.

[0159] In some embodiments, when executing the step of processing the excavator state parameters and real-time joint speeds in the real-time state by the target excavator hydraulic system model and fitting the target hydraulic system parameter relationship of the target excavator in the real-time state, the processor specifically performs the following steps:

[0160] inputting a reference input control signal of a target excavator hydraulic system, an excavator state parameter in the real-time state, and a real-time joint speed into a target excavator hydraulic system model;

[0161] The target excavator hydraulic system model processes the reference input control signal, the excavator state parameters in real time and the real-time joint speed, and outputs the reference joint speed corresponding to the reference input control signal; the relationship between the reference input control signal and the reference joint speed represents the relationship between the target hydraulic system parameters of the target excavator in real time.

[0162] In some embodiments, when the processor executes the step of converting the real-time joint expected speed into a real-time input control signal matching the real-time state of the target excavator based on the fitted target hydraulic system parameter relationship in the real-time state of the target excavator, the processor specifically executes the following steps:

[0163] Based on the relationship among the reference input control signal, the reference joint speed and the real-time joint expected speed, a real-time input control signal matching the real-time state of the target excavator is determined.

[0164] In some embodiments, the excavator state parameters include: excavator operating parameters and environmental parameters;

[0165] The excavator operating parameters include solenoid valve pilot pressure, hydraulic cylinder output pressure, engine cooling water temperature, hydraulic oil temperature, and joint position;

[0166] The environmental parameters include ambient temperature.

[0167] In some embodiments, the target excavator hydraulic system model is trained based on parameter information of the target excavator in different states during operation, and is used to fit the target hydraulic system parameter relationship of the target excavator in different states.

[0168] In some embodiments, the parameter information of the target excavator during operation includes: an input control signal of the excavator hydraulic system, an excavator state parameter, a joint speed of the excavator at a previous moment, and a joint speed of the excavator at a next moment.

[0169] In some embodiments, when the processor executes the step of training the neural network model based on the parameter information during the operation of the target excavator to obtain the trained target excavator hydraulic system model, the processor specifically performs the following steps:

[0170] The input control signal, the excavator state parameter, and the joint speed of the excavator at the previous moment are used as the input of the neural network model, and the joint speed of the excavator at the next moment is used as the output of the neural network model, and the neural network model is trained so that the neural network model learns the target hydraulic system parameter relationship between the input control signal of the target excavator in different states and the joint speed of the excavator at the next moment; wherein the excavator state parameter and the joint speed of the excavator at the previous moment represent the state of the target excavator;

[0171] When the neural network model meets the training completion condition, a trained target excavator hydraulic system model is obtained.

[0172] In some embodiments, when the processor executes the step of obtaining a trained target excavator hydraulic system model when the neural network model meets the training completion condition, the processor specifically executes the following steps:

[0173] Running the target excavator and recollecting verification parameter information;

[0174] Verifying the neural network model based on the verification parameter information to determine whether the prediction accuracy output by the neural network model meets the preset accuracy requirements;

[0175] If so, it is determined that the neural network model meets the training completion condition, and a trained target excavator hydraulic system model is obtained.

[0176] In some embodiments, the processor performs the following steps:

[0177] Analyze the influence of the operating state of the excavator and environmental factors on the relationship between the parameters of the hydraulic system respectively, and determine the operating parameters and environmental parameters of the excavator that affect the relationship between the parameters of the hydraulic system;

[0178] The excavator state parameter is determined based on the excavator operating parameter and the environmental parameter.

[0179] In some embodiments, the number of the trained target excavator hydraulic system models is the same as the number of joints of the target excavator, and different target excavator hydraulic system models determine the target hydraulic system parameter relationships of different joints of the target excavator.

[0180] In some embodiments, the processor performs the following steps:

[0181] When the target excavator hydraulic system model of the target excavator meets a preset update condition, parameter information during the operation of the target excavator is re-collected to update the target excavator hydraulic system model based on the re-collected parameter information.

[0182] In some embodiments, the preset update condition includes at least one of the following:

[0183] The prediction accuracy of the target excavator hydraulic system model does not meet the preset accuracy requirements;

[0184] The error of the execution result of the target excavator is greater than the preset error requirement;

[0185] The operating time of the target excavator reaches a preset operating time.

[0186] Based on the same inventive concept, a computer-readable storage medium corresponding to the control method of the excavator hydraulic system is also provided in the embodiment of the present application. Since the principle of solving the problem by the computer-readable storage medium in the embodiment of the present application is similar to the control method of the excavator hydraulic system in the embodiment of the present application, the implementation of the computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be repeated.

[0187] The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor executes the steps of the control method of the excavator hydraulic system, which are specifically as follows:

[0188] A neural network model is trained based on parameter information during the operation of the target excavator to obtain a trained target excavator hydraulic system model; the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed;

[0189] Obtain the real-time joint expected speed of the target excavator;

[0190] Based on the target excavator hydraulic system model, converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system;

[0191] Based on the real-time input control signal, the operation of the hydraulic system of the target excavator is controlled.

[0192] In some embodiments, when the processor executes the step of converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system based on the target excavator hydraulic system model, the processor specifically executes the following steps:

[0193] Obtain the excavator state parameters and real-time joint speed of the target excavator in real-time state;

[0194] The target excavator hydraulic system model processes the excavator state parameters and real-time joint speeds in the real-time state, and fits the target hydraulic system parameter relationship of the target excavator in the real-time state;

[0195] Based on the fitted target hydraulic system parameter relationship of the target excavator in the real-time state, the real-time joint expected speed is converted into a real-time input control signal matching the real-time state of the target excavator.

[0196] In some embodiments, when executing the step of processing the excavator state parameters and real-time joint speeds in the real-time state by the target excavator hydraulic system model and fitting the target hydraulic system parameter relationship of the target excavator in the real-time state, the processor specifically performs the following steps:

[0197] inputting a reference input control signal of a target excavator hydraulic system, an excavator state parameter in the real-time state, and a real-time joint speed into a target excavator hydraulic system model;

[0198] The target excavator hydraulic system model processes the reference input control signal, the excavator state parameters in real time and the real-time joint speed, and outputs the reference joint speed corresponding to the reference input control signal; the relationship between the reference input control signal and the reference joint speed represents the relationship between the target hydraulic system parameters of the target excavator in real time.

[0199] In some embodiments, when the processor executes the step of converting the real-time joint expected speed into a real-time input control signal matching the real-time state of the target excavator based on the fitted target hydraulic system parameter relationship in the real-time state of the target excavator, the processor specifically executes the following steps:

[0200] Based on the relationship among the reference input control signal, the reference joint speed and the real-time joint expected speed, a real-time input control signal matching the real-time state of the target excavator is determined.

[0201] In some embodiments, the excavator state parameters include: excavator operating parameters and environmental parameters;

[0202] The excavator operating parameters include solenoid valve pilot pressure, hydraulic cylinder output pressure, engine cooling water temperature, hydraulic oil temperature, and joint position;

[0203] The environmental parameters include ambient temperature.

[0204] In some embodiments, the target excavator hydraulic system model is trained based on parameter information of the target excavator in different states during operation, and is used to fit the target hydraulic system parameter relationship of the target excavator in different states.

[0205] In some embodiments, the parameter information of the target excavator during operation includes: an input control signal of the excavator hydraulic system, an excavator state parameter, a joint speed of the excavator at a previous moment, and a joint speed of the excavator at a next moment.

[0206] In some embodiments, when the processor executes the step of training the neural network model based on the parameter information during the operation of the target excavator to obtain the trained target excavator hydraulic system model, the processor specifically performs the following steps:

[0207] The input control signal, the excavator state parameter, and the joint speed of the excavator at the previous moment are used as the input of the neural network model, and the joint speed of the excavator at the next moment is used as the output of the neural network model, and the neural network model is trained so that the neural network model learns the target hydraulic system parameter relationship between the input control signal of the target excavator in different states and the joint speed of the excavator at the next moment; wherein the excavator state parameter and the joint speed of the excavator at the previous moment represent the state of the target excavator;

[0208] When the neural network model meets the training completion condition, a trained target excavator hydraulic system model is obtained.

[0209] In some embodiments, when the processor executes the step of obtaining a trained target excavator hydraulic system model when the neural network model meets the training completion condition, the processor specifically executes the following steps:

[0210] Running the target excavator and recollecting verification parameter information;

[0211] Verifying the neural network model based on the verification parameter information to determine whether the prediction accuracy output by the neural network model meets the preset accuracy requirements;

[0212] If so, it is determined that the neural network model meets the training completion condition, and a trained target excavator hydraulic system model is obtained.

[0213] In some embodiments, the processor performs the following steps:

[0214] Analyze the influence of the operating state of the excavator and environmental factors on the relationship between the parameters of the hydraulic system respectively, and determine the operating parameters and environmental parameters of the excavator that affect the relationship between the parameters of the hydraulic system;

[0215] The excavator state parameter is determined based on the excavator operating parameter and the environmental parameter.

[0216] In some embodiments, the number of the trained target excavator hydraulic system models is the same as the number of joints of the target excavator, and different target excavator hydraulic system models determine the target hydraulic system parameter relationships of different joints of the target excavator.

[0217] In some embodiments, the processor performs the following steps:

[0218] When the target excavator hydraulic system model of the target excavator meets a preset update condition, parameter information during the operation of the target excavator is re-collected to update the target excavator hydraulic system model based on the re-collected parameter information.

[0219] In some embodiments, the preset update condition includes at least one of the following:

[0220] The prediction accuracy of the target excavator hydraulic system model does not meet the preset accuracy requirements;

[0221] The error of the execution result of the target excavator is greater than the preset error requirement;

[0222] The operating time of the target excavator reaches a preset operating time.

[0223] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, 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 through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0224] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0225] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0226] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a platform server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0227] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A control method for an excavator hydraulic system, characterized in that: The method comprises: A neural network model is trained based on parameter information during the operation of the target excavator to obtain a trained target excavator hydraulic system model; the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed; Obtain the real-time joint expected speed of the target excavator; Based on the target excavator hydraulic system model, converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system; Based on the real-time input control signal, the operation of the hydraulic system of the target excavator is controlled.

2. The control method of the hydraulic system of an excavator according to claim 1, characterized in that: Based on the target excavator hydraulic system model, converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system includes: Obtain the excavator state parameters and real-time joint speed of the target excavator in real-time state; The target excavator hydraulic system model processes the excavator state parameters and real-time joint speeds in the real-time state, and fits the target hydraulic system parameter relationship of the target excavator in the real-time state; Based on the fitted target hydraulic system parameter relationship of the target excavator in the real-time state, the real-time joint expected speed is converted into a real-time input control signal matching the real-time state of the target excavator.

3. The control method of the hydraulic system of an excavator according to claim 2, characterized in that: The target excavator hydraulic system model processes the excavator state parameters and real-time joint speeds in the real-time state, and fits the target hydraulic system parameter relationship of the target excavator in the real-time state, including: inputting a reference input control signal of a target excavator hydraulic system, an excavator state parameter in the real-time state, and a real-time joint speed into a target excavator hydraulic system model; The target excavator hydraulic system model processes the reference input control signal, the excavator state parameters in real time and the real-time joint speed, and outputs the reference joint speed corresponding to the reference input control signal; the relationship between the reference input control signal and the reference joint speed represents the relationship between the target hydraulic system parameters of the target excavator in real time.

4. The control method of the hydraulic system of an excavator according to claim 3, characterized in that: Based on the fitted target hydraulic system parameter relationship under the real-time state of the target excavator, the real-time joint expected speed is converted into a real-time input control signal matching the real-time state of the target excavator, including: Based on the relationship among the reference input control signal, the reference joint speed and the real-time joint expected speed, a real-time input control signal matching the real-time state of the target excavator is determined.

5. The control method of the hydraulic system of an excavator according to claim 2, characterized in that: The excavator state parameters include: excavator operation parameters and environmental parameters; The excavator operating parameters include solenoid valve pilot pressure, hydraulic cylinder output pressure, engine cooling water temperature, hydraulic oil temperature, and joint position; The environmental parameters include ambient temperature.

6. The control method of the hydraulic system of an excavator according to claim 1, characterized in that: The target excavator hydraulic system model is obtained by training based on parameter information of the target excavator in different states during operation, and is used to fit the target hydraulic system parameter relationship of the target excavator in different states.

7. The control method of the hydraulic system of an excavator according to claim 1 or 6, characterized in that: The parameter information of the target excavator during operation includes: an input control signal of the hydraulic system of the excavator, state parameters of the excavator, joint speeds of the excavator at the previous moment, and joint speeds of the excavator at the next moment.

8. The control method of the hydraulic system of an excavator according to claim 7, characterized in that: The neural network model is trained based on the parameter information during the operation of the target excavator to obtain a trained target excavator hydraulic system model, including: The input control signal, the excavator state parameter, and the joint speed of the excavator at the previous moment are used as the input of the neural network model, and the joint speed of the excavator at the next moment is used as the output of the neural network model, and the neural network model is trained so that the neural network model learns the target hydraulic system parameter relationship between the input control signal of the target excavator in different states and the joint speed of the excavator at the next moment; wherein the excavator state parameter and the joint speed of the excavator at the previous moment represent the state of the target excavator; When the neural network model meets the training completion condition, a trained target excavator hydraulic system model is obtained.

9. The control method of the hydraulic system of an excavator according to claim 8, characterized in that: When the neural network model meets the training completion condition, a trained target excavator hydraulic system model is obtained, including: Running the target excavator and recollecting verification parameter information; Verifying the neural network model based on the verification parameter information to determine whether the prediction accuracy output by the neural network model meets the preset accuracy requirements; If so, it is determined that the neural network model meets the training completion condition, and a trained target excavator hydraulic system model is obtained.

10. The control method of the hydraulic system of an excavator according to claim 7, characterized in that: The method further comprises: Analyze the influence of the operating state of the excavator and environmental factors on the relationship between the parameters of the hydraulic system respectively, and determine the operating parameters and environmental parameters of the excavator that affect the relationship between the parameters of the hydraulic system; The excavator state parameter is determined based on the excavator operating parameter and the environmental parameter.

11. The control method of the hydraulic system of an excavator according to claim 1, characterized in that: The number of the trained target excavator hydraulic system models is the same as the number of joints of the target excavator, and different target excavator hydraulic system models determine the target hydraulic system parameter relationships of different joints of the target excavator.

12. The control method of the hydraulic system of an excavator according to claim 1, characterized in that: The method further comprises: When the target excavator hydraulic system model of the target excavator meets a preset update condition, parameter information during the operation of the target excavator is re-collected to update the target excavator hydraulic system model based on the re-collected parameter information.

13. The control method of the hydraulic system of an excavator according to claim 10, characterized in that: The preset update condition includes at least one of the following: The prediction accuracy of the target excavator hydraulic system model does not meet the preset accuracy requirements; The error of the execution result of the target excavator is greater than the preset error requirement; The operating time of the target excavator reaches a preset operating time.

14. A control device for an excavator hydraulic system, characterized in that: The device comprises: A training module is used to train a neural network model based on parameter information during the operation of a target excavator to obtain a trained target excavator hydraulic system model; the target excavator hydraulic system model is used to fit the target hydraulic system parameter relationship from the input control signal of the target excavator hydraulic system to the excavator joint speed; An acquisition module, used for acquiring the real-time joint expected speed of the target excavator; A conversion module, for converting the real-time joint expected speed into a real-time input control signal for determining the target excavator hydraulic system based on the target excavator hydraulic system model; A control module is used to control the operation of the hydraulic system of the target excavator based on the real-time input control signal.

15. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the control method of the excavator hydraulic system as described in any one of claims 1 to 13 are performed.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for controlling the hydraulic system of an excavator as claimed in any one of claims 1 to 13.

Images