Control method and device of mechanical equipment, computer equipment and storage medium
By acquiring the excavator's dynamic parameters and state information, and combining them with the dynamic compensation torque and control model, excitation signals are generated to control the excavator's movement. This solves the problems of accuracy and stability in the excavator's hydraulic control, and achieves a higher level of automation and intelligent control.
Patent Information
- Application Number
- CN202411116571.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-26
AI Technical Summary
Existing technologies struggle to achieve high-precision hydraulic control in excavators, especially given the uncertainties and time-varying nature of the system under harsh working conditions, which place high demands on control algorithms. Traditional methods are insufficient to meet the automation and intelligent control requirements of excavators.
By acquiring the dynamic parameters and current state information of the mechanical equipment, the dynamic compensation torque is determined. Combined with the target feedforward model and feedback controller, first and second excitation signals are generated, which are finally superimposed into the target excitation signal to control the mechanical equipment to perform motion.
It improves the automated control performance of excavators, enhances the motion accuracy and stability of mechanical equipment, and strengthens control capabilities under harsh working conditions.
Smart Images

Figure CN119021300A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a control method and device for mechanical equipment, a computer device and a storage medium. Background Art
[0002] With the increase of labor costs and the development of science and technology, the automation and intelligent control of excavators has become a trend in the development of construction machinery. In order to realize the automatic control of the excavator arm, it is necessary to accurately control the speed of the excavator arm joints. Only based on the joint speed control can higher-level control modes such as position control and trajectory control be achieved.
[0003] Since the excavator is a complex hydraulic control system, the manufacturing accuracy of hydraulic components, oil circuit layout and sensor accuracy cannot meet the high-precision requirements. Especially under harsh working conditions, the uncertainty and time-varying nature of the system have high requirements for the control algorithm. Traditional control methods based on precise models are difficult to use directly in excavators. Summary of the invention
[0004] The embodiments of the present application provide a control method, device, computer device and storage medium for mechanical equipment, which can improve the performance of automatic control of the mechanical equipment.
[0005] The present application provides a control method for a mechanical device, the method comprising:
[0006] Obtain the dynamic parameters and current status information of mechanical equipment;
[0007] Determining a dynamic compensation torque of the mechanical device based on the dynamic parameter and the current state information;
[0008] Determining a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determining a second excitation signal corresponding to the mechanical device according to the current state information;
[0009] Determining a target excitation signal based on the first excitation signal and the second excitation signal;
[0010] The mechanical device is controlled to perform movement based on the target excitation signal.
[0011] Accordingly, an embodiment of the present application further provides a control device for a mechanical device, the device comprising:
[0012] A first acquisition unit, used to acquire dynamic parameters and current state information of the mechanical equipment;
[0013] A first determining unit, configured to determine a dynamic compensation torque of the mechanical device based on the dynamic parameter and the current state information;
[0014] A second determination unit, configured to determine a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and to determine a second excitation signal corresponding to the mechanical device according to the current state information;
[0015] A third determination unit, configured to determine a target excitation signal based on the first excitation signal and the second excitation signal;
[0016] A first control unit is used to control the mechanical device to perform movement based on the target excitation signal.
[0017] Correspondingly, an embodiment of the present application also provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes a control method for a mechanical device provided in any embodiment of the present application.
[0018] Correspondingly, an embodiment of the present application further provides a storage medium, which stores a plurality of instructions, and the instructions are suitable for loading by a processor to execute the control method of the mechanical device as described above.
[0019] The embodiment of the present application obtains the dynamic parameters and current state information of the mechanical device, determines the dynamic compensation torque of the mechanical device based on the dynamic parameters and the current state information, determines the first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determines the second excitation signal corresponding to the mechanical device according to the current state information, determines the target excitation signal based on the first excitation signal and the second excitation signal, and controls the mechanical device to perform movement based on the target excitation signal. In this way, the performance of the automatic control of the mechanical device can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0021] Figure 1 A flow chart of a control method for a mechanical device provided in an embodiment of the present application.
[0022] Figure 2 A schematic diagram of the structure of a mechanical device provided in an embodiment of the present application.
[0023] Figure 3 A schematic diagram of the structure of another mechanical device provided in an embodiment of the present application.
[0024] Figure 4 A structural block diagram of a control device for a mechanical device provided in an embodiment of the present application.
[0025] Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.
[0027] Based on the above problems, the embodiments of the present application provide a control method, device, storage medium and computer equipment for mechanical equipment. Specifically, the control method of the mechanical equipment of the embodiments of the present application can be executed by a computer device, wherein the computer device can be a terminal, a central control device or a server and other equipment. The central control device can be a central control electrical box and other equipment, and the terminal can be a mobile phone, a tablet computer, a laptop computer, a touch screen, a personal computer (PC, Personal Computer), a personal digital assistant (Personal Digital Assistant, PDA) and other terminal devices. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network, content distribution network), and basic cloud computing services such as big data and artificial intelligence platforms.
[0028] For example, the computer device can be a server, which can obtain dynamic parameters and current state information of a mechanical device; determine the dynamic compensation torque of the mechanical device based on the dynamic parameters and the current state information; determine a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determine a second excitation signal corresponding to the mechanical device according to the current state information; determine a target excitation signal based on the first excitation signal and the second excitation signal; and control the mechanical device to perform movement based on the target excitation signal.
[0029] It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.
[0030] An embodiment of the present application provides a control method for a mechanical device, which can be executed by a terminal or a server. The embodiment of the present application takes the control method for a mechanical device executed by a server as an example for explanation.
[0031] See also Figure 1 , Figure 1 A schematic diagram of a control method for a mechanical device provided in an embodiment of the present application. The specific process of the control method for the mechanical device may be as follows:
[0032] 101. Obtain the dynamic parameters and current status information of mechanical equipment.
[0033] In the embodiment of the present application, mechanical equipment refers to machinery used for digging, shoveling, pushing, etc. Mechanical equipment may include many types, such as earth-moving machinery, excavating machinery, leveling machinery, compacting machinery, and hydraulic earth-moving machinery.
[0034] The dynamic parameters include at least a mass parameter and a position parameter of at least one target component in the mechanical device, and a distance parameter corresponding to a component joint of the target component.
[0035] The target component refers to a main component in the working process of the mechanical equipment, and the target component may at least include a first mechanical arm, a second mechanical arm and a working component of the mechanical equipment.
[0036] For example, the mechanical equipment may be an excavator, the first mechanical arm may be a large arm, the second mechanical arm may be a small arm, the working part may be a bucket, and the bucket may be used for loading and unloading materials, etc.
[0037] Among them, the component joints may include a first robotic arm joint, a second robotic arm joint and a working component joint, wherein the first robotic arm joint can be used to connect the body of the mechanical equipment and the first robotic arm, the second robotic arm joint can be used to connect the first robotic arm and the second robotic arm, and the working component joint can be used to connect the second robotic arm and the working component.
[0038] For example, the mechanical equipment may be an excavator, and the target parts may include: a boom, an arm, and a bucket, and the component joints may include: an boom joint, an arm joint, and a bucket joint, wherein the boom joint connects the body and the boom of the excavator; the arm joint connects the boom and the arm of the excavator; and the bucket joint connects the arm and the bucket of the excavator.
[0039] For example, see Figure 2 , Figure 2 A schematic diagram of the structure of a mechanical device provided in an embodiment of the present application. Figure 2 In the excavator shown, the target components may include a boom, an arm and a bucket. The component joints may include a boom joint, an arm joint and a bucket joint. The boom joint connects the body and the boom of the excavator, the arm joint connects the boom and the arm of the excavator, and the bucket joint connects the arm and the bucket.
[0040] The distance parameter refers to the distance between the joints of a component and the joints of its adjacent components. Figure 2 In the figure, the distance parameter corresponding to the upper arm joint can be the distance between the upper arm joint and the lower arm joint.
[0041] The mass parameter refers to the weight of the target component, and the position parameter refers to the coordinates of the center of gravity of the target component, which can be the coordinates of the center of gravity of the target component in a specified coordinate system.
[0042] For example, see Figure 3 , Figure 3 A schematic diagram of the structure of another mechanical device provided in an embodiment of the present application. Figure 3 In the excavator shown, corresponding coordinate systems can be created according to the joints of each component, for example, a boom joint coordinate system created with the boom joint position as the coordinate origin, etc., wherein the specified coordinate system can be the boom joint coordinate system, and the center of gravity position coordinates of each target component can be the center of gravity position coordinates in the boom joint coordinate system.
[0043] Among them, the mass of the upper arm is: M-upper arm, and the coordinates of the center of gravity of the upper arm in the coordinate system corresponding to the upper arm joint can be determined as (x0, z0); the mass of the forearm is: M-forearm, and the coordinates of the center of gravity of the forearm in the coordinate system corresponding to the upper arm joint can be determined as (x1, z1); the mass of the bucket is: M-bucket, and the coordinates of the center of gravity of the bucket in the coordinate system corresponding to the upper arm joint can be determined as (x2, z2).
[0044] In the embodiment of the present application, the state information of the mechanical device refers to the motion state information of the mechanical device, and the state information may include posture parameters and speed parameters of the joints of various components of the mechanical device.
[0045] The current state information refers to the posture parameters and speed parameters of the joints of each component in the current mechanical device. The posture parameters may be the joint angles, and the speed parameters may include the speed and acceleration of the joint movement.
[0046] In an embodiment of the present application, a plurality of sensors may be provided on the mechanical equipment, which may be used to collect posture parameters and speed parameters of the joints of each component.
[0047] For example, see Figure 3 ,exist Figure 3In the excavator shown, the first link is determined according to the line between the upper arm joint and the lower arm joint, the second link is determined according to the line between the lower arm joint and the bucket joint, and the third link is determined according to the line between the bucket joint and the end position of the bucket. Then the joint angle of the upper arm joint is the angle q0 between the z-axis of the coordinate system where the upper arm joint is located and the first link; the joint angle of the lower arm joint is the angle q1 between the z-axis of the coordinate system where the lower arm joint is located and the second link; the joint angle of the bucket joint is the angle q2 between the z-axis of the coordinate system where the bucket joint is located and the third link.
[0048] In some embodiments, the step of “obtaining dynamic parameters and current state information of the mechanical device” may include:
[0049] In response to the joint velocity command for the mechanical device, the dynamic parameters and current state information of the mechanical device are acquired.
[0050] Among them, the joint speed command refers to the instruction used to control the mechanical equipment to perform movement. The joint speed command can be triggered in a variety of ways, for example, through the joint speed signal of manual remote control, or through the planner of the mechanical equipment to issue the joint speed command.
[0051] Among them, the planner of the mechanical equipment is an intelligent control system component, which is responsible for receiving information from sensors, operators or other input devices, analyzing the current status, working environment and working objectives of the mechanical equipment, and then generating a series of control instructions to guide the mechanical equipment to complete specific working tasks.
[0052] In an embodiment of the present application, after receiving a joint speed command for a mechanical device, the dynamic parameters and current state information of the mechanical device can be obtained, so as to execute subsequent steps according to the obtained dynamic parameters and current state information, thereby controlling the movement of the mechanical device.
[0053] 102. Determine the dynamic compensation torque of the mechanical equipment based on the dynamic parameters and current state information.
[0054] The dynamic compensation torque refers to the additional torque applied to the system in the dynamic system in order to eliminate or reduce errors or adverse effects caused by internal factors of the system (such as gravity, friction, inertia, etc.) and external interference.
[0055] In the embodiment of the present application, the dynamic compensation torque of the mechanical device may include the gravity torque on the joints of each component, that is, the measurement of the rotation effect of the gravity of each target component on each target component around the component joint.
[0056] In some embodiments, the step of “determining the dynamic compensation torque of the mechanical device based on the dynamic parameters and the current state information” may include the following operations:
[0057] According to the mass parameters, position parameters, distance parameters and posture parameters, the gravity torque acting on the component joints is calculated as the dynamic compensation torque of the mechanical equipment.
[0058] Specifically, the gravity torque on the joints of each component is calculated based on the mass parameters, position parameters of each target component, and the distance parameters and posture parameters corresponding to the joints of each component, and then the dynamic compensation torque of the mechanical equipment is obtained based on the gravity torque corresponding to the joints of each component.
[0059] In some embodiments, the step of “calculating the gravity torque exerted on the joint of the component according to the mass parameter, the position parameter, the distance parameter and the posture parameter as the dynamic compensation torque of the mechanical device” may include the following operations:
[0060] Based on the posture parameters and corresponding distance parameters of the joints of each component, and the position parameters of each target component, a first transformation matrix from the first robotic arm joint to the center of gravity of the first robotic arm, a second transformation matrix from the first robotic arm joint to the center of gravity of the second robotic arm, and a third transformation matrix from the first robotic arm joint to the center of gravity of the working component are calculated;
[0061] Based on the first transformation matrix, the second transformation matrix, the third transformation matrix, and the mass parameters of each target component, the gravity torque exerted on the joint of the first robotic arm is calculated;
[0062] Based on the second transformation matrix, the third transformation matrix, and the mass parameters of the second robotic arm and the mass parameters of the working component, calculate the gravity torque on the joint of the second robotic arm;
[0063] Based on the third transformation matrix and the mass parameter of the working component, the gravity torque acting on the joint of the working component is calculated.
[0064] In the embodiment of the present application, the calculation formula for calculating the transformation matrix from the first mechanical arm joint to the center of gravity of each component joint can be as follows:
[0065]
[0066] in, Refers to the homogeneous transformation matrix from the first robot arm to the i-th joint coordinate system, Refers to the transformation matrix of the i-th center of gravity position coordinate point from the first robot joint coordinate system to the center of gravity coordinate system. Refers to the transformation matrix from the first robot joint to the center of gravity of the i-th component joint. Where i can be 0, 1, or 2.
[0067] When i is 0, the i-th joint coordinate system refers to the first robot arm joint coordinate system (that is, the coordinate system constructed with the first robot arm joint as the coordinate origin), the i-th center of gravity position coordinate point refers to the center of gravity position coordinate point of the first robot arm, and the i-th component joint refers to the first robot arm joint;
[0068] When i is 1, the i-th joint coordinate system refers to the second robot arm joint coordinate system (that is, the coordinate system constructed with the second robot arm joint as the coordinate origin), the i-th center of gravity position coordinate point refers to the center of gravity position coordinate point of the second robot arm, and the i-th component joint refers to the second robot arm joint;
[0069] When i is 2, the i-th joint coordinate system refers to the working part joint coordinate system (that is, the coordinate system constructed with the working part joint as the coordinate origin), the i-th center of gravity position coordinate point refers to the center of gravity position coordinate point of the working part, and the i-th component joint refers to the working part joint.
[0070] In the embodiment of the present application, the homogeneous transformation matrix from the first robot arm to the i-th joint coordinate system is The calculation formula can be as follows:
[0071]
[0072] Among them, T i Refers to the homogeneous coordinate transformation matrix corresponding to the i-th component joint, where i can be 0, 1, or 2.
[0073] In the present embodiment, T i The calculation formula can be as follows:
[0074]
[0075] Among them, θi refers to the posture parameter (i.e., joint angle) of the i-th component joint, L i Refers to the distance parameter of the i-th component joint.
[0076] Specifically, the calculation formula of the homogeneous coordinate transformation matrix T0 corresponding to the 0th component joint (that is, the first robot arm joint) is as follows:
[0077]
[0078] The calculation formula of the homogeneous coordinate transformation matrix T1 corresponding to the first component joint (that is, the second robot arm joint) is as follows:
[0079]
[0080] The homogeneous coordinate transformation matrix corresponding to the second component joint (i.e. the working component)
[0081] The calculation formula of T2 is as follows:
[0082]
[0083] In the embodiment of the present application, the transformation matrix of the i-th center of gravity position coordinate point from the first robot arm joint coordinate system to the center of gravity coordinate system is The calculation formula can be as follows:
[0084]
[0085] Among them, x i Refers to the X-axis coordinate value of the i-th center of gravity position coordinate, z i Refers to the z-axis coordinate value in the i-th center of gravity position coordinates.
[0086] Specifically, the transformation matrix of the 0th center of gravity position coordinate point (the center of gravity position coordinate point of the first robot arm) from the first robot arm joint coordinate system to the center of gravity coordinate system is The calculation formula can be as follows:
[0087]
[0088] The transformation matrix of the first center of gravity position coordinate point (the center of gravity position coordinate point of the second robot arm) from the first robot arm joint coordinate system to the center of gravity coordinate system The calculation formula can be as follows:
[0089]
[0090] The transformation matrix of the second center of gravity position coordinate point (the center of gravity position coordinate point of the working part) from the first robot arm joint coordinate system to the center of gravity coordinate system The calculation formula can be as follows:
[0091]
[0092] For example, the first transformation matrix from the first robotic arm joint to the center of gravity of the first robotic arm can be The calculation formula is: The second transformation matrix from the first robot joint to the center of gravity of the second robot is The calculation formula is:
[0093] The third transformation matrix from the first robot joint to the center of gravity of the working part is The calculation formula is:
[0094] Among them, based on the first transformation matrix, the second transformation matrix, the third transformation matrix, and the mass parameters of each target component, the calculation formula for calculating the gravity torque on the first mechanical arm joint can be as follows:
[0095]
[0096] in, Refers to the gravity torque on the first robot joint;
[0097] Refers to the third transformation matrix from the first robot joint to the center of gravity of the working part;
[0098] Refers to the distance in the x-axis direction in the third transformation matrix; m_bucker is the mass parameter of the working part; g is the gravitational acceleration; refers to the second transformation matrix from the joint of the first robotic arm to the center of gravity of the second robotic arm; Refers to the distance in the x-axis direction in the second transformation matrix; m_arm refers to the mass parameter of the second manipulator;
[0099] Refers to the third transformation matrix from the first robot joint to the center of gravity of the working part;
[0100] Refers to the x-axis distance in the third transformation matrix; m_boom refers to the mass parameter of the first robot arm.
[0101] in, The calculation formula can be: That is, take the value of the first column and fourth row in the matrix.
[0102] Wherein, based on the second transformation matrix, the third transformation matrix, and the mass parameters of the second robotic arm and the mass parameters of the working part, the calculation formula for calculating the gravity torque on the joint of the second robotic arm can be as follows:
[0103]
[0104] in, Refers to the gravity torque on the joint of the second robot arm; Refers to the homogeneous transformation matrix The distance in the x-axis direction.
[0105] in, The calculation formula can be That is, take the value of the first column and fourth row in the matrix.
[0106] Wherein, based on the third transformation matrix and the mass parameter of the working component, the calculation formula for calculating the gravity torque on the joint of the working component can be as follows:
[0107]
[0108] in, Refers to the gravitational torque on the joints of the working parts. Refers to the homogeneous transformation matrix The distance in the x-axis direction.
[0109] in, The calculation formula can be That is, take the value of the first column and fourth row in the matrix.
[0110] Furthermore, based on the gravity torque exerted on each component, the dynamic compensation torque of the mechanical equipment is obtained.
[0111] 103. Determine a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determine a second excitation signal corresponding to the mechanical device according to the current state information.
[0112] Among them, the excitation signal can be an electronic signal used to trigger or control the mechanical equipment to perform a specific action. These signals are usually generated by a control system (such as a PLC (Programmable Logic Controller, microprocessor, etc.) and transmitted and executed by components such as sensors and actuators.
[0113] For example, various sensors on the excavator (such as position sensors, angle sensors, pressure sensors, etc.) detect the state of the excavator and environmental parameters in real time, and convert these parameters into electrical signals (i.e., excitation signals) and transmit them to the control system. The control system determines the current state of the excavator based on these signals and makes corresponding control decisions.
[0114] In the embodiment of the present application, the first excitation signal may include excitation signals corresponding to joints of each component obtained by processing the target feedforward model.
[0115] In some embodiments, the step of “determining a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque” may include the following operations:
[0116] Input the velocity parameters and posture parameters of the component joints and the gravity torque acting on the component joints into the target feedforward model;
[0117] The velocity parameters, posture parameters, and gravity torque of the component joints are processed respectively through the target feedforward model to obtain the excitation signals corresponding to the component joints;
[0118] Based on the excitation signal corresponding to the component joint, a first excitation signal is obtained.
[0119] In the embodiment of the present application, the target feedforward model can be used to calculate the excitation signal corresponding to each component joint according to the input velocity parameters, posture parameters of each component joint, and the gravity torque received by each component joint. That is, the input of the target feedforward model is: the velocity parameters, posture parameters of each component joint, and the gravity torque received by each component joint; the input is: the excitation signal corresponding to each component joint.
[0120] In some embodiments, in order to improve the accuracy of automated control of mechanical equipment, before the step of "inputting the velocity parameters and posture parameters of the component joints and the gravity torque exerted on the component joints into the target feedforward model", the method may further include the following steps:
[0121] Obtain multiple training sample pairs;
[0122] A target feedforward model is constructed based on sample excitation signals and sample state information in multiple training sample pairs.
[0123] Each training sample pair includes a sample excitation signal and a sample state information, wherein the sample state information is state information obtained after a component joint of the mechanical device is controlled to perform a movement based on the sample excitation signal.
[0124] In some embodiments, obtaining training sample pairs may include: for multiple component joints of a mechanical device, controlling one of the component joints to move, and fixing the other component joints in a stationary state. Given a constant excitation signal (that is, a set sample excitation signal), control the moving component joint to move from one extreme position to another extreme position, and record the state information of the component joint. Use the constant excitation signal and the state information as a training sample. Then, given enough constant excitation signals, control the moving component joint to move from one extreme position to another extreme position under different constant excitation signals, and record different state information of the component joint. Based on the above method, multiple training sample pairs corresponding to each component joint can be obtained.
[0125] For example, a plurality of training sample pairs may include: a plurality of first training sample pairs corresponding to the first mechanical arm joint, a plurality of second training sample pairs corresponding to the second mechanical arm joint, and a plurality of third training sample pairs corresponding to the working part joint. Each first training sample pair includes a sample excitation signal and the motion state information of the first mechanical arm joint under the sample excitation signal, and the sample excitation signals in different first training sample pairs are different; each second training sample pair includes a sample excitation signal and the motion state information of the second mechanical arm joint under the sample excitation signal, and the sample excitation signals in different second training sample pairs are different; each third training sample pair includes a sample excitation signal and the motion state information of the working part joint under the sample excitation signal, and the sample excitation signals in different third training sample pairs are different.
[0126] In some embodiments, the step of “building a target feedforward model based on the sample excitation signals and sample state information in the plurality of training sample pairs” may include the following operations:
[0127] According to the sample state information and the dynamic parameters, the sample compensation torque corresponding to the sample state information is calculated;
[0128] Inputting sample state information and sample compensation torque into a preset feedforward model;
[0129] The sample state information and the sample compensation torque are processed by a preset feedforward model to obtain an output excitation signal;
[0130] Based on the difference between the sample excitation signal and the output excitation signal, the model parameters of the preset feedforward model are adjusted until the preset feedforward model converges to obtain the target feedforward model.
[0131] Among them, calculating the sample compensation torque corresponding to the sample state information based on the sample state information and the dynamic parameters can include: calculating the dynamic compensation torque based on the posture parameters and speed parameters in the sample state information, and the mass parameters and position parameters of the target component, as the sample compensation torque corresponding to the sample state information.
[0132] Specifically, the method for calculating the dynamic compensation torque can refer to the description of the above steps, and will not be elaborated here.
[0133] In an embodiment of the present application, a preset feedforward model can be pre-designed, and the preset feedforward model can preferably use a neural network model. Then, the preset feedforward model can be trained using training samples. Among them, the training preset feedforward model can be trained using a supervised learning method, and preferably the neural network model can be trained using a gradient descent method.
[0134] Among them, supervised learning is a machine learning task that infers functions from labeled training data. Specifically, it uses a set of sample data containing inputs and corresponding outputs (i.e., labels or categories) to train the model so that the model can learn the mapping relationship between inputs and outputs, and then predict new input samples. Supervised learning algorithms continuously adjust model parameters by analyzing the input and output pairs in the training data to minimize the difference between the predicted output and the actual output (i.e., the loss function).
[0135] Among them, the gradient descent method continuously adjusts the model parameters in an iterative manner to approach the minimum point of the objective function. The gradient descent method uses the first-order derivative (gradient) information of the function to guide the search direction. In each iteration, the algorithm calculates the gradient of the current point and updates the parameters in the opposite direction of the gradient (that is, the direction in which the function value decreases fastest). Through multiple iterations, the algorithm gradually approaches the minimum point of the objective function.
[0136] Among them, the step of training the preset feedforward model may include: inputting sample state information and sample compensation torque into the preset feedforward model; processing the sample state information and sample compensation torque through the preset feedforward model, that is, calculating the excitation signal according to the sample state information and the sample compensation torque as the model output.
[0137] Furthermore, the excitation signal output by the preset feedforward model is compared with the sample excitation signal corresponding to the sample state information to determine the difference between the two, and then the model parameters of the preset feedforward model are adjusted according to the difference value until the difference between the excitation signal output by the preset feedforward model and the sample excitation signal corresponding to the sample state information is less than the preset difference value. It can be determined that the preset feedforward model converges, thereby obtaining the target feedforward model.
[0138] Among them, the speed parameters, posture parameters, and gravity torque of each component joint are processed respectively through the target feedforward model to obtain the excitation signal corresponding to the joint of each component, which can include: calculating the excitation signal corresponding to the first robotic arm joint according to the speed parameters, posture parameters and gravity torque of the first robotic arm joint through the target feedforward model; calculating the excitation signal corresponding to the second robotic arm joint according to the speed parameters, posture parameters and gravity torque of the second robotic arm joint; calculating the excitation signal corresponding to the second robotic arm joint according to the speed parameters, posture parameters and gravity torque of the working component joint.
[0139] Then, the first excitation signal corresponding to the mechanical device can be obtained according to the excitation signal corresponding to the first mechanical arm joint, the excitation signal corresponding to the second mechanical arm joint and the excitation signal corresponding to the working component joint. That is, the first excitation signal includes the excitation signals corresponding to the joints of each component.
[0140] In the embodiment of the present application, the second excitation signal may include feedback excitation signals corresponding to the joints of each component obtained by processing the target feedback controller.
[0141] In some embodiments, the step of “determining the second excitation signal corresponding to the mechanical device according to the current state information” may include the following operations:
[0142] Input the velocity parameters of the component joints into the target feedback controller;
[0143] The velocity parameters of the component joints are processed respectively by the target feedback controller to obtain the feedback excitation signals corresponding to the component joints;
[0144] Based on the feedback excitation signal corresponding to the component joint, a second excitation signal is obtained.
[0145] In the embodiment of the present application, the target feedback controller can be used to calculate the feedback excitation signal corresponding to each component joint according to the input velocity parameters of each component joint. That is, the input of the target feedback controller is: the velocity parameters of each component joint; the output is: the feedback excitation signal corresponding to each component joint.
[0146] Among them, the feedback controller is a form of controller designed by feedback control. The feedback controller can work automatically, and after comparing the controlled variable value with the reference variable value, it changes the controlled variable to reduce the difference between the two. Feedback control can be used to adjust the input signal of the system according to the difference between the measured output signal and the expected reference signal. By constantly comparing the error between the actual output and the expected output, and correcting the error as an input signal, feedback control can make the system more stable and accurate to achieve the desired goal.
[0147] Specifically, the working mechanism of the feedback controller may include: Error detection: Compare the actual output value with the expected output value through a sensor or measuring device to calculate the error signal; Controller design: Design a controller to adjust the input signal of the system based on the error signal. The controller can be a simple proportional controller, integral controller, differential controller, or a more complex PID (Proportional-Integral-Derivative) controller; Feedback loop: Add the output of the controller as an input signal to the system to form a feedback loop. In the feedback loop, the output of the system is fed back for comparison, and the input signal is corrected based on the error signal.
[0148] In some embodiments, before the step of “inputting the velocity parameters of the component joints into the target feedback controller”, the method may further include the following operations:
[0149] Obtaining a standard excitation signal;
[0150] Control the component joints to execute motion through standard excitation signals to obtain the actual motion speed of the component joints;
[0151] Based on the difference between the actual movement speed of the component joint and the preset movement speed, the parameters of the feedback controller are adjusted to obtain the target feedback controller.
[0152] Among them, the standard excitation signal is a signal commonly used in control theory, which is specified by artificial rules. The standard excitation signal can be a sinusoidal signal and a step signal. The sinusoidal signal refers to a signal in which the joint velocity command changes sinusoidally over time.
[0153] Specifically, for each component joint in the mechanical equipment, a standard excitation signal (preferably a sinusoidal signal and a step signal) is input, and then the actual movement speed of each component joint under the control of the target feedforward model + feedback controller is observed. The parameters of the target feedforward model are fixed and unchanged, and the parameters of the feedback controller are adjusted until the actual movement speed of each component joint meets the use requirements.
[0154] Among them, the actual movement speed of each component joint meets the use requirements, which refers to the degree of compliance between the actual movement speed of the component joint and the joint speed command (that is, the preset movement speed). If the actual movement speed and the preset movement speed are adjusted to completely overlap, it is optimal. The difference between the actual movement speed and the preset movement speed can be used to measure the degree of compliance of the actual movement speed.
[0155] Among them, the speed parameters of the joints of each component are processed respectively by the target feedback controller to obtain the feedback excitation signal corresponding to the joints of each component, which can include: calculating the feedback excitation signal of the first robotic arm joint according to the speed parameters of the first robotic arm joint by the target feedback controller; calculating the feedback excitation signal of the second robotic arm joint according to the speed parameters of the second robotic arm joint; calculating the feedback excitation signal of the working component joint according to the speed parameters of the working component joint.
[0156] Then, the second excitation signal corresponding to the mechanical device can be obtained according to the feedback excitation signal corresponding to the first mechanical arm joint, the feedback excitation signal corresponding to the second mechanical arm joint and the feedback excitation signal corresponding to the working component joint. That is, the second excitation signal includes the feedback excitation signal corresponding to each component joint.
[0157] 104. Determine a target excitation signal based on the first excitation signal and the second excitation signal.
[0158] The target excitation signal may be obtained by superimposing the first excitation signal and the second excitation signal.
[0159] In some embodiments, the step of “determining a target excitation signal based on the first excitation signal and the second excitation signal” may include the following operations:
[0160] The excitation signal corresponding to the component joint is superimposed with the feedback excitation signal to obtain a total excitation signal corresponding to the component joint;
[0161] Based on the total excitation signal corresponding to the component joint, the target excitation signal is obtained.
[0162] For example, the excitation signal corresponding to the first robot joint can be The excitation signal corresponding to the second robot arm joint can be The excitation signal corresponding to the joint of the working part can be The feedback excitation signal corresponding to the first robot arm joint can be The feedback excitation signal corresponding to the second robot arm joint can be The feedback excitation signal corresponding to the working component joint can be
[0163] Furthermore, the total excitation signal corresponding to the first robot arm joint can be calculated as:
[0164] The total excitation signal corresponding to the second robot arm joint can be calculated as:
[0165] The total excitation signal corresponding to the joint of the working part can be calculated as:
[0166] Then, according to the total excitation signal corresponding to the component joint, the target excitation signal is obtained, that is, the target excitation signal includes the total excitation signal corresponding to the component joint.
[0167] 105. Control the mechanical device to perform movement based on the target excitation signal.
[0168] In some embodiments, the step of “controlling the mechanical device to perform movement based on the target excitation signal” may include the following operations:
[0169] Send the total excitation signal corresponding to the component joint to the underlying control device of the mechanical equipment;
[0170] The movements of the component joints are controlled separately through the bottom control device according to the total excitation signal corresponding to the component joints.
[0171] Among them, the underlying control device of the mechanical equipment may at least include a solenoid valve.
[0172] For example, the total excitation signal of each component is sent to the solenoid valve, and the excitation signal of the solenoid valve is adjusted according to the total excitation signal, thereby controlling the movement of the joints of each component.
[0173] The embodiment of the present application discloses a control method for mechanical equipment, which includes: obtaining dynamic parameters and current state information of the mechanical equipment; determining the dynamic compensation torque of the mechanical equipment based on the dynamic parameters and the current state information; determining a first excitation signal corresponding to the mechanical equipment according to the current state information and the dynamic compensation torque, and determining a second excitation signal corresponding to the mechanical equipment according to the current state information; determining a target excitation signal based on the first excitation signal and the second excitation signal; and controlling the mechanical equipment to perform movement based on the target excitation signal. In this way, the task execution efficiency of the loader can be improved.
[0174] In order to facilitate better implementation of the control method of the mechanical equipment provided in the embodiment of the present application, the embodiment of the present application also provides a control device for the mechanical equipment based on the control method of the mechanical equipment. The meanings of the terms are the same as those in the control method of the mechanical equipment, and the specific implementation details can refer to the description in the method embodiment.
[0175] See also Figure 4 , Figure 4 A structural block diagram of a control device for a mechanical device provided in an embodiment of the present application, which is applied to a server, includes:
[0176] The first acquisition unit 301 is used to acquire the dynamic parameters and current state information of the mechanical equipment;
[0177] A first determining unit 302, configured to determine a dynamic compensation torque of the mechanical device based on the dynamic parameter and the current state information;
[0178] A second determination unit 303 is used to determine a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and to determine a second excitation signal corresponding to the mechanical device according to the current state information;
[0179] A third determination unit 304 is configured to determine a target excitation signal based on the first excitation signal and the second excitation signal;
[0180] The first control unit 305 is configured to control the mechanical device to perform movement based on the target excitation signal.
[0181] In some embodiments, the dynamic parameters include at least a mass parameter and a position parameter of at least one target component in the mechanical device, and a distance parameter corresponding to a component joint of the target component; the current state information includes at least a posture parameter of the component joint;
[0182] The first determining unit 302 may include:
[0183] The first calculation subunit is used to calculate the gravity torque acting on the component joint according to the mass parameter, the position parameter, the distance parameter and the posture parameter as the dynamic compensation torque of the mechanical device.
[0184] In some embodiments, the at least one target component includes a first mechanical arm, a second mechanical arm and a working component, and the component joint includes a first mechanical arm joint, a second mechanical arm joint and a working component joint, wherein the first mechanical arm joint is used to connect the body of the mechanical device and the first mechanical arm, the second mechanical arm joint is used to connect the first mechanical arm and the second mechanical arm, and the working component joint is used to connect the second mechanical arm and the working component;
[0185] The first computing subunit can be specifically used for:
[0186] Based on the posture parameters and corresponding distance parameters of the joints of each component, and the position parameters of each target component, a first transformation matrix from the first robotic arm joint to the center of gravity of the first robotic arm, a second transformation matrix from the first robotic arm joint to the center of gravity of the second robotic arm, and a third transformation matrix from the first robotic arm joint to the center of gravity of the working component are calculated;
[0187] Based on the first transformation matrix, the second transformation matrix, the third transformation matrix, and the mass parameters of each target component, calculate the gravity torque exerted on the joint of the first robotic arm;
[0188] Based on the second transformation matrix, the third transformation matrix, the mass parameter of the second robotic arm, and the mass parameter of the working component, calculate the gravity torque on the joint of the second robotic arm;
[0189] Based on the third transformation matrix and the mass parameter of the working component, the gravity torque acting on the joint of the working component is calculated.
[0190] In some embodiments, the current state information also includes speed parameters of component joints;
[0191] The second determining unit 303 may include:
[0192] A first input subunit is used to input velocity parameters and posture parameters of component joints and gravity torques acting on component joints into a target feedforward model;
[0193] A first processing subunit is used to process the velocity parameters, posture parameters, and gravity torque of the component joints respectively through the target feedforward model to obtain an excitation signal corresponding to the component joints;
[0194] The first determination subunit is used to obtain the first excitation signal based on the excitation signal corresponding to the component joint.
[0195] In some embodiments, the apparatus may further include:
[0196] A second acquisition unit is used to acquire a plurality of training sample pairs, each of which includes a sample excitation signal and a sample state information, wherein the sample state information is state information obtained after the component joint of the mechanical device is controlled to perform movement based on the sample excitation signal;
[0197] A construction unit is used to construct the target feedforward model based on the sample excitation signals and sample state information in the multiple training sample pairs.
[0198] In some embodiments, a building block may include:
[0199] A second calculation subunit, configured to calculate a sample compensation torque corresponding to the sample state information according to the sample state information and the dynamic parameters;
[0200] A second input subunit, used for inputting the sample state information and the sample compensation torque into a preset feedforward model;
[0201] A second processing subunit, configured to process the sample state information and the sample compensation torque through the preset feedforward model to obtain an output excitation signal;
[0202] The adjustment subunit is used to adjust the model parameters of the preset feedforward model based on the difference between the sample excitation signal and the output excitation signal until the preset feedforward model converges to obtain the target feedforward model.
[0203] In some embodiments, the second determining unit 303 may include:
[0204] a third input subunit, for inputting velocity parameters of component joints into a target feedback controller;
[0205] A third processing subunit is used to process the velocity parameters of the component joints respectively through the target feedback controller to obtain feedback excitation signals corresponding to the component joints;
[0206] The second determination subunit is used to obtain the second excitation signal based on the feedback excitation signal corresponding to the component joint.
[0207] In some embodiments, the apparatus may further include:
[0208] A third acquisition unit, used for acquiring a standard excitation signal;
[0209] A second control unit, used for controlling the component joint to perform movement through the standard excitation signal to obtain an actual movement speed of the component joint;
[0210] The adjustment unit is used to adjust the parameters of the feedback controller based on the difference between the actual movement speed of the component joint and the preset movement speed to obtain the target feedback controller.
[0211] In some embodiments, the third determining unit 304 may include:
[0212] A superposition subunit is used to superimpose the excitation signal corresponding to the component joint with the feedback excitation signal to obtain a total excitation signal corresponding to the component joint;
[0213] The third determination subunit is used to obtain the target excitation signal based on the total excitation signal corresponding to the component joint.
[0214] In some embodiments, the first control unit 305 may include:
[0215] A sending subunit, used for sending the total excitation signal corresponding to the component joint to the bottom control device of the mechanical device;
[0216] The control subunit is used to control the movement of the component joints according to the total excitation signal corresponding to the component joints through the underlying control device.
[0217] The embodiment of the present application discloses a control device for a mechanical device, wherein a first acquisition unit 301 acquires dynamic parameters and current state information of the mechanical device; a first determination unit 302 determines the dynamic compensation torque of the mechanical device based on the dynamic parameters and the current state information; a second determination unit 303 determines a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determines a second excitation signal corresponding to the mechanical device according to the current state information; a third determination unit 304 determines a target excitation signal based on the first excitation signal and the second excitation signal; and a first control unit 305 controls the mechanical device to perform motion based on the target excitation signal. In this way, the performance of automatic control of the mechanical device can be improved.
[0218] Accordingly, the embodiment of the present application also provides a computer device, which may be a server. Figure 5 As shown, Figure 5A schematic diagram of the structure of a computer device provided in an embodiment of the present application. The computer device 800 includes a processor 801 having one or more processing cores, a memory 802 having one or more computer-readable storage media, and a computer program stored in the memory 802 and executable on the processor. The processor 801 is electrically connected to the memory 802. Those skilled in the art will appreciate that Figure 5 The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include Figure 5 More or fewer components, or combinations of certain components, or different arrangements of components may be shown.
[0219] The processor 801 is the control center of the computer device 800. It uses various interfaces and lines to connect various parts of the entire computer device 800, executes various functions of the computer device 800 and processes data by running or loading software programs and / or modules stored in the memory 802, and calling data stored in the memory 802, thereby monitoring the computer device 800 as a whole.
[0220] In the embodiment of the present application, the processor 801 in the computer device 800 will load instructions corresponding to the processes of one or more application programs into the memory 802 according to the following steps, and the processor 801 will run the application programs stored in the memory 802 to implement various functions:
[0221] Obtain the dynamic parameters and current status information of mechanical equipment;
[0222] Determine the dynamic compensation torque of the mechanical equipment based on the dynamic parameters and current state information;
[0223] Determine a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determine a second excitation signal corresponding to the mechanical device according to the current state information;
[0224] Determining a target excitation signal based on the first excitation signal and the second excitation signal;
[0225] The mechanical device is controlled to perform movement based on the target excitation signal.
[0226] The embodiment of the present application obtains the dynamic parameters and current state information of the mechanical device, determines the dynamic compensation torque of the mechanical device based on the dynamic parameters and the current state information, determines the first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determines the second excitation signal corresponding to the mechanical device according to the current state information, determines the target excitation signal based on the first excitation signal and the second excitation signal, and controls the mechanical device to perform movement based on the target excitation signal. In this way, the performance of the automatic control of the mechanical device can be improved.
[0227] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.
[0228] Optional, such as Figure 5 As shown, the computer device 800 further includes: a touch screen 803, a radio frequency circuit 804, an audio circuit 805, an input unit 806, and a power supply 807. The processor 801 is electrically connected to the touch screen 803, the radio frequency circuit 804, the audio circuit 805, the input unit 806, and the power supply 807, respectively. Those skilled in the art can understand that Figure 5 The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0229] The touch display screen 803 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch display screen 803 may include a display panel and a touch panel. Among them, the display panel may be used to display information input by the user or information provided to the user and various graphical user interfaces of the computer device, and these graphical user interfaces may be composed of graphics, guide information, icons, videos and any combination thereof. Optionally, the display panel may be configured in the form of a liquid crystal display (LCD, Liquid Crystal Display), an organic light emitting diode (OLED, Organic Light-EmittingDiode) and the like. The touch panel may be used to collect the user's touch operation on or near it (such as the user using any suitable object or attachment such as a finger, a stylus, etc. on the touch panel or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Optionally, the touch panel may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 801, and can receive the command sent by the processor 801 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 801 to determine the type of touch event, and then the processor 801 provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 803 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 803 can also be used as a part of the input unit 806 to realize the input function.
[0230] The radio frequency circuit 804 may be used to send and receive radio frequency signals, so as to establish wireless communication with a network device or other computer device through wireless communication, and to send and receive signals between the network device or other computer device.
[0231] The audio circuit 805 can be used to provide an audio interface between the user and the computer device through a speaker and a microphone. The audio circuit 805 can transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 805 and converted into audio data, and then the audio data is output to the processor 801 for processing, and then sent to another computer device through the radio frequency circuit 804, or the audio data is output to the memory 802 for further processing. The audio circuit 805 may also include an earphone jack to provide communication between an external headset and the computer device.
[0232] The input unit 806 may be used to receive input numbers, character information or user feature information (such as fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
[0233] The power supply 807 is used to supply power to various components of the computer device 800. Optionally, the power supply 807 can be logically connected to the processor 801 through a power management system, so that the power management system can manage charging, discharging, and power consumption. The power supply 807 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.
[0234] although Figure 5 Not shown, the computer device 800 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.
[0235] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0236] As can be seen from the above, the computer device provided in this embodiment can obtain the dynamic parameters and current state information of the mechanical device; determine the dynamic compensation torque of the mechanical device based on the dynamic parameters and the current state information; determine the first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determine the second excitation signal corresponding to the mechanical device according to the current state information; determine the target excitation signal based on the first excitation signal and the second excitation signal; and control the mechanical device to perform movement based on the target excitation signal.
[0237] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.
[0238] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of computer programs are stored, and the computer program can be loaded by a processor to execute the steps in any one of the control methods of a mechanical device provided in the embodiment of the present application. For example, the computer program can execute the following steps:
[0239] Obtain the dynamic parameters and current status information of mechanical equipment;
[0240] Determine the dynamic compensation torque of the mechanical equipment based on the dynamic parameters and current state information;
[0241] Determine a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determine a second excitation signal corresponding to the mechanical device according to the current state information;
[0242] Determining a target excitation signal based on the first excitation signal and the second excitation signal;
[0243] The mechanical device is controlled to perform movement based on the target excitation signal.
[0244] The embodiment of the present application obtains the dynamic parameters and current state information of the mechanical device, determines the dynamic compensation torque of the mechanical device based on the dynamic parameters and the current state information, determines the first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determines the second excitation signal corresponding to the mechanical device according to the current state information, determines the target excitation signal based on the first excitation signal and the second excitation signal, and controls the mechanical device to perform movement based on the target excitation signal. In this way, the performance of the automatic control of the mechanical device can be improved.
[0245] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.
[0246] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0247] Since the computer program stored in the storage medium can execute the steps in the control method of any mechanical device provided in the embodiments of the present application, the beneficial effects that can be achieved by the control method of any mechanical device provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.
[0248] The above is a detailed introduction to the control method, device, storage medium and computer equipment of a mechanical equipment provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A control method for mechanical equipment, It is characterized in that The method comprises: Obtain the dynamic parameters and current status information of mechanical equipment; Determining a dynamic compensation torque of the mechanical device based on the dynamic parameter and the current state information; Determining a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and determining a second excitation signal corresponding to the mechanical device according to the current state information; Determining a target excitation signal based on the first excitation signal and the second excitation signal; The mechanical device is controlled to perform movement based on the target excitation signal.
2. The method according to claim 1, It is characterized in that The dynamic parameters at least include mass parameters and position parameters of at least one target component in the mechanical device, and distance parameters corresponding to component joints of the target component; the current state information at least includes posture parameters of the component joints; The determining the dynamic compensation torque of the mechanical device based on the dynamic parameter and the current state information includes: The gravity torque acting on the component joint is calculated according to the mass parameter, the position parameter, the distance parameter and the posture parameter as the dynamic compensation torque of the mechanical device.
3. The method according to claim 2, It is characterized in that The at least one target component includes a first mechanical arm, a second mechanical arm and a working component, and the component joints include a first mechanical arm joint, a second mechanical arm joint and a working component joint, wherein the first mechanical arm joint is used to connect the body of the mechanical device and the first mechanical arm, the second mechanical arm joint is used to connect the first mechanical arm and the second mechanical arm, and the working component joint is used to connect the second mechanical arm and the working component; The step of calculating the gravity torque exerted on the component joint according to the mass parameter, the position parameter, the distance parameter and the posture parameter as the dynamic compensation torque of the mechanical device comprises: Based on the posture parameters and corresponding distance parameters of the joints of each component, and the position parameters of each target component, a first transformation matrix from the first robotic arm joint to the center of gravity of the first robotic arm, a second transformation matrix from the first robotic arm joint to the center of gravity of the second robotic arm, and a third transformation matrix from the first robotic arm joint to the center of gravity of the working component are calculated; Based on the first transformation matrix, the second transformation matrix, the third transformation matrix, and the mass parameters of each target component, calculate the gravity torque exerted on the joint of the first robotic arm; Based on the second transformation matrix, the third transformation matrix, the mass parameter of the second robotic arm, and the mass parameter of the working component, calculate the gravity torque on the joint of the second robotic arm; Based on the third transformation matrix and the mass parameter of the working component, the gravity torque acting on the joint of the working component is calculated.
4. The method according to claim 2, It is characterized in that The current state information also includes speed parameters of the component joints; The determining, according to the current state information and the dynamic compensation torque, a first excitation signal corresponding to the mechanical device includes: Inputting velocity parameters and posture parameters of the component joints and the gravity torque exerted on the component joints into a target feedforward model; The velocity parameters, posture parameters, and gravity torque of the component joints are processed respectively by the target feedforward model to obtain excitation signals corresponding to the component joints; The first excitation signal is obtained based on the excitation signal corresponding to the component joint.
5. The method according to claim 4, It is characterized in that Before inputting the velocity parameters and posture parameters of the component joints and the gravity torque exerted on the component joints into the target feedforward model, the method further includes: Acquire a plurality of training sample pairs, each training sample pair including a sample excitation signal and a sample state information, wherein the sample state information is state information obtained after the component joint of the mechanical device is controlled to perform movement based on the sample excitation signal; The target feedforward model is constructed based on the sample excitation signals and sample state information in the plurality of training sample pairs.
6. The method according to claim 5, It is characterized in that The constructing the target feedforward model based on the sample excitation signals and sample state information in the plurality of training sample pairs includes: Calculating a sample compensation torque corresponding to the sample state information according to the sample state information and the dynamic parameters; Inputting the sample state information and the sample compensation torque into a preset feedforward model; Processing the sample state information and the sample compensation torque by the preset feedforward model to obtain an output excitation signal; Based on the difference between the sample excitation signal and the output excitation signal, the model parameters of the preset feedforward model are adjusted until the preset feedforward model converges to obtain the target feedforward model.
7. The method according to claim 4, It is characterized in that The determining, according to the current state information, a second excitation signal corresponding to the mechanical device comprises: inputting velocity parameters of the component joints into a target feedback controller; The target feedback controller processes the velocity parameters of the component joints respectively to obtain feedback excitation signals corresponding to the component joints; The second excitation signal is obtained based on the feedback excitation signal corresponding to the component joint.
8. The method according to claim 7, It is characterized in that Before inputting the velocity parameters of the component joints into the target feedback controller, the method further comprises: Obtaining a standard excitation signal; Controlling the component joint to execute movement by the standard excitation signal to obtain the actual movement speed of the component joint; Based on the difference between the actual movement speed of the component joint and the preset movement speed, the parameters of the feedback controller are adjusted to obtain the target feedback controller.
9. The method according to claim 7, It is characterized in that The step of determining a target excitation signal based on the first excitation signal and the second excitation signal includes: Superimposing the excitation signal corresponding to the component joint and the feedback excitation signal to obtain a total excitation signal corresponding to the component joint; The target excitation signal is obtained based on the total excitation signal corresponding to the component joint.
10. The method according to claim 9, It is characterized in that The step of controlling the mechanical device to perform movement based on the target excitation signal comprises: Sending the total excitation signal corresponding to the component joint to the bottom-layer control device of the mechanical device; The movement of the component joints is controlled by the underlying control device according to the total excitation signal corresponding to the component joints.
11. A control device for mechanical equipment, It is characterized in that The device comprises: A first acquisition unit, used to acquire dynamic parameters and current state information of the mechanical equipment; A first determining unit, configured to determine a dynamic compensation torque of the mechanical device based on the dynamic parameter and the current state information; A second determination unit, configured to determine a first excitation signal corresponding to the mechanical device according to the current state information and the dynamic compensation torque, and to determine a second excitation signal corresponding to the mechanical device according to the current state information; A third determination unit, configured to determine a target excitation signal based on the first excitation signal and the second excitation signal; A first control unit is used to control the mechanical device to perform movement based on the target excitation signal.
12. A computer device comprising a memory, a processor and a computer program stored in the memory and running on the processor, in, When the processor executes the program, the control method of the mechanical equipment according to any one of claims 1 to 10 is implemented.
13. A storage medium, It is characterized in that The storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the control method of the mechanical equipment according to any one of claims 1 to 10.
Citation Information
Patent Citations
Mechanical arm friction identification method and device, apparatus and storage medium
CN107423515A
Force control joint control method and device, robot and readable storage medium
CN113954078A
Robot controller
WO1997010081A1
Swing control system for hybrid construction machine
WO2012081742A1
