Automatic deviation correction control method, system and equipment for drag chain cable and medium

Abstract

The invention discloses an automatic deviation rectification control method, system and device for a drag chain cable and a medium, and relates to the related field of deviation rectification control. The method comprises the steps that a connecting structure of the drag chain cable and a robot body is obtained; analyzing the connection structure to obtain a connection degree-of-freedom space of the drag chain cable; acquiring a distributed sensing device, sensing the real-time connection state of the drag chain cable according to the distributed sensing device, and determining a real-time sensing data set; performing deviation identification on the real-time sensing data set in the connection degree-of-freedom space to obtain a plurality of deviation indexes; the deviation indexes are input into a deviation correction control model, and deviation correction control parameters are obtained; and the control unit is connected with the rotation driving unit, the torque driving unit and the bending adjusting unit to control the deviation correction control parameters. The technical problems of insufficient control precision and low control efficiency of existing tow chain cable deviation rectification control are solved, and the technical effect of improving the precision and efficiency of deviation rectification control is achieved.

Description

Technical Field

[0001] The present application relates to the field of deviation correction control, and in particular to an automatic deviation correction control method, system, equipment and medium for a drag chain cable. Background Art

[0002] In the application scenario of external glass cleaning robots, the drag chain cable is an important component that connects the robot body with the power supply, control system or other necessary components. Its stability and reliability are crucial to ensure the efficiency of the cleaning operation. The robot obtains power and signals through the drag chain cable to perform cleaning tasks. However, since the robot needs to move and turn continuously during work, especially when cleaning large-area, complex-shaped surfaces such as glass curtain walls, the drag chain cable is easily affected by the external environment and deviates, resulting in poor contact with the robot body, which in turn affects the normal operation of the robot. In the existing technology, the deviation correction control of the drag chain cable depends on some basic mechanical limit devices or manual intervention. For example, some simple limit devices are used to limit the deviation range of the drag chain cable, or when the operator finds that the drag chain cable is deviated, it is manually adjusted. The manual intervention method is not only time-consuming and labor-intensive, but also unable to monitor and correct the deviation of the drag chain cable in real time, resulting in low cleaning efficiency. Simple mechanical limit devices can often only achieve rough limit, and cannot accurately control the degree of deviation of the drag chain cable, which is difficult to meet the needs of high-precision operations.

[0003] In the current related technologies, the deviation correction control of the drag chain cable has technical problems such as insufficient control accuracy and low control efficiency. Summary of the invention

[0004] The present application provides an automatic deviation correction control method, system, equipment and medium for a drag chain cable. The method obtains the connection structure between the drag chain cable and the robot body, analyzes the connection degree of freedom space (including rotational degree of freedom, torque degree of freedom and bending degree of freedom), uses a distributed sensing device to monitor the connection status of the drag chain cable in real time, and identifies deviations in the connection degree of freedom space, obtains multiple deviation indicators (rotational deviation, torque deviation and bending deviation), inputs the multiple deviation indicators into a deviation correction control model, obtains deviation correction control parameters, and controls the deviation correction control parameters by connecting a rotation drive unit, a torque drive unit and a bending adjustment unit, thereby achieving the technical effect of improving the accuracy and efficiency of the deviation correction control.

[0005] The present application provides an automatic deviation correction control method for a drag chain cable, comprising: obtaining a connection structure between the drag chain cable and a robot body; analyzing the connection structure to obtain a connection degree of freedom space of the drag chain cable, wherein the connection degree of freedom space is a rotatable degree of freedom space of the drag chain cable at the connection structure, including rotational degree of freedom, torque degree of freedom and bending degree of freedom; obtaining a distributed sensing device, sensing the real-time connection status of the drag chain cable according to the distributed sensing device, and determining a real-time sensing data set; performing deviation identification on the real-time sensing data set in the connection degree of freedom space, and obtaining multiple deviation indicators, including rotational deviation, torque deviation and bending deviation; inputting the multiple deviation indicators into a deviation correction control model to obtain deviation correction control parameters; connecting a rotation drive unit, a torque drive unit and a bending adjustment unit to control the deviation correction control parameters.

[0006] In a possible implementation, the connection structure is analyzed to obtain the connection degree of freedom space of the drag chain cable, and the following processing is performed: the working mode of the robot body is obtained, and the working mode includes a horizontal working mode and a vertical working mode; in the horizontal working mode, a connection test is performed on the connectivity between the drag chain cable and the robot body to obtain first connection test data; in the vertical working mode, a connection test is performed on the connectivity between the drag chain cable and the robot body to obtain second connection test data; a connection validity analysis is performed based on the first connection test data and the second connection test data to obtain a first connection degree of freedom space and a second connection degree of freedom space.

[0007] In a possible implementation, after acquiring the first connection degree of freedom space and the second connection degree of freedom space, the following processing is performed: identifying the real-time working mode of the robot body; if the real-time working mode is a horizontal working mode, using the first connection degree of freedom space to identify the deviation of the real-time sensing data set; if the real-time working mode is a vertical working mode, using the second connection degree of freedom space to identify the deviation of the real-time sensing data set.

[0008] In a possible implementation, a connection validity analysis is performed based on the first connection test data and the second connection test data to obtain a first connection degree of freedom space and a second connection degree of freedom space, and the following processing is performed: wherein the first connection test data and the second connection test data are signal transmission quality, power supply stability, and mechanical stress changes under different working modes; a preset validity threshold is obtained, including a signal transmission quality threshold, a power supply stability threshold, and a mechanical stress change threshold; a validity analysis is performed on the first connection test data based on the preset validity threshold to obtain a first connection degree of freedom space that meets the validity threshold; a validity analysis is performed on the second connection test data based on the preset validity threshold to obtain a second connection degree of freedom space that meets the validity threshold.

[0009] In a possible implementation, the multiple deviation indicators are input into a correction control model, correction control parameters are obtained, and the following processing is performed: input variables regarding the multiple deviation indicators are defined; control variables regarding the multiple deviation indicators are defined, wherein the control variables include rotation correction, torque correction, and bending correction; an initial model for correction control is established based on the input variables and the control variables, the initial model is trained until convergence, and the correction control model is output; the multiple deviation indicators input in real time are predicted based on the correction control model, and a response result of the correction control model is obtained by minimizing the total deviation value in the prediction time window, wherein the response result includes correction control parameters.

[0010] In a possible implementation, the initial model is trained until convergence, the deviation correction control model is output, and the following processing is performed: a collaborative factor matrix regarding the multiple deviation indicators is established; a collaborative influence feedback network is constructed according to the collaborative factor matrix, the collaborative influence feedback network and the initial model are feedback optimized, the optimized initial model is output, the optimized initial model is trained until convergence, and the deviation correction control model is output.

[0011] In a possible implementation, the response result of the deviation correction control model is obtained by minimizing the total deviation value of the prediction time window. The calculation expression is as follows: ; Where J is the total deviation value of the prediction time window, N is the length of the observation time window, that is, the total number of time steps, x(k+i) is the value of the input variable at time step k+i, u(k+i) is the value of the control variable at time step k+i, ║·║ 2 is the sum of the squares of the vector, k is the specific time step in the observation time window, i=1,2,3,..,N.

[0012] The present application also provides an automatic deviation correction control system for a drag chain cable, comprising: a connection structure acquisition module, used to obtain the connection structure between the drag chain cable and the robot body; a connection freedom space acquisition module, used to analyze the connection structure and obtain the connection freedom space of the drag chain cable, wherein the connection freedom space is the rotatable freedom space of the drag chain cable at the connection structure, including rotational freedom, torque freedom and bending freedom; a real-time connection status sensing module, used to obtain a distributed sensing device, sense the real-time connection status of the drag chain cable according to the distributed sensing device, and determine a real-time sensing data set; a deviation identification module, used to identify the deviation of the real-time sensing data set in the connection freedom space, and obtain multiple deviation indicators, including rotational deviation, torque deviation and bending deviation; a deviation correction control parameter acquisition module, used to input the multiple deviation indicators into a deviation correction control model to obtain deviation correction control parameters; a deviation correction control module, used to connect a rotation drive unit, a torque drive unit and a bending adjustment unit to control the deviation correction control parameters.

[0013] The present application also provides an electronic device, comprising: a memory for storing executable instructions; and a processor for implementing an automatic deviation correction control method for a drag chain cable when executing the executable instructions stored in the memory.

[0014] The present application also provides a computer-readable storage medium, including: a computer program stored thereon, and when the program is executed by a processor, an automatic deviation correction control method for a drag chain cable is implemented.

[0015] The present application proposes an automatic deviation correction control method, system, device and medium for a drag chain cable. First, the connection structure between the drag chain cable and the robot body is obtained, and then the connection structure is analyzed to obtain the connection degree of freedom space of the drag chain cable, wherein the connection degree of freedom space is the rotatable degree of freedom space of the drag chain cable at the connection structure, including rotational degree of freedom, torque degree of freedom and bending degree of freedom. Then, a distributed sensing device is obtained, and the real-time connection status of the drag chain cable is sensed according to the distributed sensing device to determine the real-time sensing data set. Then, deviation identification is performed on the real-time sensing data set in the connection degree of freedom space to obtain multiple deviation indicators, including rotational deviation, torque deviation and bending deviation. Then, the multiple deviation indicators are input into the deviation correction control model to obtain the deviation correction control parameters. Finally, the rotation drive unit, the torque drive unit and the bending adjustment unit are connected to control the deviation correction control parameters, thereby achieving the technical effect of improving the accuracy and efficiency of the deviation correction control. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0017] Figure 1 A schematic flow chart of an automatic deviation correction control method for a drag chain cable provided in an embodiment of the present application.

[0018] Figure 2 A schematic structural diagram of an automatic deviation correction control system for a drag chain cable provided in an embodiment of the present application.

[0019] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0020] Explanation of the accompanying drawings: connection structure acquisition module 10, connection degree of freedom space acquisition module 20, real-time connection status sensing module 30, deviation identification module 40, correction control parameter acquisition module 50, correction control module 60, input device 301, processor 302, memory 303, output device 304. DETAILED DESCRIPTION

[0021] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0022] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0023] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0024] The present application embodiment provides a method for automatically correcting the deviation of a towline cable. Figure 1 As shown, the method includes: Step S100, obtaining the connection structure between the drag chain cable and the robot body.

[0025] Specifically, use 3D scanning technology (technology that measures objects in three dimensions by means of laser or grating) or CAD (computer-aided design) model to obtain the connection structure between the drag chain cable and the robot body. First, perform a 3D scan of the connection between the drag chain cable and the robot body or access its CAD model. Then, import this data into the software for processing and analysis.

[0026] Step S200, analyzing the connection structure to obtain the connection freedom space of the drag chain cable, wherein the connection freedom space is the rotatable freedom space of the drag chain cable at the connection structure, including rotational freedom, torque freedom and bending freedom.

[0027] Specifically, use finite element analysis (FEA) or kinematic analysis software to analyze the connection structure and determine the connection freedom space of the drag chain cable (the range of freedom of the drag chain cable to rotate, twist and bend at the connection structure). In the software, set the boundary conditions and loads according to the geometry and material properties of the connection structure. Then, run the analysis to obtain the rotational freedom space of the drag chain cable at the connection structure, including rotational freedom, torque freedom and bending freedom. Among them, the rotational freedom refers to the ability of the drag chain cable to rotate around a certain axis; the torque freedom refers to the tendency or ability of the drag chain cable to rotate around a certain axis when subjected to torque; the bending freedom refers to the ability of the drag chain cable to bend and deform when subjected to bending force.

[0028] In a possible implementation, the connection structure is analyzed to obtain the connection freedom space of the drag chain cable, and step S200 further includes step S210, obtaining the working mode of the robot body, and the working mode includes a horizontal working mode and a vertical working mode. Specifically, the working mode of the robot body is obtained by reading the working mode information stored in the control unit of the robot body, or by sending a query request to the control unit. For example, when cleaning the floor, the robot is in a horizontal working mode; when cleaning the wall or glass window, it switches to a vertical working mode.

[0029] Step S220, performing a connection test on the connectivity between the drag chain cable and the robot body in the horizontal working mode, and acquiring first connection test data. Specifically, when the robot is in the horizontal working mode, start the test device or sensor, test the connectivity between the drag chain cable and the robot body in the horizontal working mode, and record the data of the drag chain cable in different operating states, such as the tension change of the cable when the robot moves, the torsion angle when turning, etc.

[0030] Step S230, in the vertical working mode, a connection test is performed on the connectivity between the drag chain cable and the robot body to obtain second connection test data. Specifically, it is similar to step S220, but the test is performed in the vertical working mode. After the robot switches to the vertical working mode, the test process in step S220 is repeated to record the data of the drag chain cable in different operating states, including the additional tension, torsion and bending generated in the vertical direction.

[0031] Step S240, performing connection validity analysis according to the first connection test data and the second connection test data, and obtaining the first connection degree of freedom space and the second connection degree of freedom space. Specifically, using data analysis software or algorithm, the test data collected in steps S220 and S230 are processed and analyzed to determine the effective degree of freedom space of the connection between the drag chain cable and the robot body in different working modes. First, the test data under the two working modes are compared to identify the connectivity differences caused by changes in the direction of gravity or other physical factors. Then, based on these data, the rotatable degree of freedom space (including rotational degree of freedom, torque degree of freedom and bending degree of freedom) of the drag chain cable at the connection structure is calculated, and these spaces define the degree to which the cable can deviate without affecting the connection performance. Since the glass sweeping robot needs to perform cleaning operations in both horizontal and vertical working modes, the physical stresses on the cable in these two modes are different. This implementation method accurately analyzes the movable range of the cable in different working modes by obtaining the first connection degree of freedom space and the second connection degree of freedom space, ensuring that the drag chain cable can maintain a stable connection with the robot body in different working modes.

[0032] In a possible implementation, after obtaining the first connection degree of freedom space and the second connection degree of freedom space, step S200 further includes step S250, identifying the real-time working mode of the robot body. Specifically, the current working mode of the robot is determined by reading sensor data on the robot body, such as horizontal or vertical position information provided by a position sensor, movement direction information provided by an acceleration sensor, etc. Alternatively, a query request is sent to the robot control system to obtain status information of the current working mode.

[0033] Step S260, if the real-time working mode is a horizontal working mode, the real-time sensing data set is identified for deviation using the first connection degree of freedom space; if the real-time working mode is a vertical working mode, the real-time sensing data set is identified for deviation using the second connection degree of freedom space. Specifically, after the real-time working mode is identified in step S250, the corresponding connection degree of freedom space is selected according to the mode for deviation identification. First, the real-time sensing data set obtained from the distributed sensing device is preprocessed, such as denoising, filtering, etc., to improve the accuracy and reliability of the data. Then, according to the real-time working mode (horizontal or vertical), the corresponding connection degree of freedom space (first or second connection degree of freedom space) is selected. In this space, the preprocessed real-time sensing data set is identified for deviation (the degree of deviation of the drag chain cable from the ideal state), and deviation indicators such as rotation deviation, torque deviation and bending deviation are calculated. Finally, the calculated deviation index is output to the subsequent correction control model for further correction control. This implementation method selects the corresponding connection degree of freedom space for deviation identification according to the real-time working mode, ensuring that the correction control model can more accurately reflect the actual deviation of the cable, thereby taking more effective correction measures and improving the efficiency and stability of the cleaning operation.

[0034] In a possible implementation, the connection validity analysis is performed according to the first connection test data and the second connection test data, and the first connection degree of freedom space and the second connection degree of freedom space are obtained. Step S240 further includes step S241, wherein the first connection test data and the second connection test data are signal transmission quality, power supply stability and mechanical stress changes in different working modes. Specifically, a variety of test data of the drag chain cable are collected when the robot body is in different working modes (horizontal working mode and vertical working mode). These data include but are not limited to signal transmission quality, power supply stability and mechanical stress changes. Among them, the signal transmission quality refers to the stability and accuracy of the cable when transmitting data, which is evaluated by measuring the bit error rate, packet loss rate and other indicators of the cable when transmitting data. Power supply stability refers to the stability of the voltage and current of the cable during the power supply process, which is evaluated by monitoring the voltage fluctuation, current change and other parameters of the cable during the power supply process. Mechanical stress changes refer to the physical stress changes of the cable under different working modes, and the stress conditions of the cable under different working modes are monitored in real time by installing stress sensors on the cable.

[0035] Step S242, obtaining preset validity thresholds, including signal transmission quality thresholds, power supply stability thresholds, and mechanical stress change thresholds. Specifically, the preset validity thresholds are reasonable threshold ranges set according to industry standards, product specifications, or actual test experience. These thresholds can ensure that the drag chain cable can maintain stable connection performance in different working modes, and are used to evaluate the connection validity of the drag chain cable in different working modes. These thresholds include signal transmission quality thresholds, power supply stability thresholds, and mechanical stress change thresholds.

[0036] Step S243, perform validity analysis on the first connection test data according to the preset validity threshold, and obtain the first connection degree of freedom space that meets the validity threshold. Specifically, compare the collected first connection test data (data in the horizontal working mode) with the preset validity threshold to evaluate the connection validity of the cable in this working mode. Analyze each test indicator (such as signal transmission quality, power supply stability, mechanical stress change) one by one to determine whether it meets the preset threshold requirements. Based on the test data that meets the threshold requirements, determine the first connection degree of freedom space, that is, the range of degrees of freedom within which the cable can rotate, twist and bend in the horizontal working mode.

[0037] Step S244, analyze the validity of the second connection test data according to the preset validity threshold, and obtain the second connection degree of freedom space that meets the validity threshold. Specifically, similar to step S243, the collected second connection test data (data in the vertical working mode) is compared with the preset validity threshold to evaluate the connection validity of the cable in this working mode. Similarly, each test indicator is analyzed one by one to determine whether it meets the preset threshold requirement. According to the test data that meets the threshold requirement, the second connection degree of freedom space is determined, that is, the range of degrees of freedom in which the cable can rotate, twist and bend in the vertical working mode. This range is different from the range in the horizontal working mode, especially in terms of torque and bending degrees of freedom. This implementation method can accurately determine the connection degree of freedom space of the cable in different working modes by collecting and analyzing the test data in different working modes and evaluating it according to the preset validity threshold. In this way, in the subsequent deviation correction control process, accurate deviation identification and control can be performed according to the real-time working mode and the corresponding connection degree of freedom space, thereby improving the efficiency and stability of the cleaning operation.

[0038] Step S300, obtaining a distributed sensing device, sensing the real-time connection status of the drag chain cable according to the distributed sensing device, and determining a real-time sensing data set.

[0039] Specifically, distributed sensing devices such as strain sensors (sensors for measuring object strain, i.e., shape changes), angle sensors (sensors for measuring the rotation angle of an object), and torque sensors (sensors for measuring the torque applied to an object) are used to monitor the real-time connection status of the drag chain cable. The sensing devices are installed at key locations of the drag chain cable, such as connection points, bending areas, etc. Then, the data of these sensing devices are collected in real time through the data acquisition system to form a real-time sensing data set.

[0040] Step S400, performing deviation identification on the real-time sensing data set in the connection degree of freedom space, and obtaining a plurality of deviation indicators, including rotation deviation, torque deviation and bending deviation.

[0041] Specifically, data analysis methods are used to identify deviations in real-time sensing data sets. The real-time sensing data sets are compared with the preset benchmark data sets, and deviation indicators such as rotation deviation, torque deviation, and bending deviation are calculated to evaluate whether the connection state of the drag chain cable deviates from the connection degree of freedom space. Among them, rotation deviation refers to the difference between the actual rotation angle of the drag chain cable and the expected rotation angle. Torque deviation refers to the difference between the actual torque applied to the drag chain cable and the expected torque. Bending deviation refers to the difference between the actual bending degree of the drag chain cable and the expected bending degree.

[0042] Step S500: input the plurality of deviation indicators into a deviation correction control model to obtain deviation correction control parameters.

[0043] Specifically, a correction control model based on artificial intelligence or machine learning is used to process deviation indicators, and multiple deviation indicators are input into the correction control model. Then, the model calculates appropriate correction control parameters such as rotation angle adjustment, torque adjustment, and bending adjustment based on these inputs.

[0044] In a possible implementation, the multiple deviation indicators are input into the correction control model to obtain the correction control parameters, and step S500 further includes step S510, defining input variables about the multiple deviation indicators. Specifically, in the control system, input variables refer to those variables that can affect the system output or state, representing the real-time state of the drag chain cable at the connection structure, and are the basis of the correction control. The input variables are the rotation deviation, torque deviation and bending deviation of the drag chain cable.

[0045] Step S520, defining control variables for the multiple deviation indicators, wherein the control variables include rotation correction, torque correction and bending correction. Specifically, in a control system, control variables refer to variables that can be actively adjusted by the system to change the system output or state. Here, the control variables are rotation correction, torque correction and bending correction, which represent the force or torque that needs to be applied to the connection structure in order to correct the deviation state of the drag chain cable.

[0046] Step S530, based on the input variables and the control variables, an initial model for the deviation correction control is established, the initial model is trained until convergence, and the deviation correction control model is output. Specifically, a machine learning or deep learning method is used to establish an initial model based on the input variables and the control variables. Then, the model is trained using historical data or simulation data until the error between the model's predicted results and the actual results reaches an acceptable range (i.e., the model converges), and the deviation correction control model is obtained.

[0047] Step S540, predict the multiple deviation indicators input in real time according to the correction control model, and obtain the response result of the correction control model by minimizing the total deviation value in the prediction time window, and the response result includes the correction control parameters. Specifically, the multiple deviation indicators obtained in real time are input into the trained correction control model, and the model minimizes the total deviation value (the sum or weighted sum of all deviation indicators in the prediction time window) within the prediction time window (a time range set to predict the system state in the future) according to these input variables, and obtains the optimal correction control parameters (i.e., rotation correction, torque correction and bending correction). This implementation method uses machine learning or deep learning methods to establish a correction control model, making full use of the information in historical data and simulation data, and improving the prediction accuracy of the model.

[0048] In a possible implementation, the initial model is trained until convergence, and the deviation correction control model is output. Step S530 further includes step S531, establishing a synergy factor matrix about the multiple deviation indicators. Specifically, a large amount of data on the deviation of the drag chain cable is collected, and these data include deviation indicators under various conditions such as different working conditions, different speeds, and different loads. The correlation coefficients between the various deviation indicators are calculated using statistical methods, and these correlation coefficients reflect the linear relationship between them. Based on the calculated correlation coefficients, a synergy factor matrix is ​​constructed. Each row and column of this matrix corresponds to a deviation indicator, and the elements in the matrix are the correlation coefficients between these indicators. The synergy factor matrix reflects the mutual influence between different deviation indicators (rotational deviation, torque deviation, bending deviation).

[0049] Step S532, construct a collaborative influence feedback network according to the collaborative factor matrix, perform feedback optimization on the collaborative influence feedback network and the initial model, output the optimized initial model, train the optimized initial model until convergence, and output the deviation correction control model. Specifically, a deep neural network is designed, whose input layer corresponds to multiple deviation indicators, and the output layer corresponds to the deviation correction control parameters (such as rotation correction, torque correction, and bending correction). The neural network is trained using the collected data, and the training goal is to minimize the error between the network output (predicted deviation correction control parameters) and the actual value. During the training process, the collaborative factor matrix is ​​introduced as a feedback mechanism. Specifically, the prediction results of the network are combined with the collaborative factor matrix, the collaborative influence of the prediction results is calculated, and then this influence is fed back to the network as additional information for adjusting the weight and bias of the network. Finally, it is determined whether the network has converged. If the prediction error of the network has not decreased significantly in multiple consecutive training cycles, it is considered that the network has converged and the training is completed. This implementation method more accurately describes the complex relationships among multiple deviation indicators by constructing a synergistic factor matrix and a synergistic influence feedback network, and makes more precise predictions and controls based on these relationships, thereby improving the accuracy and robustness of the correction control model.

[0050] In a possible implementation, step S540 further includes step S541, obtaining a response result of the deviation correction control model by minimizing the total deviation value of the prediction time window, and the calculation expression is as follows: ; Where J is the total deviation value of the prediction time window, N is the length of the observation time window, that is, the total number of time steps, x(k+i) is the value of the input variable at time step k+i, u(k+i) is the value of the control variable at time step k+i, ║·║ 2 is the sum of the squares of the vector, k is the specific time step in the observation time window, i=1,2,3,..,N.

[0051] Specifically, the prediction time window is the time range used to predict the dynamic changes of the drag chain cable. Input variables refer to external factors that affect the dynamic changes of the drag chain cable, such as rotation deviation, torque deviation and bending deviation. Control variables refer to internal factors used to adjust the dynamic changes of the drag chain cable, such as rotation correction, torque correction and bending correction. The total deviation value is used to measure the effect of the correction control. An optimization algorithm (such as gradient descent method, genetic algorithm, etc.) is used to minimize the total deviation value within the prediction time window by continuously adjusting the value of the control variable. This optimization process requires multiple iterations until a set of control variable values ​​is found so that the total deviation value reaches an acceptable range or reaches the convergence condition. This implementation method ensures that the correction control parameters can accurately reflect the dynamic changes of the drag chain cable by minimizing the total deviation value within the prediction time window, and realizes precise adjustment of the drag chain cable, thereby realizing precise correction control of the drag chain cable.

[0052] Step S600, connecting the rotation driving unit, the torque driving unit and the bending adjustment unit to control the deviation correction control parameters.

[0053] Specifically, a driving device such as an electric motor, a hydraulic cylinder or a pneumatic cylinder is used to realize the rotation, torque and bending adjustment of the drag chain cable. According to the correction control parameters, the rotation drive unit, the torque drive unit and the bending adjustment unit are controlled to make corresponding adjustments to the drag chain cable. For example, if the rotation deviation is large, the rotation angle of the drag chain cable is adjusted by the rotation drive unit; if the torque deviation is large, the torque applied to the drag chain cable is adjusted by the torque drive unit by applying a reverse torque; if the bending deviation is large, the bending degree of the drag chain cable is adjusted by the bending adjustment unit. Among them, the rotation drive unit is a driving device for realizing the rotation of an object. The torque drive unit is a driving device for providing or adjusting the torque applied to an object. The bending adjustment unit is a device for adjusting the bending degree of an object. The embodiment of the present application adopts the method of obtaining the connection structure between the drag chain cable and the robot body, analyzing the connection degree of freedom space (including rotational degree of freedom, torque degree of freedom and bending degree of freedom), using a distributed sensing device to monitor the connection status of the drag chain cable in real time, and performing deviation identification in the connection degree of freedom space, obtaining multiple deviation indicators (rotational deviation, torque deviation and bending deviation), inputting the multiple deviation indicators into the correction control model, obtaining the correction control parameters, and controlling the correction control parameters by connecting the rotation drive unit, the torque drive unit and the bending adjustment unit, thereby achieving the technical effect of improving the accuracy and efficiency of the correction control.

[0054] In the above, refer to Figure 1 The automatic deviation correction control method of a drag chain cable according to an embodiment of the present invention is described in detail. Figure 2 An automatic deviation correction control system for a drag chain cable according to an embodiment of the present invention is described.

[0055] An automatic deviation correction control system for a drag chain cable according to an embodiment of the present invention is used to solve the technical problems of insufficient control accuracy and low control efficiency in the existing deviation correction control of drag chain cables, thereby achieving the technical effect of improving the accuracy and efficiency of deviation correction control. An automatic deviation correction control system for a drag chain cable includes: a connection structure acquisition module 10, a connection degree of freedom space acquisition module 20, a real-time connection status sensing module 30, a deviation identification module 40, a deviation correction control parameter acquisition module 50, and a deviation correction control module 60.

[0056] A connection structure acquisition module 10 is used to acquire the connection structure between the drag chain cable and the robot body; a connection freedom space acquisition module 20 is used to analyze the connection structure and acquire the connection freedom space of the drag chain cable, wherein the connection freedom space is the rotatable freedom space of the drag chain cable at the connection structure, including rotational freedom, torque freedom and bending freedom; a real-time connection status sensing module 30 is used to acquire a distributed sensing device, sense the real-time connection status of the drag chain cable according to the distributed sensing device, and determine a real-time sensing data set; a deviation identification module 40 is used to identify the deviation of the real-time sensing data set in the connection freedom space, and acquire multiple deviation indicators, including rotational deviation, torque deviation and bending deviation; a correction control parameter acquisition module 50 is used to input the multiple deviation indicators into a correction control model to acquire correction control parameters; a correction control module 60 is used to connect a rotation drive unit, a torque drive unit and a bending adjustment unit to control the correction control parameters.

[0057] The specific configuration of the connection degree of freedom space acquisition module 20 will be described in detail below. As described above, the connection structure is analyzed to obtain the connection degree of freedom space of the drag chain cable. The connection degree of freedom space acquisition module 20 may further include: a working mode acquisition unit for acquiring the working mode of the robot body, the working mode including a horizontal working mode and a vertical working mode; a connection test unit for performing a connection test on the connectivity between the drag chain cable and the robot body in the horizontal working mode to obtain the first connection test data, and performing a connection test on the connectivity between the drag chain cable and the robot body in the vertical working mode to obtain the second connection test data; a connection validity analysis unit for performing a connection validity analysis based on the first connection test data and the second connection test data to obtain the first connection degree of freedom space and the second connection degree of freedom space.

[0058] Among them, after acquiring the first connection degree of freedom space and the second connection degree of freedom space, the connection degree of freedom space acquisition module 20 may further include: a real-time working mode recognition unit for identifying the real-time working mode of the robot body; a deviation recognition unit for, if the real-time working mode is a horizontal working mode, using the first connection degree of freedom space to perform deviation recognition on the real-time sensing data set; if the real-time working mode is a vertical working mode, using the second connection degree of freedom space to perform deviation recognition on the real-time sensing data set.

[0059] Among them, a connection validity analysis is performed according to the first connection test data and the second connection test data to obtain a first connection degree of freedom space and a second connection degree of freedom space, and the connection validity analysis unit may further include: a connection test data acquisition subunit is used to acquire connection test data, wherein the first connection test data and the second connection test data are signal transmission quality, power supply stability and mechanical stress change under different working modes; a preset validity threshold acquisition subunit is used to acquire preset validity thresholds, including a signal transmission quality threshold, a power supply stability threshold and a mechanical stress change threshold; a validity analysis subunit is used to perform validity analysis on the first connection test data according to the preset validity threshold, and obtain the first connection degree of freedom space that meets the validity threshold, and perform validity analysis on the second connection test data according to the preset validity threshold, and obtain the second connection degree of freedom space that meets the validity threshold.

[0060] The specific configuration of the deviation correction control parameter acquisition module 50 will be described in detail below. As described above, the multiple deviation indicators are input into the deviation correction control model to obtain the deviation correction control parameters. The deviation correction control parameter acquisition module 50 may further include: an input variable definition unit for defining input variables about the multiple deviation indicators; a control variable definition unit for defining control variables about the multiple deviation indicators, wherein the control variables include rotation correction, torque correction and bending correction; a deviation correction control model output unit for establishing an initial model for deviation correction control according to the input variables and the control variables, training the initial model until convergence, and outputting the deviation correction control model; a response result acquisition unit for predicting the multiple deviation indicators input in real time according to the deviation correction control model, and obtaining the response result of the deviation correction control model by minimizing the total deviation value of the prediction time window, wherein the response result includes the deviation correction control parameters.

[0061] Among them, the initial model is trained until convergence, and the correction control model is output. The correction control model output unit may further include: a collaborative factor matrix establishment subunit is used to establish a collaborative factor matrix about the multiple deviation indicators; a feedback optimization subunit is used to construct a collaborative influence feedback network according to the collaborative factor matrix, feedback optimize the collaborative influence feedback network and the initial model, output the optimized initial model, train the optimized initial model until convergence, and output the correction control model.

[0062] Wherein, by minimizing the total deviation value of the prediction time window, the response result of the correction control model is obtained, and the response result obtaining unit may further include: a calculation expression construction subunit for constructing a calculation expression, and the calculation expression is as follows: ; Where J is the total deviation value of the prediction time window, N is the length of the observation time window, that is, the total number of time steps, x(k+i) is the value of the input variable at time step k+i, u(k+i) is the value of the control variable at time step k+i, ║·║ 2 is the sum of the squares of the vector, k is the specific time step in the observation time window, i=1,2,3,..,N.

[0063] An automatic deviation correction control system for a drag chain cable provided in an embodiment of the present invention can execute an automatic deviation correction control method for a drag chain cable provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0064] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0065] Based on the foregoing embodiments, the embodiments of the present application further provide an electronic device and a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of the electronic device, it can implement the method described in any of the foregoing embodiments.

[0066] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing an implementation of the present invention. Figure 3The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The electronic device is in the form of a general computing device, and its components may include but are not limited to an input device 301, a processor 302, a memory 303, and an output device 304. Among them, the processor 302 may be one or more; the memory 303 may include a computer-readable medium and at least one program product, and the program product has a set (at least one) of program modules, which are configured to perform the functions of each embodiment of the present application.

[0067] The memory 303 shown in the embodiment of the present invention may adopt any combination of one or more computer-readable media; the computer-readable storage medium may be but is not limited to infrared, semiconductor systems, devices or components, or any combination of the above, for storing software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the automatic deviation correction control method for a drag chain cable in the embodiment of the present invention. The processor 302 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 303, thereby realizing the above-mentioned automatic deviation correction control method for a drag chain cable.

[0068] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An automatic deviation correction control method for a drag chain cable, characterized in that: The method comprises: Obtain the connection structure between the drag chain cable and the robot body; Analyze the connection structure to obtain the connection degree of freedom space of the drag chain cable, wherein the connection degree of freedom space is the rotatable degree of freedom space of the drag chain cable at the connection structure, including rotational degree of freedom, torque degree of freedom and bending degree of freedom; Acquire a distributed sensing device, and sense the real-time connection status of the drag chain cable according to the distributed sensing device to determine a real-time sensing data set; Performing deviation identification on the real-time sensing data set in the connection degree of freedom space to obtain a plurality of deviation indicators, including rotation deviation, torque deviation and bending deviation; Inputting the plurality of deviation indicators into a deviation correction control model to obtain deviation correction control parameters; The rotation driving unit, the torque driving unit and the bending adjusting unit are connected to control the deviation correction control parameters.

2. The automatic deviation correction control method of a drag chain cable according to claim 1, characterized in that: The connection structure is analyzed to obtain the connection freedom space of the drag chain cable, the method comprising: Acquire a working mode of the robot body, wherein the working mode includes a horizontal working mode and a vertical working mode; Performing a connection test on the connectivity between the drag chain cable and the robot body in the horizontal working mode to obtain first connection test data; Performing a connection test on the connectivity between the drag chain cable and the robot body in the vertical working mode to obtain second connection test data; A connection validity analysis is performed according to the first connection test data and the second connection test data to obtain a first connection degree of freedom space and a second connection degree of freedom space.

3. The automatic deviation correction control method of a drag chain cable according to claim 2, characterized in that: After acquiring the first connection degree of freedom space and the second connection degree of freedom space, identifying the real-time working mode of the robot body; If the real-time working mode is a horizontal working mode, performing deviation identification on the real-time sensing data set in the first connection degree of freedom space; If the real-time working mode is a vertical working mode, deviation identification is performed on the real-time sensing data set in the second connection degree of freedom space.

4. The automatic deviation correction control method of a drag chain cable according to claim 2, characterized in that: Perform connection validity analysis based on the first connection test data and the second connection test data to obtain a first connection degree of freedom space and a second connection degree of freedom space. include: The first connection test data and the second connection test data are signal transmission quality, power supply stability and mechanical stress changes in different working modes; Obtaining preset validity thresholds, including a signal transmission quality threshold, a power supply stability threshold, and a mechanical stress change threshold; Performing validity analysis on the first connection test data according to the preset validity threshold, and acquiring a first connection degree of freedom space that satisfies the validity threshold; The second connection test data is analyzed for validity according to the preset validity threshold to obtain a second connection degree of freedom space that meets the validity threshold.

5. The automatic deviation correction control method of a drag chain cable according to claim 1, characterized in that: Inputting the plurality of deviation indicators into a deviation correction control model to obtain deviation correction control parameters, the method comprising: defining input variables related to the plurality of deviation indicators; defining control variables related to the plurality of deviation indicators, wherein the control variables include a rotation correction, a torque correction, and a bending correction; Establishing an initial model for deviation correction control according to the input variables and the control variables, training the initial model until convergence, and outputting the deviation correction control model; The multiple deviation indicators input in real time are predicted according to the deviation correction control model, and the response result of the deviation correction control model is obtained by minimizing the total deviation value of the prediction time window, and the response result includes the deviation correction control parameter.

6. The automatic deviation correction control method of a drag chain cable according to claim 5, characterized in that: The initial model is trained until convergence, and the deviation correction control model is outputted. The method further includes: Establishing a synergy factor matrix regarding the plurality of deviation indicators; A collaborative influence feedback network is constructed according to the collaborative factor matrix, the collaborative influence feedback network and the initial model are feedback optimized, the optimized initial model is output, the optimized initial model is trained until convergence, and the deviation correction control model is output.

7. The automatic deviation correction control method of a drag chain cable according to claim 5, characterized in that: By minimizing the total deviation value of the prediction time window, the response result of the correction control model is obtained. The calculation expression is as follows: ； Where J is the total deviation value of the prediction time window, N is the length of the observation time window, that is, the total number of time steps, x(k+i) is the value of the input variable at time step k+i, u(k+i) is the value of the control variable at time step k+i, ║·║ 2 is the sum of the squares of the vector, k is the specific time step in the observation time window, i=1,2,3,..,N.

8. An automatic deviation correction control system for a drag chain cable, characterized in that: The system is used to implement the automatic deviation correction control method of a drag chain cable according to any one of claims 1 to 7, and the system comprises: A connection structure acquisition module is used to obtain the connection structure between the drag chain cable and the robot body; A connection freedom space acquisition module, used to analyze the connection structure and acquire the connection freedom space of the drag chain cable, wherein the connection freedom space is the rotatable freedom space of the drag chain cable at the connection structure, including rotational freedom, torque freedom and bending freedom; A real-time connection status sensing module, used to obtain a distributed sensing device, sense the real-time connection status of the drag chain cable according to the distributed sensing device, and determine a real-time sensing data set; A deviation identification module, used for performing deviation identification on the real-time sensing data set in the connection degree of freedom space, and obtaining a plurality of deviation indicators, including rotation deviation, torque deviation and bending deviation; A deviation correction control parameter acquisition module, used for inputting the plurality of deviation indicators into a deviation correction control model to acquire deviation correction control parameters; The deviation correction control module is used to connect the rotation drive unit, the torque drive unit and the bending adjustment unit to control the deviation correction control parameters.

9. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the automatic deviation correction control method of a drag chain cable as described in any one of claims 1 to 7 when executing the executable instructions stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, an automatic deviation correction control method for a drag chain cable as described in any one of claims 1 to 7 is implemented.

Images