Status Self-Check System of Hook-Detaching Robot

Abstract

The present application provides a status self-checking system for a hook-unhooking robot, which relates to the field of automated machinery technology and includes: a real-time acquisition module that acquires the real-time working data set of the hook-unhooking robot; an operation evaluation module that comprehensively evaluates the operation of the hook-unhooking robot based on the real-time working data set; a fault detection module that performs point cloud matching and data comparison on the hook-unhooking robot based on the operation status evaluation information, and performs fault detection according to the comparison result to generate a fault self-checking report; a fault tracing module that synchronizes the fault self-checking report to the human-machine interface for fault tracing; and a fault handling module that is used to formulate fault handling suggestions and send them to the human-machine interface to remotely control the hook-unhooking robot. The present application solves the technical problem in the prior art that due to insufficient fault detection accuracy, small or complex faults cannot be detected in time, affecting the operation stability of the robot, improves the fault detection accuracy and response speed, and enhances the operation reliability and safety.

Description

Technical Field

[0001] This application relates to the technical field of automated machinery, and specifically to a self-checking system for the status of a hook-unhooking robot. Background Art

[0002] In railway transportation and marshalling yard operations, hook-unhooking robots have become one of the key devices for achieving automated operations, capable of automatically completing hook-unhooking operations and improving production efficiency.

[0003] Currently, most hook-unhooking robots rely on single-sensor data for fault detection and lack comprehensive evaluation capabilities. This detection method is difficult to accurately identify minor mechanical deviations or complex multi-component collaborative faults. Especially in complex working conditions, such as when the coupler handle is deformed or the car body models are diverse, the detection accuracy and adaptability of the existing technology are significantly insufficient. In addition, after a fault occurs, manual on-site inspection and processing are required, which not only takes time and effort but also seriously affects the stability and production efficiency of the equipment. These problems have limited the application and promotion of hook-unhooking robots in complex environments to a certain extent. Summary of the Invention

[0004] This application provides a self-checking system for the status of a hook-unhooking robot, which solves the technical problem that the existing technology, due to relying on single-sensor data and having insufficient fault detection accuracy, cannot timely detect minor or complex faults, thereby affecting the running stability of the robot, and achieves the technical effects of improving the fault detection accuracy and response speed of the hook-unhooking robot and enhancing the running reliability and safety of the hook-unhooking robot.

[0005] In view of the above problems, this application provides a self-checking system for the status of a hook-unhooking robot, and the system includes:

[0006] A real-time acquisition module, used to sense multiple components of the hook-unhooking robot through a sensing unit to collect a real-time working data set of the hook-unhooking robot; an operation evaluation module, used to conduct a comprehensive operation evaluation of the hook-unhooking robot based on the real-time working data set to generate operation status evaluation information; a fault detection module, used to perform point cloud matching on the hook-unhooking robot based on the operation status evaluation information, conduct data comparison according to the point cloud matching result to generate a comparison deviation coefficient, and perform fault detection according to the comparison deviation coefficient to generate a fault self-check report; a fault tracing module, used to synchronize the fault self-check report to a human-machine interface for fault tracing to determine fault source data; a fault handling module, used to monitor the status of the hook-unhooking robot according to the fault source data, formulate fault handling suggestions, send the fault handling suggestions to the human-machine interface, and remotely control the hook-unhooking robot through the human-machine interface.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The real-time acquisition module traverses multiple components of the hook-unhooking robot through the sensing unit to collect real-time working data. Through refined acquisition at the component level, it can more precisely monitor each detail of the hook-unhooking robot during actual operation, providing basic data for the entire self-check system to ensure that fault detection and evaluation are based on accurate real-time information, thereby improving detection accuracy and data integrity. The operation evaluation module conducts a comprehensive operation evaluation on the hook-unhooking robot based on the real-time working data set, generates operation status evaluation information, and grasps the overall operation status of the robot from an overall perspective, providing a comprehensive reference basis for fault detection. The fault detection module performs point cloud matching and data comparison on the hook-unhooking robot based on the operation status evaluation information, accurately detects faults, and further converts the operation status evaluation information into specific fault detection results, enabling potential faults to be quantified and identified. The fault tracing module synchronizes the fault self-check report to the human-machine interface for fault tracing, deeply explores the root cause of the fault, determines the fault source data, helps to fundamentally understand the cause of the fault, and provides an accurate direction for subsequent fault handling. The fault handling module monitors the status of the hook-unhooking robot based on the fault tracing result, formulates corresponding fault handling suggestions, and also supports remote control of the robot through the human-machine interface to achieve intelligent fault response, enabling the self-check system not only to detect faults but also to provide solutions and remotely implement fault handling, reducing manual intervention and improving the availability and operation continuity of the hook-unhooking robot.

[0009] In summary, through the real-time acquisition module, this application comprehensively senses the operation status of the hook-unhooking robot. The operation evaluation module conducts comprehensive analysis and judgment. The fault detection module accurately locates faults. The fault tracing module quickly guides the operator to find the root cause of the fault. And the fault handling module provides solutions and supports remote operation, realizing the comprehensive monitoring and efficient maintenance of the hook-unhooking robot's status. This solution not only improves the accuracy and efficiency of fault detection but also significantly shortens the fault handling time through intelligent fault handling suggestions and remote control functions, enhancing the operation reliability and production efficiency of the hook-unhooking robot, enabling it to better adapt to production requirements in a complex industrial environment.

[0010] The above description is only an overview of the technical solution of this application. In order to be able to more clearly understand the technical means of this application, it can be implemented in accordance with the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. Brief Description of the Drawings

[0011] Figure 1 It is a schematic structural diagram of the status self-check system of the hook-unhooking robot provided by the embodiment of this application.

[0012] Figure 2It is a schematic flowchart of the process of incremental learning of the long-term status score and the short-term status score in the status self-check system of the hook-unhooking robot provided by the embodiments of the present application to generate a learning result.

[0013] Explanation of reference numerals: Real-time acquisition module 10, operation evaluation module 20, fault detection module 30, fault tracing module 40, fault handling module 50. Detailed implementation manners

[0014] By providing a status self-check system for the hook-unhooking robot in the embodiments of the present application, the technical problem in the prior art that due to relying on single sensor data and insufficient fault detection accuracy, it is impossible to timely detect minor or complex faults, thereby affecting the operation stability of the robot is solved, and the technical effects of improving the fault detection accuracy and response speed of the hook-unhooking robot and enhancing the operation reliability and safety of the hook-unhooking robot are achieved.

[0015] As Figure 1 shown, the embodiments of the present application provide a status self-check system for the hook-unhooking robot, and the system includes:

[0016] A real-time acquisition module 10, configured to sense through a sensing unit for multiple components of the hook-unhooking robot and acquire a real-time working data set of the hook-unhooking robot.

[0017] Specifically, the sensing unit is a device that can sense physical quantities (such as position, speed, force, etc.) and convert them into measurable signals, and usually includes a sensor and a signal conditioning circuit. The real-time working data set is a set containing the relevant working information of each component of the hook-unhooking robot at the current moment, such as the position coordinates of the robotic arm, the numerical value of the moving speed, the magnitude of the torque received, and other information.

[0018] The real-time acquisition module 10 realizes data acquisition by installing various sensing units on different components of the hook-unhooking robot. These sensing units will read data at regular time intervals or under specific triggering conditions. For example, for the robotic arm part, angle sensors may be installed at the joints, displacement sensors may be installed on the moving components, and force sensors may be installed on the driving devices. These sensors will continuously sense the state changes of the components, convert the physical quantities into electrical signals or digital signals, and then convert the signals into a form suitable for acquisition through a signal conditioning circuit (such as amplification, filtering, etc.), and finally be collected by a collection device (such as a data acquisition card) to form a real-time working data set.

[0019] Acquiring the real-time working data set of the hook-unhooking robot provides comprehensive and accurate operation data for the entire self-check system, which is the basis for subsequent modules to perform operations such as evaluation and detection.

[0020] The operation evaluation module 20 is used to comprehensively evaluate the operation of the unhooking robot based on the real-time working dataset and generate operation status evaluation information.

[0021] Specifically, the operation evaluation module 20 receives the real-time working dataset from the real-time acquisition module 10, classifies and organizes the data. For example, it classifies the position data, speed data, torque data, etc. of the robotic arm separately. Then, it analyzes these data according to the preset evaluation rules. These evaluation rules can be formulated based on the ideal operation model of the unhooking robot. For example, for the movement of the robotic arm, according to the design parameters of the robot, its movement trajectory should be within a certain spatial range and the speed should be within a reasonable interval. By comparing and comprehensively analyzing the actual data collected with these ideal values, the overall operation status of the unhooking robot is evaluated to generate operation status evaluation information. For example, it is judged whether the movement trajectory of the robotic arm meets the expectations based on the position and speed data of the robotic arm, and it is judged whether the mechanical structure is under abnormal pressure based on the torque data. This operation status evaluation information is a comprehensive description of the overall operation condition of the unhooking robot, including whether the collaborative work between the various components of the robot is normal and whether the overall performance is within the normal range, etc.

[0022] Through the comprehensive evaluation of the real-time working dataset, the operation status of the unhooking robot can be grasped as a whole, providing a preliminary judgment basis for subsequent fault detection.

[0023] The fault detection module 30 is used to perform point cloud matching on the unhooking robot based on the operation status evaluation information, perform data comparison according to the point cloud matching result to generate a comparison deviation coefficient, and perform fault detection according to the comparison deviation coefficient to generate a fault self-check report.

[0024] Specifically, the comparison deviation coefficient is a quantified value used to represent the degree of difference between the current data and the normal data. The fault self-check report is a report on whether there are faults in the unhooking robot and the fault-related information (such as the possible components where the fault occurs, the severity of the fault, etc.).

[0025] Based on the operation status evaluation information generated by the operation evaluation module 20, the fault detection module 30 performs point cloud matching. For the key components of the unhooking robot, a point cloud model in the normal operation state is established in advance. For example, the three-dimensional shape of the robotic arm during normal operation can be represented by a point cloud. Then, the component data in the currently collected operation state is converted into a point cloud form and matched with the pre-stored normal point cloud model. In the process of point cloud matching, algorithms such as the Iterative Closest Point (ICP) algorithm can be used. For example, the relative position between the current point cloud and the normal point cloud is continuously adjusted through the ICP algorithm to minimize the matching error. After the point cloud matching is completed, data comparison is performed according to the matching result. For example, the differences in parameters such as the distance and angle between the point clouds are compared to generate a comparison deviation coefficient. If this coefficient exceeds the pre-set threshold, it is determined that a fault exists, and finally a fault self-check report is generated, which includes information such as the components where the fault may occur and the type of the fault (such as structural deformation, abnormal movement, etc.).

[0026] Through precise point cloud matching and data comparison techniques, the fault situation of the unhooking robot can be accurately detected, and the operation status evaluation information can be further transformed into specific fault detection results, improving the accuracy of fault detection.

[0027] The fault tracing module 40 is used to synchronize the fault self-check report to the human-machine interface for fault tracing to determine the fault source data.

[0028] Specifically, the human-machine interface is an interface for operators to interact with the unhooking robot, which can be a combination of a display screen and operation buttons, or a touch screen, etc. The fault tracing module 40 synchronizes the fault self-check report to the human-machine interface. On the human-machine interface, the operator can view the detailed information in the fault self-check report. Then, the fault tracing module 40 will trace the fault source based on the fault-related information in the report and in combination with the structure and working principle of the unhooking robot. For example, if the fault self-check report shows that the movement trajectory of the robotic arm is abnormal, then the fault tracing module 40 will analyze factors such as the drive system, control system, and mechanical structure of the robotic arm, such as checking the working parameters of the drive motor, the command output of the control system, and the connection of the robotic arm joints. By gradually checking, it is determined which component or which link causes the fault, so as to determine the fault source data.

[0029] By displaying the fault self-check report on the human-machine interface and conducting traceability analysis, the root cause of the fault can be deeply explored, providing an accurate direction for subsequent fault handling.

[0030] The fault handling module 50 is used to monitor the status of the unhooking robot according to the fault source data, formulate fault handling suggestions, send the fault handling suggestions to the human-machine interface, and remotely control the unhooking robot through the human-machine interface.

[0031] Specifically, the fault handling module 50 monitors the status of the unhooking robot according to the fault source data and sets monitoring strategies for faulty components or fault-related parameters. For example, if the fault source is the wear of the robotic arm joint, then parameters such as the position and force of the joint will be monitored with emphasis. During the monitoring process, fault handling suggestions are formulated according to the specific situation of the fault. These fault handling suggestions are solutions and operation suggestions proposed for the fault situation. If the parameters of a certain component are abnormal, the handling suggestion can be to adjust the control parameters of the component; if a component is damaged, the handling suggestion can be to replace the component. Then the fault handling suggestions are sent to the human-machine interface, and the operator can remotely control the unhooking robot through the human-machine interface to perform fault handling operations.

[0032] Targeted status monitoring and handling suggestion formulation based on the fault source data, and remote control of the unhooking robot through the human-machine interface improve the efficiency and accuracy of fault handling.

[0033] Furthermore, the operation evaluation module 20 of the present application embodiment further includes:

[0034] A clustering analysis unit for traversing the real-time working data set for clustering analysis, determining a plurality of operation data, using the plurality of operation data as clustering centers to partition the real-time working data set, and generating a plurality of operation data clusters.

[0035] A long-term operation evaluation unit for identifying the coupler type of the unhooking robot and performing long-term operation evaluation on the plurality of operation data clusters according to the coupler type to generate a long-term status score.

[0036] A short-term operation evaluation unit for performing short-term operation evaluation on the plurality of operation data clusters according to the coupler type to generate a short-term status score.

[0037] A status verification unit for performing incremental learning on the long-term status score and the short-term status score to generate a learning result, and performing status verification based on the learning result to obtain a status verification token.

[0038] A reverse screening unit for performing reverse screening on the plurality of operation data clusters according to the status verification token to generate the operation status evaluation information.

[0039] Specifically, the clustering analysis unit first performs clustering analysis on the real-time working dataset, grouping similar data points in the dataset into one category. It traverses the entire real-time working dataset and determines multiple running data as clustering centers by calculating the similarity between data points (such as Euclidean distance, etc.). These clustering centers are representative data points in the dataset. Then, based on these clustering centers, the data in the real-time working dataset is divided into different categories, thereby generating multiple running data clusters. Exemplarily, K-means clustering, DBSCAN clustering algorithm, etc. can be used. Taking the K-means clustering algorithm as an example, K initial clustering centers are set (K is the number of clusters to be divided), and then the positions of these clustering centers are continuously adjusted until the convergence condition is met, thus obtaining multiple running data clusters. For example, when K = 3, running data clusters representing normal operation, low-speed operation, and high-speed operation states can be obtained. Through clustering analysis, the complex real-time working dataset is classified, enabling subsequent evaluations to be carried out for different types of data clusters, improving the pertinence and efficiency of the evaluations.

[0040] The long-term operation evaluation unit determines the coupler type by reading the configuration information of the uncoupling robot or identifying certain features of the coupler (such as the shape and connection method of the coupler), and extracts the running data clusters related to the current coupler type from the historical data for long-term operation evaluation, that is, evaluates and analyzes the running data of the uncoupling robot over a long period of time (such as the past few hours, days, or even weeks), analyzes the laws of running data such as the movement trajectory and force condition of the robotic arm during the long-term operation of the uncoupling robot, such as the average value and change trend of the data, and generates a long-term state score for each running data cluster according to the statistical characteristics of the long-term data (such as average value, standard deviation, etc.). This long-term state score reflects the state of all aspects of the uncoupling robot during long-term operation. In long-term operation evaluation, time series analysis methods can be used. For example, for the force data cluster of the coupler, an autoregressive moving average (ARMA) model is used to analyze the change trend of the force data over a long period of time, thereby generating a long-term state score for this data cluster.

[0041] The short-term operation evaluation unit extracts the recent operation data clusters related to the current coupler type from the real-time working dataset according to the coupler type for short-term operation evaluation. The short-term operation evaluation focuses on the operation data clusters related to the coupler within a relatively short period (such as a few minutes to a few hours). Similar to the long-term operation evaluation, by analyzing the data change rules in the data clusters, each operation data cluster is evaluated and a short-term status score is generated. In short-term operation evaluation, a sliding window algorithm can be used. For example, when analyzing the short-term manipulator movement speed data cluster, a relatively short time window (such as 10 minutes) is set, and statistics such as the average value and variance of the speed are calculated within this window, and then a short-term status score is generated based on these statistics. The short-term operation evaluation can timely reflect the operation status of the uncoupling robot within a short period. Combined with the long-term operation evaluation, it can more comprehensively evaluate the operation of the robot.

[0042] The status verification unit performs incremental learning on the long-term status score and the short-term status score. The long-term status score and the short-term status score are input into the incremental learning model to learn the relationship between the two. For example, the long-term force condition of the manipulator in the long-term status score and the recent force fluctuation condition in the short-term status score. Through the incremental learning algorithm, the association pattern between the two is learned to generate a learning result. Then, based on this learning result, status verification is performed. By comparing the learning result with a pre-set standard or model, for example, comparing the learned long-term and short-term relationships of the manipulator force with the model in the normal working state, a status verification token is generated. This status verification token is the result identifier for verifying whether the device operation status is normal, usually a binary value (normal or abnormal). Through incremental learning and status verification, the relationship between the long-term and short-term operation status scores can be better utilized to improve the accuracy of the operation status evaluation of the uncoupling robot and timely detect abnormal operation statuses.

[0043] The reverse screening unit performs reverse screening on multiple operation data clusters according to the status verification token, removes abnormal data clusters, and then aggregates the screened data clusters to generate the final operation status evaluation information. Through reverse screening, the data can be optimized according to the verification result of the operation status to generate the operation status evaluation information under the normal operation status, providing a more effective basis for subsequent fault detection and other operations.

[0044] Furthermore, as Figure 2 shown, the status verification unit is also used to perform the following steps:

[0045] Step 1: Based on the multiple operation data clusters, perform state feature analysis on the uncoupling robot to construct multiple operation feature vectors.

[0046] Step 2: Standardize and learn the long-term state score and the short-term state score according to the multiple operation feature vectors to generate multiple standard sample parameters, where the multiple standard sample parameters include long-term standard sample parameters and short-term standard sample parameters.

[0047] Step 3: Use stochastic gradient descent to adjust the parameters of the long-term standard sample parameters to generate a long-term training parameter set, and use stochastic gradient descent to adjust the parameters of the short-term standard sample parameters to generate a short-term training parameter set.

[0048] Step 4: Perform incremental learning on the long-term standard sample parameters according to the time series based on the long-term training parameter set to generate a long-term learning result, and perform incremental learning on the short-term standard sample parameters according to the time series based on the short-term training parameter set to generate a short-term learning result.

[0049] Step 5: Add the long-term learning result and the short-term learning result to the learning result.

[0050] Specifically, perform state feature analysis on multiple operation data clusters, and extract features that can reflect their operation states, such as the mean, variance, extreme value, change trend, etc. of the data. Taking the operation data cluster containing the manipulator movement speed data as an example, calculate features such as the average value, variance, maximum value, and minimum value of the speed. Then, combine these features in a certain order to form operation feature vectors. These operation feature vectors are used to represent the operation state features of the hook-unhooking robot in a certain aspect. By constructing operation feature vectors, complex operation data clusters can be represented in a concise and structured manner, facilitating subsequent learning and analysis operations, and providing an effective data representation form for standardized learning.

[0051] Standardize and learn the long-term state score and the short-term state score according to multiple operation feature vectors. First, standardize the long-term state score and the short-term state score according to the statistics related to the operation feature vectors (such as the mean and standard deviation of the features) (such as the z-score standardization formula) to obtain multiple standard sample parameters, including long-term standard sample parameters and short-term standard sample parameters. Through standardized learning, the long-term state score and the short-term state score are made comparable on the same scale.

[0052] For the long-term standard sample parameters, the random gradient descent algorithm is used to adjust the parameters. First, a loss function (such as the mean squared error loss function) is defined. Then, according to the update formula of the random gradient descent algorithm, in each iteration, the gradient of the loss function with respect to the long-term standard sample parameters is calculated, and the parameters are adjusted according to the update formula. After multiple iterations, a long-term training parameter set is generated. For the short-term standard sample parameters, the same method is used to generate a short-term training parameter set. By adjusting the standard sample parameters through the random gradient descent algorithm, the parameters can be optimized to better meet the actual operation state evaluation requirements, improve the effect of subsequent incremental learning, and thus more accurately reflect the long-term and short-term operation states of the uncoupling robot.

[0053] For the long-term training parameter set, the state verification unit performs incremental learning on the long-term standard sample parameters based on this parameter set according to the time series. At each time step, according to the existing learning results and the current standard sample parameters, an incremental learning algorithm (such as the incremental neural network algorithm) is used for learning. For example, in a neural network, the output is calculated based on the input long-term standard sample parameters and the existing long-term training parameter set, and then the long-term training parameter set is adjusted according to the difference between the output and the target value (such as the target value determined according to the long-term state score). After learning through the entire time series, a long-term learning result is generated. For the short-term training parameter set and the short-term standard sample parameters, the same method is used to generate a short-term learning result.

[0054] The long-term learning result and the short-term learning result are added to the previously generated learning results, integrating the operation state information at different time scales to form a more comprehensive learning result, providing a richer and more accurate basis for subsequent state verification.

[0055] Furthermore, the fault detection module 30 in the embodiment of the present application includes:

[0056] A point cloud data acquisition unit, which is used to activate the scanning unit to scan the uncoupling robot and draw a point cloud data set of the uncoupling robot.

[0057] A motion analysis unit, which is used to perform motion analysis on the uncoupling robot based on the point cloud data set and extract a three-dimensional motion trajectory.

[0058] A preset motion trajectory determination unit, which is used to map the operation state evaluation information to the point cloud data set for motion analysis to determine a preset motion trajectory.

[0059] A point cloud matching unit, which is used to match the three-dimensional motion trajectory with the preset motion trajectory according to the point cloud data set to generate a point cloud matching result.

[0060] A deviation identification unit is used to determine whether there is a deviation between the three-dimensional motion trajectory and the preset motion trajectory according to the point cloud matching result. If there is a deviation, a plurality of deviation points are determined, and a comparison deviation coefficient between the three-dimensional motion trajectory and the preset motion trajectory is calculated based on the plurality of deviation points.

[0061] Specifically, the scanning unit is a device or component for scanning the hook-unhooking robot to obtain information such as its surface shape and spatial position, such as a laser scanner. The point cloud data acquisition unit activates the scanning unit to start scanning the hook-unhooking robot to obtain the position information of each point on the surface of the hook-unhooking robot. For each scanning point of the hook-unhooking robot, the scanning unit records its three-dimensional coordinates (x, y, z) and possible other attributes (such as reflectivity, etc.). As the scanning progresses, the information of these points is continuously collected, and finally the point cloud data set of the hook-unhooking robot is drawn. The point cloud data set provides an accurate three-dimensional space data basis for subsequent motion analysis, trajectory comparison, etc. of the hook-unhooking robot, and can intuitively reflect the appearance shape and spatial position information of the hook-unhooking robot.

[0062] The motion analysis unit analyzes the motion process of the hook-unhooking robot based on the point cloud data set, including the analysis of aspects such as motion trajectory, speed, and acceleration. First, the point cloud data of consecutive frames is analyzed. For each point cloud data frame, the positions of various key points (such as joint points, end points, etc.) on the hook-unhooking robot are determined. Then, as time goes by, the positions of these key points are connected to extract the three-dimensional motion trajectory of the hook-unhooking robot. For example, if the robotic arm of the hook-unhooking robot is in motion, the three-dimensional motion trajectory of the end point of the robotic arm is constructed by analyzing the position changes of the end point of the robotic arm in different point cloud data frames. In the motion analysis process, an algorithm based on feature point matching can be used. By identifying feature points (such as corner points, edge points, etc.) in the point cloud data set and matching them between different frames, a continuous motion trajectory is constructed between the discrete point cloud data points by combining the interpolation algorithm.

[0063] The preset motion trajectory determination unit maps the operation state evaluation information to the point cloud data set for motion analysis. The operation state evaluation information includes the normal operation parameters of the hook-unhooking robot in different working modes, such as speed range, torque limit, etc. According to this information, combined with the point cloud data set, the structure and kinematic model of the hook-unhooking robot are analyzed. For example, if the operation state evaluation information indicates that the motion speed of the robotic arm should be between v1 and v2 in a certain working mode, and the structural information such as the length of the robotic arm is known, then according to the point cloud data set, the ideal motion path of the robotic arm under these speed limits is determined, so as to determine the preset motion trajectory, providing a standard reference for subsequent trajectory comparison.

[0064] The point cloud matching unit uses the Iterative Closest Point (ICP) algorithm to match the three-dimensional motion trajectory with the preset motion trajectory according to the point cloud data set. First, initial corresponding point pairs are selected, and then the transformation (such as translation, rotation, etc.) between the two point clouds is calculated to minimize the sum of the distances between the corresponding point pairs. This process is continuously iterated until the convergence condition is met, generating a point cloud matching result, including information such as the degree of matching and the corresponding relationship of the matching points. The point cloud matching result can accurately reflect the relationship between the three-dimensional motion trajectory and the preset motion trajectory, providing a direct basis for judging whether there is a deviation in the trajectory.

[0065] The deviation identification unit determines whether there is a deviation between the three-dimensional motion trajectory and the preset motion trajectory according to the point cloud matching result. If there is a deviation, the distances between the corresponding points in the point cloud data after matching are compared to determine multiple deviation points, that is, the positions of the points where there is a deviation. For example, if the coordinate of a certain point in the three-dimensional motion trajectory differs from the coordinate of the corresponding point in the preset motion trajectory by more than a certain threshold, it is determined as a deviation point. Then, based on these deviation points, methods such as mean square error (MSE) and maximum deviation calculation are used to quantify the overall error degree and calculate the comparison deviation coefficient between the three-dimensional motion trajectory and the preset motion trajectory. By calculating the comparison deviation coefficient, the deviation degree between the three-dimensional motion trajectory and the preset motion trajectory can be quantitatively described, providing a quantitative basis for judging whether there is a fault in the unhooking robot and the severity of the fault, and improving the accuracy of fault identification.

[0066] Furthermore, the fault detection module 30 in the embodiment of the present application further includes:

[0067] A judgment unit, configured to set a deviation critical value according to the preset motion trajectory and judge whether the comparison deviation coefficient is greater than the deviation critical value.

[0068] A detection unit, configured to generate a detection instruction when the comparison deviation coefficient is greater than the deviation critical value, and perform continuous fault detection on the unhooking robot through the detection instruction combined with the three-dimensional motion trajectory to generate a fault detection result.

[0069] An abnormal analysis unit, configured to perform abnormal analysis based on the fault detection result combined with the comparison deviation coefficient, identify the fault mode of the unhooking robot, and add the fault mode to the fault self-check report.

[0070] A troubleshooting unit, configured to generate a troubleshooting instruction when the comparison deviation coefficient is less than or equal to the deviation critical value, and perform continuous troubleshooting on the unhooking robot through the troubleshooting instruction combined with the three-dimensional motion trajectory to generate a fault troubleshooting result.

[0071] A status analysis unit, configured to perform status analysis based on the troubleshooting results in combination with the comparison deviation coefficient, identify the status type of the hook unhooking robot, and add the status type to the fault self-check report.

[0072] Specifically, the judgment unit sets a deviation critical value according to the characteristics of the preset motion trajectory and the normal operation requirements of the hook unhooking robot, which is used to measure the acceptable degree of the deviation between the three-dimensional motion trajectory and the preset motion trajectory. Then, the previously calculated comparison deviation coefficient is compared with this deviation critical value to determine whether the comparison deviation coefficient is greater than the deviation critical value.

[0073] When the comparison deviation coefficient is greater than the deviation critical value, the detection unit generates a detection instruction. This detection instruction includes the specific content to be detected, such as the detailed inspection requirements for components such as robotic arm joints and sensors. Then, according to the detection instruction and in combination with the three-dimensional motion trajectory, continuous fault detection is performed on the hook unhooking robot. For example, the detection instruction requires detecting the force condition during the movement of the robotic arm. Combining the position and speed information of the robotic arm in the three-dimensional motion trajectory, analyze which positions have abnormal forces. Through detection means such as sensor data acquisition and mechanical structure inspection, a fault detection result is generated, which includes the specific location of the fault (such as wear of a certain joint), the type of the fault (such as mechanical fault or electrical fault), etc., and can accurately determine whether there is a fault in the hook unhooking robot and the specific situation of the fault, providing an important basis for subsequent fault mode identification and repair.

[0074] The abnormality analysis unit performs abnormality analysis based on the fault detection result in combination with the comparison deviation coefficient. The comparison deviation coefficient can reflect the severity of the fault, and the fault detection result provides the specific information of the fault. A fault tree can be constructed according to the fault detection result, starting from the top event (such as abnormal movement of the robotic arm) and gradually analyzing to the basic event (such as joint wear) to identify the fault mode. For example, if the fault detection result shows that a certain joint of the robotic arm has abnormal movement and the comparison deviation coefficient is large, by analyzing the kinematic model, force condition, etc. of the robotic arm, the fault mode may be identified as a decrease in motion accuracy caused by joint wear. Then, the identified fault mode is added to the fault self-check report, enabling maintenance personnel to intuitively understand the fault situation of the hook unhooking robot.

[0075] When the comparison deviation coefficient is less than or equal to the deviation critical value, the troubleshooting unit generates a troubleshooting instruction. The troubleshooting instruction includes inspection requirements for some key components or operating parameters of the unhooking robot. Then, the unhooking robot is continuously troubleshot according to the troubleshooting instruction in combination with the three-dimensional motion trajectory. For example, the troubleshooting instruction may require checking the sensor accuracy of the robotic arm, and analyzing whether the sensor data is accurate by combining the motion data of the robotic arm in the three-dimensional motion trajectory. Through the troubleshooting operation, a troubleshooting result is finally generated, which may indicate whether there are potential fault hazards in the unhooking robot or whether the faults have been completely eliminated.

[0076] The status analysis unit performs status analysis based on the troubleshooting result in combination with the comparison deviation coefficient, and judges the status type according to pre-set rules (such as different ranges of the comparison deviation coefficient corresponding to different status types). If the troubleshooting result shows that there are no potential fault hazards in the unhooking robot and the comparison deviation coefficient is within the normal range, then the status type may be identified as the normal status. If there are some small deviations but they have not reached the fault level, it may be identified as the potential fault status. Then, the identified status type is added to the fault self-check report, enabling the operator to comprehensively understand the operating status of the unhooking robot. By identifying the status type through status analysis and adding it to the fault self-check report, it is convenient to monitor and manage the overall operating status of the unhooking robot.

[0077] Furthermore, the fault tracing module 40 in the embodiment of the present application further includes:

[0078] A fault mode extraction unit, configured to extract the fault mode of the unhooking robot based on the fault self-check report for data analysis, and obtain a fault self-check data set.

[0079] An evolution path construction unit, configured to synchronize the fault self-check data set to the human-machine interface for time evolution, and construct a fault evolution path.

[0080] A multi-dimensional correlation analysis unit, configured to perform multi-dimensional correlation analysis on the unhooking robot through the human-machine interface according to the fault evolution path, and generate a correlation decay factor.

[0081] A traceability positioning unit, configured to perform traceability positioning on the fault evolution path according to the correlation decay factor, and determine multiple fault source positioning information.

[0082] A fault source data determination unit, configured to add the multiple fault source positioning information to the fault source data.

[0083] Specifically, the fault mode extraction unit extracts key information from the fault self-check report, such as fault mode, comparison deviation coefficient, fault detection result, etc., and organizes the extracted data into a structured data set to obtain a fault self-check data set for subsequent analysis.

[0084] The fault evolution path describes the development and change of the fault mode over time, including the characteristics of each stage in the process of the fault from the initial state to the final state. The evolution path construction unit synchronizes the fault self-check data set to the human-machine interface, where the data is arranged and displayed in chronological order. For example, if the fault self-check data set contains data on the wear of the robotic arm joints at different time points, then on the human-machine interface, a curve will be plotted or a data table will be displayed with time as the horizontal axis and the wear degree, relevant working parameters, etc. as the vertical axis. In this way, the fault evolution path is constructed, intuitively presenting the development of the fault over time, such as whether the wear gradually intensifies or suddenly deteriorates, etc. The fault evolution path can clearly show the development process of the fault, helping to better understand the generation and development mechanism of the fault.

[0085] The multi-dimensional correlation analysis unit conducts multi-dimensional correlation analysis on the hook-unhooking robot on the human-machine interface according to the fault evolution path, analyzing the fault evolution path from multiple dimensions such as time, space, and different fault characteristics to find the correlation relationships between the dimensions. For example, analyzing the correlation relationship between the fault development speed and the working environment temperature of the robot from the time dimension, and analyzing the correlation relationship between the wear of different joints of the robotic arm from the space dimension, etc. By analyzing the mutual influence and variation law between the data of different dimensions, the correlation decay factor is calculated. The correlation decay factor is used to measure the correlation change in the fault development process, which can reflect the change of the correlation relationship between the dimensions in the fault development process and provide an important basis for fault traceability and location. Exemplarily, this correlation decay factor can be obtained by quantifying the change of the correlation coefficient (such as the Pearson correlation coefficient) between the data of different dimensions over time or other factors.

[0086] The traceability and location unit conducts traceability and location on the fault evolution path according to the correlation decay factor to determine the source location or the starting cause of the fault, that is, to find out where the fault initially occurred or what caused the fault to start. If the correlation decay factor shows that there is a significant change in the correlation relationship between two dimensions at a certain time point or in a certain working state (such as changing from a strong correlation to a weak correlation), then start in-depth analysis from this change point. For example, if the correlation between the wear degree of the robotic arm and the working load suddenly decays at a certain moment, further analyze the working conditions of the robotic arm, the load change situation, the surrounding environment, etc. before and after this moment, so as to determine multiple fault source location information, which may be the sudden damage of a certain component, the abnormal increase of the working load, etc. that caused the start of the fault. This process can be completed using a causal analysis algorithm, such as the Granger causality test algorithm, to judge the causal relationship between different factors to determine the fault source. Determining the fault source location information through traceability and location helps to fundamentally solve the fault problem of the hook-unhooking robot and improve the maintenance efficiency and the reliability of the robot.

[0087] The fault source data determination unit adds the determined fault source location information to the fault source data in a specific format (such as in the form of a data record). For example, if the fault source location information includes the name of the fault source (such as a certain sensor failure), the location of the fault source (such as at the joint of the robotic arm), the occurrence time of the fault source, etc., these information will be added to the fault source data according to a certain field structure, which is convenient for unified management and analysis of the fault source, and provides data support for subsequent fault prevention and improvement measures.

[0088] Through the above process, not only can the evolution process of the fault be intuitively displayed, but also the correlation between the fault and other factors can be clarified through multi-dimensional correlation analysis, and finally the root cause of the fault can be accurately located, providing clear guidance for subsequent fault handling, and significantly improving the efficiency and accuracy of fault handling.

[0089] Furthermore, the fault handling module 50 in the embodiment of the present application includes:

[0090] A fault risk assessment unit, configured to traverse multiple components of the unhooking robot according to the multiple fault source location information to perform a fault risk assessment, and generate multiple fault risk levels.

[0091] A fault sorting unit, configured to perform a priority sorting on the multiple fault source location information based on the multiple fault risk levels, and generate a fault to-be-processed sequence.

[0092] An operating state matching unit, configured to perform an operating state matching on the unhooking robot according to the fault to-be-processed sequence, and generate a fault state warning signal according to the matching result.

[0093] A state tracking unit, configured to retrieve historical maintenance records, perform state tracking according to the fault state warning signal, obtain fault state trend data, and formulate the fault handling suggestions for the unhooking robot based on the fault state trend data in combination with the historical maintenance records.

[0094] Specifically, the fault risk assessment unit traverses multiple relevant components of the unhooking robot according to the fault source location information, performs a risk assessment on each fault source, and considers the impact of the fault on the operation, safety and production of the unhooking robot. According to the assessment results, a fault risk level is assigned to each fault source. For example, it can be divided into three levels: low, medium, and high.

[0095] The fault sorting unit sorts multiple fault source location information according to the generated multiple fault risk levels. For example, using the bubble sort algorithm, starting from the first fault source location information, compare its fault risk level with the next one. If the risk level of the former is lower than that of the latter, swap their positions, and so on. After multiple rounds of comparison, the fault source location information with a high risk level can be ranked in the front, thus generating a fault to-be-processed sequence, which clarifies the order of fault handling. During the sorting process, if the risk levels of multiple fault source location information are the same, secondary sorting can also be performed according to other factors (such as the maintenance cost of the components involved in the fault source location information, and the one with a lower maintenance cost is processed first). Through priority sorting, the order of fault handling is clarified, and the efficiency of fault handling is improved.

[0096] The running state matching unit starts to match the running state of the unhooking robot according to the content in the fault to-be-processed sequence to check if there is a corresponding fault state. First, it is necessary to collect the current running state data of the unhooking robot, such as the temperature, movement speed, current and other parameters of each component. For example, if there is information about motor failure in the fault to-be-processed sequence, check whether the current of the motor is abnormal and whether the temperature is too high. A state monitoring system can be used to collect data, and then pattern recognition algorithms are used for matching. If the current of the motor exceeds the normal range and the temperature is also on the high side, it is determined that it matches the motor failure situation in the fault to-be-processed sequence, and a fault state alarm signal is generated according to this matching result. This signal can be a specific digital code (such as 1 indicating motor failure alarm) or an audible and visual signal (such as a red light flashing indicating a fault). Through running state matching, a fault state alarm signal is generated in a timely manner to remind the operator to handle the fault, thereby reducing the downtime and improving the fault response speed.

[0097] The status tracking unit retrieves historical maintenance records related to faults from the database, including fault handling history, repair time, maintenance content, etc. Then, based on the fault status alarm signal, it starts to track the status of the unhooking robot, generating fault status trend data, which reflects the development trend of the fault status over time, such as whether the fault parameters (temperature, pressure, etc.) of a certain component are rising or falling. For example, if the fault status alarm signal is that the temperature of a certain component is too high, it continuously monitors the temperature change of this component, records the temperature data every 5 minutes, and plots these data into a curve, which is the fault status trend data. According to the fault status trend data and historical maintenance records, fault handling suggestions are formulated. For example, if the fault status trend data shows that the fault of a certain component is developing gradually, and there are various methods to handle this fault in the historical maintenance records, such as repair, replacement of components, adjustment of working parameters, etc., then different fault handling suggestion schemes can be formulated. Then, according to the actual situation such as the current working requirements of the unhooking robot and maintenance resources, the most appropriate fault handling suggestion scheme is selected. Combining historical maintenance records and status tracking can formulate more reasonable fault handling suggestions, improve the efficiency of fault handling and the availability of the unhooking robot, and provide strong support for the stable operation of the unhooking robot.

[0098] Furthermore, the fault handling module 50 in the embodiment of the present application further includes:

[0099] A simulation execution unit, which is used to simulate and execute the fault handling suggestions for the unhooking robot and generate a fault handling report.

[0100] A real-time feedback unit, which is used to perform real-time feedback on the fault handling suggestions based on the fault handling report, update the fault handling suggestions, and generate fault handling optimization suggestions.

[0101] A fault visualization unit, which is used to send the fault handling optimization suggestions to the human-machine interface for fault visualization and generate a fault visualization interface.

[0102] A remote dynamic monitoring unit, which is used to execute the fault handling optimization suggestions through the fault visualization interface for remote dynamic monitoring and generate remote control commands.

[0103] A fault repair control unit, which is used to execute the remote control commands through the human-machine interface to perform fault repair control on the unhooking robot.

[0104] Specifically, the simulation execution unit creates a virtual environment similar to the actual hook-removing robot through simulation software (such as MATLAB / Simulink, V-REP), operates according to the fault handling suggestions in the simulation environment, records the results of the simulation execution, and generates a fault handling report. This fault handling report records the simulation execution results, including the processing process, expected effects, and potential problems. By simulating the execution of the fault handling suggestions for the hook-removing robot, the effectiveness of the handling suggestions can be pre-evaluated without actually affecting the normal operation of the robot (if it is still running) or avoiding unnecessary risks (such as avoiding more serious faults caused by incorrect handling), providing detailed reference information for subsequent optimization.

[0105] The real-time feedback unit analyzes the data in the report through data analysis algorithms. For example, if the fault handling report shows that the pressure of a certain component in the simulation execution exceeds the normal range after processing, it can be determined that there is a problem with the original fault handling suggestion. Data mining techniques can be used to extract key information from the report, and then the original fault handling suggestion can be modified based on this information. For example, if the original suggestion is to increase the power of a certain component, and the report shows that the increase in power has caused other problems, it can be adjusted to appropriately reduce the power and increase other auxiliary measures, thereby generating optimized fault handling suggestions. Through timely feedback and optimization, the accuracy and effectiveness of the fault handling suggestions can be improved, making the fault handling plan more scientific and reasonable, and reducing problems such as secondary faults that may occur during fault handling.

[0106] The fault visualization unit converts the data format of the optimized fault handling suggestions and displays them on the human-machine interface in the form of intuitive graphs, images, or visual interfaces for easy understanding by the operator. For example, if the optimization suggestions involve some complex parameter adjustments, these parameters can be represented in the form of charts or graphs. Graphics drawing tools (such as OpenGL, etc.) can be used to create visual elements, and various parts of the optimized fault handling suggestions (such as operation steps, components involved, etc.) can be combined in an intuitive way on the fault visualization interface to facilitate the operator to quickly understand the fault handling plan, improve the efficiency of fault handling, and reduce operation errors caused by understanding deviations.

[0107] The remote dynamic monitoring unit establishes a connection with the unhooking robot through a network communication protocol (such as the TCP / IP protocol), and then uses the fault visualization interface to execute the optimized suggestions for fault handling. During the execution process, remote dynamic monitoring is carried out, and sensors (such as temperature sensors, pressure sensors, etc.) are used to collect the operation data of the unhooking robot in real time, such as the force on the robotic arm, the temperature of the motor, etc. These data are transmitted through the network to the remote monitoring center, and the monitoring center uses data analysis software to analyze the data. If data anomalies are found (such as too high motor temperature), remote control commands are generated according to preset rules (such as reducing the motor power when the motor temperature exceeds 80°C).

[0108] In the human-machine interface of the fault repair control unit, after the operator confirms the remote control command, the human-machine interface sends the command to the control system of the unhooking robot through a communication link (such as industrial Ethernet, etc.) to achieve the fault repair control of the unhooking robot. In this process, a signal conversion device can be used to convert the digital command into an electrical signal suitable for the device to receive. By executing the remote control command through the human-machine interface, precise fault repair control of the unhooking robot is achieved, ensuring that the fault can be effectively handled and improving the availability and reliability of the equipment.

[0109] In summary, the state self-checking system of the unhooking robot provided by the embodiments of the present application has the following technical effects:

[0110] Generally speaking, through the real-time acquisition module 10 in the embodiments of the present application, the operation state of the unhooking robot is comprehensively sensed, the operation evaluation module 20 conducts comprehensive analysis and judgment, the fault detection module 30 accurately locates the fault, the fault tracing module 40 quickly guides the operator to find the root cause of the fault, and the fault handling module 50 provides solutions and supports remote operation, realizing the comprehensive monitoring and efficient maintenance of the state of the unhooking robot. This system not only improves the accuracy and efficiency of fault detection, but also significantly shortens the fault handling time through intelligent fault handling suggestions and remote control functions, improves the operation reliability and production efficiency of the unhooking robot, and enables it to better meet the production requirements in a complex industrial environment.

[0111] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. Self-check system for the state of a hook-unhooking robot, characterized in that The system includes: A real-time acquisition module, which is used to sense multiple components of the uncoupling robot through a sensing unit, and acquire a real-time working data set of the uncoupling robot; An operation evaluation module, which is used to comprehensively evaluate the operation of the uncoupling robot based on the real-time working data set, and generate operation status evaluation information; A fault detection module, which is used to perform point cloud matching on the uncoupling robot based on the operation status evaluation information, perform data comparison according to the point cloud matching result, generate a comparison deviation coefficient, and perform fault detection according to the comparison deviation coefficient to generate a fault self-check report; A fault tracing module, which is used to synchronize the fault self-check report to the human-machine interface for fault tracing to determine the fault source data; A fault handling module, which is used to monitor the status of the uncoupling robot according to the fault source data, formulate fault handling suggestions, send the fault handling suggestions to the human-machine interface, and remotely control the uncoupling robot through the human-machine interface; The operation evaluation module further includes: A clustering analysis unit, which is used to traverse the real-time working data set for clustering analysis, determine multiple operation data, use the multiple operation data as clustering centers to divide the real-time working data set, and generate multiple operation data clusters; A long-term operation evaluation unit, which is used to identify the coupler type of the uncoupling robot, and perform long-term operation evaluation on the multiple operation data clusters according to the coupler type to generate a long-term status score; A short-term operation evaluation unit, which is used to perform short-term operation evaluation on the multiple operation data clusters according to the coupler type to generate a short-term status score; A status verification unit, which is used to perform incremental learning on the long-term status score and the short-term status score to generate a learning result, and perform status verification based on the learning result to obtain a status verification token; A reverse screening unit, which is used to perform reverse screening on the multiple operation data clusters according to the status verification token to generate the operation status evaluation information.

2. The state self-checking system of the hook-unhooking robot according to claim 1, characterized in that, The status verification unit is further used to perform the following steps: Perform status feature analysis on the uncoupling robot based on the multiple operation data clusters to construct multiple operation feature vectors; Standardize and learn the long-term status score and the short-term status score according to the multiple operation feature vectors to generate multiple standard sample parameters, and the multiple standard sample parameters include long-term standard sample parameters and short-term standard sample parameters; Use stochastic gradient descent to adjust the parameters of the long-term standard sample parameters to generate a long-term training parameter set, and use stochastic gradient descent to adjust the parameters of the short-term standard sample parameters to generate a short-term training parameter set; Perform incremental learning on the long-term standard sample parameters according to the time series based on the long-term training parameter set to generate a long-term learning result, and perform incremental learning on the short-term standard sample parameters according to the time series based on the short-term training parameter set to generate a short-term learning result; Add the long-term learning result and the short-term learning result to the learning result.

3. The state self-checking system of the hook-unhooking robot according to claim 1, characterized in that, The fault detection module includes: A point cloud data acquisition unit, which is used to activate a scanning unit to scan the uncoupling robot and draw a point cloud data set of the uncoupling robot; A motion analysis unit for performing motion analysis on the unhooking robot based on the point cloud data set and extracting a three-dimensional motion trajectory; A preset motion trajectory determination unit for mapping the operation state evaluation information to the point cloud data set for motion analysis to determine a preset motion trajectory; A point cloud matching unit for matching the three-dimensional motion trajectory with the preset motion trajectory according to the point cloud data set to generate a point cloud matching result; A deviation identification unit for judging whether there is a deviation between the three-dimensional motion trajectory and the preset motion trajectory according to the point cloud matching result. If there is a deviation, a plurality of deviation points are determined, and a comparison deviation coefficient between the three-dimensional motion trajectory and the preset motion trajectory is calculated according to the plurality of deviation points.

4. The state self-checking system of the hook-unhooking robot according to claim 3, characterized in that, The fault detection module further includes: A judgment unit for setting a deviation critical value according to the preset motion trajectory and judging whether the comparison deviation coefficient is greater than the deviation critical value; A detection unit for generating a detection instruction when the comparison deviation coefficient is greater than the deviation critical value, and performing continuous fault detection on the unhooking robot through the detection instruction combined with the three-dimensional motion trajectory to generate a fault detection result; An abnormal analysis unit for performing abnormal analysis based on the fault detection result combined with the comparison deviation coefficient, identifying the fault mode of the unhooking robot, and adding the fault mode to the fault self-check report; A troubleshooting unit for generating a troubleshooting instruction when the comparison deviation coefficient is less than or equal to the deviation critical value, and performing continuous troubleshooting on the unhooking robot through the troubleshooting instruction combined with the three-dimensional motion trajectory to generate a fault troubleshooting result; A status analysis unit for performing status analysis based on the fault troubleshooting result combined with the comparison deviation coefficient, identifying the status type of the unhooking robot, and adding the status type to the fault self-check report.

5. The status self-checking system of the hook-unhooking robot according to claim 4, characterized in that The fault tracing module includes: A fault mode extraction unit for extracting the fault mode of the unhooking robot based on the fault self-check report for data analysis to obtain a fault self-check data set; An evolution path construction unit for synchronizing the fault self-check data set to the human-machine interface for time evolution to construct a fault evolution path; A multi-dimensional correlation analysis unit for performing multi-dimensional correlation analysis on the unhooking robot according to the fault evolution path through the human-machine interface to generate a correlation decay factor; A tracing and positioning unit for tracing and positioning the fault evolution path according to the correlation decay factor to determine a plurality of fault source positioning information; A fault source data determination unit for adding the plurality of fault source positioning information to the fault source data.

6. The state self-checking system of the hook-unhooking robot according to claim 5, characterized in that, The fault processing module includes: A fault risk assessment unit for traversing multiple components of the unhooking robot according to the plurality of fault source positioning information for fault risk assessment to generate a plurality of fault risk levels; A fault sorting unit for performing priority sorting on the plurality of fault source positioning information based on the plurality of fault risk levels to generate a fault to-be-processed sequence; An operation state matching unit for performing operation state matching on the unhooking robot according to the fault to-be-processed sequence, and generating a fault state alarm signal according to the matching result; A status tracking unit, which is used to retrieve historical maintenance records, perform status tracking according to the fault status warning signal, obtain fault status trend data, and formulate the fault handling suggestions for the unhooking robot based on the fault status trend data in combination with the historical maintenance records.

7. The state self-checking system of the hook-unhooking robot according to claim 1, characterized in that, The fault handling module further includes: A simulation execution unit, which is used to simulate the execution of the fault handling suggestions for the unhooking robot and generate a fault handling report; A real-time feedback unit, which is used to perform real-time feedback on the fault handling suggestions based on the fault handling report, update the fault handling suggestions, and generate fault handling optimization suggestions; A fault visualization unit, which is used to send the fault handling optimization suggestions to the human-machine interface for fault visualization and generate a fault visualization interface; A remote dynamic monitoring unit, which is used to perform remote dynamic monitoring by executing the fault handling optimization suggestions through the fault visualization interface and generate remote control commands; A fault repair control unit, which is used to perform fault repair control on the unhooking robot by executing the remote control commands through the human-machine interface.

Images