Modularized robot connection state monitoring and automatic repairing system and method

Abstract

The invention relates to the technical field of modular robots, in particular to a modular robot connection state monitoring and automatic repairing system and method. The control module is used for controlling the whole system, coordinately receiving external commands and managing the operation of each module; the communication module is used for data transmission and information exchange among the modules; the sensing module is used for providing real-time monitoring data for environment sensing and fault detection; the fault detection module is used for identifying and diagnosing possible connection faults or communication errors in the system; and the calculation and analysis module is used for executing a graph convolutional network and other high-precision data analysis tasks to carry out fault classification and priority ranking. According to the method, deep learning technologies such as the graph convolutional network are adopted to process the module connection topological graph, connection abnormity or fault points are automatically recognized, classification and priority ranking are carried out, and therefore the fault detection precision and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of modular robots, and in particular to a modular robot connection status monitoring and automatic repair system and method. Background Art

[0002] With the continuous development of robotics technology, the concept of modular robots has received more and more attention. Modular robots are composed of multiple functional modules that can be connected and separated through standardized interfaces, so as to achieve rapid assembly, disassembly and reconfiguration of robots. This design makes modular robots highly flexible, scalable and adaptable, and can be applied to various complex and changing environments. During the operation of modular robots, the connection status between modules is crucial. Once a module connection is abnormal or fails, it will directly affect the normal operation of the robot. Therefore, real-time monitoring and identification of the connection status of the modules and rapid repair when a failure occurs are the key to the reliability and safety of modular robots.

[0003] The existing authorization announcement number is CN118769227A, "A modular wiring harness management system and method for industrial robots". It preprocesses the data collected by each sensor, performs periodic analysis on the preprocessed data, identifies the periodic pattern of wiring harness state changes, and simultaneously performs multivariate time series analysis. It analyzes the mutual influence between different sensor data according to the multivariate autoregressive model, combines the periodic analysis with the multivariate time series analysis, detects the modular wiring harness state of the industrial robot, obtains the adaptive management information generated in the process of modular wiring harness state detection, determines the modular wiring harness state according to the adaptive management information and generates different signals, and adjusts the modular wiring harness management of the industrial robot according to the generated signals, thereby optimizing resource allocation and reducing the maintenance cost of the industrial robot.

[0004] However, its detection method is single and only uses magnetic sensors and a simple threshold judgment mechanism. It may not be able to accurately detect complex connection states (such as weak magnetic interference, nonlinear magnetic field distribution), and the threshold judgment cannot handle complex abnormal patterns (such as gradually deteriorating connection states or intermittent failures); in addition, it is highly dependent on sensors, and its performance will be significantly reduced in environments with sensor failures or strong magnetic interference, and there are no other supplementary data sources (such as mechanics, visual sensors) to make up for the lack of sensor data, resulting in insufficient robustness; at the same time, it lacks intelligent analysis, and the data analysis method is only based on static threshold judgment, lacks adaptability and learning ability, and is difficult to cope with dynamic environments and complex modular robot structures; finally, its main function is connection state detection, and does not cover subsequent repair strategies or path planning, and the overall application scenarios are limited. Therefore, we provide a modular robot connection state monitoring and automatic repair system and method. Summary of the invention

[0005] In view of the above-mentioned shortcomings of the prior art, the first purpose of the present invention is to provide a modular robot connection status monitoring and automatic repair system and method to solve the problems in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A modular robot connection status monitoring and automatic repair system and method, including a control module responsible for controlling and coordinating the entire system to receive external commands and manage the operation of each module, a communication module responsible for data transmission and information exchange between modules, a perception module for environmental perception and fault detection to provide real-time monitoring data, a fault detection module for identifying and diagnosing possible connection failures or communication errors in the system, a calculation and analysis module for executing graph convolutional networks and other high-precision data analysis tasks to classify and prioritize faults, a reconstruction path planning module for using a dynamic programming algorithm to calculate the optimal repair path to ensure rapid reconstruction of the system in the event of a failure, a repair execution module responsible for the actual physical repair process, and a verification and recovery module for verifying the system status after repair and checking the connection status through sensors to ensure that the system is restored to a normal working state.

[0008] The present invention is further configured as follows: the control module coordinates the operations of each module and sends instructions to the communication module to ensure that the data flow is smoothly transmitted between the modules; the communication module receives the environmental monitoring data transmitted by the perception module to ensure that the real-time monitoring information can be accurately transmitted to other modules for processing; the perception module provides real-time environmental data for analysis by the fault detection module to identify and diagnose possible connection failures or communication errors.

[0009] The present invention is further configured as follows: the fault detection module transmits the detected fault information to the calculation and analysis module for in-depth analysis through a graph convolutional network, and classifies and sorts the fault priorities; the calculation and analysis module passes the results of fault classification and priority sorting to the reconstruction path planning module to calculate the optimal repair path based on the analysis results to ensure rapid repair.

[0010] The present invention is further configured as follows: the reconstruction path planning module provides an optimal repair path, and the repair execution module performs physical repair operations according to the path; after the repair execution module completes the repair, the verification and recovery module detects the connection status again through a sensor to ensure that the system returns to a normal working state and restarts the task.

[0011] The present invention is further configured to include the following steps:

[0012] S1, magnetic sensor array real-time perception module connection status;

[0013] S2, high-precision data analysis for fault detection and classification;

[0014] S3, graph convolutional network automatically identifies connection anomalies or fault points and classifies and prioritizes them;

[0015] S4, dynamic programming algorithm generates the optimal reconstruction path;

[0016] S5, self-locking module interface and automatic reconstruction mechanism to perform repair;

[0017] S6. Multimodal sensor fusion improves system robustness and adaptability;

[0018] S7. Self-diagnosis and self-repair mechanisms adapt to unknown environments and extend mission life.

[0019] The present invention is further configured as follows: in the step S1, the magnetic sensor array real-time sensing of the module connection status and the step S2, high-precision data analysis for fault detection and classification, a magnetic sensor array and a high-precision data analysis method are used, the magnetic sensor array is used to sense the connection status between modules in real time, and the high-precision data analysis method is used to perform fault detection and classification.

[0020] The present invention is further configured as follows: in the step S3, the graph convolutional network automatically identifies connection anomalies or fault points and classifies and prioritizes them, and uses the graph convolutional network deep learning technology to automatically identify connection anomalies or fault points, and classify and prioritize them. GCN can handle complex module connection topologies.

[0021] The present invention is further configured as follows: in the step S4, in which the dynamic programming algorithm generates the optimal reconstruction path, the dynamic programming algorithm is used to generate the optimal reconstruction path, and the connection position, module load and environmental constraints are taken into consideration. The optimal reconstruction path is generated by the dynamic programming algorithm, which can improve the flexibility and adaptability of the repair strategy.

[0022] The present invention is further configured as follows: in the step S5, the self-locking module interface and the automatic reconstruction mechanism are used to perform the repair, and the self-locking module interface and the automatic reconstruction mechanism are used to simplify the monitoring and repair process of the module connection status. The self-locking module interface can provide a high-strength mechanical connection and support rapid separation, thereby simplifying the monitoring and repair process of the module connection status.

[0023] The present invention is further configured as follows: in the step S6, multimodal sensor fusion improves the system robustness and adaptability, and in the step S7, self-diagnosis and self-repair mechanism adapts to unknown environments and extends the mission life, a self-diagnosis and self-repair mechanism is adopted to enable the modular robot to adapt to unknown environments, self-repair to extend the mission life, through the self-diagnosis and self-repair mechanism.

[0024] Beneficial Effects

[0025] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:

[0026] 1. The present invention uses deep learning technologies such as graph convolutional networks to process module connection topology maps, automatically identify connection anomalies or fault points, and classify and prioritize them, thereby improving the accuracy and efficiency of fault detection. Compared with the methods in the prior art that rely on manually designed feature extraction and classifiers, the present invention can more effectively cope with environmental noise and interference, reduce false alarms and missed alarms, and use dynamic programming algorithms to generate optimal reconstruction paths when repairing module connection failures, taking into account connection locations, module loads, and environmental constraints to optimize reconstruction efficiency. Compared with the methods in the prior art that rely on preset paths and strategies, the present invention has higher flexibility and adaptability, and can solve problems quickly and effectively, especially in complex and changing environments.

[0027] 2. The present invention adopts a low-power magnetic sensor array to improve the real-time and reliability of fault detection. The present invention also combines multiple modal sensing data such as magnetic sensors, IMUs and visual information, and improves the robustness and adaptability of the system through multi-modal sensing fusion technology. Compared with the problems of insufficient magnetic sensor accuracy or insufficient data acquisition speed in the prior art, the present invention can significantly improve the real-time and robustness. The modular design of the present invention makes the system highly flexible and adaptable, and can be applied to various complex and changeable environments such as disaster search and rescue, deep space exploration, industrial robots, etc. Compared with the prior art, the present invention can better adapt to different application scenarios and needs.

[0028] 3. After detecting the fault point, the present invention can automatically start the self-repair mechanism by removing the faulty module or reconnecting the failed module, or starting the spare module replacement process when the module cannot be repaired, thereby improving the reliability and safety of the system. Compared with the prior art, the present invention can automatically repair when a fault occurs, reduce manual intervention and maintenance time, and improve the system availability and task continuity. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of a system module of a modular robot connection status monitoring and automatic repair system of the present invention;

[0030] Figure 2 A schematic diagram of a direct connection module of a modular robot connection status monitoring and automatic repair system of the present invention;

[0031] Figure 3 A schematic diagram of a flow chart of a modular robot connection status monitoring and automatic repair method of the present invention;

[0032] Figure 4 It is a schematic diagram of the initial structure of a modular robot connection status monitoring and automatic repair method of the present invention;

[0033] Figure 5 A schematic diagram of an obstacle point setting process of a modular robot connection status monitoring and automatic repair method of the present invention;

[0034] Figure 6 The figure is a schematic diagram of the optimal reconstruction path flow of a modular robot connection status monitoring and automatic repair method of the present invention. DETAILED DESCRIPTION

[0035] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments, and the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments in 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.

[0036] It should be further explained that the drawings and implementation modes of the present invention mainly describe the concept of the present invention. On the basis of this concept, the specific forms and settings of some connection relationships, positional relationships, power mechanisms, power supply systems, hydraulic systems and control systems may not be fully described. However, on the premise that those skilled in the art understand the concept of the present invention, those skilled in the art can implement the above-mentioned specific forms and settings in a well-known manner.

[0037] When an element is referred to as being "fixed to" or "disposed on" another element, it may be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or indirectly connected to the other element.

[0038] The directional words "inside and outside" refer to the inside and outside relative to the outline of each component itself. The directions or positional relationships indicated by the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" are based on the directions or positional relationships shown in the drawings and are only for the convenience of describing the present invention and simplifying the description. They do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0039] For ease of description, spatially relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used here to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" may include both "above" and "below". The device may also be positioned in other different ways, and the spatially relative descriptions used here are interpreted accordingly.

[0040] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, and "several" means one or more, unless otherwise clearly and specifically defined.

[0041] The present invention will be further described below in conjunction with the embodiments.

[0042] Example 1

[0043] like Figure 1-6 As shown, a modular robot connection status monitoring and automatic repair system includes a control module responsible for the control and coordination of the entire system to receive external commands and manage the operation of each module, a communication module responsible for data transmission and information exchange between modules, a perception module for environmental perception and fault detection to provide real-time monitoring data, a fault detection module for identifying and diagnosing possible connection failures or communication errors in the system, a calculation and analysis module for executing graph convolutional networks and other high-precision data analysis tasks to classify and prioritize faults, a reconstruction path planning module for using a dynamic programming algorithm to calculate the optimal repair path to ensure rapid reconstruction of the system in the event of a failure, a repair execution module responsible for the actual physical repair process, and a verification and recovery module for verifying the system status after repair by checking the connection status through sensors to ensure that the system is restored to a normal working state;

[0044] The control module coordinates the operation of each module and sends instructions to the communication module to ensure smooth data flow between modules; the communication module receives environmental monitoring data transmitted by the perception module to ensure that real-time monitoring information can be accurately transmitted to other modules for processing; the perception module provides real-time environmental data for analysis by the fault detection module to identify and diagnose possible connection failures or communication errors;

[0045] The fault detection module transmits the detected fault information to the calculation and analysis module for in-depth analysis through the graph convolution network, and classifies and sorts the fault priorities; the calculation and analysis module transmits the results of fault classification and priority sorting to the reconstruction path planning module to calculate the optimal repair path based on the analysis results to ensure rapid repair;

[0046] The reconstruction path planning module provides the optimal repair path, and the repair execution module performs physical repair operations according to the path; after the repair execution module completes the repair, the verification and recovery module detects the connection status again through the sensor to ensure that the system returns to normal working state and restarts the task.

[0047] In this embodiment, it is assumed that a modular robot consists of 16 modules connected to form a complex mesh topology (such as Figure 4 Each module uses a magnetic sensor to monitor the connection status in real time. Connection topology: Each module is connected through a self-locking interface.

[0048] Main path: Module 1 --- Module 2 --- Module 3 --- Module 4 --- Module 5

[0049] Parallel path 1: Module 2 --- Module 6 --- Module 7 --- Module 8 --- Module 5

[0050] Parallel path 2: Module 3 --- Module 9 --- Module 10 --- Module 11 --- Module 4

[0051] Cross connection: module 6 --- module 9, module 7 --- module 10, module 8 --- module 11

[0052] Extended network: Module 5 --- Module 12 --- Module 13 --- Module 14 Module 12 --- Module 15 --- Module 16

[0053] Assume that during operation, the connections between module 7 and module 10 and between module 8 and module 11 fail at the same time, resulting in failure of normal data flow transmission.

[0054] This multi-point failure may be caused by loose connection, local communication failure or external interference. At this time, a magnetic sensor array and a high-precision data analysis method are used to perceive the connection status between modules in real time, and fault detection and classification are performed through a high-precision data analysis method. The magnetic sensor array consists of 10 low-power magnetic sensors distributed at various key positions of the modular robot to monitor the module connection status in real time. The high-precision data analysis method uses a graph convolutional network (GCN) to automatically identify connection anomalies or fault points through deep learning of the module connection topology, and classify and prioritize them. The magnetic sensor array not only detects the physical connection status between modules, but also identifies loose connection anomalies through the distribution of magnetic field strength (such as detecting a 30% drop in magnetic field strength between modules 7-10), and analyzes abnormal nodes in the topology map through GCN (such as a sudden increase in communication delay of modules 8-11), and classifies them as intermittent communication failures. This process covers types of anomalies not covered by the prior art, verifying the comprehensiveness of the detection scope of this patent.

[0055] The dynamic programming algorithm is used to generate the optimal reconstruction path. In terms of connection location, redundant paths in the mesh topology are used first. In terms of module load, tasks are distributed through a load balancing algorithm to avoid overloading of a single point. In terms of environmental restrictions, communication bottlenecks are avoided to optimize reconstruction efficiency. The dynamic programming algorithm calculates the optimal path set from the initial state to the target state by establishing the state transition equation F(i,j)=min{F(i-1,k)+C(k,j)} (where C(k,j) is the repair cost from module k to module j, considering multiple path selections in the mesh topology).

[0056] The planning result is to bypass the faulty connection. The system automatically selects the optimal reconstruction path: module 7->module 8->module 5->module 4->module 11.

[0057] This path was chosen based on the following advantages:

[0058] Utilizes existing stable connections (7-8, 8-5, 5-4, 4-11)

[0059] Minimizes path length and reduces communication delays

[0060] Avoided all faulty connection points (7-10 and 8-11)

[0061] Provides a reliable data transmission channel through the backbone network (module 4-5)

[0062] from Figure 6As can be seen in Figure 1, the reconstructed path fully utilizes the redundancy of the mesh topology, ensuring the reliability of the connection while achieving the selection of the shortest path. The reconstruction of this path not only solves the problem of communication interruption, but also provides a better load balancing effect, because it disperses the nodes through which the data flows and avoids the situation where a single point is overloaded.

[0063] In terms of performance indicators, the time complexity of the dynamic programming algorithm in the mesh topology is O(n^3). Since it is necessary to consider the combination of multiple paths, the reconstruction planning time is about 2.5 seconds. However, compared with the chain topology, the mesh structure provides higher fault tolerance and more flexible reconstruction options.

[0064] After completing the optimal path planning (module 7->module 8->module 5->module 4->module 11), the self-repair process of the modular robot is started. The self-locking module interface and automatic reconstruction mechanism are used to simplify the monitoring and repair process of the module connection status. The self-locking module interface provides high-strength mechanical connection and supports fast separation (through high-strength mechanical connection (maximum load-bearing capacity 500N) and fast separation mechanism, the fault connection points of modules 7-10 and modules 8-11 are removed, and a reinforced connection is established on the planned new path). In the mesh topology, due to the existence of multiple parallel paths and cross-connections, the system can perform the reconstruction process more efficiently. The response time of the spare module is optimized to 10 seconds, and the completion time of the entire reconstruction process is shortened to 14 seconds. In terms of performance indicators, the module replacement success rate in multi-point failure scenarios is increased to 99.2%, and the total repair time is about 16 seconds (including path planning and module replacement).

[0065] After the connection status verification repair is completed, the connection status of the newly established path (7-8-5-4-11) is verified through the magnetic sensor and GCN. Since the mesh topology provides more reference points and verification paths, the system can more accurately evaluate the connection quality. In terms of performance indicators, the verification time of complex topologies is optimized to 0.3 seconds, and the system recovery success rate is increased to 99.5%.

[0066] Example 2

[0067] like Figure 3 As shown, a modular robot connection status monitoring and automatic repair method includes the following steps:

[0068] S1, magnetic sensor array real-time perception module connection status;

[0069] S2, high-precision data analysis for fault detection and classification;

[0070] S3, graph convolutional network automatically identifies connection anomalies or fault points and classifies and prioritizes them;

[0071] S4, dynamic programming algorithm generates the optimal reconstruction path;

[0072] S5, self-locking module interface and automatic reconstruction mechanism to perform repair;

[0073] S6. Multimodal sensor fusion improves system robustness and adaptability;

[0074] S7, self-diagnosis and self-repair mechanisms adapt to unknown environments and extend mission life;

[0075] In the step S1, the magnetic sensor array senses the module connection status in real time, and the step S2, high-precision data analysis for fault detection and classification, a magnetic sensor array and a high-precision data analysis method are used to sense the connection status between modules in real time through the magnetic sensor array, and fault detection and classification are performed through the high-precision data analysis method;

[0076] In the step S3, the graph convolution network automatically identifies the connection anomalies or fault points and classifies and prioritizes them. The graph convolution network deep learning technology is used to automatically identify the connection anomalies or fault points, and classify and prioritize them. GCN can handle complex module connection topologies;

[0077] In the step S4, the dynamic programming algorithm is used to generate the optimal reconstruction path. The dynamic programming algorithm is used to generate the optimal reconstruction path. The connection position, module load and environmental restrictions are considered. The optimal reconstruction path is generated by the dynamic programming algorithm, which can improve the flexibility and adaptability of the repair strategy.

[0078] In the step S5, the self-locking module interface and the automatic reconstruction mechanism are used to perform the repair, and the monitoring and repair process of the module connection status are simplified. The self-locking module interface can provide a high-strength mechanical connection and support rapid separation, thereby simplifying the monitoring and repair process of the module connection status;

[0079] In the step S6, multimodal sensor fusion improves the system robustness and adaptability, and in the step S7, self-diagnosis and self-repair mechanism adapts to unknown environments and prolongs the mission life, the self-diagnosis and self-repair mechanism is adopted to enable the modular robot to adapt to unknown environments, self-repair to prolong the mission life, through the self-diagnosis and self-repair mechanism.

[0080] In this embodiment, the magnetic sensor array monitors the connection status between modules in real time and performs fault detection and classification through high-precision data analysis. When a fault occurs, the graph convolutional network (GCN) automatically identifies the connection anomaly or fault point, sorts them according to priority, and handles complex module connection topology. Then, the dynamic programming algorithm generates the optimal repair path, taking into account the connection location, module load and environmental constraints, and improving the flexibility and adaptability of the repair strategy.

[0081] During the repair process, the self-locking module interface and automatic reconstruction mechanism simplify the module connection and repair process, ensuring high-strength mechanical connection and rapid separation. Through multimodal sensor fusion and self-diagnosis and self-repair mechanism, the system can automatically adapt to and extend the mission life in unknown environments, achieving efficient self-repair and improving system robustness.

[0082] How it works

[0083] In the actual use of the present invention, the repair execution module and the verification and recovery module respectively undertake the tasks of actual physical repair and post-repair function verification. The connection status between each functional module is monitored in real time through a magnetic sensor, and high-precision data analysis and graph convolutional network (GCN) are used to identify and locate faults, realizing the rapid self-repair capability of the modular robot during task execution.

[0084] At the fault detection level, the system mainly relies on the magnetic sensor array to perceive the module connection status in real time. The sensitivity of the magnetic sensor array can reach 10^-6T, and it can capture the smallest connection anomalies between modules at a sampling frequency of 100Hz. The signals collected by the sensor will be initially processed and fault detected by the high-precision data analysis module. Subsequently, these data will be input into the graph convolutional network for deep learning. GCN uses its perception of topological structure to automatically identify abnormal connections or fault points, and classify and prioritize them according to the fault type. This step can achieve a detection accuracy of about 99.2% in the test, and can complete topological analysis and fault detection within 0.2 seconds.

[0085] After fault identification is completed, the system's reconstruction path planning module will use a dynamic programming (DP) algorithm to quickly generate the optimal repair path. Dynamic planning establishes the state transition equation F(i,j)=min{F(i-1,k)+C(k,j)}, and gives the optimal repair plan from the initial state to the target state while considering multiple factors such as connection location, module load, and environmental restrictions. This ensures that when a fault occurs, existing valid modules are reused as much as possible, and adjacent nodes are used for quick connection first to avoid more disconnection or reset actions. The time complexity of the planning process is about O(n^2), and it takes an average of about 1.5 seconds in actual testing. It can quickly obtain the optimal reconstruction strategy and greatly improve the repair efficiency.

[0086] Repair execution mainly relies on the self-locking module interface and automatic reconstruction mechanism to complete physical operations. The maximum load-bearing capacity of the self-locking interface can reach 500N. On the one hand, it can provide a high-strength connection during normal operation, and on the other hand, it supports rapid separation, so that the faulty module can be replaced or the faulty connection can be cut off in time. The automatic reconstruction mechanism will be executed according to the optimal repair path generated by dynamic planning. If necessary, the failed module can be removed or reconnected; if a specific module fails completely, the system will call the spare module replacement process. The spare module response time is about 10 seconds. The entire repair process, including path planning and module replacement, takes a total of about 14 seconds, and the module replacement success rate can reach 98.5%.

[0087] After the repair is completed, the system will once again verify the connection status through the magnetic sensor and GCN to ensure that all modules have resumed normal function. The verification process takes about 0.2 seconds to complete. If the topology is consistent with expectations, the control module will notify the robot to resume the task. Through multimodal sensor fusion and self-diagnosis and self-repair mechanisms, the entire system can autonomously respond to faults in unknown environments, extend mission life, and maintain high robustness. The final test data shows that after combining magnetic sensors, GCN and dynamic programming algorithms, the system's fault detection accuracy is as high as 99.2%, and the reconstruction efficiency is significantly improved, truly realizing efficient modular robot automatic fault detection and rapid repair.

[0088] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0089] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0090] Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments do not limit the scope of the present application. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the accompanying drawings are not drawn according to the actual proportional relationship. The technology, method and equipment known to those of ordinary skill in the relevant field may not be discussed in detail, but in appropriate cases, the technology, method and equipment should be considered as a part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so that once a certain item is defined in an accompanying drawing, it does not need to be further discussed in subsequent drawings.

Claims

1. A modular robot connection status monitoring and automatic repair system, characterized in that: It includes a control module responsible for the control and coordination of the entire system, receiving external commands and managing the operation of each module, a communication module responsible for data transmission and information exchange between modules, a perception module for environmental perception and fault detection to provide real-time monitoring data, a fault detection module for identifying and diagnosing possible connection failures or communication errors in the system, a calculation and analysis module for executing graph convolutional networks and other high-precision data analysis tasks for fault classification and priority sorting, a reconstruction path planning module for using a dynamic programming algorithm to calculate the optimal repair path to ensure rapid reconstruction of the system in the event of a failure, a repair execution module responsible for the actual physical repair process, and a verification and recovery module for verifying the system status after repair by checking the connection status through sensors to ensure that the system returns to normal working status.

2. A modular robot connection status monitoring and automatic repair system according to claim 1, characterized in that: The control module coordinates the operations of each module and sends instructions to the communication module to ensure smooth transmission of data flow between modules; the communication module receives environmental monitoring data transmitted by the perception module to ensure that real-time monitoring information can be accurately transmitted to other modules for processing; The perception module provides real-time environmental data for analysis by the fault detection module to identify and diagnose possible connection failures or communication errors.

3. A modular robot connection status monitoring and automatic repair system according to claim 1, characterized in that: The fault detection module transmits the detected fault information to the calculation and analysis module for in-depth analysis through the graph convolutional network, and classifies and sorts the fault priorities; the calculation and analysis module passes the results of fault classification and priority sorting to the reconstruction path planning module to calculate the optimal repair path based on the analysis results to ensure rapid repair.

4. A modular robot connection status monitoring and automatic repair system according to claim 1, characterized in that: The reconstruction path planning module provides the optimal repair path, and the repair execution module performs physical repair operations according to the path; after the repair execution module completes the repair, the verification and recovery module detects the connection status again through the sensor to ensure that the system returns to normal working state and restarts the task.

5. A modular robot connection status monitoring and automatic repair method, characterized in that: The following steps are involved: S1, magnetic sensor array real-time perception module connection status; S2, high-precision data analysis for fault detection and classification; S3, graph convolutional network automatically identifies connection anomalies or fault points and classifies and prioritizes them; S4, dynamic programming algorithm generates the optimal reconstruction path; S5, self-locking module interface and automatic reconstruction mechanism to perform repair; S6. Multimodal sensor fusion improves system robustness and adaptability; S7. Self-diagnosis and self-repair mechanisms adapt to unknown environments and extend mission life.

6. A modular robot connection status monitoring and automatic repair method according to claim 5, characterized in that: In the step S1 of real-time sensing of module connection status by the magnetic sensor array and the step S2 of high-precision data analysis for fault detection and classification, a magnetic sensor array and a high-precision data analysis method are used to sense the connection status between modules in real time through the magnetic sensor array, and to perform fault detection and classification through a high-precision data analysis method.

7. A modular robot connection status monitoring and automatic repair method according to claim 5, characterized in that: In the step S3, the graph convolutional network automatically identifies connection anomalies or fault points and classifies and prioritizes them. The graph convolutional network deep learning technology is used to automatically identify connection anomalies or fault points, and classify and prioritize them. GCN can handle complex module connection topologies.

8. A modular robot connection status monitoring and automatic repair method according to claim 5, characterized in that: In the step S4, the dynamic programming algorithm is used to generate the optimal reconstruction path. The dynamic programming algorithm is used to generate the optimal reconstruction path, and the connection position, module load and environmental restrictions are considered. The optimal reconstruction path is generated by the dynamic programming algorithm, which can improve the flexibility and adaptability of the repair strategy.

9. A modular robot connection status monitoring and automatic repair method according to claim 5, characterized in that: In the step S5, the self-locking module interface and automatic reconstruction mechanism are used to perform the repair, and the monitoring and repair process of the module connection status are simplified. The self-locking module interface can provide a high-strength mechanical connection and support rapid separation, thereby simplifying the monitoring and repair process of the module connection status.

10. A modular robot connection status monitoring and automatic repair method according to claim 5, characterized in that: The multimodal sensor fusion in step S6 improves the robustness and adaptability of the system, and the self-diagnosis and self-repair mechanism in step S7 adapts to unknown environments and prolongs the mission life. The self-diagnosis and self-repair mechanism is adopted to enable the modular robot to adapt to unknown environments and self-repair to prolong the mission life through the self-diagnosis and self-repair mechanism.

Images