Real-time fault detection method and detection system for robot during movement

Abstract

The application discloses a real-time fault detection method and system for a robot during movement, wherein a plurality of first self-collection data of each part of the robot in a normal working state are acquired; a self-collection training sample set is formed based on the plurality of first self-collection data, and a dynamic fault detection model containing independent variables is constructed according to the self-collection training sample set; real-time working data of each part of the robot are monitored, and the real-time working data are associated with the dynamic fault detection model of the independent variables to output corresponding second self-collection data; the second self-collection data are compared with normal working data corresponding to the dynamic fault detection model of the independent variables to determine whether a fault occurs to the robot during movement; if the robot has a fault during movement, the corresponding fault part is marked based on the second self-collection data, and the robot is triggered to autonomously repair the fault part.

Description

Technical Field

[0001] The present invention relates to the technical field of robot fault detection, and in particular to a real-time fault detection method and detection system for a robot during movement. Background Art

[0002] With the advancement of technology, robots now include multiple parts, such as mobile parts, support parts, extension parts, working parts, and visual parts. These parts assist each other and complete corresponding robot operations. In existing technologies, a controller collects operating data from each part individually, and this data collection requires manual triggering. The operating data is then compared with normal data to determine the corresponding fault status, resulting in the inability to detect faults in existing robots in real time. Summary of the Invention

[0003] The purpose of the present invention is to overcome the shortcomings of the existing technology. The present invention provides a real-time fault detection method and detection system for a robot during movement. The first self-collected data is converted into the second self-collected data based on the dynamic fault detection model of the independent variable, and the second self-collected data is compared with the normal working data to determine whether a fault occurs. At this time, the first self-collected data is collected in real time for the corresponding part, and is autonomously transformed in the dynamic fault detection model of the independent variable, so as to facilitate real-time fault monitoring of all parts and avoid multi-directional conversion and recording of data. In addition, multiple repair data are formed into a repair data set, and the repair data set is interacted with the dynamic fault detection model of the independent variable to form a repair change of the dynamic fault detection model of the independent variable, so as to expand the learning part of the dynamic fault detection model of the independent variable and improve the learning degree of the dynamic fault detection model of the independent variable.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a real-time fault detection method for a robot during movement, comprising: acquiring multiple first self-collected data of various parts of the robot in normal working conditions; forming a self-collected training sample set based on the multiple first self-collected data, and constructing a dynamic fault detection model containing independent variables based on the self-collected training sample set; monitoring the real-time working data of various parts of the robot, and associating the real-time working data with the dynamic fault detection model of the independent variables to output corresponding second self-collected data; comparing the second self-collected data with the normal working data corresponding to the dynamic fault detection model of the independent variables to determine whether the robot has a fault during movement; if the robot has a fault during movement, marking the corresponding fault part based on the second self-collected data, triggering the robot to autonomously repair the fault part and forming repair data; storing multiple repair data, and forming a repair data set with the multiple repair data, interacting with the dynamic fault detection model of the independent variables based on the repair data set, and forming a repair change of the dynamic fault detection model of the independent variables.

[0005] In addition, an embodiment of the present invention further provides a real-time fault detection system for a robot during motion, the real-time fault detection system comprising: an acquisition module for acquiring a plurality of first self-collected data of various parts of the robot in a normal working state; a training module for forming a self-collected training sample set based on the plurality of first self-collected data, and constructing a dynamic fault detection model including an independent variable based on the self-collected training sample set; a monitoring module for monitoring the real-time working data of various parts of the robot, and associating the real-time working data with the dynamic fault detection model of the independent variable to output corresponding second self-collected data; a fault module for comparing the second self-collected data with the normal working data corresponding to the dynamic fault detection model of the independent variable to determine whether a fault has occurred in the robot during motion; a repair module for marking the corresponding fault part based on the second self-collected data if a fault has occurred in the robot during motion, triggering the robot to autonomously repair the fault part, and generating repair data; and a storage module for storing the plurality of repair data, forming a repair data set from the plurality of repair data, interacting with the dynamic fault detection model of the independent variable based on the repair data set, and generating a repair change of the dynamic fault detection model of the independent variable.

[0006] In an embodiment of the present invention, a plurality of first self-collected data of various parts of the robot in a normal working state are obtained through the method in the embodiment of the present invention; a self-collected training sample set is formed based on the plurality of first self-collected data, and a dynamic fault detection model containing independent variables is constructed based on the self-collected training sample set; the real-time working data of various parts of the robot are monitored, and the real-time working data are associated with the dynamic fault detection model of the independent variable to output the corresponding second self-collected data; the normal working data corresponding to the dynamic fault detection model of the independent variable are compared based on the second self-collected data to determine whether the robot has a fault during movement, wherein the first self-collected data is converted into the second self-collected data based on the dynamic fault detection model of the independent variable, and the second self-collected data is compared with the normal working data. Determine whether a fault occurs. At this time, the first self-collected data collects data from the corresponding part in real time, and performs autonomous transformation in the dynamic fault detection model of the independent variable, so as to facilitate real-time fault monitoring of all parts and avoid multi-directional transformation and recording of data. In addition, if the robot fails during movement, the corresponding fault part is marked based on the second self-collected data, and the robot is triggered to autonomously repair the fault part and form repair data; multiple repair data are stored, and the multiple repair data are formed into a repair data set, based on the repair data set, interact with the dynamic fault detection model of the independent variable, and form a repair change of the dynamic fault detection model of the independent variable, so as to expand the learning part of the dynamic fault detection model of the independent variable and improve the learning degree of the dynamic fault detection model of the independent variable. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0008] Figure 1 1 is a flow chart of a method for real-time fault detection of a robot during motion according to an embodiment of the present invention;

[0009] Figure 2 This is a schematic diagram of a first process of self-collecting data in a method for real-time fault detection of a robot during motion according to an embodiment of the present invention;

[0010] Figure 3 1 is a flow chart of a dynamic fault detection model including independent variables in a real-time fault detection method for a robot during motion according to an embodiment of the present invention;

[0011] Figure 41 is a schematic diagram of a second process of self-collecting data in a method for real-time fault detection of a robot during motion according to an embodiment of the present invention;

[0012] Figure 5 Schematic diagram of the structure of a real-time fault detection system for a robot during motion according to an embodiment of the present invention;

[0013] Figure 6 The figure shows a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0015] Example

[0016] See also Figures 1 to 4 A method for real-time fault detection of a robot during motion, comprising:

[0017] S11: Acquire a plurality of first self-collected data of each part of the robot in a normal working state;

[0018] In the specific implementation process of the present invention, the specific steps may be:

[0019] S111: Control each part of the robot to move one by one, and record corresponding working data based on the action time;

[0020] S112: Delineating a data area corresponding to the part based on the working data;

[0021] S113: monitoring each of the data areas, and collecting corresponding first self-collected data in the data area in real time;

[0022] S114: If the same first self-collected data exists in the data area, trace back the time of the first self-collected data, and perform duplication confirmation of the data area based on data adjacent to the first self-collected data.

[0023] Among them, multiple first self-collected data of various parts of the robot in normal working state are obtained; a self-collected training sample set is formed based on the multiple first self-collected data, and a dynamic fault detection model containing independent variables is constructed according to the self-collected training sample set; the real-time working data of various parts of the robot are monitored, and the real-time working data are associated with the dynamic fault detection model of the independent variable to output the corresponding second self-collected data; based on the second self-collected data and the normal working data corresponding to the dynamic fault detection model of the independent variable, it is determined whether the robot has a fault during the movement process, wherein the first self-collected data is converted into the second self-collected data based on the dynamic fault detection model of the independent variable, and the second self-collected data is compared with the normal working data to determine whether a fault has occurred. At this time, the first self-collected data collects data for the corresponding part in real time, and is autonomously converted in the dynamic fault detection model of the independent variable, so as to facilitate real-time fault monitoring of all parts and avoid multi-directional conversion and recording of data.

[0024] In addition, if the robot fails during movement, the corresponding fault part is marked based on the second self-collected data, and the robot is triggered to autonomously repair the fault part and form repair data; multiple repair data are stored, and the multiple repair data are formed into a repair data set, based on the repair data set, the dynamic fault detection model of the independent variable is interacted with, and the repair change of the dynamic fault detection model of the independent variable is formed, so as to expand the learning part of the dynamic fault detection model of the independent variable and improve the learning degree of the dynamic fault detection model of the independent variable.

[0025] S12: forming a self-collected training sample set based on the plurality of first self-collected data, and constructing a dynamic fault detection model including independent variables according to the self-collected training sample set;

[0026] In the specific implementation process of the present invention, the specific steps may be:

[0027] S121: forming a self-collected training sample set based on the plurality of first self-collected data, and marking corresponding data regions of the self-collected training sample set;

[0028] S122: removing duplicates from a plurality of the first self-collected data in the self-collected training sample set, and retaining the different first self-collected data;

[0029] S123: Input the self-collected training sample set into the reference model. The reference model evolves the input data and the output data to construct a dynamic fault detection model including independent variables. The dynamic fault detection model of the independent variables has a model variable, and the model variable serves as the independent variable.

[0030] Among them, the self-collected training sample set is screened and duplicate data is removed to ensure the uniqueness of the data collected in the self-collected training sample set, retain the different first self-collected data, reduce the calculation of duplicate data, and avoid the impact of duplicate data.

[0031] In addition, the self-collected training sample set is input into the reference model, and the reference model evolves the input data and output data to construct a dynamic fault detection model containing independent variables. The dynamic fault detection model of the independent variable has a model variable, and the model variable serves as the independent variable. The dynamic fault detection model regulates itself based on the independent variable, and can make corresponding changes along with the changes in the independent variable to adapt to the application of the dynamic fault detection model in various scenarios.

[0032] In addition, the independent variable can also be a time factor or a scenario factor. Corresponding input is made based on the time parameter or scenario parameter to change the presentation mode of the dynamic fault detection model, and the overall adjustment can be made based on the adjustment of a single independent variable to improve the application of the dynamic fault detection model in various scenarios.

[0033] S13: monitoring real-time working data of each part of the robot, and associating the real-time working data with the dynamic fault detection model of the independent variable to output corresponding second self-collected data;

[0034] In the specific implementation process of the present invention, the specific steps may be:

[0035] S131: monitors the real-time working data of each part of the robot;

[0036] S132: Using the real-time operating data as input data of the dynamic fault detection model of the independent variable, and triggering the operation of the dynamic fault detection model of the independent variable as the real-time operating data is generated, wherein the dynamic fault detection model of the independent variable is directly associated with the real-time operating data;

[0037] S133: inputting the real-time working data within the framework of the dynamic fault detection model of the independent variable, and outputting corresponding second self-collected data.

[0038] In which, the real-time working data is used as the input data of the dynamic fault detection model of the independent variable, and the operation of the dynamic fault detection model of the independent variable is triggered as the real-time working data is generated. At this time, the dynamic fault detection model of the independent variable can monitor the generation of real-time working data and directly make corresponding fault detection and troubleshooting. The dynamic fault detection model of the independent variable is directly associated with the real-time working data to strengthen the output of the dynamic fault detection model of the independent variable and avoid the conversion of real-time working data.

[0039] In addition, the real-time operating data is inputted within the framework of the dynamic fault detection model of the independent variable, and the corresponding second self-collected data is outputted.

[0040] S14: comparing the second self-collected data with normal operating data corresponding to the dynamic fault detection model of the independent variable to determine whether a fault occurs during the movement of the robot;

[0041] In the specific implementation process of the present invention, the specific steps may be: using the second self-collected data as the output data of the dynamic fault detection model of the independent variable; comparing the second self-collected data with the normal working data corresponding to the dynamic fault detection model of the independent variable to determine the data change; wherein, the second self-collected data and the normal working data are compared in the dynamic fault detection model of the same independent variable; if the data change meets the preset change threshold, it is determined that the robot has a fault during the movement.

[0042] Among them, the second self-collected data is output by the dynamic fault detection model based on the independent variable, and the normal working data corresponding to the second self-collected data and the dynamic fault detection model of the independent variable are compared to determine the data change amount, and fault measurement is performed through a quantification strategy of the change amount. The second self-collected data and the normal working data are compared in the dynamic fault detection model of the same independent variable; if the data change amount meets the preset change amount threshold, it is determined that the robot has a fault during the movement process, thereby realizing real-time fault detection of various parts of the robot.

[0043] S15: If the robot fails during movement, a corresponding fault location is marked based on the second self-collected data, and the robot is triggered to autonomously repair the fault location, and generate repair data;

[0044] In the specific implementation process of the present invention, the specific steps include: when the robot fails, triggering the fault traversal of the robot to determine the corresponding second self-collected data; determining the corresponding part based on the second self-collected data, and marking the corresponding fault part; triggering the robot to autonomously repair the fault part, and repair the second self-collected data; making adjustments based on the second self-collected data, and retesting the part to form repair data.

[0045] S16: storing a plurality of the repair data, and forming a repair data set from the plurality of the repair data, interacting with the dynamic fault detection model of the independent variable based on the repair data set, and forming a repair variation of the dynamic fault detection model of the independent variable.

[0046] In the specific implementation process of the present invention, the specific steps include: storing multiple repair data, and forming the multiple repair data into a repair data set; performing data screening based on the repair data set, and performing the same screening on the repair data, and eliminating duplicate data; interacting with the dynamic fault detection model of the independent variable based on the repair data set, and forming the repair change amount of the dynamic fault detection model of the independent variable.

[0047] The method for real-time fault detection of the robot during movement also includes: obtaining the repair change of the dynamic fault detection model of the independent variable; performing dynamic adjustment according to the repair change, and testing the degree of change of the repair change; and regulating the repair system of the dynamic fault detection model of the independent variable according to the degree of change of the repair change.

[0048] In an embodiment of the present invention, through the method in the embodiment of the present invention, the first self-collected data is converted into the second self-collected data based on the dynamic fault detection model of the independent variable, and the second self-collected data is compared with the normal working data to determine whether a fault occurs. At this time, the first self-collected data performs data collection on the corresponding part in real time, and is autonomously transformed in the dynamic fault detection model of the independent variable, so as to facilitate real-time fault monitoring of all parts and avoid multi-directional conversion and recording of data. In addition, multiple repair data are formed into a repair data set, and the repair data set is interacted with the dynamic fault detection model of the independent variable to form a repair change amount of the dynamic fault detection model of the independent variable, so as to expand the learning part of the dynamic fault detection model of the independent variable and improve the learning degree of the dynamic fault detection model of the independent variable.

[0049] Example

[0050] See also Figure 5 , Figure 5The figure is a schematic diagram of the structure of a real-time fault detection system for a robot during movement in an embodiment of the present invention.

[0051] like Figure 5 As shown, a real-time fault detection system for a robot during motion, the real-time fault detection system for a robot during motion comprising:

[0052] Acquisition module 21: used to acquire a plurality of first self-collected data of each part of the robot in a normal working state;

[0053] Training module 22: used to form a self-collected training sample set based on the plurality of first self-collected data, and to construct a dynamic fault detection model containing independent variables according to the self-collected training sample set;

[0054] Monitoring module 23: used to monitor the real-time working data of each part of the robot, and associate the real-time working data with the dynamic fault detection model of the independent variable to output corresponding second self-collected data;

[0055] Fault module 24: used for comparing the second self-collected data with the normal working data corresponding to the dynamic fault detection model of the independent variable to determine whether a fault occurs during the movement of the robot;

[0056] Repair module 25: for, if a fault occurs during the movement of the robot, marking the corresponding fault location based on the second self-collected data, triggering the robot to autonomously repair the fault location, and generating repair data;

[0057] The storage module 26 is used to store a plurality of the repair data, and form a repair data set from the plurality of the repair data, interact with the dynamic fault detection model of the independent variable based on the repair data set, and form a repair variation of the dynamic fault detection model of the independent variable.

[0058] The present invention provides a real-time fault detection method and system for a robot during movement, which converts first self-collected data into second self-collected data based on a dynamic fault detection model of an independent variable, and compares the second self-collected data with normal working data to determine whether a fault occurs. At this time, the first self-collected data collects data from the corresponding part in real time, and is autonomously converted in the dynamic fault detection model of the independent variable, so as to facilitate real-time fault monitoring of all parts and avoid multi-directional conversion and recording of data. In addition, multiple repair data are formed into a repair data set, and the repair data set is interacted with the dynamic fault detection model of the independent variable to form a repair change amount of the dynamic fault detection model of the independent variable, so as to expand the learning part of the dynamic fault detection model of the independent variable and improve the learning degree of the dynamic fault detection model of the independent variable.

[0059] Example

[0060] See also Figure 6 , refer to the following Figure 6 An electronic device 40 according to this embodiment of the present invention will be described. Figure 6 The electronic device 40 shown is only an example and should not limit the functionality and scope of use of the embodiments of the present invention.

[0061] like Figure 6 As shown, the electronic device 40 is a general-purpose computing device. Components of the electronic device 40 may include, but are not limited to, at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).

[0062] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 performs the steps according to various exemplary embodiments of the present invention described in the above “Example Method” section of this specification.

[0063] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache memory unit 422 , and may further include a read-only memory unit (ROM) 423 .

[0064] The storage unit 42 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0065] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0066] The electronic device 40 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 40, and / or any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 45. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 46. Figure 6 As shown, the network adapter 46 communicates with other modules of the electronic device 40 via the bus 43. Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0067] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0068] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be performed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium, which may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. Furthermore, the computer program instructions are stored therein, and when executed by a computer, the computer executes the above methods.

[0069] In addition, the above is a detailed introduction to the real-time fault detection method and system for the robot during movement provided by the embodiments of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for general technical personnel in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for real-time fault detection during robot motion, characterized in that: include: Acquire a plurality of first self-collected data of each part of the robot in a normal working state; forming a self-collected training sample set based on the plurality of first self-collected data, and constructing a dynamic fault detection model including independent variables according to the self-collected training sample set; Monitoring real-time working data of various parts of the robot and associating the real-time working data with the dynamic fault detection model of the independent variable to output corresponding second self-collected data, including: monitoring the real-time working data of various parts of the robot; using the real-time working data as input data of the dynamic fault detection model of the independent variable, and triggering the operation of the dynamic fault detection model of the independent variable as the real-time working data is generated, wherein the dynamic fault detection model of the independent variable is directly associated with the real-time working data; inputting the real-time working data within the framework of the dynamic fault detection model of the independent variable, and outputting the corresponding second self-collected data; comparing the second self-collected data with normal operating data corresponding to the dynamic fault detection model of the independent variable to determine whether a fault occurs in the robot during movement; If the robot fails during movement, a corresponding fault location is marked based on the second self-collected data, and the robot is triggered to autonomously repair the fault location, thereby generating repair data; Storing a plurality of the repair data, and forming a repair data set from the plurality of the repair data, interacting with the dynamic fault detection model of the independent variable based on the repair data set, and forming a repair variation of the dynamic fault detection model of the independent variable; the obtaining of a plurality of first self-collected data of each part of the robot in a normal working state includes: Control the movements of each part of the robot one by one, and record the corresponding working data based on the movement time; Delineate the data area of ​​the corresponding part based on the working data; Monitoring each of the data areas and collecting corresponding first self-collected data in the data area in real time; If the same first self-collected data exists in the data area, the time of the first self-collected data is traced back, and duplication of the data area is confirmed based on data adjacent to the first self-collected data.

2. The method for real-time fault detection of a robot during motion according to claim 1, characterized in that: The forming of a self-collected training sample set based on the plurality of first self-collected data, and constructing a dynamic fault detection model containing independent variables according to the self-collected training sample set, includes: forming a self-collected training sample set based on the plurality of first self-collected data, and marking corresponding data regions of the self-collected training sample set; Removing duplicates from a plurality of the first self-collected data in the self-collected training sample set, and retaining the first self-collected data that are different from each other; The self-collected training sample set is input into the reference model, and the reference model evolves the input data and output data to construct a dynamic fault detection model including independent variables, wherein the dynamic fault detection model of the independent variables has a model variable, and the model variable serves as the independent variable.

3. The method for real-time fault detection of a robot during motion according to claim 1, characterized in that: The comparing the second self-collected data with the normal operating data corresponding to the dynamic fault detection model of the independent variable to determine whether a fault occurs during the movement of the robot includes: using the second self-collected data as output data of the dynamic fault detection model of the independent variable; Comparing the second self-collected data with the normal working data corresponding to the dynamic fault detection model of the independent variable to determine the data change; wherein the second self-collected data and the normal working data are compared in the dynamic fault detection model of the same independent variable; If the data change amount meets the preset change amount threshold, it is determined that the robot has failed during the movement process.

4. The method for real-time fault detection of a robot during motion according to claim 3, characterized in that: If the robot fails during movement, marking the corresponding fault location based on the second self-collected data, triggering the robot to autonomously repair the fault location, and generating repair data, including: When a fault occurs to the robot, triggering a fault traversal of the robot to determine the corresponding second self-collected data; determining a corresponding location based on the second self-collected data, and marking the corresponding fault location; triggering the robot to autonomously repair the faulty part and repair the second self-collected data; Adjustments are made based on the second self-collected data, and the site is retested to form repair data.

5. The method for real-time fault detection of a robot during motion according to claim 4, characterized in that: The storing of a plurality of the repair data and forming a repair data set from the plurality of the repair data, interacting with the dynamic fault detection model of the independent variable based on the repair data set to form a repair variation of the dynamic fault detection model of the independent variable, includes: storing a plurality of the repair data, and forming the plurality of the repair data into a repair data set; Performing data screening based on the repair data set, performing identical screening on the repair data, and eliminating duplicate data; The repair data set interacts with the dynamic fault detection model of the independent variable, and forms a repair variation of the dynamic fault detection model of the independent variable.

6. The method for real-time fault detection during robot movement according to claim 5, characterized in that: The method for real-time fault detection during robot motion further includes: Obtaining a repair change of a dynamic fault detection model of the independent variable; Performing dynamic adjustment according to the repair variation, and testing the degree of change of the repair variation; A repair system of the dynamic fault detection model of the independent variable is regulated according to the degree of change of the repair change amount.

7. A real-time fault detection system for a robot during motion, characterized in that: The real-time fault detection system of the robot during movement includes: Acquisition module: used to acquire multiple first self-collected data of various parts of the robot under normal working conditions; A training module: configured to form a self-collected training sample set based on the plurality of first self-collected data, and to construct a dynamic fault detection model including independent variables according to the self-collected training sample set; A monitoring module is configured to monitor the real-time working data of each part of the robot and associate the real-time working data with the dynamic fault detection model of the independent variable to output corresponding second self-collected data, including: monitoring the real-time working data of each part of the robot; using the real-time working data as input data of the dynamic fault detection model of the independent variable, and triggering the operation of the dynamic fault detection model of the independent variable as the real-time working data is generated, wherein the dynamic fault detection model of the independent variable is directly associated with the real-time working data; inputting the real-time working data within the framework of the dynamic fault detection model of the independent variable and outputting corresponding second self-collected data; Fault module: used for comparing the second self-collected data with the normal working data corresponding to the dynamic fault detection model of the independent variable to determine whether a fault occurs in the robot during movement; A repair module: configured to, if a fault occurs during the movement of the robot, mark the corresponding fault location based on the second self-collected data, trigger the robot to autonomously repair the fault location, and generate repair data; A storage module is configured to store a plurality of the repair data, and form a repair data set from the plurality of the repair data, interact with the dynamic fault detection model of the independent variable based on the repair data set, and form a repair variation of the dynamic fault detection model of the independent variable; The method of obtaining a plurality of first self-collected data of each part of the robot in a normal working state includes: controlling each part of the robot to move one by one, and recording corresponding working data based on the action time; delineating a data area of ​​the corresponding part based on the working data; monitoring each of the data areas, and collecting the corresponding first self-collected data in the data area in real time; if the same first self-collected data exists in the data area, tracing back the time of the first self-collected data, and duplication confirmation of the data area based on data adjacent to the first self-collected data.

Images