Robot fault detection method and system based on virtual test

Abstract

The invention discloses a robot fault detection method and system based on virtual testing, and the method comprises the steps: defining a fault type set of a robot, and classifying faults in the fault type set of the robot; according to the classified fault type set, constructing a sub-function library of mathematical description of the fault; the sub-functions corresponding to the faults are integrated, and an overall fault judgment function of the robot is defined according to fault cross influence items; fault information of historical tasks of the robot is simulated, and effectiveness testing is conducted on the overall fault judgment function according to the fault information of the historical tasks; and determining a safety control sequence of the robot according to the validity test result, and outputting an overall fault detection result of the robot. According to the method, the fault type set, the fault sub-function library and the overall fault judgment function are defined, and the control parameter sequence is verified and optimized, so that the influence on the robot fault is minimized.

Description

Technical Field

[0001] The present invention relates to the field of robot control technology, and in particular to a robot fault detection method and system based on virtual testing. Background Art

[0002] With the development of robotics technology, robots are widely used in various industrial, commercial and personal applications. However, the complexity of robotic systems also brings potential risks of failure, which may lead to mission failure, property loss and even personal injury.

[0003] Robot fault detection method is one of the key technologies to ensure the stability and safety of robot systems during operation. With the advancement of robot technology, fault detection methods are becoming increasingly diverse and cover different detection needs, such as sensor failure, mechanical failure, electrical failure, etc. Traditional fault handling methods often repair the fault after it occurs, but fail to effectively prevent the occurrence of faults during the execution of tasks or reduce their impact on the tasks.

[0004] Therefore, the prior art needs to be improved. Summary of the invention

[0005] The technical problem to be solved by the present invention is that, in response to the defects of the prior art, the present invention provides a robot fault detection method and system based on virtual testing to solve the problem that the existing robot fault detection and processing methods are unable to prevent faults that occur while a task is being performed or reduce their impact on the task.

[0006] The technical solution adopted by the present invention to solve the technical problem is as follows: In a first aspect, the present invention provides a robot fault detection method based on virtual testing, comprising: defining a fault type set of the robot, and classifying the faults in the fault type set of the robot; According to the classified fault type set, a sub-function library of mathematical description of faults is constructed; Integrate the sub-functions corresponding to each fault, and define the overall fault judgment function of the robot according to the fault cross-influence items; Simulating the fault information of the historical tasks of the robot, and performing a validity test on the overall fault judgment function according to the fault information of the historical tasks; The safety control sequence of the robot is determined according to the effectiveness test result, and the overall fault detection result of the robot is output.

[0007] In one implementation, the defining a robot fault type set and classifying the faults in the robot fault type set includes: Defines the set of fault types for the robot ; According to the degree of impact of each fault on task completion, the faults in the fault type set are divided into three levels: minor, moderate and severe, and the classification mark is used The fault level corresponding to each fault is marked.

[0008] In one implementation, the sub-function library of the mathematical description of the fault is: ; in, Indicates in status and control parameters Next, fault Probability of occurrence; represents the current state vector of the robot; Represents a sequence of control parameters.

[0009] In one implementation, the overall fault judgment function is: ; in, Indicates a fault The weight of Indicates a fault and The cross-impact weights of Indicates a fault and The cross-influence function.

[0010] In one implementation, simulating the fault information of the robot's historical tasks and performing a validity test on the overall fault judgment function according to the fault information of the historical tasks includes: Obtaining historical data corresponding to the historical tasks of the robot; Simulating, according to the historical data, state parameters and control parameters collected when the robot performs the historical task when a fault occurs; Inputting the state parameter and the control parameter into the overall fault judgment function to calculate the overall fault prediction value; The overall fault prediction value is compared with a first threshold, and the validity of the overall fault judgment function is determined according to the comparison result.

[0011] In one implementation, comparing the overall fault prediction value with a first threshold, and determining the validity of the overall fault judgment function according to the comparison result, includes: The overall fault prediction value With the first threshold Make a comparison; If the overall failure prediction value Greater than the first threshold ,and , it is determined that the overall fault judgment function has been verified; Counting the percentage of all cases where the overall fault judgment function passes the verification; Determining whether the percentage is higher than a set value; If the percentage is higher than the set value, it is determined that the overall fault judgment function is valid.

[0012] In one implementation, determining the safety control sequence of the robot according to the effectiveness test result and outputting the overall fault detection result of the robot includes: When it is determined that the overall fault judgment function is valid, the control parameter sequence of the robot is changed so that the overall fault judgment function value is less than a second threshold value , obtain the safety control sequence of the robot; Output the safety control sequence of the robot and the corresponding overall failure probability parameters.

[0013] In a second aspect, the present invention provides a robot fault detection system based on virtual testing, comprising: A fault classification module, used for defining a fault type set of the robot and classifying the faults in the fault type set of the robot; A sub-function library module is used to construct a sub-function library for mathematical description of faults according to the classified fault type set; An overall fault judgment function module is used to integrate the sub-functions corresponding to each fault and define the overall fault judgment function of the robot according to the cross-impact items of the faults; A validity test module, used for simulating the fault information of the historical tasks of the robot, and performing a validity test on the overall fault judgment function according to the fault information of the historical tasks; The safety control sequence module is used to determine the safety control sequence of the robot according to the effectiveness test result and output the overall fault detection result of the robot.

[0014] In a third aspect, the present invention provides a terminal comprising: a processor and a memory, wherein the memory stores a robot fault detection program based on virtual testing, and when the robot fault detection program based on virtual testing is executed by the processor, it is used to implement the operation of the robot fault detection method based on virtual testing as described in the first aspect.

[0015] In a fourth aspect, the present invention further provides a medium, which is a computer-readable storage medium, and which stores a robot fault detection program based on virtual testing. When the robot fault detection program based on virtual testing is executed by a processor, it is used to implement the operation of the robot fault detection method based on virtual testing as described in the first aspect.

[0016] The present invention adopts the above technical solution to achieve the following effects: The present invention minimizes the impact of robot failures by defining a set of fault types, a fault sub-function library, and an overall fault judgment function, and by verifying and optimizing a control parameter sequence. The method provided by the present invention can effectively improve the task completion rate of the robot in fault conditions through virtual testing, reduce the risk of equipment damage and personal injury, and has important practical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 the structures shown in these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of the robot fault detection method based on virtual testing in the present invention.

[0019] Figure 2 It is a schematic diagram of the process flow of the method for reducing robot failures through virtual testing in the present invention.

[0020] Figure 3 It is a schematic diagram for verifying the effectiveness of the overall fault judgment function in the present invention.

[0021] Figure 4 It is a schematic diagram of determining the safety control sequence in the present invention.

[0022] Figure 5 It is a functional principle diagram of a terminal in one implementation of the present invention.

[0023] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0025] Exemplary Methods At present, robot fault detection method is one of the key technologies to ensure the stability and safety of robot systems during operation. With the advancement of robot technology, fault detection methods are becoming increasingly diverse and cover different detection needs, such as sensor failure, mechanical failure, electrical failure, etc. Traditional fault handling methods often repair the fault after it occurs, but fail to effectively prevent the occurrence of faults during the execution of tasks or reduce their impact on the tasks.

[0026] In view of the problem that the existing robot fault detection and processing methods cannot prevent faults that occur during the execution of tasks or reduce their impact on the tasks, a robot fault detection method based on virtual testing is provided in an embodiment of the present invention. The method defines a set of fault types of the robot and classifies the faults in the set of fault types of the robot; a sub-function library of mathematical descriptions of faults can be constructed according to the classified set of fault types; the sub-functions corresponding to each fault are integrated, and the overall fault judgment function of the robot is defined according to the cross-impact items of the faults; and the fault information of the historical tasks of the robot is simulated, and the validity of the overall fault judgment function is tested according to the fault information of the historical tasks; the safety control sequence of the robot can be determined according to the validity test results, and the overall fault detection result of the robot can be output. Therefore, in the embodiment of the present invention, by defining a set of fault types, a fault sub-function library, an overall fault judgment function, and by verifying and optimizing the control parameter sequence, the impact of robot faults can be minimized.

[0027] like Figure 1 As shown, an embodiment of the present invention provides a robot fault detection method based on virtual testing, comprising the following steps: Step S100, defining a fault type set of the robot, and classifying the faults in the fault type set of the robot.

[0028] In this embodiment, the method is a method that can reduce robot failures through virtual testing to improve the reliability and work efficiency of the robot; therefore, when a robot fails, the method can minimize the impact of the failure by optimizing the control parameter sequence.

[0029] like Figure 2 As shown, the implementation process of the method for reducing robot failures through virtual testing in this embodiment mainly includes: S11, definition and classification of fault types; S12, fault sub-function library construction; S13, overall fault judgment function design; S14, verifying the validity of the overall fault judgment function; S15, determine the safety control sequence; S16, output results (output safety control sequence).

[0030] In the process of fault type definition and classification, a The classification method, in which each Represents a specific type of fault. According to the degree of impact of the fault on task completion, the fault is divided into three levels: minor (Class 1), moderate (Class 2) and severe (Class 3). , which can clearly indicate the severity of each fault. In addition, this embodiment also distinguishes the fault set affected by the control operation and the set of faults that are not affected by the control operation , focusing on the former to minimize the impact of failures.

[0031] Specifically, in an implementation of this embodiment, step S100 includes the following steps: Step S101, defining the fault type set of the robot ; Step S102: classify the faults in the fault type set into three levels: slight, medium and severe according to the degree of impact of each fault on task completion, and use classification identifiers The fault level corresponding to each fault is marked.

[0032] As an example, in this embodiment, when defining and classifying the fault types of the robot, a set of possible fault types of the robot is first defined. ,in represents the i-th fault type.

[0033] Then, according to the degree of impact of the fault on task completion, the faults are divided into the following three categories: 1. Minor fault (Class 1): has little impact on task completion and can usually be resolved through self-repair or simple adjustment.

[0034] 2. Moderate failure (Class 2): has a certain impact on task completion and may require manual intervention or restarting the robot.

[0035] 3. Serious failure (Class 3): The task cannot be completed and urgent repair or replacement of parts is required.

[0036] Finally, use Indicates a fault The classification level, . To mark each fault after classification.

[0037] It is worth mentioning that in this embodiment, faults affected by control operations can also be distinguished: Definition is the set of faults affected by the control operation, The present embodiment is directed to a set of faults that are affected by the control operation.

[0038] In this embodiment, a set of fault types is defined, and faults are divided into three levels: minor, moderate, and severe, and a corresponding weight is set for each fault. This classification method not only considers the characteristics of the fault itself, but also combines the degree of impact of the fault on task completion, which can more accurately evaluate the impact of the fault.

[0039] like Figure 1 As shown, an embodiment of the present invention provides a robot fault detection method based on virtual testing, comprising the following steps: Step S200: construct a sub-function library of mathematical description of faults according to the classified fault type set.

[0040] In this embodiment, during the construction of the fault sub-function library, a fault sub-function library is proposed. , which contains mathematical models of faults for different tasks These sub-functions are used to receive the input robot state vector and the control parameter vector , and outputs a fault in a given state The probability of occurrence. That is, the constructed sub-function library can accurately describe the probability of each fault, which can quantify how various factors affect the occurrence of faults.

[0041] As an example, in this embodiment, a sub-function library of mathematical descriptions of various faults is defined. For example, for a control task of moving from point a to point b, the sub-functions in the library describe the mathematical expressions of various faults of the robot from parts to the whole machine that may cause the failure of the task. The inputs of these sub-functions are the robot's own state parameters when performing the task and the control instruction parameters (or sequence) when performing the task, and the output of each sub-function is the probability of causing the failure of the task.

[0042] Specifically, the sub-function library of the mathematical description of the fault is: ; in, Indicates in status and control parameters Next, fault Probability of occurrence; represents the current state vector of the robot; Represents a sequence of control parameters.

[0043] In this embodiment, a sub-function library containing multiple fault mathematical models is constructed, which can accept the robot's state vector and control parameter vector as input and output the probability of fault occurrence. This can quantify how different factors affect the occurrence of faults and provide data support for optimizing control strategies.

[0044] like Figure 1 As shown, an embodiment of the present invention provides a robot fault detection method based on virtual testing, comprising the following steps: Step S300, integrating the sub-functions corresponding to each fault, and defining the overall fault judgment function of the robot according to the fault cross-influence items.

[0045] In this embodiment, in the process of designing the overall fault judgment function, an overall fault judgment function is proposed. This function not only combines the impact of a single fault, but also adds the interaction between faults. , and assigns corresponding weights to each fault and its cross-effect and In this way, It can more accurately predict the probability of failure due to malfunction when the robot performs a task.

[0046] As an example, in this embodiment, the fault sub-functions are integrated, the cross-effect items of the faults are considered, and the overall fault judgment function is defined as , the fault judgment function outputs the probability of failure of the robot to perform task i due to various faults.

[0047] Specifically, the overall fault judgment function is: ; in, Indicates a fault The weight of Indicates a fault and The cross-impact weights of Indicates a fault and The cross-influence function.

[0048] This embodiment integrates all fault sub-functions, takes into account the cross-effects between faults, and assigns corresponding weights to each fault and its cross-effect, which can more accurately predict the probability of failure due to faults when the robot performs a task.

[0049] like Figure 1As shown, an embodiment of the present invention provides a robot fault detection method based on virtual testing, comprising the following steps: Step S400, simulating the fault information of the historical tasks of the robot, and performing a validity test on the overall fault judgment function according to the fault information of the historical tasks.

[0050] In this embodiment, a verification scheme is proposed in the process of verifying the effectiveness of the overall fault judgment function. , that is, the robot's state parameters, control parameters, and information on whether a failure actually occurred when it performed a task in the past, to test By setting the threshold (e.g., 0.8), the performance of the function in predicting failures can be evaluated. If the function can correctly predict failures in most cases, it is considered effective; otherwise, it can be improved by adjusting the weights of each sub-function.

[0051] Specifically, in an implementation of this embodiment, step S400 includes the following steps: Step S401, obtaining historical data corresponding to the historical tasks of the robot; Step S402, simulating the state parameters and control parameters collected when the robot performs the historical task according to the historical data when a fault occurs; Step S403, inputting the state parameter and the control parameter into the overall fault judgment function to calculate the overall fault prediction value; Step S404: compare the overall fault prediction value with the first threshold, and determine the validity of the overall fault judgment function according to the comparison result.

[0052] In one implementation of this embodiment, step S404 includes the following steps: Step S404a, the overall fault prediction value With the first threshold Make a comparison; Step S404b, if the overall fault prediction value Greater than the first threshold ,and , it is determined that the overall fault judgment function has been verified; Step S404c, counting the percentage of all cases where the overall fault judgment function passes the verification; Step S404d, determining whether the percentage is higher than a set value; Step S404e: if the percentage is higher than the set value, it is determined that the overall fault judgment function is valid.

[0053] As an example, in this embodiment, historical data corresponding to the robot's historical tasks are obtained, wherein the historical data include: state parameters, control parameters, and information on whether an actual fault has occurred; by simulating the typical control instructions collected multiple times when the robot has performed a task in history, the effectiveness of the overall fault judgment function is tested.

[0054] The simulation data used to verify the effectiveness of the overall fault judgment function in this embodiment is: ; in, Represents: the state parameters of the robot when the robot fails to complete the task due to a fault for the kth time.

[0055] Represents: the control parameters of the robot when the robot fails to complete the task due to a fault for the kth time.

[0056] Represents: the actual fault condition of the kth simulation (where 0 represents no fault and 1 represents a fault).

[0057] Set the first threshold: ,For example, is 0.8.

[0058] like Figure 3 As shown, the verification process of the validity of the overall fault judgment function is as follows: S21, calculation ; S22, will With setting threshold Compare; S23, judgment and Is it established? If yes, go to step S25; if no, go to step S24; S24, determining that the verification has not passed; S25, Statistics The percentage of cases that passed the verification out of all cases; S26, Judgment Verify whether the pass percentage > the set value; if yes, execute step S28; if no, execute step S27; S27, adjust weight and ; S28, judgment efficient.

[0059] In the actual effectiveness verification process, suppose that the robot has failed to perform a certain task n times in history, and the robot's own and environmental state parameters before performing the task when the kth failure occurs have been collected. , and the control parameter sequence used by the robot to perform the task ,Will As an overall fault judgment function Input, calculate this time The value of is determined by whether its output value is greater than the threshold value to determine whether the overall fault judgment function is successfully verified.

[0060] 4.1. Suppose that we need to verify n typical control instructions when a certain task is executed and a failure occurs. For each simulation case k, calculate ; 4.2 If and , then the simulation is considered to have been verified successfully, otherwise it is considered to have failed the verification.

[0061] 4.3. Count the percentage of cases where the overall fault judgment function passes verification in all cases. If the percentage is higher than a set value (for example, 90%), the overall fault judgment function is considered valid.

[0062] 4.4. If the ratio is less than or equal to the set value (for example, 90%), the overall fault judgment function is considered invalid, and the weights of each sub-function in the overall fault judgment function must be adjusted and 4.1 to 4.3 must be repeated until the overall fault judgment function after adjusting the weight has a ratio higher than the set value when verifying all situations. The overall fault judgment function is considered valid.

[0063] In this embodiment, a verification scheme based on historical data is proposed to test the effectiveness of the overall fault judgment function. The performance of the function in predicting faults can be evaluated by setting a threshold to ensure its reliability.

[0064] like Figure 1 As shown, an embodiment of the present invention provides a robot fault detection method based on virtual testing, comprising the following steps: Step S500, determining the safety control sequence of the robot according to the effectiveness test result, and outputting the overall fault detection result of the robot.

[0065] In this embodiment, in the process of determining the safety control sequence, it is necessary to determine a safety control sequence that can minimize the probability of failure. To this end, the second threshold is set in this embodiment. (e.g., 0.2), and adjust the control parameter sequence by iterative adjustment Until a condition is met ,Right now The final output safety control sequence ensures that the robot can successfully complete the task with the lowest possible risk of failure, while providing the overall failure probability at this time. For reference.

[0066] Specifically, in an implementation of this embodiment, step S500 includes the following steps: Step S501: when it is determined that the overall fault judgment function is valid, the control parameter sequence of the robot is changed so that the overall fault judgment function value is less than a second threshold value. , obtain the safety control sequence of the robot; Step S502, outputting the safety control sequence of the robot and the corresponding overall failure probability parameters.

[0067] As an example, in this embodiment, after confirming that the overall fault judgment function is valid, the control parameter sequence is changed so that the overall fault judgment function value is less than the second threshold, thereby determining the safety control sequence.

[0068] Set the second threshold: (e.g., 0.2); like Figure 4 As shown, the safety control sequence of the robot includes: S31, initialization control parameter sequence ; S32, calculation , and set the threshold Compare; S33, judgment Is it established? If yes, go to step S35; if no, go to step S34; S34, adjust the control parameter sequence , return to step S32; S35, output safety control sequence .

[0069] In the actual process of optimizing the safety control sequence, when initializing the control parameter sequence After that, the control parameter sequence is iteratively adjusted. , then stop the iteration and output the safety control sequence Otherwise, continue to adjust the control parameter sequence and repeat steps S32 and S33 until the set number of iterations is reached.

[0070] This embodiment provides a method for iteratively adjusting a control parameter sequence to find a safe control sequence that can minimize the probability of failure, thereby ensuring that the robot can successfully complete the task with the lowest possible risk of failure.

[0071] This embodiment achieves the following technical effects through the above technical solution: This embodiment minimizes the impact of robot failures by defining a set of fault types, a fault sub-function library, and an overall fault judgment function, and by verifying and optimizing a control parameter sequence. The method provided in this embodiment can effectively improve the robot's task completion rate in fault conditions through virtual testing, reduce the risk of equipment damage and personal injury, and has important practical application value.

[0072] Exemplary Devices Based on the above embodiments, the present invention further provides a robot fault detection system based on virtual testing, comprising: A fault classification module, used for defining a fault type set of the robot and classifying the faults in the fault type set of the robot; A sub-function library module is used to construct a sub-function library for mathematical description of faults according to the classified fault type set; An overall fault judgment function module is used to integrate the sub-functions corresponding to each fault and define the overall fault judgment function of the robot according to the cross-impact items of the faults; A validity test module, used for simulating the fault information of the historical tasks of the robot, and performing a validity test on the overall fault judgment function according to the fault information of the historical tasks; The safety control sequence module is used to determine the safety control sequence of the robot according to the effectiveness test result and output the overall fault detection result of the robot.

[0073] This embodiment achieves the following technical effects through the above technical solution: This embodiment minimizes the impact of robot failures by defining a set of fault types, a fault sub-function library, and an overall fault judgment function, and by verifying and optimizing a control parameter sequence. The method provided in this embodiment can effectively improve the robot's task completion rate in fault conditions through virtual testing, reduce the risk of equipment damage and personal injury, and has important practical application value.

[0074] Based on the above embodiment, the present invention further provides a terminal, whose principle block diagram can be as follows: Figure 5 shown.

[0075] The terminal includes: a processor, a memory, an interface, a display screen and a communication module connected through a system bus; wherein the processor of the terminal is used to provide computing and control capabilities; the memory of the terminal includes a storage medium and an internal memory; the storage medium stores an operating system and a computer program; the internal memory provides an environment for the operation of the operating system and the computer program in the storage medium; the interface is used to connect to external devices; the display screen is used to display corresponding information; and the communication module is used to communicate with a cloud server or other devices.

[0076] When the computer program is executed by a processor, it is used to implement the operation of a robot fault detection method based on virtual testing.

[0077] It can be understood by those skilled in the art that Figure 5 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0078] In one embodiment, a terminal is provided, which includes: a processor and a memory, wherein the memory stores a robot fault detection program based on virtual testing, and the robot fault detection program based on virtual testing is used to implement the operation of the above-mentioned robot fault detection method based on virtual testing when executed by the processor.

[0079] In one embodiment, a storage medium is provided, wherein the storage medium stores a robot fault detection program based on virtual testing, and when the robot fault detection program based on virtual testing is executed by a processor, it is used to implement the operation of the robot fault detection method based on virtual testing as described above.

[0080] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and volatile memory.

[0081] In summary, the present invention provides a robot fault detection method and system based on virtual testing, including: defining a robot fault type set, and classifying the faults in the robot fault type set; constructing a sub-function library of mathematical descriptions of faults according to the classified fault type set; integrating the sub-functions corresponding to each fault, and defining the overall fault judgment function of the robot according to the cross-impact terms of the faults; simulating the fault information of the robot's historical tasks, and performing validity testing on the overall fault judgment function according to the fault information of the historical tasks; determining the robot's safety control sequence according to the validity test results, and outputting the robot's overall fault detection results. The present invention minimizes the impact of robot faults by defining a fault type set, a fault sub-function library, an overall fault judgment function, and by verifying and optimizing the control parameter sequence.

[0082] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A robot fault detection method based on virtual testing, characterized in that: include: defining a fault type set of the robot, and classifying the faults in the fault type set of the robot; According to the classified fault type set, a sub-function library of mathematical description of faults is constructed; Integrate the sub-functions corresponding to each fault, and define the overall fault judgment function of the robot according to the fault cross-influence item; Simulating the fault information of the historical tasks of the robot, and performing a validity test on the overall fault judgment function according to the fault information of the historical tasks; The safety control sequence of the robot is determined according to the effectiveness test result, and the overall fault detection result of the robot is output.

2. The robot fault detection method based on virtual testing according to claim 1, characterized in that: The defining of a robot fault type set and classifying the faults in the robot fault type set includes: Defines the set of fault types for the robot ; According to the degree of impact of each fault on task completion, the faults in the fault type set are divided into three levels: minor, moderate and severe, and the classification mark is used The fault level corresponding to each fault is marked.

3. The robot fault detection method based on virtual testing according to claim 1, characterized in that: The sub-function library of the mathematical description of the fault is: ； in, Indicates in status and control parameters Next, fault Probability of occurrence; represents the current state vector of the robot; Represents a sequence of control parameters.

4. The robot fault detection method based on virtual testing according to claim 1, characterized in that: The overall fault judgment function is: ； in, Indicates a fault The weight of Indicates a fault and The cross-impact weights of Indicates a fault and The cross-influence function.

5. The robot fault detection method based on virtual testing according to claim 1, characterized in that: The simulating the fault information of the historical tasks of the robot and performing validity testing on the overall fault judgment function according to the fault information of the historical tasks includes: Obtaining historical data corresponding to the historical tasks of the robot; Simulating, according to the historical data, state parameters and control parameters collected when the robot performs the historical task when a fault occurs; Inputting the state parameter and the control parameter into the overall fault judgment function to calculate the overall fault prediction value; The overall fault prediction value is compared with a first threshold, and the validity of the overall fault judgment function is determined according to the comparison result.

6. The robot fault detection method based on virtual testing according to claim 5, characterized in that: Comparing the overall fault prediction value with the first threshold, and determining the validity of the overall fault judgment function according to the comparison result, includes: The overall fault prediction value With the first threshold Make a comparison; If the overall failure prediction value Greater than the first threshold ,and , it is determined that the overall fault judgment function has been verified; Counting the percentage of all cases where the overall fault judgment function passes the verification; Determining whether the percentage is higher than a set value; If the percentage is higher than the set value, it is determined that the overall fault judgment function is valid.

7. The robot fault detection method based on virtual testing according to claim 1, characterized in that: Determining the safety control sequence of the robot according to the effectiveness test result and outputting the overall fault detection result of the robot includes: When it is determined that the overall fault judgment function is valid, the control parameter sequence of the robot is changed so that the overall fault judgment function value is less than a second threshold value , obtain the safety control sequence of the robot; Output the safety control sequence of the robot and the corresponding overall failure probability parameters.

8. A robot fault detection system based on virtual testing, characterized in that: include: A fault classification module, used for defining a fault type set of the robot and classifying the faults in the fault type set of the robot; A sub-function library module is used to construct a sub-function library for mathematical description of faults according to the classified fault type set; An overall fault judgment function module is used to integrate the sub-functions corresponding to each fault and define the overall fault judgment function of the robot according to the cross-impact items of the faults; A validity test module, used for simulating the fault information of the historical tasks of the robot, and performing a validity test on the overall fault judgment function according to the fault information of the historical tasks; The safety control sequence module is used to determine the safety control sequence of the robot according to the effectiveness test result and output the overall fault detection result of the robot.

9. A terminal, characterized in that: include: A processor and a memory, wherein the memory stores a robot fault detection program based on virtual testing, and when the robot fault detection program based on virtual testing is executed by the processor, it is used to implement the operation of the robot fault detection method based on virtual testing as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a robot fault detection program based on virtual testing, and when the robot fault detection program based on virtual testing is executed by a processor, it is used to implement the operation of the robot fault detection method based on virtual testing as described in any one of claims 1-7.

Images