Fault processing method of robot, electronic equipment and computer program product

Abstract

The invention is suitable for the technical field of robots, and provides a robot fault processing method, electronic equipment and a computer program product. The fault processing method of the robot comprises the steps that robot data of the robot are acquired, and the robot data comprise real-time operation information and / or historical fault data; adjusting a fault probability threshold according to the robot data; and according to the fault probability threshold value, when it is detected that the robot breaks down, fault processing is carried out. According to the embodiment of the invention, the adaptability of fault detection to a complex operation environment can be improved.

Description

Technical Field

[0001] The present application belongs to the field of robot technology, and in particular, relates to a robot fault handling method, electronic equipment and computer program product. Background Art

[0002] A robot is an intelligent machine that can work semi-autonomously or fully autonomously. It can move to the work area autonomously through navigation to perform tasks. Fault detection is an important means to ensure the reliability of robot operation. Traditional robot fault detection methods mainly rely on regular maintenance and manual inspection, which are inefficient and prone to missed detection or false detection. Some related technologies will use robot autonomous fault detection, but the current autonomous fault detection method is difficult to adapt to the complex operating environment of robots. Summary of the invention

[0003] The embodiments of the present application provide a robot fault handling method, electronic device and computer program product, which can solve the problem in related technologies that robot fault detection is difficult to adapt to the complex operating environment of the robot.

[0004] A first aspect of an embodiment of the present application provides a robot fault handling method, comprising: acquiring robot data of the robot, the robot data including real-time operation information and / or historical fault data; adjusting a fault probability threshold according to the robot data; and performing fault handling when a robot fault is detected according to the fault probability threshold.

[0005] In some embodiments of the first aspect, the robot data includes real-time operation information, and adjusting the fault probability threshold based on the robot data includes: determining the current task load of the robot based on the real-time operation information; when the task load is higher than a first load threshold, lowering the failure probability threshold; when the task load is lower than a second load threshold, increasing the failure probability threshold, the second load threshold being less than or equal to the first load threshold.

[0006] In some embodiments of the first aspect, the robot data includes real-time operation information, and adjusting the fault probability threshold based on the robot data includes: determining the environmental complexity of the robot's current operating environment based on the real-time operation information; when the environmental complexity is higher than a first complexity threshold, lowering the fault probability threshold.

[0007] In some embodiments of the first aspect, the robot data includes historical fault data, and adjusting the fault probability threshold based on the robot data includes: determining a historical failure frequency of the robot based on the historical failure data; when the historical failure frequency is higher than a first frequency threshold, lowering the failure probability threshold; when the historical failure frequency is lower than a second frequency threshold, increasing the failure probability threshold, the second frequency threshold being less than or equal to the first frequency threshold.

[0008] In some embodiments of the first aspect, when a fault of the robot is detected according to the fault probability threshold, fault processing is performed, including: estimating the failure probability of various preset faults of the robot in a future time period according to historical fault data; determining a fault to be detected among the various preset faults according to the failure probability; when the future time period arrives, performing fault detection on the robot according to real-time information corresponding to the fault to be detected and the fault probability threshold; and performing fault processing when a fault of the robot is detected.

[0009] In some embodiments of the first aspect, the failure probability of each type of preset failure of the robot in a future time period is estimated based on the historical failure data, including: obtaining the historical work data of the robot, the historical work data including historical working hours and attendance numbers; inputting the historical work data and the historical failure data into a failure analysis model, and determining the failure probability based on the output result of the failure analysis model.

[0010] In some embodiments of the first aspect, the inputting the historical working data and the historical fault data into a fault analysis model, and determining the fault probability according to the output result of the fault analysis model, comprises: inputting the historical working data and the historical fault data into a plurality of fault analysis models to obtain the output result of each fault analysis model; different fault analysis models are used to extract different types of data features, and output the fault probability according to the extracted data features; and the output results of each fault analysis model are fused to obtain the fault probability.

[0011] In some embodiments of the first aspect, the process of outputting the fault probability in the first fault analysis mode in the fault analysis model includes: determining common data features exhibited by multiple sensors; and determining the fault probability based on the common data features.

[0012] A second aspect of an embodiment of the present application provides a robot fault handling device, comprising: an acquisition unit, used to acquire robot data of the robot, the robot data including real-time operation information and / or historical fault data; an adjustment unit, used to adjust a fault probability threshold according to the robot data; and a fault handling unit, used to perform fault handling when a robot fault is detected according to the fault probability threshold.

[0013] A third aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned robot fault handling method when executing the computer program.

[0014] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned robot fault handling method are implemented.

[0015] A fifth aspect of an embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the steps of the above-mentioned robot fault handling method.

[0016] In an embodiment of the present application, the fault probability threshold is adjusted according to the robot data of the robot, and fault processing is performed according to the fault probability threshold when a robot fault is detected. Since the robot data includes real-time operation information and / or historical fault data, the fault probability threshold can be adjusted according to the real-time or historical situation of the robot, so that the fault processing can adapt to the operating environment of the robot, thereby improving the adaptability of fault detection to complex operating environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] Figure 1 It is a schematic diagram of the implementation flow of a robot fault handling method provided in an embodiment of the present application;

[0019] Figure 2 is a schematic diagram of the structure of the robot provided in an embodiment of the present application;

[0020] Figure 3 It is a structural schematic diagram of a robot fault handling device provided in an embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are protected by the present application.

[0023] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0024] In the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0025] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0026] Some related technologies will adopt the method of autonomous fault detection by robots, but the current autonomous fault detection method is difficult to adapt to the complex operating environment of robots.

[0027] In view of this, the present application proposes a robot fault handling method, which can adjust the fault probability threshold according to the real-time or historical situation of the robot, so that the fault handling can adapt to the operating environment of the robot and improve the adaptability of fault detection to complex operating environments.

[0028] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0029] Figure 1The present invention provides a schematic diagram of a robot fault handling method according to an embodiment of the present invention, which can be applied to an electronic device. The electronic device can be a computer, a mobile phone or other intelligent device for controlling or communicating with the robot, or the robot itself.

[0030] Specifically, the robot fault handling method may include the following steps S101 to S103.

[0031] Step S101, obtaining robot data of the robot.

[0032] The robot data may include real-time operation information and / or historical fault data. The real-time operation information may include the real-time status of the robot and the collected environmental information, which can reflect the actual working condition of the robot. The historical fault data may include the fault type and time of the fault that occurred in the past, which can reflect the working condition of the robot in the past operation process.

[0033] Step S102, adjusting the fault probability threshold according to the robot data.

[0034] In an embodiment of the present application, the fault probability threshold can be adjusted according to the real-time operation information and / or the historical fault data, so that the fault probability threshold is related to the real-time operation information and / or the historical fault data. The fault probability threshold is used to determine whether the robot has a fault.

[0035] Step S103, when a robot failure is detected, fault processing is performed according to the fault probability threshold.

[0036] Specifically, when the failure probability of the robot is greater than or equal to the failure probability threshold, it can be confirmed that the robot has failed and corresponding failure processing is performed. When the failure probability of the robot is less than the failure probability threshold, it can be confirmed that the robot has not failed.

[0037] Among them, fault handling may include but is not limited to sending warning information to remind maintenance, automatic restart or power off. Specifically, the warning information may carry the robot identification, current failure rate, recommended maintenance time, etc. The warning information can be delivered to the relevant maintenance personnel via email, SMS, etc. At the same time, the triggering time and content of the warning information can be recorded for subsequent tracking and management.

[0038] In an embodiment of the present application, the fault probability threshold is adjusted according to the robot data of the robot, and fault processing is performed according to the fault probability threshold when a robot fault is detected. Since the robot data includes real-time operation information and / or historical fault data, the fault probability threshold can be adjusted according to the real-time or historical situation of the robot, so that the fault processing can adapt to the operating environment of the robot, thereby improving the adaptability of fault detection to complex operating environments.

[0039] Specifically, in some embodiments of the present application, if the robot data includes real-time operation information, adjusting the fault probability threshold according to the robot data includes: determining the current task load of the robot according to the real-time operation information. When the task load is higher than a first load threshold, lowering the fault probability threshold. When the task load is lower than a second load threshold, raising the fault probability threshold.

[0040] Specifically, the real-time operation information may include information such as the task type and time of the task currently being executed by the robot and the task waiting to be executed, which can be used to evaluate the current task load of the robot. The task load represents the workload of the robot, and the load threshold is used to determine whether the task load of the robot is high or low.

[0041] When the task load is higher than the first load threshold, it means that the current task load of the robot is high, the robot is in a busy state, and the possibility of a fault is high. At this time, the fault probability threshold is lowered to detect the fault more timely. When the task load is lower than the second load threshold, it means that the robot is in a relatively idle state and the possibility of a fault is low. At this time, increasing the fault probability threshold can reduce unnecessary maintenance. The second load threshold is less than or equal to the first load threshold.

[0042] Correspondingly, if the task load is less than or equal to the first load threshold, or greater than or equal to the second load threshold, it means that the task load of the robot is moderate and the original failure probability threshold can be maintained.

[0043] In other embodiments of the present application, if the robot data includes real-time operation information, adjusting the fault probability threshold according to the robot data may include: determining the environmental complexity of the robot's current operating environment according to the real-time operation information, and when the environmental complexity is higher than a first complexity threshold, lowering the fault probability threshold.

[0044] Specifically, the real-time operation information may include sensor information detected by the robot in real time, which can be used to evaluate the environmental complexity of the robot's current operating environment. The complexity threshold is used to determine whether the robot's current operating environment is relatively complex.

[0045] When the environmental complexity is higher than the first complexity threshold, it means that the current operating environment of the robot is relatively complex and the possibility of failure is high. At this time, the failure probability threshold is lowered to detect the failure more timely.

[0046] Correspondingly, if the environmental complexity is less than or equal to the first complexity threshold, it means that the current operating environment of the robot is simple, and the original fault probability threshold can be maintained. In other embodiments of the present application, if the robot data includes real-time operating information, adjusting the fault probability threshold according to the robot data may include: determining the health of the robot according to the real-time operating information, and if the health is lower than the first health threshold, lowering the fault probability threshold.

[0047] Specifically, the real-time operation information may include sensor information detected by the robot in real time, battery power, continuous operation time, etc., which can be used to evaluate the health of the robot. The health threshold is used to determine whether the robot is in a healthy state.

[0048] If the health level is lower than the first health level threshold, it means that the robot is in an unhealthy state. At this time, the fault probability threshold is lowered to detect the fault more timely. Correspondingly, if the health level is greater than or equal to the first health level threshold, it means that the robot is in a healthy state, and the original fault probability threshold can be maintained.

[0049] In some other embodiments of the present application, if the robot data includes historical fault data, adjusting the fault probability threshold according to the robot data includes: determining the historical fault frequency of the robot according to the historical fault data. When the historical fault frequency is higher than a first frequency threshold, lowering the fault probability threshold; when the historical fault frequency is lower than a second frequency threshold, raising the fault probability threshold.

[0050] Specifically, the historical fault data may include the type and number of faults that have occurred in the history of the robot, which can be used to determine the historical fault frequency of the robot. The frequency threshold is used to determine whether the frequency of past faults of the robot is high or low.

[0051] When the historical fault frequency is higher than the first frequency threshold, it means that the robot fault is more likely to occur again. At this time, the fault probability threshold is lowered to detect the fault more promptly. When the historical fault frequency is lower than the second frequency threshold, it means that the robot is not prone to failure. At this time, increasing the fault probability threshold can reduce unnecessary maintenance. The second frequency threshold is less than or equal to the first frequency threshold.

[0052] Correspondingly, if the historical failure frequency is less than or equal to the first frequency threshold, or greater than or equal to the second frequency threshold, it means that the failure frequency of the robot is moderate and the original failure probability threshold can be maintained.

[0053] It is understandable that the above-mentioned increase or decrease in the fault probability threshold may refer to adjustment according to a specific step size, such as 5% each time; the corresponding adjustment amount may also be set according to the triggering condition of the adjustment, such as increasing by 10% when the historical fault frequency is higher than the first frequency threshold, and decreasing by 5% when the environmental complexity is higher than the first complexity threshold, and this application does not impose any restrictions on this. In practical applications, any number of the above-mentioned task load, environmental complexity, health level, and historical fault frequency may be comprehensively evaluated to adjust the fault probability threshold.

[0054] Combined with the adjusted fault probability threshold, the robot can perform fault handling in real time.

[0055] For details, please refer to Figure 2 , according to the fault probability threshold, when a robot fault is detected, fault processing is performed, which may include steps S201 to S204.

[0056] Step S201, based on historical fault data, estimate the failure probability of various preset faults of the robot in the future time period.

[0057] In some embodiments of the present application, historical fault data can be used to determine the failure frequency of various preset faults of the robot. Since robots often have the same failure repeatedly, the failure frequency of various preset faults can be used to estimate the failure probability of various preset faults of the robot in future time periods.

[0058] In some embodiments of the present application, based on historical fault data, estimating the failure probability of various preset faults of the robot in future time periods can include: obtaining the historical working data of the robot; inputting the historical working data and historical fault data into a fault analysis model, and determining the failure probability based on the output results of the fault analysis model.

[0059] The historical work data may include historical working hours and attendance numbers. Attendance numbers refer to the number of times a robot has been present in a certain period of time, and historical working hours may include the specific duration of each work task of the robot. The fault analysis model may extract features from historical working hours, attendance numbers, and information such as the fault type and number of faults of the robot's historical faults, and output the fault probability based on the features.

[0060] It should be noted that the fault analysis model may be a model using logistic regression, decision tree, random forest or other existing machine learning algorithms, and this application does not impose any restrictions on this.

[0061] In order to ensure the reliability of the output results, in some embodiments of the present application, historical working data and historical fault data are input into a fault analysis model, and the fault probability is determined based on the output results of the fault analysis model, which may include: inputting the historical working data and the historical fault data into multiple fault analysis models to obtain the output results of each fault analysis model; and fusing the output results of each fault analysis model to obtain the fault probability.

[0062] Among them, different fault analysis models can be used to extract different types of data features and output the fault probability based on the extracted data features.

[0063] Specifically, the above-mentioned different types of data features may include common data features. The process of outputting the fault probability in the first fault analysis mode in the fault analysis model may include: determining the common data features exhibited by multiple sensors; and determining the fault probability based on the common data features. For example, the principal component analysis method (PCA) dimensionality reduction technology or clustering model may be used to identify abnormal features commonly exhibited on multiple sensors to obtain common data features.

[0064] In other implementations, the above different types of data features may also include but are not limited to: 1. Time-related features (such as working hours, periodicity): time series models can be used to capture the time dependency of data and identify trends and periodic anomalies. 2. Static features (such as sensor readings, temperature, current): anomaly detection models are used to identify abnormal data that fluctuates significantly or exceeds a preset threshold.

[0065] For the output results of each fault analysis model, a fusion strategy can be used to fuse them to obtain the fault probability. The fusion strategy may include but is not limited to: weighted fusion, assigning different weights according to the performance and reliability of each fault analysis model, combining the output results of multiple fault analysis models, voting method, selecting the prediction results of most fault analysis models as the final decision, serial fusion, the output of multiple fault analysis models is used as input and sent to another model or decision layer for further analysis, hierarchical fusion, using different fault analysis models at different levels for anomaly detection, and then summarizing the results of each level to make the final decision. By fusing the output results of each fault analysis model to obtain the fault probability, the fault probability can refer to different types of features to improve the accuracy of the fault probability.

[0066] In order to ensure the reliability of input data, in some implementations, historical fault data and historical working data can be preprocessed in advance. Preprocessing includes but is not limited to: data cleaning, such as removing invalid, duplicate or abnormal data to ensure data accuracy; standardization: standardizing data so that data of different dimensions have consistent dimensions to facilitate subsequent analysis and modeling.

[0067] In order to ensure the reliability of the output results, in some implementations, each fault analysis model may be cross-validated to evaluate the reliability of each fault analysis model.

[0068] In order to ensure the reliability of the fault probability, in some implementations, the output results of the target fault analysis model may be selected for fusion. The target fault analysis model is a complementary model, thereby reducing the overlapping blind spots between different fault analysis models.

[0069] Step S202: determining a to-be-detected fault from among various preset faults according to the fault probability.

[0070] Specifically, the fault to be detected refers to the fault to be detected. A preset fault with a high fault probability N (N>0) can be selected as the fault to be detected. The value of N can be selected according to the actual situation.

[0071] Step S203, when the future time period arrives, the robot is subjected to fault detection according to the real-time information corresponding to the fault to be detected and the fault probability threshold.

[0072] That is to say, when the future time period arrives, the faults to be detected can be determined based on the fault probability, and the robot can be fault-detected based on the real-time information corresponding to the faults to be detected and the fault probability threshold. In this way, there is no need to detect all preset faults one by one, but to detect and determine the faults to be detected that are more likely to occur in the future time period, thereby improving the efficiency of fault detection and reducing unnecessary maintenance.

[0073] The real-time information corresponding to the fault to be detected refers to the information required for fault detection of the fault to be detected, such as sensor information, electrical parameter information, continuous operation time, practical service life, etc. Based on the real-time information corresponding to the fault to be detected, the failure probability of the fault to be detected can be determined, and compared with the failure probability threshold to determine whether the fault to be detected occurs.

[0074] Step S204, when a robot failure is detected, perform fault processing.

[0075] In some embodiments of the present application, when a robot failure is detected, fault handling can be performed. The fault handling method can refer to the description of the aforementioned step S103, which is not described in detail in this application. In this way, potential faults can be discovered and handled in a timely manner to ensure the continuity and stability of the robot service, while reducing unnecessary maintenance frequency and manual inspection costs, thereby reducing overall maintenance costs.

[0076] It can be understood that corresponding faults to be detected can be determined for multiple future time periods respectively, and the robot can be controlled to perform fault detection in real time after the robot starts working. In the process of real-time fault detection, the corresponding fault to be detected is selected according to the current time, and the robot is subjected to fault detection based on the real-time information corresponding to the fault to be detected and the fault probability threshold.

[0077] For example, when the robot starts working, it determines the faults to be detected corresponding to every ten minutes in the next hour. In the first ten minutes (1 to 10 minutes), the faults to be detected corresponding to the first ten minutes are selected, and the robot is detected for faults based on the real-time information and fault probability threshold corresponding to the faults to be detected. Correspondingly, ten minutes later, the faults to be detected corresponding to the second ten minutes (11 to 20 minutes) are selected, and the robot is detected for faults based on the real-time information and fault probability threshold corresponding to the faults to be detected. Since some faults are correlated with the continuous running time, this method can detect faults that may occur at different time nodes separately, which helps to improve the reliability of fault detection.

[0078] In some embodiments of the application, after a robot failure is detected, feedback information from a maintenance person may be received. The feedback information may be used to evaluate or adjust parameters of the aforementioned fault detection model to improve its accuracy and practicality.

[0079] Furthermore, the above feedback information can be used to evaluate the reliability of fault detection, so as to readjust the fault rate threshold according to the evaluation result, so that the fault rate threshold is more suitable for the actual operating environment of the robot.

[0080] It should be noted that, for the sake of simplicity of description, the aforementioned method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders.

[0081] like Figure 3 Shown is a schematic structural diagram of a robot fault handling device 300 provided in an embodiment of the present application, wherein the robot fault handling device 300 is configured on an electronic device.

[0082] Specifically, the robot fault handling device 300 may include:

[0083] An acquisition unit 301 is used to acquire robot data of the robot, wherein the robot data includes real-time operation information and / or historical fault data;

[0084] An adjusting unit 302, configured to adjust a fault probability threshold according to the robot data;

[0085] The fault processing unit 303 is used to perform fault processing when a fault of the robot is detected according to the fault probability threshold.

[0086] In some embodiments of the present application, the adjustment unit 302 can be specifically used to: determine the current task load of the robot based on the real-time operation information; when the task load is higher than a first load threshold, lower the failure probability threshold; when the task load is lower than a second load threshold, increase the failure probability threshold, and the second load threshold is less than or equal to the first load threshold.

[0087] In some embodiments of the present application, the adjustment unit 302 may be specifically used to: determine the environmental complexity of the current operating environment of the robot based on the real-time operating information; when the environmental complexity is higher than a first complexity threshold, reduce the fault probability threshold.

[0088] In some embodiments of the present application, the adjustment unit 302 can be specifically used to: determine the historical failure frequency of the robot based on the historical failure data; when the historical failure frequency is higher than a first frequency threshold, lower the failure probability threshold; when the historical failure frequency is lower than a second frequency threshold, increase the failure probability threshold, and the second frequency threshold is less than or equal to the first frequency threshold.

[0089] In some embodiments of the present application, the fault processing unit 303 can be specifically used to: estimate the failure probability of various preset faults of the robot in a future time period based on historical fault data; determine the fault to be detected among the various preset faults based on the failure probability; when the future time period arrives, perform fault detection on the robot based on the real-time information corresponding to the fault to be detected and the fault probability threshold; and perform fault processing when a fault of the robot is detected.

[0090] In some embodiments of the present application, the fault processing unit 303 can be specifically used to: obtain historical work data of the robot, the historical work data including historical working hours and attendance numbers; input the historical work data and the historical fault data into a fault analysis model, and determine the fault probability according to the output result of the fault analysis model.

[0091] In some embodiments of the present application, the fault processing unit 303 can be specifically used to: input the historical working data and the historical fault data into multiple fault analysis models to obtain the output results of each fault analysis model; different fault analysis models are used to extract different types of data features, and output the fault probability based on the extracted data features; the output results of each fault analysis model are merged to obtain the fault probability.

[0092] In some embodiments of the present application, the fault processing unit 303 may be specifically used to: determine common data features exhibited by multiple sensors; and determine the fault probability according to the common data features.

[0093] It should be noted that, for the convenience and simplicity of description, the specific working process of the above robot fault handling device 300 can be referred to Figure 1 to Figure 2 The corresponding process of the method will not be repeated here.

[0094] like Figure 4 , which is a schematic diagram of an electronic device provided in an embodiment of the present application. Specifically, the electronic device 4 may include: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40, such as a robot fault handling program. When the processor 40 executes the computer program 42, the steps in the above-mentioned robot fault handling method embodiments are implemented, such as Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 3 The functions of the acquisition unit 301, the adjustment unit 302 and the fault processing unit 303 are shown.

[0095] The computer program may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0096] For example, the computer program can be divided into: an acquisition unit, an adjustment unit, and a fault processing unit. The specific functions of each unit are as follows: an acquisition unit, used to acquire robot data of the robot, the robot data including real-time operation information and / or historical fault data; an adjustment unit, used to adjust a fault probability threshold according to the robot data; a fault processing unit, used to perform fault processing when a robot fault is detected according to the fault probability threshold.

[0097] The electronic device may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 These are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0098] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0099] The memory 41 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. The memory 41 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 41 may also include both an internal storage unit of the electronic device and an external storage device. The memory 41 is used to store the computer program and other programs and data required by the electronic device. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0100] It should be noted that, for the convenience and brevity of description, the structure of the above electronic device can also refer to the specific description of the structure in the method embodiment, which will not be repeated here.

[0101] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0102] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0103] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0107] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0108] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A robot fault handling method, characterized in that: include: Acquiring robot data of the robot, wherein the robot data includes real-time operation information and / or historical fault data; adjusting a failure probability threshold based on the robot data; According to the fault probability threshold, when a fault of the robot is detected, fault processing is performed.

2. The robot fault handling method according to claim 1, characterized in that: The robot data includes real-time operation information, and adjusting the fault probability threshold according to the robot data includes: Determining the current task load of the robot according to the real-time operation information; When the task load is higher than a first load threshold, lowering the failure probability threshold; When the task load is lower than a second load threshold, the failure probability threshold is increased, and the second load threshold is less than or equal to the first load threshold.

3. The robot fault handling method according to claim 1, characterized in that: The robot data includes real-time operation information, and adjusting the fault probability threshold according to the robot data includes: Determining the environmental complexity of the current operating environment of the robot according to the real-time operating information; When the environmental complexity is higher than a first complexity threshold, the failure probability threshold is lowered.

4. The robot fault handling method according to claim 1, characterized in that: The robot data includes historical fault data, and adjusting the fault probability threshold according to the robot data includes: Determining a historical failure frequency of the robot according to the historical failure data; When the historical fault frequency is higher than a first frequency threshold, lowering the fault probability threshold; When the historical fault frequency is lower than a second frequency threshold, the fault probability threshold is increased, and the second frequency threshold is less than or equal to the first frequency threshold.

5. The robot fault handling method according to any one of claims 1 to 4, characterized in that: The method of performing fault processing when a fault of the robot is detected according to the fault probability threshold comprises: Based on historical failure data, estimate the failure probability of various preset failures of the robot in the future time period; According to the fault probability, determining a fault to be detected from among the various types of preset faults; When the future time period arrives, performing fault detection on the robot according to the real-time information corresponding to the fault to be detected and the fault probability threshold; When a fault of the robot is detected, fault processing is performed.

6. The robot fault handling method according to claim 5, characterized in that: The method of estimating the failure probability of various preset failures of the robot in the future time period based on the historical failure data includes: Obtaining historical work data of the robot, wherein the historical work data includes historical working hours and attendance numbers; The historical working data and the historical fault data are input into a fault analysis model, and the fault probability is determined according to an output result of the fault analysis model.

7. The robot fault handling method according to claim 6, characterized in that: The step of inputting the historical working data and the historical fault data into a fault analysis model and determining the fault probability according to an output result of the fault analysis model comprises: Inputting the historical working data and the historical fault data into a plurality of the fault analysis models to obtain output results of each of the fault analysis models; different fault analysis models are used to extract different types of data features, and output the fault probability according to the extracted data features; The output results of each fault analysis model are fused to obtain the fault probability.

8. The robot fault handling method according to claim 7, characterized in that: The process of outputting the failure probability in the first failure analysis mode in the failure analysis model includes: Identify common data characteristics exhibited by multiple sensors; The failure probability is determined based on the common data feature.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the robot fault handling method according to any one of claims 1 to 8 are implemented.

10. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the steps of the robot fault handling method according to any one of claims 1 to 8.

Images