Industrial robot fault diagnosis method, system and medium

Abstract

The present application provides a method, system and medium for fault diagnosis of industrial robots. The method includes: evaluating the influence index of the fault point through the statistical data of the fault point in each environment of the industrial robot, obtaining the influence sub-factor of the fault point according to the fault statistical data of the fault point in the same environment combined with the recorded data of the robot, and combining the influence sub-factor of the fault point in each environment and the environmental operation load influence index processing to obtain the fault induced evaluation index and screen the re-inspection type fault point, and then obtain the meta-node load instability evaluation index of each meta-node according to the reliability evaluation of each meta-node combined with the monitoring characteristic data processing, and mark the fault potential meta-node for priority processing; thereby re-inspecting the fault point identification by combining the influence of the statistical evaluation of the robot's fault point with the impact of the operating environment, and performing reliability and load instability evaluation on each component, identifying the potential meta-node, and realizing the diagnosis and identification technology of the potential meta-node of the important fault point of the robot.

Description

Technical Field

[0001] The present application relates to the technical field of industrial robots, and in particular to an industrial robot fault diagnosis method, system and medium. Background Art

[0002] Industrial robots are widely used in precision manufacturing, logistics, production line processing and other fields. Due to the complexity and diversity of the types, functions, loads and working environments of industrial robots, their fault troubleshooting and diagnosis are hidden and difficult. Currently, fault prevention and diagnosis of industrial robots are mainly carried out through system alarm feedback. There is no diagnostic technology for fault information analysis of the industrial robot's job type, working environment, load, working conditions and other factors. It is also impossible to perform information analysis and big data diagnosis on the faulty links and faulty components that induce the fault in order to identify the main fault inducing points.

[0003] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention

[0004] The purpose of the present application is to provide an industrial robot fault diagnosis method, system and medium, which can identify key fault points by combining the influence of statistical evaluation of the robot's fault points with the influence of the working environment, and perform reliability and load instability evaluation on each component to identify the hidden danger nodes of key fault points, thereby realizing the diagnosis and identification technology of hidden danger nodes of important fault points of the robot.

[0005] The present application also provides an industrial robot fault diagnosis method, comprising the following steps:

[0006] Obtain the fault distribution characteristic information of industrial robots in various working environments within the preset working period, classify and aggregate the fault point types and location distribution, obtain the fault point characteristic data of each fault point of the same type and evaluate them, and obtain the fault point impact index;

[0007] Obtain the working environment characteristic data of various working environments, and process them to obtain the environmental working load impact index of various working environments;

[0008] Obtain the fault report record data of the same type of industrial robots in the same working environment during the preset working period, and process it in combination with the fault point statistical data of each same type of fault point in the same working environment to obtain the fault point influence sub-factor of each same type of fault point in the same working environment;

[0009] According to the fault point influence sub-factors of each fault point of the same type in each operating environment combined with the corresponding environmental operating load influence index and the fault point influence index, the fault induced evaluation index of each fault point of the same type is obtained, and the fault points of the re-inspection type are sorted and screened;

[0010] Extracting metaverse identification feature data according to metaverse attribute information of each metaverse of each recheck type fault point, and performing aggregation processing to obtain metaverse reliability evaluation data of the entire metaverse;

[0011] According to the node monitoring characteristic data of each node of each re-inspection type fault point combined with the node reliability evaluation data processing, the node load instability assessment index of each node is obtained, and the node with potential fault hazards is sorted and marked for priority optimization processing.

[0012] Optionally, in the industrial robot fault diagnosis method described in the present application, the fault distribution characteristic information of the industrial robot in a preset working period in various working environments is obtained, the fault point type and location distribution are classified and aggregated, the fault point characteristic data of each fault point of the same type is obtained and evaluated, and the fault point influence index is obtained, including:

[0013] Obtaining fault distribution characteristic information of industrial robots in various working environments within preset working periods, including fault point type distribution information, fault point location distribution information, and fault point record information of the robot's fault points;

[0014] The fault point record information includes fault point duration information, fault point total ratio information, fault point repair cost distribution information and fault point downtime ratio information;

[0015] Classify and aggregate the fault point type and location distribution according to the fault point type distribution information and the fault point location distribution information to obtain fault point feature data of each fault point of the same type;

[0016] The fault point characteristic data includes point importance coefficient, fault frequency ratio data, repair cost data and induced downtime ratio data;

[0017] The fault point impact is evaluated based on the fault point characteristic data of each fault point of the same type to obtain the fault point impact index.

[0018] Optionally, in the industrial robot fault diagnosis method described in the present application, the acquiring of operating environment characteristic data of various operating environments and processing to obtain environmental operating load impact indexes of various operating environments include:

[0019] Obtain the operating environment characteristic data of various operating environments, including environment type, over-temperature load rate, electromagnetic interference amount, operating overload rate and overload duration ratio;

[0020] Processing the operating environment characteristic data through a preset environmental operating load impact assessment model to obtain environmental operating load impact indexes for various operating environments;

[0021] The calculation formula of the environmental operation load impact index is:

[0022] ;

[0023] in, is the environmental operating load impact index, , , , They are electromagnetic interference, over-temperature load rate, operation overload rate, and overload duration ratio. , , , is the preset characteristic coefficient.

[0024] Optionally, in the industrial robot fault diagnosis method described in the present application, the fault report record data of the industrial robot of the same type in a preset working period in the same working environment is acquired, and the fault point fault statistical data of each same type of fault point in the same working environment are processed to obtain the fault point influence sub-factor of each same type of fault point in the same working environment, including:

[0025] Obtain the fault report record information of the same type of industrial robots in the preset working period in the same working environment, and extract the fault report record data, including the fault downtime data, fault alarm level and fault repair cost data;

[0026] Obtaining statistical data on the fault points of the same type of industrial robots in the same operating environment, including fault repair time data and fault repair cost data;

[0027] The fault point fault statistical data is combined with the corresponding point importance coefficient of the fault point and the fault report record data to obtain the fault point influence sub-factor of each fault point of the same type in the same operating environment.

[0028] Optionally, in the industrial robot fault diagnosis method described in the present application, the fault point influence sub-factors of each same type of fault point in each type of operating environment are processed in combination with the corresponding environmental operating load influence index and the fault point influence index to obtain the fault induced evaluation index of each same type of fault point, and sort and screen the re-inspection type fault points, including:

[0029] According to the fault point influence sub-factors of each fault point of the same type in each operating environment combined with the corresponding environmental operating load influence index and the fault point influence index, a preset fault induction evaluation model is used to obtain the fault induction evaluation index of each fault point of the same type;

[0030] Sorting the various types of fault points of the industrial robot according to the corresponding fault induction evaluation index, and taking the high-ranked type of fault points as the re-inspected type of fault points;

[0031] The calculation formula of the fault induction evaluation index is:

[0032] ;

[0033] in, is the fault induction assessment index, , are the failure point influence factor and environmental operation load influence index of the i-th type of operating environment in the k-type operating environment, respectively. is the fault point impact index, k is the number of types of operating environments, , , is the preset characteristic coefficient.

[0034] Optionally, in the industrial robot fault diagnosis method described in the present application, extracting meta-section identification feature data according to the meta-section attribute information of each meta-section of each re-inspection type fault point, and performing aggregation processing to obtain the meta-section reliability evaluation data of the entire meta-section, includes:

[0035] Obtaining metaverse attribute information of each metaverse of each re-inspection type fault point, and metaverse monitoring characteristic data within the preset working period;

[0036] The meta-section attribute information includes meta-section function information, meta-section installation time information, meta-section loss information and meta-section historical maintenance information;

[0037] Extracting meta-section identification feature data according to the meta-section attribute information, including meta-section key coefficient, meta-section life reliability data, meta-section wear degree data and meta-section maintenance rating;

[0038] Aggregation processing is performed according to the meta-section identification feature data to obtain the meta-section reliability evaluation data of the entire meta-section.

[0039] Optionally, in the industrial robot fault diagnosis method described in the present application, the meta-node monitoring feature data of each meta-node of each re-inspection type fault point is combined with the meta-node reliability evaluation data processing to obtain the meta-node load instability assessment index of each meta-node, and sort and mark the meta-nodes with potential fault hazards for priority optimization processing, including:

[0040] Extracting high load rate data, high load time-frequency data and energy consumption overload rate data according to the metanode monitoring characteristic data of each metanode of each re-inspection type fault point;

[0041] Processing the high load rate data, high load time-frequency data and energy consumption overload rate data in combination with the metanode reliability evaluation data to obtain a metanode load instability evaluation index of each metanode;

[0042] Sorting each metanode according to the corresponding metanode load instability assessment index, marking the metanode with the highest ranking as a potential fault metanode, and performing priority optimization processing;

[0043] The calculation formula of the node load instability evaluation index is:

[0044] ;

[0045] in, is the node load instability assessment index, , , They are respectively the high load rate data, energy consumption overload rate data, and high load time-frequency data of the jth node in the total number of nodes in the same node in each re-inspection type fault point, This is the reliability evaluation data of the Yuanjie. , , is the preset characteristic coefficient.

[0046] In a second aspect, the present application provides an industrial robot fault diagnosis system, the system comprising: a memory and a processor, the memory comprising a program of an industrial robot fault diagnosis method, and the program of the industrial robot fault diagnosis method, when executed by the processor, implements the following steps:

[0047] Obtain the fault distribution characteristic information of industrial robots in various working environments within the preset working period, classify and aggregate the fault point types and location distribution, obtain the fault point characteristic data of each fault point of the same type and evaluate them, and obtain the fault point impact index;

[0048] Obtain the operating environment characteristic data of various operating environments, and process them to obtain the environmental operating load impact index of various operating environments;

[0049] Obtain the fault report record data of the same type of industrial robots in the same working environment during the preset working period, and process it in combination with the fault point statistical data of each same type of fault point in the same working environment to obtain the fault point influence sub-factor of each same type of fault point in the same working environment;

[0050] According to the fault point influence sub-factors of each fault point of the same type in each operating environment combined with the corresponding environmental operating load influence index and the fault point influence index, the fault induced evaluation index of each fault point of the same type is obtained, and the fault points of the re-inspection type are sorted and screened;

[0051] Extracting metaverse identification feature data according to metaverse attribute information of each metaverse of each recheck type fault point, and performing aggregation processing to obtain metaverse reliability evaluation data of the entire metaverse;

[0052] According to the node monitoring characteristic data of each node of each re-inspection type fault point combined with the node reliability evaluation data processing, the node load instability assessment index of each node is obtained, and the node with potential fault hazards is sorted and marked for priority optimization processing.

[0053] Optionally, in the industrial robot fault diagnosis system described in the present application, the fault distribution characteristic information of the industrial robot in a preset working period in various working environments is obtained, the fault point type and location distribution are classified and aggregated, the fault point characteristic data of each fault point of the same type is obtained and evaluated, and the fault point influence index is obtained, including:

[0054] Obtaining fault distribution characteristic information of industrial robots in various working environments within preset working periods, including fault point type distribution information, fault point location distribution information, and fault point record information of the robot's fault points;

[0055] The fault point record information includes fault point duration information, fault point total ratio information, fault point repair cost distribution information and fault point downtime ratio information;

[0056] Classify and aggregate the fault point type and location distribution according to the fault point type distribution information and the fault point location distribution information to obtain fault point feature data of each fault point of the same type;

[0057] The fault point characteristic data includes point importance coefficient, fault frequency ratio data, repair cost data and induced downtime ratio data;

[0058] The fault point impact is evaluated based on the fault point characteristic data of each fault point of the same type to obtain the fault point impact index.

[0059] In a third aspect, the present application also provides a computer-readable storage medium, in which an industrial robot fault diagnosis method program is stored. When the industrial robot fault diagnosis method program is executed by a processor, the steps of the industrial robot fault diagnosis method as described in any one of the above items are implemented.

[0060] As can be seen from the above, the present application provides an industrial robot fault diagnosis method, system and medium, which obtains fault point characteristic data and fault point influence index through the distribution of fault location points of the industrial robot in various environments, obtains fault point influence sub-factors according to the fault point fault statistical data of each same type of fault point in the same operating environment combined with the fault point fault statistical data of the robot in the same operating environment, obtains the fault induced evaluation index and screens the re-inspection type fault points according to the fault point influence sub-factors of each same type of fault point in various operating environments combined with the corresponding environmental operating load influence index and the fault point influence index, and then performs an overall meta-node reliability evaluation on each meta-node of each re-inspection type of fault point, and obtains the meta-node load instability evaluation index of each meta-node in combination with the monitoring characteristic data processing of each meta-node, and marks the fault potential meta-nodes for priority processing; thereby realizing the key detection fault point identification by combining the impact of the robot's fault point statistical evaluation with the operating environment impact, and performing reliability and load instability evaluation on each component, identifying the potential meta-nodes of key fault points, and realizing the diagnosis and identification technology of the potential meta-nodes of important fault points of the robot.

[0061] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 A flowchart of an industrial robot fault diagnosis method provided in an embodiment of the present application;

[0064] Figure 2 A flow chart of obtaining a fault point influence index in a method for diagnosing a fault of an industrial robot provided in an embodiment of the present application;

[0065] Figure 3 A flow chart of obtaining environmental operating load impact indexes of various operating environments in the industrial robot fault diagnosis method provided in an embodiment of the present application;

[0066] Figure 4 A flow chart of obtaining the fault point influence sub-factors of each fault point of the same type in the industrial robot fault diagnosis method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of 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 belong to the scope of protection of the present application.

[0068] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0069] Please refer to Figure 1 , Figure 1 1 is a flow chart of an industrial robot fault diagnosis method in some embodiments of the present application. The industrial robot fault diagnosis method is used in a terminal device, such as a computer, a mobile phone terminal, etc. The industrial robot fault diagnosis method includes the following steps:

[0070] S11. Obtain fault distribution characteristic information of industrial robots of different types in preset working periods in various working environments, classify and aggregate the fault point types and location distributions, obtain fault point characteristic data of each fault point of the same type and evaluate them, and obtain the fault point impact index;

[0071] S12, obtaining operating environment characteristic data of various operating environments, and processing to obtain environmental operating load impact indexes of various operating environments;

[0072] S13, obtaining fault report record data of a type of industrial robot in a preset working period in a type of working environment, processing the fault point statistical data of each type of fault point in the type of working environment, and obtaining the fault point influence sub-factor of each type of fault point in the type of working environment;

[0073] S14, processing the fault point influence sub-factors of each fault point of the same type in each operating environment in combination with the corresponding environmental operating load influence index and the fault point influence index to obtain the fault induced evaluation index of each fault point of the same type, and sorting and screening the re-inspection type fault points;

[0074] S15, extracting metasection identification feature data according to the metasection attribute information of each metasection of each recheck type fault point, and performing aggregation processing to obtain the metasection reliability evaluation data of the entire metasection;

[0075] S16. Processing the node monitoring characteristic data of each node of each re-inspection type fault point in combination with the node reliability evaluation data to obtain the node load instability assessment index of each node, and sorting and marking the node with potential fault hazards for priority optimization processing.

[0076] It should be noted that, in order to diagnose the main fault points and cause points of the hidden dangers of various types of industrial robots, find out the fault points that are most likely to induce robot failures in various types of industrial robots working under different working conditions, environments and loads, as well as the components and joints (referred to as meta-joints) of the fault points, firstly, statistical classification is performed through the fault distribution characteristic information of the industrial robots of different types in a certain preset working period in various working environments, and the fault point types and location distributions are classified and aggregated to obtain the fault point characteristic data of each fault point of the same type and evaluate them to obtain the fault point influence index, that is, statistics are performed on various types of fault points of the robots of different types and the extracted characteristic data are analyzed to obtain the influence of each fault point. The fault point can be a module, part, component of the robot, or a component, unit, or structural part. At the same time, the load impact of the robot working environment is evaluated to obtain the environmental operation load impact index, that is, the impact of the environmental load on the robot when the robot performs load operations in various environments, reflecting the degree of influence of the environment and workload on the robot-induced failures, and then the fault report record data of the robot in the same environment is obtained, combined with the faults of various types of fault points in the same environment. The statistical data of point faults are processed to obtain the fault point influence sub-factors of various fault points in the same environment, that is, to evaluate the impact of the faults of each fault point on the overall robot failure situation. Then, the fault point influence sub-factors of the same type of fault points in various environments are combined with the corresponding environmental operation load influence index and the fault point influence index to obtain the fault induced evaluation index of various fault points, that is, to evaluate the fault induced degree results of various fault points in all working conditions, and select the key detection type fault points by sorting, that is, to find one or several types of fault points that have the greatest impact on inducing robot failures. The type of fault point is identified, and then each meta-node of the re-inspected fault point is evaluated. The overall meta-node reliability evaluation data of each meta-node is obtained by aggregating the extracted meta-node identification feature data, and processed in combination with the monitoring feature data of each meta-node to obtain the meta-node load instability assessment index of each meta-node, that is, the assessment result of the instability induction degree of each component in each key detection fault point under the workload, and then the front meta-nodes are sorted and marked as fault potential meta-nodes, that is, the important cause potential meta-nodes of important fault points are diagnosed and analyzed, and priority optimization processing is performed to realize the diagnosis and identification technology of potential meta-nodes of important fault points of the robot.

[0077] Please refer to Figure 2 , Figure 2 The present invention is a flowchart of obtaining a fault point influence index of an industrial robot fault diagnosis method in some embodiments of the present application. According to an embodiment of the present invention, the method of obtaining fault distribution characteristic information of industrial robots in various types of working environments within a preset working period, classifying and aggregating the fault point type and location distribution, obtaining fault point characteristic data of each fault point of the same type and evaluating it, and obtaining a fault point influence index includes:

[0078] S21. Obtaining fault distribution characteristic information of various types of industrial robots in preset working periods in various working environments, including fault point type distribution information, fault point location distribution information, and fault point record information of the fault points of the robots;

[0079] S22, the fault point record information includes fault point duration information, fault point total ratio information, fault point repair cost distribution information and fault point downtime ratio information;

[0080] S23, classifying and aggregating the fault point type and location distribution according to the fault point type distribution information and the fault point location distribution information, and obtaining fault point characteristic data of each fault point of the same type;

[0081] S24, the fault point characteristic data includes point importance coefficient, fault frequency ratio data, repair cost data and induced downtime ratio data;

[0082] S25. Perform fault point impact evaluation based on the fault point characteristic data of each fault point of the same type to obtain a fault point impact index.

[0083] It should be noted that in order to identify and determine the fault points that induce industrial robot failures and evaluate the impact of each fault point, it is necessary to obtain the fault distribution characteristic information of a certain type of industrial robot in a preset working period in various working environments, that is, the fault distribution information of various types of robots working under different working environments including electromagnetic interference, temperature and humidity, working load and other conditions, including the fault point type distribution information, fault point location distribution information, and fault point record information of the fault point, wherein the fault point record information includes the fault point duration information, the total ratio information of the fault point location to all points, the distribution information of the fault point repair cost, and the ratio of the fault point downtime to the total downtime. According to the fault point type and location distribution information, the type and location distribution of the fault point are classified and aggregated to obtain the fault point characteristic data of each fault point of the same type, that is, the fault point type and location distribution are classified and aggregated, where the fault point type includes drive end fault, host fault, control end fault, servo fault, execution end fault, etc. The fault point characteristic data includes the importance coefficient of the fault point, the proportion of the fault frequency, the repair cost data and the proportion of the number of robot shutdowns induced. Then, the fault point impact evaluation and calculation are performed according to the characteristic data of each fault point to obtain the fault point impact index, where the calculation formula of the fault point impact index is:

[0084] ;

[0085] in, is the fault point impact index, , , , They are the point importance coefficient, failure frequency ratio data, repair cost data, and induced downtime ratio data. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0086] Please refer to Figure 3 , Figure 3 The present invention is a flowchart of obtaining the environmental operating load impact index of various operating environments in the industrial robot fault diagnosis method in some embodiments of the present application. According to the embodiment of the present invention, the method of obtaining the operating environment characteristic data of various operating environments and processing the data to obtain the environmental operating load impact index of various operating environments includes:

[0087] S31. Obtaining operating environment characteristic data of various operating environments, including environment type, over-temperature load rate, electromagnetic interference amount, operating overload rate and overload duration ratio;

[0088] S32, processing the operating environment characteristic data through a preset environmental operating load impact assessment model to obtain environmental operating load impact indexes for various operating environments;

[0089] The calculation formula of the environmental operation load impact index is:

[0090] ;

[0091] in, is the environmental operating load impact index, , , , They are electromagnetic interference, over-temperature load rate, operation overload rate, and overload duration ratio. , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0092] It should be noted that since the fault inducing conditions of industrial robots in different working conditions are different, that is, the degree to which the working conditions induce the robot's fault points and fault states, in order to measure the impact of load operations in working conditions on the robot's fault induction, the impact of the operating load in the working conditions is evaluated. The operating environment characteristic data of various operating environments are obtained, including environmental categories such as temperature, humidity, electromagnetic radiation, load, over-temperature load rate, electromagnetic interference, operating load overload rate and proportion of the duration of overload conditions, and then the environmental operating load impact index of various operating environments is obtained according to the calculation formula of the preset environmental operating load impact evaluation model based on the operating environment characteristic data.

[0093] Please refer to Figure 4 , Figure 4 The present invention is a flowchart of obtaining the fault point influence sub-factor of each fault point of the same type in the industrial robot fault diagnosis method in some embodiments of the present application. According to the embodiment of the present invention, the fault report record data of the industrial robot of the same type in the preset working period in the same working environment is obtained, combined with the fault point fault statistical data of each fault point of the same type in the same working environment, to obtain the fault point influence sub-factor of each fault point of the same type in the same working environment, including:

[0094] S41, obtaining fault report record information of a type of industrial robot in a preset working period in a similar working environment, and extracting fault report record data, including fault downtime data, fault alarm level, and fault repair cost data;

[0095] S42, obtaining fault statistics of the same type of fault points of the same type of industrial robots in the same type of operating environment, including fault repair time data and fault repair cost data;

[0096] S43, processing is performed according to the fault statistical data of the fault point in combination with the corresponding point importance coefficient of the fault point and the fault report record data to obtain the fault point influence sub-factor of each fault point of the same type in the same operating environment.

[0097] It should be noted that in order to evaluate the influence of each fault point on the overall robot failure, the fault report record data of the robot working under the same environmental conditions within a preset time period, including the robot's fault downtime, fault alarm level and fault repair cost, is processed with the fault point statistical data of each similar fault point in the same environment to obtain the influence sub-factor of each similar fault point operating under the same environmental conditions on the overall robot failure. The calculation formula of the fault point influence sub-factor is:

[0098] ;

[0099] in, is the fault point impact factor, , , They are fault repair time data, fault repair cost data, and point importance coefficient. , , They are respectively the fault downtime data, fault repair cost data, and fault alarm level. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0100] According to an embodiment of the present invention, the fault point influence sub-factors of the same type of fault points in various operating environments are processed in combination with the corresponding environmental operating load influence index and the fault point influence index to obtain the fault induced evaluation index of each same type of fault point, and sort and filter the re-inspection type fault points, including:

[0101] According to the fault point influence sub-factors of each fault point of the same type in each operating environment combined with the corresponding environmental operating load influence index and the fault point influence index, a preset fault induction evaluation model is used to obtain the fault induction evaluation index of each fault point of the same type;

[0102] Sorting the various types of fault points of the industrial robot according to the corresponding fault induction evaluation index, and taking the high-ranked type of fault points as the re-inspected type of fault points;

[0103] The calculation formula of the fault induction evaluation index is:

[0104] ;

[0105] in, is the fault induction assessment index, , are the failure point influence factor and environmental operation load influence index of the i-th type of operating environment in the k-type operating environment, respectively. is the fault point impact index, k is the number of types of operating environments, , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0106] It should be noted that after obtaining the influence factors of various types of fault points on the overall robot under different working conditions, the influence index of each environmental operating load and the fault point influence index, the fault point influence sub-factors of each similar fault point in various environments are combined with the corresponding environmental operating load influence index and the fault point influence index to obtain the fault induced evaluation index of each type of fault point, that is, the degree of fault induced influence of various types of fault points on the overall robot under all working conditions is evaluated, and the key detection type fault points are screened out by sorting, that is, one or several types of fault points with the greatest impact on inducing robot failures are found as the type of fault points for further key detection.

[0107] According to an embodiment of the present invention, the step of extracting metaverse identification feature data according to metaverse attribute information of each metaverse of each recheck type fault point, and performing aggregation processing to obtain metaverse reliability evaluation data of the entire metaverse includes:

[0108] Obtaining metaverse attribute information of each metaverse of each re-inspection type fault point, and metaverse monitoring characteristic data within the preset working period;

[0109] The meta-section attribute information includes meta-section function information, meta-section installation time information, meta-section loss information and meta-section historical maintenance information;

[0110] Extracting meta-section identification feature data according to the meta-section attribute information, including meta-section key coefficient, meta-section life reliability data, meta-section wear degree data and meta-section maintenance rating;

[0111] Aggregation processing is performed according to the meta-section identification feature data to obtain the meta-section reliability evaluation data of the entire meta-section.

[0112] It should be noted that, further, the meta-nodes in each key detection type fault point are diagnosed to analyze and identify the hidden danger meta-nodes with greater impact, by obtaining the meta-node attribute information of each meta-node of each re-inspection type fault point, including the function and purpose of the meta-node, the installation time of the meta-node, the meta-node wear status and the information of the historical maintenance of the meta-node, and then extracting the meta-node identification feature data, including the meta-node critical coefficient, the meta-node life reliability data, the meta-node wear degree data and the meta-node maintenance rating, according to the identification feature data of all the meta-nodes distributed in each re-inspection fault point, the meta-node reliability evaluation data of the whole meta-node is obtained, that is, the overall reliability evaluation result of a certain meta-node of each re-inspection fault point is evaluated, wherein the calculation formula of the meta-node reliability evaluation data is:

[0113] ;

[0114] in, This is the reliability evaluation data of the Yuanjie. , , are the node life reliability data, node wear data, and node maintenance rating of the jth node in the total number of nodes in the same node in each re-inspection type fault point, respectively. is the key coefficient of the meta-section, , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0115] According to an embodiment of the present invention, the meta-node monitoring feature data of each meta-node of each re-inspection type fault point is combined with the meta-node reliability evaluation data processing to obtain the meta-node load instability assessment index of each meta-node, and sort and mark the meta-nodes with potential fault hazards for priority optimization processing, including:

[0116] Extracting high load rate data, high load time-frequency data and energy consumption overload rate data according to the metanode monitoring characteristic data of each metanode of each re-inspection type fault point;

[0117] Processing the high load rate data, high load time-frequency data and energy consumption overload rate data in combination with the metanode reliability evaluation data to obtain a metanode load instability evaluation index of each metanode;

[0118] Sorting each metanode according to the corresponding metanode load instability assessment index, marking the metanode with the highest ranking as a potential fault metanode, and performing priority optimization processing;

[0119] The calculation formula of the node load instability evaluation index is:

[0120] ;

[0121] in, is the node load instability assessment index, , , They are respectively the high load rate data, energy consumption overload rate data, and high load time-frequency data of the jth node in the total number of nodes in the same node in each re-inspection type fault point, This is the reliability evaluation data of the Yuanjie. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0122] It should be noted that, based on the monitoring feature data of all the metanodes distributed in each re-inspected fault point, data including the high load rate of the workload process, the duration and frequency of high load, and the overload rate of energy consumption are extracted, and combined with the metanode reliability evaluation data for processing, the metanode load instability assessment index of each metanode as a whole is obtained, that is, the instability degree of all the number metanodes of a certain metanode of each re-inspected fault point under the workload is evaluated, and then the metanodes at the front are sorted and marked as fault potential metanodes, that is, the important fault-inducing potential metanodes of important fault points are diagnosed and analyzed, and they are prioritized for optimization processing, thereby realizing the diagnosis and identification technology of potential danger metanodes of important fault points of the robot.

[0123] It is worth mentioning that it also includes:

[0124] Aggregate the metanode load instability assessment index of each metanode of the recheck type fault point in combination with the corresponding fault point influence index to obtain the unit operation fault influence index of the recheck type fault point;

[0125] According to the metanode load instability assessment index of each metanode of the recheck type fault point, combined with the unit operation fault influence index, a unit fault induced correction index of each metanode for the recheck type fault point is obtained;

[0126] According to the comparison between the unit fault induction correction index of each meta-segment and the preset unit fault induction threshold, the meta-segments that do not meet the threshold comparison requirements are replaced;

[0127] The calculation formulas of the unit operation fault influence index and the unit fault induced correction index are respectively:

[0128] ;

[0129] ;

[0130] in, is the unit operation failure impact index, is the unit operation failure impact index, is the node load instability assessment index of the sth node among all the node types in the rechecked type fault point, is the fault point impact index, , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0131] It should be noted that, in order to further diagnose a certain type of metanode that has an excessive influence on the re-inspection type fault point where the metanode is located, the key metanodes that induce faults are identified and processed in a targeted manner to reduce the probability of fault occurrence frequency, the metanode load instability assessment index of all types of metanodes in the re-inspection type fault point is combined with the fault point influence index of the corresponding fault point to obtain the unit operation fault influence index of the re-inspection type fault point, that is, the overall operation fault influence of each metanode in the fault point on the fault point unit, and then the metanode load instability assessment index and the unit operation fault influence index of each metanode are processed to obtain the unit fault induction correction index of each metanode to the re-inspection type fault point, that is, the degree of fault induction of each metanode to the fault point unit, and then compared with the preset unit fault induction threshold. If the threshold comparison requirement is not met, the metanode of this category is a high-induced fault component and needs to be replaced, thereby realizing the diagnosis and identification of the metanode with a greater degree of fault influence on the induced fault point.

[0132] In a second aspect, the present invention further discloses an industrial robot fault diagnosis system, comprising a memory and a processor, wherein the memory comprises an industrial robot fault diagnosis method program, and when the industrial robot fault diagnosis method program is executed by the processor, the following steps are implemented:

[0133] Obtain the fault distribution characteristic information of industrial robots in various working environments within the preset working period, classify and aggregate the fault point types and location distribution, obtain the fault point characteristic data of each fault point of the same type and evaluate them, and obtain the fault point impact index;

[0134] Obtain the working environment characteristic data of various working environments, and process them to obtain the environmental working load impact index of various working environments;

[0135] Obtain the fault report record data of the same type of industrial robots in the same working environment during the preset working period, and process it in combination with the fault point statistical data of each same type of fault point in the same working environment to obtain the fault point influence sub-factor of each same type of fault point in the same working environment;

[0136] According to the fault point influence sub-factors of each fault point of the same type in each operating environment combined with the corresponding environmental operating load influence index and the fault point influence index, the fault induced evaluation index of each fault point of the same type is obtained, and the fault points of the re-inspection type are sorted and screened;

[0137] Extracting metaverse identification feature data according to metaverse attribute information of each metaverse of each recheck type fault point, and performing aggregation processing to obtain metaverse reliability evaluation data of the entire metaverse;

[0138] According to the node monitoring characteristic data of each node of each re-inspection type fault point combined with the node reliability evaluation data processing, the node load instability assessment index of each node is obtained, and the node with potential fault hazards is sorted and marked for priority optimization processing.

[0139] It should be noted that, in order to diagnose the main fault points and cause points of the hidden dangers of various types of industrial robots, find out the fault points that are most likely to induce robot failures in various types of industrial robots working under different working conditions, environments and loads, as well as the components and joints (referred to as meta-joints) of the fault points, firstly, statistical classification is performed through the fault distribution characteristic information of the industrial robots of different types in a certain preset working period in various working environments, and the fault point types and location distributions are classified and aggregated to obtain the fault point characteristic data of each fault point of the same type and evaluate them to obtain the fault point influence index, that is, statistics are performed on various types of fault points of the robots of different types and the extracted characteristic data are analyzed to obtain the influence of each fault point. The fault point can be a module, part, component of the robot, or a component, unit, or structural part. At the same time, the load impact of the robot working environment is evaluated to obtain the environmental operation load impact index, that is, the impact of the environmental load on the robot when the robot performs load operations in various environments, reflecting the degree of influence of the environment and workload on the robot-induced failures, and then the fault report record data of the robot in the same environment is obtained, combined with the faults of various types of fault points in the same environment. The statistical data of point faults are processed to obtain the fault point influence sub-factors of various fault points in the same environment, that is, to evaluate the impact of the faults of each fault point on the overall robot failure situation. Then, the fault point influence sub-factors of the same type of fault points in various environments are combined with the corresponding environmental operation load influence index and the fault point influence index to obtain the fault induced evaluation index of various fault points, that is, to evaluate the fault induced degree results of various fault points in all working conditions, and select the key detection type fault points by sorting, that is, to find one or several types of fault points that have the greatest impact on inducing robot failures. The type of fault point is identified, and then each meta-node of the re-inspected fault point is evaluated. The overall meta-node reliability evaluation data of each meta-node is obtained by aggregating the extracted meta-node identification feature data, and processed in combination with the monitoring feature data of each meta-node to obtain the meta-node load instability assessment index of each meta-node, that is, the assessment result of the instability induction degree of each component in each key detection fault point under the workload, and then the front meta-nodes are sorted and marked as fault potential meta-nodes, that is, the important cause potential meta-nodes of important fault points are diagnosed and analyzed, and priority optimization processing is performed to realize the diagnosis and identification technology of potential meta-nodes of important fault points of the robot.

[0140] According to an embodiment of the present invention, the acquisition type of fault distribution characteristic information of industrial robots in preset working periods in various working environments, classifying and aggregating the fault point types and location distributions, obtaining and evaluating the fault point characteristic data of each fault point of the same type, and obtaining the fault point influence index include:

[0141] Obtaining fault distribution characteristic information of industrial robots in various working environments within preset working periods, including fault point type distribution information, fault point location distribution information, and fault point record information of the robot's fault points;

[0142] The fault point record information includes fault point duration information, fault point total ratio information, fault point repair cost distribution information and fault point downtime ratio information;

[0143] Classify and aggregate the fault point type and location distribution according to the fault point type distribution information and the fault point location distribution information to obtain fault point feature data of each fault point of the same type;

[0144] The fault point characteristic data includes point importance coefficient, fault frequency ratio data, repair cost data and induced downtime ratio data;

[0145] The fault point impact is evaluated based on the fault point characteristic data of each fault point of the same type to obtain the fault point impact index.

[0146] It should be noted that in order to identify and determine the fault points that induce industrial robot failures and evaluate the impact of each fault point, it is necessary to obtain the fault distribution characteristic information of a certain type of industrial robot in a preset working period in various working environments, that is, the fault distribution information of various types of robots working under different working environments including electromagnetic interference, temperature and humidity, working load and other conditions, including the fault point type distribution information, fault point location distribution information, and fault point record information of the fault point, wherein the fault point record information includes the fault point duration information, the total ratio information of the fault point location to all points, the distribution information of the fault point repair cost, and the ratio of the fault point downtime to the total downtime. According to the fault point type and location distribution information, the type and location distribution of the fault point are classified and aggregated to obtain the fault point characteristic data of each fault point of the same type, that is, the fault point type and location distribution are classified and aggregated, where the fault point type includes drive end fault, host fault, control end fault, servo fault, execution end fault, etc. The fault point characteristic data includes the importance coefficient of the fault point, the proportion of the fault frequency, the repair cost data and the proportion of the number of robot shutdowns induced. Then, the fault point impact evaluation and calculation are performed according to the characteristic data of each fault point to obtain the fault point impact index, where the calculation formula of the fault point impact index is:

[0147] ;

[0148] in, is the fault point impact index, , , , They are the point importance coefficient, failure frequency ratio data, repair cost data, and induced downtime ratio data. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0149] According to an embodiment of the present invention, the step of acquiring the operating environment characteristic data of various operating environments and processing the data to obtain the environmental operating load impact index of the various operating environments includes:

[0150] Obtain the operating environment characteristic data of various operating environments, including environment type, over-temperature load rate, electromagnetic interference amount, operating overload rate and overload duration ratio;

[0151] Processing the operating environment characteristic data through a preset environmental operating load impact assessment model to obtain environmental operating load impact indexes for various operating environments;

[0152] The calculation formula of the environmental operation load impact index is:

[0153] ;

[0154] in, is the environmental operating load impact index, , , , They are electromagnetic interference, over-temperature load rate, operation overload rate, and overload duration ratio. , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0155] It should be noted that since the fault inducing conditions of industrial robots in different working conditions are different, that is, the degree to which the working conditions induce the robot's fault points and fault states, in order to measure the impact of load operations in working conditions on the robot's fault induction, the impact of the operating load in the working conditions is evaluated. The operating environment characteristic data of various operating environments are obtained, including environmental categories such as temperature, humidity, electromagnetic radiation, load, over-temperature load rate, electromagnetic interference, operating load overload rate and proportion of the duration of overload conditions, and then the environmental operating load impact index of various operating environments is obtained according to the calculation formula of the preset environmental operating load impact evaluation model based on the operating environment characteristic data.

[0156] According to an embodiment of the present invention, the acquisition of fault report record data of a type of industrial robot in a preset working period in a similar working environment is combined with the fault point fault statistical data of each type of fault point in the same working environment for processing to obtain the fault point influence sub-factor of each type of fault point in the same working environment, including:

[0157] Obtain the fault report record information of the same type of industrial robots in the preset working period in the same working environment, and extract the fault report record data, including the fault downtime data, fault alarm level and fault repair cost data;

[0158] Obtaining statistical data on the fault points of the same type of industrial robots in the same operating environment, including fault repair time data and fault repair cost data;

[0159] The fault point fault statistical data is combined with the corresponding point importance coefficient of the fault point and the fault report record data to obtain the fault point influence sub-factor of each fault point of the same type in the same operating environment.

[0160] It should be noted that in order to evaluate the influence of each fault point on the overall robot failure, the fault report record data of the robot working under the same environmental conditions within a preset time period, including the robot's fault downtime, fault alarm level and fault repair cost, is processed with the fault point statistical data of each similar fault point in the same environment to obtain the influence sub-factor of each similar fault point operating under the same environmental conditions on the overall robot failure. The calculation formula of the fault point influence sub-factor is:

[0161] ;

[0162] in, is the fault point impact factor, , , They are fault repair time data, fault repair cost data, and point importance coefficient. , , They are respectively the fault downtime data, fault repair cost data, and fault alarm level. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0163] According to an embodiment of the present invention, the fault point influence sub-factors of the same type of fault points in various operating environments are processed in combination with the corresponding environmental operating load influence index and the fault point influence index to obtain the fault induced evaluation index of each same type of fault point, and sort and filter the re-inspection type fault points, including:

[0164] According to the fault point influence sub-factors of each fault point of the same type in each operating environment combined with the corresponding environmental operating load influence index and the fault point influence index, a preset fault induction evaluation model is used to obtain the fault induction evaluation index of each fault point of the same type;

[0165] Sorting the various types of fault points of the industrial robot according to the corresponding fault induction evaluation index, and taking the high-ranked type of fault points as the re-inspected type of fault points;

[0166] The calculation formula of the fault induction evaluation index is:

[0167] ;

[0168] in, is the fault induction assessment index, , are the failure point influence factor and environmental operation load influence index of the i-th type of operating environment in the k-type operating environment, respectively. is the fault point impact index, k is the number of types of operating environments, , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0169] It should be noted that after obtaining the influence factors of various types of fault points on the overall robot under different working conditions, the influence index of each environmental operating load and the fault point influence index, the fault point influence sub-factors of each similar fault point in various environments are combined with the corresponding environmental operating load influence index and the fault point influence index to obtain the fault induced evaluation index of each type of fault point, that is, the degree of fault induced influence of various types of fault points on the overall robot under all working conditions is evaluated, and the key detection type fault points are screened out by sorting, that is, one or several types of fault points with the greatest impact on inducing robot failures are found as the type of fault points for further key detection.

[0170] According to an embodiment of the present invention, the step of extracting metaverse identification feature data according to metaverse attribute information of each metaverse of each recheck type fault point, and performing aggregation processing to obtain metaverse reliability evaluation data of the entire metaverse includes:

[0171] Obtaining metaverse attribute information of each metaverse of each re-inspection type fault point, and metaverse monitoring characteristic data within the preset working period;

[0172] The meta-section attribute information includes meta-section function information, meta-section installation time information, meta-section loss information and meta-section historical maintenance information;

[0173] Extracting meta-section identification feature data according to the meta-section attribute information, including meta-section key coefficient, meta-section life reliability data, meta-section wear degree data and meta-section maintenance rating;

[0174] Aggregation processing is performed according to the meta-section identification feature data to obtain the meta-section reliability evaluation data of the entire meta-section.

[0175] It should be noted that, further, the meta-nodes in each key detection type fault point are diagnosed to analyze and identify the hidden danger meta-nodes with greater impact, by obtaining the meta-node attribute information of each meta-node of each re-inspection type fault point, including the function and purpose of the meta-node, the installation time of the meta-node, the meta-node wear status and the information of the historical maintenance of the meta-node, and then extracting the meta-node identification feature data, including the meta-node critical coefficient, the meta-node life reliability data, the meta-node wear degree data and the meta-node maintenance rating, according to the identification feature data of all the meta-nodes distributed in each re-inspection fault point, the meta-node reliability evaluation data of the whole meta-node is obtained, that is, the overall reliability evaluation result of a certain meta-node of each re-inspection fault point is evaluated, wherein the calculation formula of the meta-node reliability evaluation data is:

[0176] ;

[0177] in, This is the reliability evaluation data of the Yuanjie. , , are the node life reliability data, node wear data, and node maintenance rating of the jth node in the total number of nodes in the same node in each re-inspection type fault point, respectively. is the key coefficient of the meta-section, , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0178] According to an embodiment of the present invention, the meta-node monitoring feature data of each meta-node of each re-inspection type fault point is combined with the meta-node reliability evaluation data processing to obtain the meta-node load instability assessment index of each meta-node, and sort and mark the meta-nodes with potential fault hazards for priority optimization processing, including:

[0179] Extracting high load rate data, high load time-frequency data and energy consumption overload rate data according to the metanode monitoring characteristic data of each metanode of each re-inspection type fault point;

[0180] Processing the high load rate data, high load time-frequency data and energy consumption overload rate data in combination with the metanode reliability evaluation data to obtain a metanode load instability evaluation index of each metanode;

[0181] Sorting each metanode according to the corresponding metanode load instability assessment index, marking the metanode with the highest ranking as a potential fault metanode, and performing priority optimization processing;

[0182] The calculation formula of the node load instability evaluation index is:

[0183] ;

[0184] in, is the node load instability assessment index, , , They are respectively the high load rate data, energy consumption overload rate data, and high load time-frequency data of the jth node in the total number of nodes in the same node in each re-inspection type fault point, This is the reliability evaluation data of the Yuanjie. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0185] It should be noted that, based on the monitoring feature data of all the metanodes distributed in each re-inspected fault point, data including the high load rate of the workload process, the duration and frequency of high load, and the overload rate of energy consumption are extracted, and combined with the metanode reliability evaluation data for processing, the metanode load instability assessment index of each metanode as a whole is obtained, that is, the instability degree of all the number metanodes of a certain metanode of each re-inspected fault point under the workload is evaluated, and then the metanodes at the front are sorted and marked as fault potential metanodes, that is, the important fault-inducing potential metanodes of important fault points are diagnosed and analyzed, and they are prioritized for optimization processing, thereby realizing the diagnosis and identification technology of potential danger metanodes of important fault points of the robot.

[0186] It is worth mentioning that it also includes:

[0187] Aggregate the metanode load instability assessment index of each metanode of the recheck type fault point in combination with the corresponding fault point influence index to obtain the unit operation fault influence index of the recheck type fault point;

[0188] According to the metanode load instability assessment index of each metanode of the recheck type fault point, combined with the unit operation fault influence index, a unit fault induced correction index of each metanode for the recheck type fault point is obtained;

[0189] According to the comparison between the unit fault induction correction index of each meta-segment and the preset unit fault induction threshold, the meta-segments that do not meet the threshold comparison requirements are replaced;

[0190] The calculation formulas of the unit operation fault influence index and the unit fault induced correction index are respectively:

[0191] ;

[0192] ;

[0193] in, is the unit operation failure impact index, is the unit operation failure impact index, is the node load instability assessment index of the sth node among all the node types in the rechecked type fault point, is the fault point impact index, , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset robot performance monitoring platform database).

[0194] It should be noted that, in order to further diagnose a certain type of metanode that has an excessive influence on the re-inspection type fault point where the metanode is located, the key metanodes that induce faults are identified and processed in a targeted manner to reduce the probability of fault occurrence frequency, the metanode load instability assessment index of all types of metanodes in the re-inspection type fault point is combined with the fault point influence index of the corresponding fault point to obtain the unit operation fault influence index of the re-inspection type fault point, that is, the overall operation fault influence of each metanode in the fault point on the fault point unit, and then the metanode load instability assessment index and the unit operation fault influence index of each metanode are processed to obtain the unit fault induction correction index of each metanode to the re-inspection type fault point, that is, the degree of fault induction of each metanode to the fault point unit, and then compared with the preset unit fault induction threshold. If the threshold comparison requirement is not met, the metanode of this category is a high-induced fault component and needs to be replaced, thereby realizing the diagnosis and identification of the metanode with a greater degree of fault influence on the induced fault point.

[0195] A third aspect of the present invention provides a readable storage medium, which stores an industrial robot fault diagnosis method program. When the industrial robot fault diagnosis method program is executed by a processor, the steps of the industrial robot fault diagnosis method as described in any one of the above items are implemented.

[0196] The present invention discloses an industrial robot fault diagnosis method, system and medium. The method obtains fault point characteristic data and fault point influence index through the fault position point distribution of the industrial robot in various environments, obtains fault point influence sub-factors according to the fault point fault statistical data of each same type of fault point in the same operating environment combined with the fault point fault statistical data of the robot in the same operating environment, obtains fault induction evaluation index and screens re-inspection type fault points according to the fault point influence sub-factors of each same type of fault point in various operating environments combined with the corresponding environmental operating load influence index and fault point influence index, and then performs overall meta-node reliability evaluation on each meta-node of each re-inspection type of fault point, obtains the meta-node load instability evaluation index of each meta-node in combination with the monitoring characteristic data processing of each meta-node, and marks the meta-nodes with hidden danger of fault for priority processing; thereby realizing the key detection fault point identification by combining the influence of the statistical evaluation of the robot's fault point with the influence of the operating environment, and performing reliability and load instability evaluation on each component, identifying the hidden danger meta-nodes of the key fault point, and realizing the diagnosis and identification technology of the hidden danger meta-nodes of the important fault point of the robot.

[0197] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the 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 can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0198] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; 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 present embodiment.

[0199] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0200] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, the aforementioned program can be stored in a readable storage medium, and when the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0201] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for fault diagnosis of an industrial robot, comprising the following steps: Obtain the fault distribution characteristic information of industrial robots in various working environments within the preset working period, classify and aggregate the fault point types and location distribution, obtain the fault point characteristic data of each fault point of the same type and evaluate them, and obtain the fault point impact index; Obtain the operating environment characteristic data of various operating environments, and process them to obtain the environmental operating load impact index of various operating environments; Obtain the fault report record data of the same type of industrial robots in the same working environment during the preset working period, and process it in combination with the fault point statistical data of each same type of fault point in the same working environment to obtain the fault point influence sub-factor of each same type of fault point in the same working environment; According to the fault point influence sub-factors of each fault point of the same type in each operating environment combined with the corresponding environmental operating load influence index and the fault point influence index, the fault induced evaluation index of each fault point of the same type is obtained, and the fault points of the re-inspection type are sorted and screened; Extracting meta-node identification feature data according to the meta-node attribute information of each meta-node of each re-inspection type fault point, and obtaining the meta-node reliability evaluation data of each meta-node as a whole through aggregation processing. The meta-node is the fault point of the robot fault and the components and joints of the fault point; According to the node monitoring characteristic data of each node of each re-inspection type fault point combined with the node reliability evaluation data processing, the node load instability assessment index of each node is obtained, and the node with potential fault hazards is sorted and marked for priority optimization processing.

2. The industrial robot fault diagnosis method according to claim 1, characterized in that: The acquisition of fault distribution characteristic information of industrial robots in various working environments within preset working periods, classifying and aggregating the fault point types and location distributions, obtaining and evaluating the fault point characteristic data of each fault point of the same type, and obtaining the fault point influence index include: Obtaining fault distribution characteristic information of industrial robots in various working environments within preset working periods, including fault point type distribution information, fault point location distribution information, and fault point record information of the robot's fault points; The fault point record information includes fault point duration information, fault point total ratio information, fault point repair cost distribution information and fault point downtime ratio information; Classify and aggregate the fault point type and location distribution according to the fault point type distribution information and the fault point location distribution information to obtain fault point feature data of each fault point of the same type; The fault point characteristic data includes point importance coefficient, fault frequency ratio data, repair cost data and induced downtime ratio data; The fault point impact is evaluated based on the fault point characteristic data of each fault point of the same type to obtain the fault point impact index.

3. The industrial robot fault diagnosis method according to claim 2, characterized in that: The method of obtaining the operating environment characteristic data of various operating environments and processing them to obtain the environmental operating load impact index of various operating environments includes: Obtain the operating environment characteristic data of various operating environments, including environment type, over-temperature load rate, electromagnetic interference amount, operating overload rate and overload duration ratio; Processing the operating environment characteristic data through a preset environmental operating load impact assessment model to obtain environmental operating load impact indexes for various operating environments; The calculation formula of the environmental operation load impact index is: ； in, is the environmental operating load impact index, , , , They are electromagnetic interference, over-temperature load rate, operation overload rate, and overload duration ratio. , , , is the preset characteristic coefficient.

4. The industrial robot fault diagnosis method according to claim 3, characterized in that: The acquisition of fault report record data of the same type of industrial robot in a preset working period in the same working environment is combined with the fault point fault statistical data of each same type of fault point in the same working environment for processing to obtain the fault point influence sub-factor of each same type of fault point in the same working environment, including: Obtain the fault report record information of the same type of industrial robots in the preset working period in the same working environment, and extract the fault report record data, including the fault downtime data, fault alarm level and fault repair cost data; Obtaining statistical data on the fault points of the same type of industrial robots in the same operating environment, including fault repair time data and fault repair cost data; The fault point fault statistical data is combined with the corresponding point importance coefficient of the fault point and the fault report record data to obtain the fault point influence sub-factor of each fault point of the same type in the same operating environment.

5. The industrial robot fault diagnosis method according to claim 4, characterized in that: The fault point influence sub-factors of the same type of fault points in various operating environments are processed in combination with the corresponding environmental operating load influence index and the fault point influence index to obtain the fault induced evaluation index of each same type of fault point, and sort and filter the re-inspection type of fault points, including: According to the fault point influence sub-factors of each fault point of the same type in each operating environment combined with the corresponding environmental operating load influence index and the fault point influence index, a preset fault induction evaluation model is used to obtain the fault induction evaluation index of each fault point of the same type; Sorting the various types of fault points of the industrial robot according to the corresponding fault induction evaluation index, and taking the high-ranked type of fault points as the re-inspected type of fault points; The calculation formula of the fault induction evaluation index is: ； in, is the fault induction assessment index, , are the failure point influence factor and environmental operation load influence index of the i-th type of operating environment in the k-type operating environment, respectively. is the fault point impact index, k is the number of types of operating environments, , , is the preset characteristic coefficient.

6. The industrial robot fault diagnosis method according to claim 5, characterized in that: The step of extracting metaverse identification feature data according to the metaverse attribute information of each metaverse of each recheck type fault point, and performing aggregation processing to obtain the metaverse reliability evaluation data of the entire metaverse includes: Obtaining metaverse attribute information of each metaverse of each re-inspection type fault point, and metaverse monitoring characteristic data within the preset working period; The meta-section attribute information includes meta-section function information, meta-section installation time information, meta-section loss information and meta-section historical maintenance information; Extracting meta-section identification feature data according to the meta-section attribute information, including meta-section key coefficient, meta-section life reliability data, meta-section wear degree data and meta-section maintenance rating; Aggregation processing is performed according to the meta-section identification feature data to obtain the meta-section reliability evaluation data of the entire meta-section.

7. The industrial robot fault diagnosis method according to claim 6, characterized in that: The process of combining the node monitoring characteristic data of each node of each re-inspection type fault point with the node reliability evaluation data to obtain the node load instability assessment index of each node, and sorting and marking the node with potential fault risk for priority optimization processing includes: Extracting high load rate data, high load time-frequency data and energy consumption overload rate data according to the metanode monitoring characteristic data of each metanode of each re-inspection type fault point; Processing the high load rate data, high load time-frequency data and energy consumption overload rate data in combination with the metanode reliability evaluation data to obtain a metanode load instability evaluation index of each metanode; Sorting each metanode according to the corresponding metanode load instability assessment index, marking the metanode with the highest ranking as a potential fault metanode, and performing priority optimization processing; The calculation formula of the node load instability evaluation index is: ； in, is the node load instability assessment index, , , They are respectively the high load rate data, energy consumption overload rate data, and high load time-frequency data of the jth node in the total number of nodes in the same node in each re-inspection type fault point, This is the reliability evaluation data of the Yuanjie. , , is the preset characteristic coefficient.

8. An industrial robot fault diagnosis system, characterized in that: The system includes: a memory and a processor, wherein the memory includes a program of an industrial robot fault diagnosis method, and when the program of the industrial robot fault diagnosis method is executed by the processor, the following steps are implemented: Obtain the fault distribution characteristic information of industrial robots in various working environments within the preset working period, classify and aggregate the fault point types and location distribution, obtain the fault point characteristic data of each fault point of the same type and evaluate them, and obtain the fault point impact index; Obtain the operating environment characteristic data of various operating environments, and process them to obtain the environmental operating load impact index of various operating environments; Obtain the fault report record data of the same type of industrial robots in the same working environment during the preset working period, and process it in combination with the fault point statistical data of each same type of fault point in the same working environment to obtain the fault point influence sub-factor of each same type of fault point in the same working environment; According to the fault point influence sub-factors of each fault point of the same type in each operating environment combined with the corresponding environmental operating load influence index and the fault point influence index, the fault induced evaluation index of each fault point of the same type is obtained, and the fault points of the re-inspection type are sorted and screened; Extracting meta-node identification feature data according to the meta-node attribute information of each meta-node of each re-inspection type fault point, and obtaining the meta-node reliability evaluation data of each meta-node as a whole through aggregation processing. The meta-node is the fault point of the robot fault and the components and joints of the fault point; According to the node monitoring characteristic data of each node of each re-inspection type fault point combined with the node reliability evaluation data processing, the node load instability assessment index of each node is obtained, and the node with potential fault hazards is sorted and marked for priority optimization processing.

9. The industrial robot fault diagnosis system according to claim 8, characterized in that: The acquisition of fault distribution characteristic information of industrial robots in various working environments within preset working periods, classifying and aggregating the fault point types and location distributions, obtaining and evaluating the fault point characteristic data of each fault point of the same type, and obtaining the fault point influence index include: Obtaining fault distribution characteristic information of industrial robots in various working environments within preset working periods, including fault point type distribution information, fault point location distribution information, and fault point record information of the robot's fault points; The fault point record information includes fault point duration information, fault point total ratio information, fault point repair cost distribution information and fault point downtime ratio information; Classify and aggregate the fault point type and location distribution according to the fault point type distribution information and the fault point location distribution information to obtain fault point feature data of each fault point of the same type; The fault point characteristic data includes point importance coefficient, fault frequency ratio data, repair cost data and induced downtime ratio data; The fault point impact is evaluated based on the fault point characteristic data of each fault point of the same type to obtain the fault point impact index.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an industrial robot fault diagnosis method program, and when the industrial robot fault diagnosis method program is executed by a processor, the steps of the industrial robot fault diagnosis method according to any one of claims 1 to 7 are implemented.

Images