A method and system for industrial robot fault diagnosis based on small sample learning

Abstract

The present application provides an industrial robot fault diagnosis method and system based on small sample learning. The method includes: monitoring preset industrial robot operation monitoring information, extracting real-time operation feature data, and combining with standard operation feature data for comparison and processing to obtain operation deviation data, further processing to obtain robot fault diagnosis data, obtaining the total operation time data of the industrial robot, the robot fault characteristic data set and the maintenance record data set, processing to obtain the failure rate data and the average fault repair time data, processing to obtain the accuracy retention index according to the accuracy feature data, processing to obtain the robot anti-interference ability index according to the interference simulation test results, and combining the failure rate data, the average fault repair time data and the accuracy retention index for processing to obtain the robot reliability index, and formulating a maintenance plan accordingly, thereby realizing the technology of industrial robot fault diagnosis based on small sample learning.

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 and system based on small sample learning. Background Art

[0002] With the continuous development of industrial automation, industrial robots are increasingly used in manufacturing. However, industrial robots may experience various faults during operation, such as mechanical failure, electrical failure, sensor failure, etc. These failures not only affect production efficiency, but may also lead to safety accidents; therefore, timely and accurate diagnosis of industrial robot failures is crucial.

[0003] Traditional industrial robot fault diagnosis methods usually require a large amount of fault sample data for training to achieve a high diagnostic accuracy; however, in practical applications, it is often difficult or even impossible to obtain a large amount of fault sample data; in addition, industrial robots have many types of faults and complex fault characteristics, which also brings great challenges to fault diagnosis.

[0004] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention

[0005] The purpose of the present application is to provide an industrial robot fault diagnosis method and system based on small sample learning. The method and system can obtain robot fault diagnosis data by extracting the real-time operation characteristic data of the industrial robot and combining it with the standard operation characteristic data for multiple processing, and judge the fault condition of the industrial robot. In addition, the obtained failure rate data, average fault repair time data, accuracy retention index and robot anti-interference ability index are combined for processing to obtain the robot reliability index, and a maintenance plan is formulated accordingly, thereby realizing the technology of industrial robot fault diagnosis based on small sample learning.

[0006] The present application also provides an industrial robot fault diagnosis method based on small sample learning, comprising the following steps:

[0007] Monitor preset industrial robot operation monitoring information and extract real-time operation feature data;

[0008] Acquire standard operation characteristic data of the industrial robot, and perform comparative processing on the standard operation characteristic data in combination with the real-time operation characteristic data to obtain operation deviation data;

[0009] Processing the operation deviation data to obtain robot fault diagnosis data;

[0010] Determine whether the industrial robot fails according to the robot fault diagnosis data, and record the judgment result information and processing information;

[0011] Obtaining total operation time data, robot fault characteristic data set, and maintenance record data set of the industrial robot within a preset time period, and processing to obtain failure rate data and mean fault repair time data;

[0012] Acquiring precision characteristic data of the industrial robot and processing to obtain a precision retention index;

[0013] Performing an interference simulation test on the industrial robot, and obtaining an anti-interference capability index of the robot according to the interference simulation test result;

[0014] The failure rate data, the mean fault repair time data and the accuracy retention index are processed in combination with the robot anti-interference ability index to obtain a robot reliability index, and a maintenance plan for the industrial robot is formulated accordingly.

[0015] Optionally, in the industrial robot fault diagnosis method based on small sample learning described in the present application, the monitoring of preset industrial robot operation monitoring information and extracting real-time operation feature data include:

[0016] Monitor preset industrial robots in real time and collect operation monitoring information, including motion monitoring information, motor monitoring information, and sensor monitoring information;

[0017] Extracting real-time operation characteristic data based on the operation monitoring information, including motion monitoring information, motor monitoring information and sensor monitoring information,

[0018] The real-time operation characteristic data includes real-time position data, real-time speed data, real-time acceleration data, real-time current data, real-time temperature data, real-time amplitude data, real-time force sensor feedback value data and real-time visual sensor data.

[0019] Optionally, in the industrial robot fault diagnosis method based on small sample learning described in the present application, the acquiring of standard operation characteristic data of the industrial robot and performing comparative processing in combination with the real-time operation characteristic data to obtain operation deviation data includes:

[0020] Acquiring standard operation characteristic data of the industrial robot, including standard position data, standard speed data, standard acceleration data, standard current data, standard temperature data, standard amplitude data, standard force sensor feedback value data, and standard visual sensor data;

[0021] Performing comparison processing based on the standard operation characteristic data and the real-time operation characteristic data to obtain operation deviation data;

[0022] The operation deviation data includes position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation value data and visual sensor deviation data.

[0023] Optionally, in the industrial robot fault diagnosis method based on small sample learning described in the present application, the processing according to the operation deviation data to obtain robot fault diagnosis data includes:

[0024] The position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation data and visual sensor deviation data are processed through a preset robot fault diagnosis model to obtain robot fault diagnosis data.

[0025] Optionally, in the industrial robot fault diagnosis method based on small sample learning described in the present application, the acquiring of the total operation time data of the industrial robot within a preset time period, the robot fault characteristic data set, and the maintenance record data set, and processing to obtain the failure rate data and the mean fault repair time data, includes:

[0026] Obtaining all the judgment result information and corresponding processing information of the industrial robot within a preset time period, and extracting corresponding total operation time data, robot fault characteristic data set, and maintenance record data set;

[0027] The robot fault characteristic data set includes fault frequency record data and fault response time data corresponding to each fault;

[0028] The maintenance record data set includes total number of fault maintenance data and repair time data corresponding to each fault maintenance;

[0029] Processing the total operation time data and the failure frequency record data to obtain failure rate data;

[0030] The average fault repair time data is obtained by processing the fault response time data corresponding to each fault, the total number of fault maintenance data, and the repair time data corresponding to each fault maintenance.

[0031] Optionally, in the industrial robot fault diagnosis method based on small sample learning described in the present application, the failure rate data, the mean fault repair time data and the accuracy retention index are processed in combination with the robot anti-interference ability index to obtain the robot reliability index, and a maintenance plan for the industrial robot is formulated accordingly, including:

[0032] According to the failure rate data, the mean fault repair time data and the accuracy retention index, combined with the robot anti-interference ability index, a robot reliability index is obtained;

[0033] Comparing the robot reliability index with a preset robot reliability threshold to obtain a threshold comparison result;

[0034] Determining the reliability level of the robot according to the threshold comparison result;

[0035] A maintenance plan for the industrial robot is formulated accordingly according to the reliability level, including a maintenance cycle and a maintenance level.

[0036] In a second aspect, the present application provides an industrial robot fault diagnosis system based on small sample learning, the system comprising: a memory and a processor, the memory comprising a program of an industrial robot fault diagnosis method based on small sample learning, and the program of the industrial robot fault diagnosis method based on small sample learning is executed by the processor to implement the following steps:

[0037] Monitor preset industrial robot operation monitoring information and extract real-time operation feature data;

[0038] Acquire standard operation characteristic data of the industrial robot, and perform comparative processing on the standard operation characteristic data in combination with the real-time operation characteristic data to obtain operation deviation data;

[0039] Processing the operation deviation data to obtain robot fault diagnosis data;

[0040] Determine whether the industrial robot fails according to the robot fault diagnosis data, and record the judgment result information and processing information;

[0041] Obtaining total operation time data, robot fault characteristic data set, and maintenance record data set of the industrial robot within a preset time period, and processing to obtain failure rate data and mean fault repair time data;

[0042] Acquiring precision characteristic data of the industrial robot and processing to obtain a precision retention index;

[0043] Performing an interference simulation test on the industrial robot, and obtaining an anti-interference capability index of the robot according to the interference simulation test result;

[0044] The failure rate data, the mean fault repair time data and the accuracy retention index are processed in combination with the robot anti-interference ability index to obtain a robot reliability index, and a maintenance plan for the industrial robot is formulated accordingly.

[0045] Optionally, in the industrial robot fault diagnosis system based on small sample learning described in the present application, the monitoring of preset industrial robot operation monitoring information and extracting real-time operation feature data include:

[0046] Monitor preset industrial robots in real time and collect operation monitoring information, including motion monitoring information, motor monitoring information, and sensor monitoring information;

[0047] Extracting real-time operation characteristic data based on the operation monitoring information, including motion monitoring information, motor monitoring information and sensor monitoring information,

[0048] The real-time operation characteristic data includes real-time position data, real-time speed data, real-time acceleration data, real-time current data, real-time temperature data, real-time amplitude data, real-time force sensor feedback value data and real-time visual sensor data.

[0049] Optionally, in the industrial robot fault diagnosis system based on small sample learning described in the present application, the step of acquiring the standard operation characteristic data of the industrial robot and performing comparative processing in combination with the real-time operation characteristic data to obtain the operation deviation data includes:

[0050] Acquiring standard operation characteristic data of the industrial robot, including standard position data, standard speed data, standard acceleration data, standard current data, standard temperature data, standard amplitude data, standard force sensor feedback value data, and standard visual sensor data;

[0051] Performing comparison processing based on the standard operation characteristic data and the real-time operation characteristic data to obtain operation deviation data;

[0052] The operation deviation data includes position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation value data and visual sensor deviation data.

[0053] Optionally, in the industrial robot fault diagnosis system based on small sample learning described in the present application, the processing according to the operation deviation data to obtain the robot fault diagnosis data includes:

[0054] The position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation data and visual sensor deviation data are processed through a preset robot fault diagnosis model to obtain robot fault diagnosis data.

[0055] As can be seen from the above, the industrial robot fault diagnosis method and system based on small sample learning provided by the present application monitors the preset industrial robot operation monitoring information, extracts real-time operation feature data, obtains the standard operation feature data of the industrial robot, and compares and processes the real-time operation feature data to obtain operation deviation data, processes the operation deviation data to obtain robot fault diagnosis data, judges whether the industrial robot has a fault based on the robot fault diagnosis data, and records the judgment result information and processing information, obtains the total operation time data of the industrial robot within a preset time period, the robot fault characteristic data set and the maintenance record data set, and processes to obtain the failure rate data and the average fault repair time data, obtains the accuracy feature data of the industrial robot, and processes to obtain the accuracy retention index, performs interference simulation test on the industrial robot, and obtains the robot anti-interference ability index based on the interference simulation test results, and processes the failure rate data, the average fault repair time data and the accuracy retention index based on the robot anti-interference ability index to obtain the robot reliability index, and formulates the maintenance plan of the industrial robot accordingly, thereby realizing the technology of industrial robot fault diagnosis based on small sample learning.

[0056] 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 particularly pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] 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.

[0058] Figure 1 A flowchart of an industrial robot fault diagnosis method based on small sample learning provided in an embodiment of the present application;

[0059] Figure 2 A flowchart of extracting real-time operation feature data of an industrial robot fault diagnosis method based on small sample learning provided in an embodiment of the present application;

[0060] Figure 3 A flowchart of obtaining operation deviation data of an industrial robot fault diagnosis method based on small sample learning provided in an embodiment of the present application;

[0061] Figure 4A flowchart of obtaining failure rate data and mean fault repair time data for an industrial robot fault diagnosis method based on small sample learning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] 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.

[0063] 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.

[0064] Please refer to Figure 1 , Figure 1 The present invention is a flowchart of an industrial robot fault diagnosis method based on small sample learning in some embodiments of the present invention. The industrial robot fault diagnosis method based on small sample learning is used in terminal devices, such as computers, mobile phone terminals, etc. The industrial robot fault diagnosis method based on small sample learning includes the following steps:

[0065] S11, monitoring preset industrial robot operation monitoring information, and extracting real-time operation feature data;

[0066] S12, obtaining standard operation characteristic data of the industrial robot, and performing comparison processing with the real-time operation characteristic data to obtain operation deviation data;

[0067] S13, processing the operation deviation data to obtain robot fault diagnosis data;

[0068] S14, judging whether the industrial robot has a fault according to the robot fault diagnosis data, and recording the judgment result information and processing information;

[0069] S15, obtaining total operation time data, robot fault characteristic data set, and maintenance record data set of the industrial robot within a preset time period, and processing to obtain failure rate data and mean fault repair time data;

[0070] S16, acquiring the precision characteristic data of the industrial robot, and processing to obtain the precision retention index;

[0071] S17, performing an interference simulation test on the industrial robot, and obtaining the robot anti-interference capability index according to the interference simulation test result;

[0072] S18. Process the failure rate data, mean fault repair time data and precision retention index in combination with the robot anti-interference ability index to obtain a robot reliability index, and formulate a maintenance plan for the industrial robot accordingly.

[0073] It should be noted that with the continuous development of industrial automation, industrial robots are being used more and more widely in production and manufacturing. However, various faults may occur in industrial robots during operation, such as mechanical faults, electrical faults, sensor faults, etc. These faults will not only affect production efficiency, but may also lead to safety accidents. Therefore, timely and accurate diagnosis of industrial robot faults and effective maintenance are crucial. Traditional industrial robot fault diagnosis methods usually require a large amount of fault sample data for training to obtain a high diagnostic accuracy. However, in practical applications, it is often difficult or even impossible to obtain a large amount of fault sample data. Therefore, it is necessary to study an industrial robot fault diagnosis method based on small sample learning. In this embodiment, firstly, by monitoring the preset industrial robot operation monitoring information and extracting real-time operation feature data, the standard operation feature data of the industrial robot is obtained, and the real-time operation feature data is combined for diagnosis. Perform comparative processing to obtain operation deviation data, process the operation deviation data to obtain robot fault diagnosis data, judge whether the industrial robot has a fault based on the robot fault diagnosis data, and record the judgment result information and processing information, obtain the total operation time data of the industrial robot within a preset time period, the robot fault characteristic data set and the maintenance record data set, and process to obtain the failure rate data and the average failure repair time data, obtain the precision characteristic data of the industrial robot, and process to obtain the precision retention index, perform interference simulation test on the industrial robot, and obtain the robot anti-interference ability index based on the interference simulation test results, and process according to the failure rate data, the average failure repair time data and the precision retention index in combination with the robot anti-interference ability index to obtain the robot reliability index, and formulate a maintenance plan for the industrial robot accordingly, thereby realizing the technology of industrial robot fault diagnosis based on small sample learning.

[0074] Please refer to Figure 2 , Figure 2The present invention is a flowchart of extracting real-time operation feature data of an industrial robot fault diagnosis method based on small sample learning in some embodiments of the present application. According to an embodiment of the present invention, the monitoring preset industrial robot operation monitoring information and extracting real-time operation feature data include:

[0075] S21. Real-time monitoring of the preset industrial robot and collection of operation monitoring information, including motion monitoring information, motor monitoring information, and sensor monitoring information;

[0076] S22, extracting real-time operation characteristic data according to the operation monitoring information, including motion monitoring information, motor monitoring information and sensor monitoring information;

[0077] S23. The real-time operation characteristic data includes real-time position data, real-time speed data, real-time acceleration data, real-time current data, real-time temperature data, real-time amplitude data, real-time force sensor feedback value data and real-time visual sensor data.

[0078] It should be noted that in order to monitor the status of the industrial robot so as to better understand the fault conditions of the industrial robot, it is necessary to monitor the real-time operation monitoring information of the preset industrial robot, including motion monitoring information, motor monitoring information and sensor monitoring information. Then, the real-time position data, real-time speed data and real-time acceleration data are extracted according to the motion monitoring information, the real-time current data, real-time temperature data and real-time amplitude data are extracted according to the motor monitoring information, and the real-time force sensor feedback value data and real-time visual sensor data are extracted according to the sensor monitoring information, wherein the force sensor feedback value refers to the grasping force detected by the force sensor, and the visual sensor data refers to the image feature data collected by the visual sensor.

[0079] Please refer to Figure 3 , Figure 3 The present invention is a flowchart of obtaining operation deviation data of an industrial robot fault diagnosis method based on small sample learning in some embodiments of the present application. According to an embodiment of the present invention, the step of obtaining the standard operation characteristic data of the industrial robot and performing comparative processing in combination with the real-time operation characteristic data to obtain the operation deviation data includes:

[0080] S31, obtaining standard operation characteristic data of the industrial robot, including standard position data, standard speed data, standard acceleration data, standard current data, standard temperature data, standard amplitude data, standard force sensor feedback value data, and standard visual sensor data;

[0081] S32, performing comparison processing based on the standard operation characteristic data and the real-time operation characteristic data to obtain operation deviation data;

[0082] S33, the operation deviation data includes position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation value data and visual sensor deviation data.

[0083] It should be noted that the standard operating characteristic data corresponding to the industrial robot are obtained through the relevant database, including standard position, standard speed, standard acceleration, standard current, standard temperature, standard amplitude, standard force sensor feedback value and standard visual sensor data, and then compared one by one with the extracted real-time operating characteristic data to obtain the corresponding operating deviation data.

[0084] According to an embodiment of the present invention, the step of processing the operation deviation data to obtain robot fault diagnosis data includes:

[0085] The position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation data and visual sensor deviation data are processed through a preset robot fault diagnosis model to obtain robot fault diagnosis data.

[0086] It should be noted that after obtaining various operation deviation data of the industrial robot, these data are input into the preset robot fault diagnosis model for calculation formula processing to obtain robot fault diagnosis data, which can feedback the fault condition of the industrial robot;

[0087] The calculation formula of the robot fault diagnosis data is:

[0088] ;

[0089] in, For robot fault diagnosis data, , , They are position deviation data, velocity deviation data, and acceleration deviation data, respectively. , , They are current deviation data, temperature deviation data, and amplitude deviation data. , They are the force sensor feedback deviation data and the visual sensor deviation data. , , , , , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset industrial robot fault detection platform).

[0090] Please refer to Figure 4 , Figure 4 The present invention is a flowchart of obtaining failure rate data and mean fault repair time data of an industrial robot fault diagnosis method based on small sample learning in some embodiments of the present application. According to an embodiment of the present invention, the total operation time data of the industrial robot within a preset time period, the robot fault characteristic data set and the maintenance record data set are obtained, and the failure rate data and mean fault repair time data are obtained by processing, including:

[0091] S41, obtaining all the judgment result information and corresponding processing information of the industrial robot within a preset time period, and extracting corresponding total operation time data, robot fault characteristic data set, and maintenance record data set;

[0092] S42, the robot fault characteristic data set includes fault frequency record data and fault response time data corresponding to each fault;

[0093] S43, the maintenance record data set includes the total number of fault maintenance data and the repair time data corresponding to each fault maintenance;

[0094] S44, processing the total operation time data and the failure frequency record data to obtain failure rate data;

[0095] S45, processing is performed according to the fault response time data corresponding to each fault, the total number of fault maintenance data, and the repair time data corresponding to each fault maintenance to obtain average fault repair time data.

[0096] It should be noted that the failure rate data can be obtained by counting the number of failures and the total operating time of the industrial robot within a certain period of time, and then comparing the above two data. The average failure repair time data of the industrial robot can be obtained by counting the total number of maintenance failures, the repair time spent on each repair, and the robot's failure response time within a certain period of time, and calculating the average value after processing.

[0097] According to an embodiment of the present invention, the failure rate data, the mean fault repair time data, and the accuracy retention index are processed in combination with the robot anti-interference ability index to obtain a robot reliability index, and a maintenance plan for the industrial robot is formulated accordingly, including:

[0098] According to the failure rate data, the mean fault repair time data and the accuracy retention index, combined with the robot anti-interference ability index, a robot reliability index is obtained;

[0099] Comparing the robot reliability index with a preset robot reliability threshold to obtain a threshold comparison result;

[0100] Determining the reliability level of the robot according to the threshold comparison result;

[0101] A maintenance plan for the industrial robot is formulated accordingly according to the reliability level, including a maintenance cycle and a maintenance level.

[0102] It should be noted that the reliability of the industrial robot itself will affect the frequency and severity of failures. The maintenance plan of the industrial robot can be formulated according to the reliability level of the robot, including the maintenance cycle and maintenance level, so as to reduce the probability of robot failure. Therefore, the robot reliability index can be obtained by processing the failure rate data, the mean fault repair time data and the accuracy retention index in combination with the robot anti-interference ability index;

[0103] Among them, the calculation formula of the robot reliability index is:

[0104] ;

[0105] in, is the robot reliability index, , , , They are failure rate data, mean fault repair time data, accuracy retention index, and robot anti-interference ability index. , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset industrial robot fault detection platform).

[0106] According to an embodiment of the present invention, it also includes:

[0107] The step of acquiring the precision characteristic data of the industrial robot and processing to obtain the precision retention index specifically includes:

[0108] Acquiring precision characteristic data of the industrial robot, including repeated positioning accuracy data, trajectory accuracy data, and feedback signal accuracy data;

[0109] Processing is performed according to the repeated positioning accuracy data, the trajectory accuracy data and the feedback signal accuracy data to obtain an accuracy retention index;

[0110] The calculation formula of the precision retention index is:

[0111] ;

[0112] in, is the precision retention index, , , They are repeat positioning accuracy data, trajectory accuracy data, and feedback signal accuracy data. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset industrial robot fault detection platform).

[0113] It should be noted that industrial robots have their own accuracy data, including repeatability accuracy, trajectory accuracy and feedback signal accuracy data. Repeatability accuracy refers to the consistency of the robot's repeated positioning of the same position. Trajectory accuracy reflects the degree of deviation of the robot from the theoretical trajectory when performing a specific trajectory motion. Feedback signal accuracy refers to the resolution and accuracy of the encoder. By processing the above data, the accuracy retention index can be obtained.

[0114] According to an embodiment of the present invention, it also includes:

[0115] The performing of interference simulation test on the industrial robot and obtaining the robot anti-interference capability index according to the interference simulation test result specifically includes:

[0116] Performing an interference simulation test on the industrial robot to obtain simulation test data;

[0117] Extracting anti-electromagnetic performance test data, anti-vibration performance test data and temperature rise performance test data according to the simulation test data;

[0118] The anti-electromagnetic performance test data, the anti-vibration performance test data and the temperature rise performance test data are input into a preset anti-interference ability detection model for processing to obtain the robot anti-interference ability index;

[0119] The calculation formula of the robot's anti-interference ability index is:

[0120] ;

[0121] in, is the robot's anti-interference ability index, , , They are anti-electromagnetic performance test data, anti-vibration performance test data, and temperature rise performance test data. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset industrial robot fault detection platform).

[0122] It should be noted that interference simulation tests are carried out on industrial robots, and their anti-interference capabilities are judged based on the test results, where interference factors include electromagnetic interference, vibration, and temperature.

[0123] In a second aspect, the present invention further discloses an industrial robot fault diagnosis system based on small sample learning, comprising a memory and a processor, wherein the memory comprises an industrial robot fault diagnosis method program based on small sample learning, and when the industrial robot fault diagnosis method program based on small sample learning is executed by the processor, the following steps are implemented:

[0124] Monitor preset industrial robot operation monitoring information and extract real-time operation feature data;

[0125] Acquire standard operation characteristic data of the industrial robot, and perform comparative processing on the standard operation characteristic data in combination with the real-time operation characteristic data to obtain operation deviation data;

[0126] Processing the operation deviation data to obtain robot fault diagnosis data;

[0127] Determine whether the industrial robot fails according to the robot fault diagnosis data, and record the judgment result information and processing information;

[0128] Obtaining total operation time data, robot fault characteristic data set, and maintenance record data set of the industrial robot within a preset time period, and processing to obtain failure rate data and mean fault repair time data;

[0129] Acquiring precision characteristic data of the industrial robot and processing to obtain a precision retention index;

[0130] Performing an interference simulation test on the industrial robot, and obtaining an anti-interference capability index of the robot according to the interference simulation test result;

[0131] The failure rate data, the mean fault repair time data and the accuracy retention index are processed in combination with the robot anti-interference ability index to obtain a robot reliability index, and a maintenance plan for the industrial robot is formulated accordingly.

[0132] It should be noted that with the continuous development of industrial automation, industrial robots are being used more and more widely in production and manufacturing. However, various faults may occur in industrial robots during operation, such as mechanical faults, electrical faults, sensor faults, etc. These faults will not only affect production efficiency, but may also lead to safety accidents. Therefore, timely and accurate diagnosis of industrial robot faults is crucial. Traditional industrial robot fault diagnosis methods usually require a large amount of fault sample data for training to obtain a high diagnostic accuracy. However, in practical applications, it is often difficult or even impossible to obtain a large amount of fault sample data. Therefore, it is necessary to study an industrial robot fault diagnosis method based on small sample learning. In this embodiment, first, by monitoring the preset industrial robot operation monitoring information and extracting real-time operation feature data, the standard operation feature data of the industrial robot is obtained, and the real-time operation feature data is combined for comparison processing. , obtain operation deviation data, process the operation deviation data, obtain robot fault diagnosis data, judge whether the industrial robot has a fault according to the robot fault diagnosis data, and record the judgment result information and processing information, obtain the total operation time data of the industrial robot within a preset time period, the robot fault characteristic data set and the maintenance record data set, and process to obtain the failure rate data and the average failure repair time data, obtain the precision characteristic data of the industrial robot, and process to obtain the precision retention index, perform interference simulation test on the industrial robot, and obtain the robot anti-interference ability index according to the interference simulation test results, and process according to the failure rate data, the average failure repair time data and the precision retention index, combined with the robot anti-interference ability index, obtain the robot reliability index, and formulate a maintenance plan for the industrial robot accordingly, thereby realizing the technology of industrial robot fault diagnosis based on small sample learning.

[0133] According to an embodiment of the present invention, the monitoring of preset industrial robot operation monitoring information and extracting real-time operation characteristic data includes:

[0134] Monitor preset industrial robots in real time and collect operation monitoring information, including motion monitoring information, motor monitoring information, and sensor monitoring information;

[0135] Extracting real-time operation characteristic data according to the operation monitoring information, including motion monitoring information, motor monitoring information and sensor monitoring information;

[0136] The real-time operation characteristic data includes real-time position data, real-time speed data, real-time acceleration data, real-time current data, real-time temperature data, real-time amplitude data, real-time force sensor feedback value data and real-time visual sensor data.

[0137] It should be noted that in order to monitor the status of the industrial robot so as to better understand the fault conditions of the industrial robot, it is necessary to monitor the real-time operation monitoring information of the preset industrial robot, including motion monitoring information, motor monitoring information and sensor monitoring information. Then, the real-time position data, real-time speed data and real-time acceleration data are extracted according to the motion monitoring information, the real-time current data, real-time temperature data and real-time amplitude data are extracted according to the motor monitoring information, and the real-time force sensor feedback value data and real-time visual sensor data are extracted according to the sensor monitoring information, wherein the force sensor feedback value refers to the grasping force detected by the force sensor, and the visual sensor data refers to the image feature data collected by the visual sensor.

[0138] According to an embodiment of the present invention, the step of acquiring the standard operation characteristic data of the industrial robot and performing comparison processing in combination with the real-time operation characteristic data to obtain the operation deviation data includes:

[0139] Acquiring standard operation characteristic data of the industrial robot, including standard position data, standard speed data, standard acceleration data, standard current data, standard temperature data, standard amplitude data, standard force sensor feedback value data, and standard visual sensor data;

[0140] Performing comparison processing based on the standard operation characteristic data and the real-time operation characteristic data to obtain operation deviation data;

[0141] The operation deviation data includes position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation value data and visual sensor deviation data.

[0142] It should be noted that the standard operating characteristic data corresponding to the industrial robot are obtained through the relevant database, including standard position, standard speed, standard acceleration, standard current, standard temperature, standard amplitude, standard force sensor feedback value and standard visual sensor data, and then compared one by one with the extracted real-time operating characteristic data to obtain the corresponding operating deviation data.

[0143] According to an embodiment of the present invention, the step of processing the operation deviation data to obtain robot fault diagnosis data includes:

[0144] The position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation data and visual sensor deviation data are processed through a preset robot fault diagnosis model to obtain robot fault diagnosis data.

[0145] It should be noted that after obtaining various operation deviation data of the industrial robot, these data are input into the preset robot fault diagnosis model for calculation formula processing to obtain robot fault diagnosis data, which can feedback the fault condition of the industrial robot;

[0146] The calculation formula of the robot fault diagnosis data is:

[0147] ;

[0148] in, For robot fault diagnosis data, , , They are position deviation data, velocity deviation data, and acceleration deviation data, respectively. , , They are current deviation data, temperature deviation data, and amplitude deviation data. , They are the force sensor feedback deviation data and the visual sensor deviation data. , , , , , , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset industrial robot fault detection platform).

[0149] According to an embodiment of the present invention, the acquiring of the total operation time data of the industrial robot within a preset time period, the robot fault characteristic data set, and the maintenance record data set, and processing to obtain the failure rate data and the mean fault repair time data, includes:

[0150] Obtaining all the judgment result information and corresponding processing information of the industrial robot within a preset time period, and extracting corresponding total operation time data, robot fault characteristic data set, and maintenance record data set;

[0151] The robot fault characteristic data set includes fault frequency record data and fault response time data corresponding to each fault;

[0152] The maintenance record data set includes total number of fault maintenance data and repair time data corresponding to each fault maintenance;

[0153] Processing the total operation time data and the failure frequency record data to obtain failure rate data;

[0154] The average fault repair time data is obtained by processing the fault response time data corresponding to each fault, the total number of fault maintenance data, and the repair time data corresponding to each fault maintenance.

[0155] It should be noted that the failure rate data can be obtained by counting the number of failures and the total operating time of the industrial robot within a certain period of time, and then comparing the above two data. The average failure repair time data of the industrial robot can be obtained by counting the total number of maintenance failures, the repair time spent on each repair, and the robot's failure response time within a certain period of time, and calculating the average value after processing.

[0156] According to an embodiment of the present invention, the failure rate data, the mean fault repair time data, and the accuracy retention index are processed in combination with the robot anti-interference ability index to obtain a robot reliability index, and a maintenance plan for the industrial robot is formulated accordingly, including:

[0157] According to the failure rate data, the mean fault repair time data and the accuracy retention index, combined with the robot anti-interference ability index, a robot reliability index is obtained;

[0158] Comparing the robot reliability index with a preset robot reliability threshold to obtain a threshold comparison result;

[0159] Determining the reliability level of the robot according to the threshold comparison result;

[0160] A maintenance plan for the industrial robot is formulated accordingly according to the reliability level, including a maintenance cycle and a maintenance level.

[0161] It should be noted that the reliability of the industrial robot itself will affect the frequency and severity of failures. The maintenance plan of the industrial robot can be formulated according to the reliability level of the robot, including the maintenance cycle and maintenance level, so as to reduce the probability of robot failure. Therefore, the robot reliability index can be obtained by processing the failure rate data, the mean fault repair time data and the accuracy retention index in combination with the robot anti-interference ability index;

[0162] Among them, the calculation formula of the robot reliability index is:

[0163] ;

[0164] in, is the robot reliability index, , , , They are failure rate data, mean fault repair time data, accuracy retention index, and robot anti-interference ability index. , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset industrial robot fault detection platform).

[0165] According to an embodiment of the present invention, it also includes:

[0166] The step of acquiring the precision characteristic data of the industrial robot and processing to obtain the precision retention index specifically includes:

[0167] Acquiring precision characteristic data of the industrial robot, including repeated positioning accuracy data, trajectory accuracy data, and feedback signal accuracy data;

[0168] Processing is performed according to the repeated positioning accuracy data, the trajectory accuracy data and the feedback signal accuracy data to obtain an accuracy retention index;

[0169] The calculation formula of the precision retention index is:

[0170] ;

[0171] in, is the precision retention index, , , They are repeat positioning accuracy data, trajectory accuracy data, and feedback signal accuracy data. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset industrial robot fault detection platform).

[0172] It should be noted that industrial robots have their own accuracy data, including repeatability accuracy, trajectory accuracy and feedback signal accuracy data. Repeatability accuracy refers to the consistency of the robot's repeated positioning of the same position. Trajectory accuracy reflects the degree of deviation of the robot from the theoretical trajectory when performing a specific trajectory motion. Feedback signal accuracy refers to the resolution and accuracy of the encoder. By processing the above data, the accuracy retention index can be obtained.

[0173] According to an embodiment of the present invention, it also includes:

[0174] The performing of interference simulation test on the industrial robot and obtaining the robot anti-interference capability index according to the interference simulation test result specifically includes:

[0175] Performing an interference simulation test on the industrial robot to obtain simulation test data;

[0176] Extracting anti-electromagnetic performance test data, anti-vibration performance test data and temperature rise performance test data according to the simulation test data;

[0177] The anti-electromagnetic performance test data, the anti-vibration performance test data and the temperature rise performance test data are input into a preset anti-interference ability detection model for processing to obtain the robot anti-interference ability index;

[0178] The calculation formula of the robot's anti-interference ability index is:

[0179] ;

[0180] in, is the robot's anti-interference ability index, , , They are anti-electromagnetic performance test data, anti-vibration performance test data, and temperature rise performance test data. , , is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset industrial robot fault detection platform).

[0181] It should be noted that interference simulation tests are carried out on industrial robots, and their anti-interference capabilities are judged based on the test results, where interference factors include electromagnetic interference, vibration, and temperature.

[0182] The present invention discloses an industrial robot fault diagnosis method and system based on small sample learning. The method and system monitor preset industrial robot operation monitoring information, extract real-time operation characteristic data, obtain standard operation characteristic data of the industrial robot, and compare and process the real-time operation characteristic data to obtain operation deviation data. The method processes the operation deviation data to obtain robot fault diagnosis data. The method determines whether the industrial robot fails according to the robot fault diagnosis data, and records the judgment result information and processing information. The method obtains the total operation time data, robot fault characteristic data set and maintenance record data set of the industrial robot within a preset time period, processes the data to obtain the failure rate data and the average failure repair time data, obtains the accuracy characteristic data of the industrial robot, processes the data to obtain the accuracy retention index, performs interference simulation test on the industrial robot, processes the data to obtain the robot anti-interference ability index according to the interference simulation test result, processes the failure rate data, the average failure repair time data and the accuracy retention index in combination with the robot anti-interference ability index to obtain the robot reliability index, and formulates a maintenance plan for the industrial robot accordingly, thereby realizing the technology of industrial robot fault diagnosis based on small sample learning.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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 industrial robot fault diagnosis based on small sample learning, characterized in that: The following steps are involved: Monitor preset industrial robot operation monitoring information and extract real-time operation feature data; Acquire standard operation characteristic data of the industrial robot, and perform comparative processing on the standard operation characteristic data in combination with the real-time operation characteristic data to obtain operation deviation data; Processing the operation deviation data to obtain robot fault diagnosis data; Determine whether the industrial robot fails according to the robot fault diagnosis data, and record the judgment result information and processing information; Obtaining total operation time data, robot fault characteristic data set, and maintenance record data set of the industrial robot within a preset time period, and processing to obtain failure rate data and mean fault repair time data; Acquiring precision characteristic data of the industrial robot and processing to obtain a precision retention index; Performing an interference simulation test on the industrial robot, and obtaining an anti-interference capability index of the robot according to the interference simulation test result; According to the failure rate data, mean fault repair time data and precision retention index, combined with the robot anti-interference ability index, a robot reliability index is obtained, and a maintenance plan for the industrial robot is formulated accordingly; The obtaining of the total operation time data of the industrial robot within a preset time period, the robot fault characteristic data set and the maintenance record data set, and processing to obtain the failure rate data and the mean fault repair time data, includes: Obtaining all the judgment result information and corresponding processing information of the industrial robot within a preset time period, and extracting corresponding total operation time data, robot fault characteristic data set, and maintenance record data set; The robot fault characteristic data set includes fault frequency record data and fault response time data corresponding to each fault; The maintenance record data set includes total number of fault maintenance data and repair time data corresponding to each fault maintenance; Processing the total operation time data and the failure frequency record data to obtain failure rate data; Processing is performed according to the fault response time data corresponding to each fault, the total number of fault maintenance data, and the repair time data corresponding to each fault maintenance to obtain average fault repair time data; The processing according to the failure rate data, the mean fault repair time data and the precision retention index is combined with the robot anti-interference ability index to obtain the robot reliability index, and the maintenance plan of the industrial robot is formulated accordingly, including: According to the failure rate data, the mean fault repair time data and the accuracy retention index, combined with the robot anti-interference ability index, a robot reliability index is obtained; Comparing the robot reliability index with a preset robot reliability threshold to obtain a threshold comparison result; Determining the reliability level of the robot according to the threshold comparison result; Formulate a maintenance plan for the industrial robot according to the reliability level, including maintenance cycles and maintenance levels; Among them, the calculation formula of the robot reliability index is: ； in, is the robot reliability index, , , , They are failure rate data, mean fault repair time data, accuracy retention index, and robot anti-interference ability index. , is the preset characteristic coefficient; The step of acquiring the precision characteristic data of the industrial robot and processing to obtain the precision retention index specifically includes: Acquiring precision characteristic data of the industrial robot, including repeated positioning accuracy data, trajectory accuracy data, and feedback signal accuracy data; Processing is performed according to the repeated positioning accuracy data, the trajectory accuracy data and the feedback signal accuracy data to obtain an accuracy retention index; The calculation formula of the precision retention index is: ； in, is the precision retention index, , , They are repeat positioning accuracy data, trajectory accuracy data, and feedback signal accuracy data. , , is the preset characteristic coefficient.

2. The industrial robot fault diagnosis method based on small sample learning according to claim 1 is characterized in that: The monitoring presets the industrial robot operation monitoring information and extracts the real-time operation characteristic data, including: Monitor preset industrial robots in real time and collect operation monitoring information, including motion monitoring information, motor monitoring information, and sensor monitoring information; Extracting real-time operation characteristic data based on the operation monitoring information, including motion monitoring information, motor monitoring information and sensor monitoring information, The real-time operation characteristic data includes real-time position data, real-time speed data, real-time acceleration data, real-time current data, real-time temperature data, real-time amplitude data, real-time force sensor feedback value data and real-time visual sensor data.

3. The industrial robot fault diagnosis method based on small sample learning according to claim 2 is characterized in that: The step of acquiring the standard operation characteristic data of the industrial robot and performing comparison processing with the real-time operation characteristic data to obtain the operation deviation data includes: Acquiring standard operation characteristic data of the industrial robot, including standard position data, standard speed data, standard acceleration data, standard current data, standard temperature data, standard amplitude data, standard force sensor feedback value data, and standard visual sensor data; Performing comparison processing based on the standard operation characteristic data and the real-time operation characteristic data to obtain operation deviation data; The operation deviation data includes position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation value data and visual sensor deviation data.

4. The industrial robot fault diagnosis method based on small sample learning according to claim 3 is characterized in that: The step of processing the operation deviation data to obtain robot fault diagnosis data includes: The position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation data and visual sensor deviation data are processed through a preset robot fault diagnosis model to obtain robot fault diagnosis data.

5. An industrial robot fault diagnosis system based on small sample learning, characterized in that: The system includes: a memory and a processor, wherein the memory includes a program of an industrial robot fault diagnosis method based on small sample learning, and when the program of the industrial robot fault diagnosis method based on small sample learning is executed by the processor, the following steps are implemented: Monitor preset industrial robot operation monitoring information and extract real-time operation feature data; Acquire standard operation characteristic data of the industrial robot, and perform comparative processing on the standard operation characteristic data in combination with the real-time operation characteristic data to obtain operation deviation data; Processing the operation deviation data to obtain robot fault diagnosis data; Determine whether the industrial robot fails according to the robot fault diagnosis data, and record the judgment result information and processing information; Obtaining total operation time data, robot fault characteristic data set, and maintenance record data set of the industrial robot within a preset time period, and processing to obtain failure rate data and mean fault repair time data; Acquiring precision characteristic data of the industrial robot and processing to obtain a precision retention index; Performing an interference simulation test on the industrial robot, and obtaining an anti-interference capability index of the robot according to the interference simulation test result; According to the failure rate data, mean fault repair time data and precision retention index, combined with the robot anti-interference ability index, a robot reliability index is obtained, and a maintenance plan for the industrial robot is formulated accordingly; The obtaining of the total operation time data of the industrial robot within a preset time period, the robot fault characteristic data set and the maintenance record data set, and processing to obtain the failure rate data and the mean fault repair time data, includes: Obtaining all the judgment result information and corresponding processing information of the industrial robot within a preset time period, and extracting corresponding total operation time data, robot fault characteristic data set, and maintenance record data set; The robot fault characteristic data set includes fault frequency record data and fault response time data corresponding to each fault; The maintenance record data set includes total number of fault maintenance data and repair time data corresponding to each fault maintenance; Processing the total operation time data and the failure frequency record data to obtain failure rate data; Processing is performed according to the fault response time data corresponding to each fault, the total number of fault maintenance data, and the repair time data corresponding to each fault maintenance to obtain average fault repair time data; The processing according to the failure rate data, the mean fault repair time data and the precision retention index is combined with the robot anti-interference ability index to obtain the robot reliability index, and the maintenance plan of the industrial robot is formulated accordingly, including: According to the failure rate data, the mean fault repair time data and the accuracy retention index, combined with the robot anti-interference ability index, a robot reliability index is obtained; Comparing the robot reliability index with a preset robot reliability threshold to obtain a threshold comparison result; Determining the reliability level of the robot according to the threshold comparison result; Formulate a maintenance plan for the industrial robot according to the reliability level, including maintenance cycles and maintenance levels; Among them, the calculation formula of the robot reliability index is: ； in, is the robot reliability index, , , , They are failure rate data, mean fault repair time data, accuracy retention index, and robot anti-interference ability index. , is the preset characteristic coefficient; The step of acquiring the precision characteristic data of the industrial robot and processing to obtain the precision retention index specifically includes: Acquiring precision characteristic data of the industrial robot, including repeated positioning accuracy data, trajectory accuracy data, and feedback signal accuracy data; Processing is performed according to the repeated positioning accuracy data, the trajectory accuracy data and the feedback signal accuracy data to obtain an accuracy retention index; The calculation formula of the precision retention index is: ； in, is the precision retention index, , , They are repeat positioning accuracy data, trajectory accuracy data, and feedback signal accuracy data. , , is the preset characteristic coefficient.

6. The industrial robot fault diagnosis system based on small sample learning according to claim 5 is characterized in that: The monitoring presets the industrial robot operation monitoring information and extracts the real-time operation characteristic data, including: Monitor preset industrial robots in real time and collect operation monitoring information, including motion monitoring information, motor monitoring information, and sensor monitoring information; Extracting real-time operation characteristic data based on the operation monitoring information, including motion monitoring information, motor monitoring information and sensor monitoring information, The real-time operation characteristic data includes real-time position data, real-time speed data, real-time acceleration data, real-time current data, real-time temperature data, real-time amplitude data, real-time force sensor feedback value data and real-time visual sensor data.

7. The industrial robot fault diagnosis system based on small sample learning according to claim 6 is characterized in that: The step of acquiring the standard operation characteristic data of the industrial robot and performing comparison processing with the real-time operation characteristic data to obtain the operation deviation data includes: Acquiring standard operation characteristic data of the industrial robot, including standard position data, standard speed data, standard acceleration data, standard current data, standard temperature data, standard amplitude data, standard force sensor feedback value data, and standard visual sensor data; Performing comparison processing based on the standard operation characteristic data and the real-time operation characteristic data to obtain operation deviation data; The operation deviation data includes position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation value data and visual sensor deviation data.

8. The industrial robot fault diagnosis system based on small sample learning according to claim 7 is characterized in that: The step of processing the operation deviation data to obtain robot fault diagnosis data includes: The position deviation data, speed deviation data, acceleration deviation data, current deviation data, temperature deviation data, amplitude deviation data, force sensor feedback deviation data and visual sensor deviation data are processed through a preset robot fault diagnosis model to obtain robot fault diagnosis data.

Images