Robot fault monitoring method, electronic equipment and computer readable storage medium
By processing the abnormal probability of robot operating parameters and establishing correspondence, the problems of inaccurate fault identification and ineffective early warning in the prior art are solved, and more accurate fault identification and early warning are achieved.
Patent Information
- Application Number
- CN202510201896.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-24
- Publication Date
- 2025-05-30
AI Technical Summary
The prior art is difficult to accurately identify the specific type of robot failure, and it is impossible to effectively use abnormal parameters to conduct early warnings, resulting in inaccurate early warnings.
By obtaining the historical operation parameters during the robot operation, processing these parameters is used to determine the probability of anomaly, and establishing the correspondence between the exception parameters and the preset fault, so as to accurately identify the fault type and provide early warning.
It realizes the specific correspondence between abnormal parameters and fault types, which improves the accuracy of fault identification and the effectiveness of early warning.
Smart Images
Figure CN120067707A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of robots, and in particular to a robot fault monitoring method, an electronic device, and a computer-readable storage medium. Background Art
[0002] With the development and progress of technology, robots have almost completely replaced manual welding in the automotive manufacturing process. For example, the welding shop has achieved 100% automation of various processes and key processes, which is a key link in the automotive production and manufacturing process. In such a production environment, the stability of robots on the production line is crucial for production efficiency and product quality control, and it is necessary to monitor the working status of robots.
[0003] Currently, the fault warning for robots is relatively general, and it is difficult to know the specific fault type. For example, when a robot collides or an emergency stop alarm occurs, only a collision alarm will be prompted, but it will not correspond to which axis of the robot has collided. Moreover, abnormal parameters cannot be well utilized. Even if some parameters are abnormal, they cannot be well utilized for warning, and accurate warning cannot be achieved. Summary of the Invention
[0004] In view of the above problems, the present application provides a robot fault monitoring method, an electronic device, and a computer-readable storage medium. By establishing a correspondence between abnormal parameters and preset faults, the abnormal parameters can be corresponded to specific faults, which can specifically reflect the faults of the robot. Moreover, by comparing the operating parameters with the abnormal parameters to determine whether there is a preset fault, various parameters can be well utilized, making the warning more accurate.
[0005] The first aspect of the present application provides a robot fault monitoring method, including: obtaining historical operating parameters of a robot during a historical period in the process of operation; wherein, the end time of the historical period is the current time, and the duration of the historical period is less than a preset duration; processing the historical operating parameters to obtain the abnormal probability of the historical operating parameters, and determining the historical operating parameters as abnormal parameters when the abnormal probability is greater than a preset probability, and establishing a correspondence between the abnormal parameters and preset faults; detecting that the similarity between the operating parameters and the abnormal parameters during the operation of the robot reaches a preset similarity, then determining that the robot has a preset fault corresponding to the abnormal parameters.
[0006] In some specific embodiments, the step of processing historical operating parameters to obtain the abnormal probability of the historical operating parameters includes: establishing a historical characteristic curve corresponding to the historical operating parameters based on the historical operating parameters; comparing the historical characteristic curve with a standard characteristic curve to obtain the similarity between the historical characteristic curve and the standard characteristic curve; wherein, the standard characteristic curve is established based on historical normal operating parameters; obtaining the abnormal probability of the historical operating parameters according to the similarity; wherein, there is a preset corresponding relationship between the similarity and the abnormal probability.
[0007] In some specific embodiments, the step of comparing the historical characteristic curve with the standard characteristic curve to obtain the similarity between the historical characteristic curve and the standard characteristic curve includes: obtaining a first similarity between a first characteristic value of the historical characteristic curve and a first standard characteristic value of the standard characteristic curve, and obtaining a second similarity between a second characteristic value of the historical characteristic curve and a second standard characteristic value of the standard characteristic curve; the step of obtaining the abnormal probability of the historical operating parameters according to the similarity includes: if the first similarity does not meet the first standard similarity, and / or the second similarity does not meet the second standard similarity, then determining the abnormal probability of the historical operating parameters according to the difference degrees between the first similarity and the first standard similarity and between the second similarity and the second standard similarity.
[0008] In some specific embodiments, the step of processing historical operating parameters to obtain the abnormal probability of the historical operating parameters includes: performing a differential analysis on the historical operating parameters and the predicted operating parameters corresponding to a historical time period to obtain a differential degree; wherein, the predicted operating parameters are predicted based on historical normal parameters before the historical time period; determining the abnormal probability of the historical operating parameters according to the differential degree; wherein, there is a corresponding relationship between the differential degree and the abnormal probability.
[0009] In some specific embodiments, the step of performing a differential analysis on the historical operating parameters and the predicted operating parameters corresponding to a historical time period to obtain a differential degree includes: performing a residual analysis on the historical operating parameters and the predicted operating parameters within the historical time period to obtain a residual value; the step of determining the abnormal probability of the historical operating parameters according to the differential degree includes: determining the abnormal probability of the historical operating parameters according to the residual value; wherein, there is a corresponding relationship between the residual value and the abnormal probability.
[0010] In some specific embodiments, the steps of establishing the correspondence between abnormal parameters and preset faults include: if alarm information is monitored within a historical period and the alarm information includes a preset fault, then taking the preset fault as the first preset fault and establishing the correspondence between the abnormal parameter and the first preset fault; if alarm information is monitored within a historical period and the alarm information does not include a preset fault, then determining the preset fault corresponding to the abnormal parameter based on the characteristic information of the abnormal parameter and taking it as the second preset fault, and establishing the correspondence between the abnormal parameter and the second preset fault; if no alarm information is monitored within a historical period, then determining the preset hidden fault corresponding to the abnormal parameter based on the characteristic information of the abnormal parameter, taking the preset hidden fault as the third preset fault, and establishing the correspondence between the abnormal parameter and the third preset fault.
[0011] In some specific embodiments, if alarm information is monitored within a historical period and the alarm information does not include a preset fault, then the steps of determining the preset fault corresponding to the abnormal parameter based on the characteristic information of the abnormal parameter and taking it as the second preset fault, and establishing the correspondence between the abnormal parameter and the second preset fault include: if no alarm information is monitored within a historical period and the type of the abnormal parameter belongs to the type of robot position parameters, then determining that the abnormal parameter corresponds to a structural looseness fault and establishing the correspondence between the abnormal parameter and the structural looseness fault.
[0012] In some specific embodiments, the method further includes: obtaining the total number of times a preset fault occurs for the same robot within a preset period; if the total number reaches the preset number, then sending the position information of the robot and the fault information within the preset period to the user terminal.
[0013] A second aspect of the present application provides an electronic device, including: a processor; a memory for storing a computer program, where the computer program, when executed by the processor, implements the robot fault monitoring method of any one of the above.
[0014] A third aspect of the present application provides a computer-readable storage medium, where a computer program is stored in the storage medium, and the computer program, when executed by the processor, implements the robot fault monitoring method as described in any one of the above.
[0015] The beneficial technical effects that this application at least has: Based on the robot fault monitoring method, electronic device, and computer-readable storage medium provided by this application, the method includes: obtaining the historical operation parameters of a robot during a historical period; wherein, the end time of the historical period is the current time, and the duration of the historical period is less than a preset duration; processing the historical operation parameters to obtain the abnormal probability of the historical operation parameters, and when the abnormal probability is greater than a preset probability, determining the historical operation parameters as abnormal parameters, and establishing a correspondence relationship between the abnormal parameters and a preset fault; detecting that the similarity between the operation parameters during the robot's operation and the abnormal parameters reaches a preset similarity, then determining that the robot has the preset fault corresponding to the abnormal parameters. Therefore, by establishing a correspondence relationship between the abnormal parameters and the preset faults, the abnormal parameters can be corresponded to specific faults, which can specifically reflect the faults of the robot. By comparing the operation parameters with the abnormal parameters to determine whether there is a preset fault, various parameters can be utilized well, making the early warning more accurate.
[0016] The above description is only an overview of the technical solution of the embodiments of this application. In order to be able to understand the technical means of the embodiments of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the embodiments of this application more obvious and understandable, the following specifically lists the specific implementation manners of this application. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The drawings are only used to illustrate the embodiments and are not considered to be a limitation of this application. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:
[0018] Figure 1 is a flowchart of an embodiment of the robot fault monitoring method provided by this application;
[0019] Figure 2 is a flowchart of another embodiment of the robot fault monitoring method provided by this application;
[0020] Figure 3 is a flowchart of yet another embodiment of the robot fault monitoring method provided by this application;
[0021] Figure 4 is a flowchart of yet another embodiment of the robot fault monitoring method provided by this application;
[0022] Figure 5 is a flowchart of yet another embodiment of the robot fault monitoring method provided by this application;
[0023] Figure 6 is a flowchart of yet another embodiment of the robot fault monitoring method provided by this application;
[0024] Figure 7 It is a schematic flowchart of another embodiment of the robot fault monitoring method provided by this application;
[0025] Figure 8 It is a schematic structural framework diagram of an embodiment of the electronic device provided by this application;
[0026] Figure 9 It is a schematic structural framework diagram of an embodiment of the computer-readable storage medium provided by this application. Detailed implementation manners
[0027] Hereinafter, the exemplary embodiments of this application will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited by the embodiments set forth herein. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the protection scope of this application.
[0028] If there are descriptions involving "first", "second", etc. in the embodiments of this application, such descriptions of "first", "second", etc. are only for descriptive purposes and should not be construed as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the meaning of "and / or" appearing throughout the text is that it includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, or solution B, or a solution that satisfies both A and B simultaneously. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by this application.
[0029] In the first aspect of this application, a robot fault monitoring method is provided, and this method can be applied to a robot monitoring system. Among them, the robot monitoring system can include a switch and a monitoring device. The switch is connected to the robot and the monitoring device, and some operation data of the robot can be transmitted to the monitoring device through the switch, and then the processing of the operation data can be realized through the monitoring device.
[0030] Figure 1 It is a schematic flowchart of an embodiment of the robot fault monitoring method provided by this application. Combining Figure 1 , this method includes the following steps:
[0031] S101: Obtain the historical operation parameters of the robot during the historical period in the running process; wherein, the end time of the historical period is the current time, and the duration of the historical period is less than the preset duration.
[0032] Among them, the operating parameters during the operation of the robot can be recorded by the robot itself or by other devices. The recorded data can be transmitted to the robot monitoring system, so that the robot monitoring system can obtain the operating parameters and process the operating parameters. The preset duration of the historical period can be a relatively short duration, so as to be able to reflect the parameter status of the robot in a timely manner.
[0033] Specifically, the robot system can include a robot body, external devices of the robot, and control devices of the robot. The robot body is the core part of the robot system. The external devices are arranged on the robot body to achieve a certain specific function. The control devices are used to control the robot. Among them, the robot body can include axes, motors, reducers, encoders, etc.; the external devices can include welding tongs, welders, grippers, pipeline packages, gun changers, fixtures, water and gas modules, etc.; the control devices can include network communication connection devices, power modules, drive devices, control modules, IO signal circuits, etc.
[0034] Correspondingly, the operating parameters during the operation of the robot can include parameters of various types such as body parameters, peripheral device parameters, and control parameters. These parameters can often reflect the working status of the corresponding devices and the working status of the entire robot system.
[0035] S102: Process the historical operating parameters to obtain the abnormal probability of the historical operating parameters. When the abnormal probability is greater than the preset probability, determine that the historical operating parameters are abnormal parameters, and establish a corresponding relationship between the abnormal parameters and the preset faults.
[0036] It should be understood that the historical operating parameters can reflect the working status of the robot during the historical period. If the historical operating parameters are abnormal, it is very likely that the robot was working abnormally during the historical period.
[0037] When the robot is working normally, even when executing the same instruction and at the same stage of executing the same instruction, the operating parameters will not remain unchanged. As long as the fluctuation of the operating parameters is small, it can be considered that the robot is in a normal working state. And even if the fluctuation of the operating parameters is large, the operating parameters are not necessarily abnormal, and the robot is not necessarily in an abnormal working state. Therefore, after processing the historical operating parameters in this embodiment, even if the historical operating parameters have large fluctuations, it will not directly determine that the historical operating parameters are abnormal, but determine the abnormal probability of the historical operating parameters. Among them, the abnormal probability of the historical operating parameters represents to a certain extent the abnormal probability of the robot's work.
[0038] The preset probability can be set in advance according to the actual performance of the robot system and the actual needs of the user. When the abnormal probability is greater than the preset probability, it indicates that there is a high possibility that the historical operating parameters have problems. At this time, the historical operating parameters can be used as abnormal parameters. When the historical operating parameters are abnormal parameters, it means that the robot is very likely to have failed during the historical period. At this time, a corresponding relationship is established between the abnormal parameters and the preset faults, that is, a corresponding relationship is established between the historical operating parameters within the historical period and the preset faults.
[0039] S103: If it is detected that the similarity between the operating parameters during the operation of the robot and the abnormal parameters reaches the preset similarity, it is determined that the robot has the preset fault corresponding to the abnormal parameters.
[0040] The corresponding relationship established in the above steps will be stored. During the subsequent process, when it is detected that the similarity between the operating parameters during the operation and the abnormal parameters reaches the preset similarity, the preset fault corresponding to the preset parameters will be determined through the abnormal parameters and the stored corresponding relationship.
[0041] Among them, the operating parameters during the operation of the robot can also be detected according to the detection period. The duration of the detection period can be the duration of the above historical period, which is convenient for comparing the operating parameters and the abnormal parameters. When obtaining the similarity between the operating parameters and the abnormal parameters, the work instructions to which they belong and the execution stage of the work instructions can be considered. For example, the operating parameters and the abnormal parameters under the same work instruction and the same execution stage will be compared.
[0042] The evaluation method of the similarity between the operating parameters and the abnormal parameters is not limited in this embodiment and can be various evaluation methods. For example, the similarity between the two can be determined according to the relationship between the characteristic values corresponding to the operating parameters and the abnormal parameters. Among them, the preset similarity can be determined according to the actual performance of the robot system, the actual needs of the user, and the specific application scenario, without specific limitations. When the similarity between the operating parameters and the abnormal parameters reaches the preset similarity, it indicates that the operating parameters and the abnormal parameters are very similar. At this time, the operating parameters are considered as abnormal parameters, and the corresponding preset fault is determined according to the abnormal parameters.
[0043] In summary, by establishing a corresponding relationship between the abnormal parameters and the preset faults, the abnormal parameters can be corresponded to specific faults. When the similarity between the operating parameters and the abnormal parameters reaches the preset similarity, the preset fault can be determined through the abnormal parameters, which can specifically reflect the faults of the robot. Moreover, by comparing the operating parameters and the abnormal parameters to determine whether there is a preset fault, various parameters during the operation of the robot can be well utilized. As long as the parameters have certain abnormalities, the corresponding preset fault can be obtained according to the abnormal parameters, which makes the early warning of the robot more accurate.
[0044] Figure 2 It is a schematic flowchart of another embodiment of the robot fault monitoring method provided by this application. In combination with Figure 2 , in some specific embodiments, the step of processing historical operation parameters to obtain the abnormal probability of historical operation parameters includes:
[0045] S201: Establish a historical characteristic curve corresponding to the historical operation parameters based on the historical operation parameters;
[0046] It should be understood that the historical operation parameters are data within a historical period. The historical operation parameters have multiple data points, and different data points correspond to different historical moments in the historical period. According to the multiple data points of the historical operation parameters, a historical characteristic curve can be established. The historical characteristic curve can reflect some statistical characteristics of the historical operation parameters, such as variance, mean, standard deviation, peak value, skewness, etc.
[0047] S202: Compare the historical characteristic curve with the standard characteristic curve to obtain the similarity between the historical characteristic curve and the standard characteristic curve; wherein, the standard characteristic curve is established based on historical normal operation parameters.
[0048] During the operation of the robot, a large amount of historical normal operation parameters can be obtained. The historical normal operation parameters correspond to the historical normal working state of the robot. Through a large amount of historical normal operation parameters, a standard characteristic curve can be established.
[0049] Among them, the historical characteristic curve and the standard characteristic curve for comparison can be the characteristic curves in the same instruction and the same execution stage. For the comparison method of the similarity between the two curves, this embodiment does not make specific limitations and can be set according to actual needs.
[0050] S203: Obtain the abnormal probability of the historical operation parameters according to the similarity; wherein, there is a preset corresponding relationship between the similarity and the abnormal probability.
[0051] It should be understood that the similarity between the historical characteristic curve and the standard characteristic curve can reflect the difference between the historical operation parameters and the normal operation parameters. Moreover, the lower the similarity between the two curves, the greater the difference between the historical operation parameters and the normal operation parameters, indicating that the abnormal probability of the historical operation parameters is greater. Therefore, in the preset corresponding relationship between the similarity and the abnormal probability, it can be that the higher the similarity, the lower the abnormal probability.
[0052] In this embodiment, by establishing a comparison between the historical characteristic curve and the standard curve, the difference between the historical data and the normal data can be more comprehensively reflected, and then the abnormal probability can be determined according to the difference relationship, making the determined abnormal probability more accurate.
[0053] Figure 3 It is a schematic flowchart of another embodiment of the robot fault monitoring method provided by this application.
[0054] Combined with Figure 3 , in some specific embodiments, the step of comparing the historical feature curve with the standard feature curve to obtain the similarity between the historical feature curve and the standard feature curve, that is, the above step S202, includes:
[0055] S301: Obtain the first similarity between the first eigenvalue of the historical feature curve and the first standard eigenvalue of the standard feature curve, and obtain the second similarity between the second eigenvalue of the historical feature curve and the second standard eigenvalue of the standard feature curve.
[0056] Combined with the above content, both the historical feature curve and the standard feature curve can reflect multiple eigenvalues. The historical feature curve in this embodiment can obtain the first eigenvalue and the second eigenvalue, and the standard feature curve can obtain the first standard eigenvalue and the second standard eigenvalue. For example, the first eigenvalue and the second eigenvalue can be any two of variance, mean, standard deviation, peak value, skewness, etc., without specific limitation. The first standard eigenvalue and the second standard eigenvalue are of the same type as the first eigenvalue and the second eigenvalue respectively, but the standard eigenvalue is the eigenvalue corresponding to the normal operating parameter.
[0057] In this embodiment, the similarity of two straight lines is obtained by separately obtaining the first similarity and the second similarity.
[0058] The step of obtaining the abnormal probability of the historical operating parameter according to the similarity, that is, the above step S203, includes:
[0059] S302: If the first similarity does not meet the first standard similarity, and / or the second similarity does not meet the second standard similarity, then determine the abnormal probability of the historical operating parameter according to the difference degree between the first similarity and the first standard similarity and between the second similarity and the second standard similarity.
[0060] The first similarity not meeting the first standard similarity indicates that the similarity between the first eigenvalue and the first standard eigenvalue is low, indicating that the first eigenvalue is very likely to be an abnormal value. Similarly, the second similarity not meeting the second standard similarity indicates that the similarity between the second eigenvalue and the second standard eigenvalue is low, indicating that the second eigenvalue is very likely to be an abnormal value.
[0061] It should be understood that if one of the first similarity and the second similarity does not meet, it indicates that there is a certain abnormal probability for the historical operating parameter. At this time, the corresponding abnormal probability is determined through the difference degree between the similarities. The relationship between the difference degree and the abnormal probability can be preset, and the corresponding abnormal probability is greater when the difference degree is greater.
[0062] Figure 4 It is a schematic flowchart of another embodiment of the robot fault monitoring method provided by this application.
[0063] Combined with Figure 4 , in some specific embodiments, the step of processing historical operation parameters to obtain the abnormal probability of historical operation parameters includes:
[0064] S401: Perform a differential analysis on the historical operation parameters and the predicted operation parameters corresponding to the historical time period to obtain the degree of difference; wherein, the predicted operation parameters are predicted based on the historical normal parameters before the historical time period.
[0065] This embodiment provides another way to obtain the abnormal probability of historical operation parameters, that is, by comparing the predicted operation parameters with the historical operation parameters, and then obtaining the abnormal probability.
[0066] During the operation of the robot, the probability of abnormal operation parameters is relatively small, and the operation parameters during future operation can generally be predicted through historical normal data. Therefore, through the historical normal parameters before the historical time period, the operation parameters during the historical time period, that is, the predicted operation parameters, can be predicted.
[0067] It should be understood that the predicted operation parameters are the operation parameters of the robot under the predicted normal operation state. The degree of difference between the historical operation parameters and the predicted operation parameters actually reflects the degree of difference between the historical operation parameters and the normal operation parameters theoretically.
[0068] S402: Determine the abnormal probability of the historical operation parameters according to the degree of difference; wherein, there is a corresponding relationship between the degree of difference and the abnormal probability.
[0069] When the degree of difference is large, it indicates that the difference between the historical operation parameters and the normal operation parameters theoretically is larger, and it indicates that the abnormal probability of the historical operation parameters is larger. Therefore, in the corresponding relationship between the degree of difference and the abnormal probability, the larger the degree of difference, the larger the corresponding abnormal probability.
[0070] Figure 5 It is a schematic flowchart of another embodiment of the robot fault monitoring method provided by this application.
[0071] Combined with Figure 5 , in some specific embodiments, the step of performing a differential analysis on the historical operation parameters and the predicted operation parameters corresponding to the historical time period, that is, the above step S401, includes:
[0072] S501: Perform a residual analysis on the historical operation parameters and the predicted operation parameters within the historical time period to obtain the residual value.
[0073] Combining the above content, the historical operating parameters can have multiple data points, and the predicted operating parameters also correspond to multiple data points. At this time, residual analysis can be performed on each pair of corresponding data points in the historical operating parameters and the predicted operating parameters, and then multiple corresponding residual values can be obtained.
[0074] The step of determining the abnormal probability of the historical operating parameters according to the degree of differentiation, that is, the above step S402, includes:
[0075] S502: Determine the abnormal probability of the historical operating parameters according to the residual value; among them, there is a corresponding relationship between the residual value and the abnormal probability.
[0076] The residual value actually reflects the degree of differentiation. The corresponding relationship between the residual value and the abnormal probability is established in advance, and then the corresponding abnormal probability can be determined according to the residual value and the corresponding relationship. Combining the above content, when there are multiple residual values, the multiple residual values can be analyzed to obtain a final residual value, and then the abnormal probability can be determined according to the final residual value.
[0077] Figure 6 It is a schematic flowchart of another embodiment of the robot fault monitoring method provided by the present application.
[0078] Combining Figure 6 , in some specific embodiments, the step of establishing the corresponding relationship between the abnormal parameter and the preset fault includes:
[0079] S601: If an alarm message is detected within the historical period and the alarm message includes a preset fault, then regard the preset fault as the first preset fault, and establish the corresponding relationship between the abnormal parameter and the first preset fault.
[0080] When it is determined that the historical operating parameter is an abnormal parameter, that is, the historical operating parameter in the historical period is abnormal. Generally, there will be an alarm message of the robot corresponding to the historical period to reflect the abnormal operation of the robot through the alarm message.
[0081] The preset fault is a relatively specific fault type. If the alarm message includes a preset fault description, it means that the specific fault corresponding to the historical period is reflected in the alarm message. If the alarm message does not include a specific fault type, it means that the alarm message within the historical period may be a relatively general alarm. At this time, regard the preset fault in the alarm message as the first preset fault and establish the corresponding relationship with the abnormal parameter.
[0082] S602: If alarm information is detected within a historical period and the alarm information does not include a preset fault, then determine the preset fault corresponding to the abnormal parameter based on the characteristic information of the abnormal parameter and use it as the second preset fault, and establish a corresponding relationship between the abnormal parameter and the second preset fault.
[0083] Combined with the above content, although there is alarm information in the historical period, the alarm information does not include a preset fault. At this time, the alarm information in the historical period is relatively general. Such alarm information is not convenient for the staff to troubleshoot faults and is unqualified alarm information.
[0084] At this time, we need to determine the preset fault of the robot through the characteristic information of the abnormal parameter. The characteristics of the abnormal parameter can be various characteristic values, which are not specifically limited here. After obtaining the characteristic information of the abnormal parameter, it can be compared with the characteristic information of the corresponding normal parameter, and then the difference between the characteristic information can be determined, and further the corresponding preset fault can be determined according to the difference.
[0085] After determining the fault corresponding to the abnormal parameter according to the characteristic information, use it as the second preset fault, and establish a corresponding relationship between the abnormal parameter and the second preset fault. When the similarity between the operating parameter and the abnormal parameter reaches the preset similarity, it is determined that the robot has the second preset fault, realizing accurate alarm of the robot.
[0086] S603: If no alarm information is detected within a historical period, then determine the preset hidden fault corresponding to the abnormal parameter based on the characteristic information of the abnormal parameter, and use the preset hidden fault as the third preset fault, and establish a corresponding relationship between the abnormal parameter and the third preset fault.
[0087] If the historical operating parameter in the historical period is an abnormal parameter, it means that the robot operates abnormally in the historical period, but no corresponding alarm information is generated. At this time, the robot is very likely to have a hidden fault. This kind of fault is not sufficient to generate alarm information, but the hidden fault may affect the operating state of the robot, and the hidden fault is very likely to develop into a larger obvious fault.
[0088] At this time, this kind of preset hidden fault also needs to be warned. Therefore, we use the preset hidden fault as the third preset fault and establish a corresponding relationship between the abnormal parameter and the third preset fault. When the similarity between the operating parameter and the abnormal parameter reaches the preset similarity, it is determined that the robot has the third preset fault, realizing the alarm of the robot.
[0089] In some specific embodiments, if alarm information is monitored within a historical period and the alarm information does not include a preset fault, then the step of determining the preset fault corresponding to the abnormal parameter based on the characteristic information of the abnormal parameter and using it as the second preset fault, and establishing the corresponding relationship between the abnormal parameter and the second preset fault, that is, the above step S602, includes:
[0090] If no alarm information is monitored within the historical period, and the parameter type of at least one group of abnormal type parameters in the abnormal parameters is a position parameter type, then determine the structural looseness fault corresponding to the abnormal parameter, and establish the corresponding relationship between the abnormal parameter and the structural looseness fault; wherein, the abnormal parameters include multiple types of parameters, and at least one type of parameter is an abnormal type parameter.
[0091] Specifically, since there are multiple types of robot operation parameters, and there are also multiple types of parameters in the historical operation parameters, that is, the abnormal parameters also have multiple types of parameters, such as torque type parameters, current type parameters, etc. Among the abnormal parameters, one or more types of parameters can be abnormal type parameters. Among them, when there are multiple types of parameters in the historical operation parameters, the abnormal probabilities of each type of parameter can be obtained respectively according to the method of the above embodiment, and then when the abnormal probability is greater than the preset probability, determine that this type of parameter is an abnormal type parameter. As long as one type of parameter in the historical operation parameters is an abnormal type parameter, it is considered that the historical operation parameters are abnormal parameters.
[0092] At this time, as long as there is a group of abnormal type data in the abnormal parameters that is of the position parameter type, determine the structural looseness fault corresponding to the abnormal parameter, and establish the corresponding relationship between the abnormal parameter and the structural looseness fault. Among them, the position parameter type can be types such as axis angle, TCP, command position, feedback position, etc.
[0093] It should be understood that in the prior art, the faults of the robot are not determined by the operation parameters of the position parameter type, so it is difficult to detect the structural looseness fault of the robot. And in this embodiment, the structural looseness fault is determined through the abnormality of the position type parameter, which can better identify the structural looseness fault and achieve early warning.
[0094] Figure 7 It is a schematic flowchart of another embodiment of the robot fault monitoring method provided by the present application.
[0095] Combined with Figure 7 In some specific embodiments, this method further includes:
[0096] S701: Obtain the total number of times the preset fault occurs for the same robot within the preset period.
[0097] The preset time period can be a relatively long time period, for example, it can be one week, one month, etc. The purpose of obtaining the total number of preset faults that occur to the same robot within the preset time period is to understand the frequency of faults that occur to the same robot within a relatively long time period.
[0098] S702: If the total number reaches the preset number, the position information of the robot and the fault information within the preset time period are sent to the user terminal.
[0099] The total number can be large. If the total number is greater than the preset number, it means that the number of abnormalities that occur to the robot within the preset time period is large, and the frequency of faults that occur to the robot is high. At this time, we need to remind the staff to pay attention to this robot, that is, the position information of the robot and the fault information within the preset time period are sent to the user terminal, so that the staff can pay key attention to it.
[0100] The second aspect of this application provides an electronic device, including: a processor; a memory for storing a computer program, and when the computer program is executed by the processor, it implements the robot fault monitoring method in any of the above embodiments.
[0101] Figure 8 It is a schematic structural framework diagram of an embodiment of the electronic device 500 provided by this application.
[0102] In some specific embodiments, the electronic device 500 includes a central processing unit (CPU) 501 and a read-only memory (ROM) 502. The central processing unit 501 is the processor, and the read-only memory (ROM) 502 is the memory. The central processing unit 501 can execute various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 into the random access memory (RAM) 503, for example, execute the method in the above embodiment. In the RAM 503, various programs and data required for system operation are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other through a bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.
[0103] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as required. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is installed on the drive 510 as required so that a computer program read therefrom is installed into the storage section 508 as required.
[0104] Specifically, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 509, and / or installed from the removable medium 511. When the computer program is executed by a central processing unit (CPU) 501, various functions defined in the system of the present application are executed.
[0105] A third aspect of the present application provides a computer-readable storage medium 40, Figure 9 which is a schematic structural framework diagram of an embodiment of the computer-readable storage medium 40 provided by the present application.
[0106] A computer program 41 is stored on the computer-readable storage medium 40, and when the computer program 41 is executed by a processor, it implements the robot fault monitoring method in any of the above embodiments.
[0107] It should be noted that the computer-readable medium 40 shown in the embodiments of the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0108] In summary, based on the robot fault monitoring method, electronic device, and computer-readable storage medium provided by the present application, the method includes: obtaining historical operation parameters of a robot during a historical period; where the end time of the historical period is the current time, and the duration of the historical period is less than a preset duration; processing the historical operation parameters to obtain the abnormal probability of the historical operation parameters, and determining that the historical operation parameters are abnormal parameters when the abnormal probability is greater than a preset probability, and establishing a correspondence between the abnormal parameters and a preset fault; detecting that the similarity between the operation parameters during the robot operation and the abnormal parameters reaches a preset similarity, then determining that the robot has the preset fault corresponding to the abnormal parameters. Therefore, by establishing a correspondence between the abnormal parameters and the preset fault, the abnormal parameters can be mapped to specific faults, which can specifically reflect the faults of the robot. By comparing the operation parameters with the abnormal parameters to determine whether there is a preset fault, various types of parameters can be well utilized, making the early warning more accurate.
[0109] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation of the present application. Those of ordinary skill in the art can easily make corresponding adaptations or modifications according to the main concept and spirit of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope required by the claims.
Claims
1. A robot fault monitoring method, characterized in that: include: Obtaining historical operating parameters of a historical period during the operation of the robot; wherein the end time of the historical period is the current time, and the duration of the historical period is less than a preset duration; Processing the historical operating parameters to obtain an abnormal probability of the historical operating parameters, and determining that the historical operating parameters are abnormal parameters when the abnormal probability is greater than a preset probability, and establishing a corresponding relationship between the abnormal parameters and a preset fault; When it is detected that the similarity between the operating parameters during the operation of the robot and the abnormal parameters reaches a preset similarity, it is determined that the robot has the preset fault corresponding to the abnormal parameters.
2. The fault monitoring method according to claim 1, characterized in that: The step of processing the historical operating parameters to obtain the abnormal probability of the historical operating parameters includes: Establishing a historical characteristic curve corresponding to the historical operating parameter based on the historical operating parameter; Comparing the historical characteristic curve with a standard characteristic curve to obtain the similarity between the historical characteristic curve and the standard characteristic curve; wherein the standard characteristic curve is established based on historical normal operating parameters; The abnormal probability of the historical operating parameter is obtained according to the similarity; wherein there is a preset corresponding relationship between the similarity and the abnormal probability.
3. The robot fault monitoring method according to claim 2, characterized in that: The step of comparing the historical characteristic curve with the standard characteristic curve to obtain the similarity between the historical characteristic curve and the standard characteristic curve includes: Obtaining a first similarity between a first characteristic value of the historical characteristic curve and a first standard characteristic value of the standard characteristic curve, and obtaining a second similarity between a second characteristic value of the historical characteristic curve and a second standard characteristic value of the standard characteristic curve; The step of obtaining the abnormal probability of the historical operating parameters according to the similarity includes: If the first similarity does not satisfy the first standard similarity, and / or the second similarity does not satisfy the second standard similarity, the abnormal probability of the historical operating parameter is determined according to the degree of difference between the first similarity and the first standard similarity and between the second similarity and the second standard similarity.
4. The robot fault monitoring method according to claim 1, characterized in that: The step of processing the historical operating parameters to obtain the abnormal probability of the historical operating parameters includes: Performing a differentiation analysis on the historical operating parameters and the predicted operating parameters corresponding to the historical period to obtain a degree of differentiation; wherein the predicted operating parameters are predicted based on historical normal parameters before the historical period; The abnormal probability of the historical operating parameter is determined according to the differentiation degree; wherein there is a corresponding relationship between the differentiation degree and the abnormal probability.
5. The robot fault monitoring method according to claim 4, characterized in that: The step of performing a differentiation analysis on the historical operating parameters and the predicted operating parameters corresponding to the historical period to obtain a degree of differentiation includes: Performing residual analysis on the historical operating parameters and the predicted operating parameters within the historical period to obtain residual values; The step of determining the abnormal probability of the historical operating parameter according to the degree of differentiation includes: The abnormal probability of the historical operating parameter is determined according to the residual value; wherein there is a corresponding relationship between the residual value and the abnormal probability.
6. The robot fault monitoring method according to claim 1, characterized in that: The step of establishing a corresponding relationship between the abnormal parameters and the preset faults comprises: If alarm information is monitored within the historical period and the alarm information includes a preset fault, the preset fault is used as a first preset fault, and a corresponding relationship between the abnormal parameter and the first preset fault is established; If alarm information is monitored within the historical period and the alarm information does not include a preset fault, determining the preset fault corresponding to the abnormal parameter based on the characteristic information of the abnormal parameter and taking it as a second preset fault, and establishing a corresponding relationship between the abnormal parameter and the second preset fault; If no alarm information is detected during the historical period, a preset hidden fault corresponding to the abnormal parameter is determined based on the characteristic information of the abnormal parameter, and the preset hidden fault is used as a third preset fault, and a corresponding relationship between the abnormal parameter and the third preset fault is established.
7. The robot fault monitoring method according to claim 6, characterized in that: If alarm information is monitored within the historical period and the alarm information does not include a preset fault, the steps of determining a preset fault corresponding to the abnormal parameter based on the characteristic information of the abnormal parameter and using it as a second preset fault, and establishing a corresponding relationship between the abnormal parameter and the second preset fault include: If no alarm information is detected during the historical period, and the parameter type of at least one group of abnormal parameters among the abnormal parameters is a position parameter type, it is determined that the abnormal parameters correspond to a structural loosening fault, and a corresponding relationship between the abnormal parameters and the structural loosening fault is established; wherein, the abnormal parameters include multiple types of parameters, and at least one type of parameters is an abnormal type parameter.
8. The robot fault monitoring method according to claim 1, characterized in that: The method further comprises: Get the total number of preset faults that occur on the same robot within a preset period of time; If the total number of times reaches the preset number of times, the position information of the robot and the fault information within the preset time period are sent to the user terminal.
9. An electronic device, characterized in that: include: processor; A memory for storing a computer program, wherein the computer program, when executed by the processor, implements the robot fault monitoring method according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the robot fault monitoring method according to any one of claims 1 to 8 is implemented.