Robot control method and device, electronic equipment and storage medium
By detecting and correcting the operating parameters of the robot, the robot automatically solves the problem of long repair time for robot failures and improving production efficiency.
Patent Information
- Application Number
- CN202510127046.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-28
- Publication Date
- 2025-03-25
AI Technical Summary
The robot fails and repairs on the production line for a long time, which affects production efficiency and product quality.
By obtaining the historical running parameters during the robot running, processing these parameters to determine the probability of exception, correcting the exception class parameters in the exception parameters to obtain the target parameters, and controlling the robot to work with the target parameters.
It improves the robot's automatic resolution ability when a fault occurs, reduces fault repair time, and improves production efficiency.
Smart Images
Figure CN119681904A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of robot technology, and in particular to a robot control method, device, electronic device and storage medium. Background Art
[0002] With the development and progress of technology, robots have almost completely replaced manual welding in the automobile manufacturing process. For example, the welding workshop has achieved 100% automation of various processes and key procedures, which is a key link in the automobile manufacturing process.
[0003] In this production environment, the stability of robots on the production line is crucial to production efficiency and product quality control. At present, after a robot fails, the repair time is long, which affects production efficiency. Summary of the invention
[0004] In view of the above problems, the present application provides a robot control method, device, electronic device and storage medium. By correcting the abnormal parameters in the abnormal parameters, more accurate target parameters can be obtained. When the robot works with the target parameters, it can automatically solve some faults, thereby improving production efficiency.
[0005] The first aspect of the present application provides a robot control method, comprising: obtaining historical operating parameters of a historical period during the operation of the robot; wherein the end moment of the historical period is the current moment, 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 that the historical operating parameters are abnormal parameters when the abnormal probability is greater than the preset probability; wherein the abnormal parameters include multiple types of parameters, and at least one type of parameter is an abnormal type parameter; correcting the abnormal type parameters belonging to the preset parameter type among the abnormal parameters to obtain target parameters corresponding to the abnormal parameters, and controlling the robot to work with the target parameters.
[0006] In some specific embodiments, the step of correcting abnormal class parameters belonging to preset parameter types among the abnormal parameters to obtain target parameters corresponding to the abnormal parameters includes: determining abnormal data values of the abnormal class parameters belonging to preset parameter types among the abnormal parameters, and determining multiple groups of normal data values corresponding to the abnormal data values based on historical data before the historical period; determining fitting data values based on the multiple groups of normal data values, and replacing the abnormal data values in the abnormal class parameters with the fitting data values to obtain the target parameters corresponding to the abnormal parameters.
[0007] In some specific embodiments, the step of determining fitting data values based on multiple groups of normal data values, and replacing abnormal data values in abnormal class parameters with fitting data values to obtain target parameters corresponding to the abnormal parameters includes: removing a preset number of groups of maximum normal data values and a preset number of groups of minimum normal data values from the multiple groups of normal data values to obtain multiple corrected groups of normal data values, and obtaining an average data value of the corrected multiple groups of normal data values; replacing abnormal data values in abnormal class parameters with the average data value to obtain target parameters corresponding to the abnormal parameters.
[0008] In some specific embodiments, the steps of processing historical operating parameters to obtain abnormal probabilities 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, include: processing each type of parameter in the historical operating parameters separately to obtain the abnormal probability corresponding to each type of parameter, and comparing the abnormal probability of each type of parameter with the corresponding preset probability; if the abnormal probability of any type of parameter is greater than the corresponding preset probability, the parameters of the corresponding category are used as abnormal class parameters, and the historical operating parameters are used as abnormal parameters.
[0009] In some specific embodiments, after the step of processing historical operating parameters to obtain the abnormal probability of the historical operating parameters, and determining that the historical operating parameters are abnormal parameters when the abnormal probability is greater than the preset probability, it includes: if the abnormal parameters contain abnormal parameters of a non-preset parameter type, and there is no alarm information in the historical period, then determining the warning level according to the probability value of the abnormal probability: wherein different warning levels correspond to non-overlapping probability value ranges; and generating corresponding warning information based on the warning level for warning.
[0010] In some specific embodiments, the step of processing historical operating parameters to obtain abnormal probability of historical operating parameters includes: outputting standard parameters corresponding to the historical time period through a preset statistical model; wherein the preset statistical model is obtained by training the historical parameters before the historical time period; comparing the standard parameters with the historical operating parameters to obtain the similarity between the two, and determining the abnormal probability of the historical operating parameters based on the similarity; wherein there is a preset corresponding relationship between the abnormal probability and the similarity.
[0011] In some specific embodiments, the step of processing historical operating parameters to obtain abnormal probability of historical operating parameters includes: outputting prediction parameters corresponding to the historical time period through a preset deep learning model; wherein the preset deep learning model is obtained by training the historical parameters before the historical time period; comparing the prediction parameters with the historical operating parameters to obtain the degree of differentiation between the two, and determining the abnormal probability of the historical operating parameters according to the degree of differentiation; wherein there is a corresponding relationship between the degree of differentiation and the abnormal probability.
[0012] A second aspect of the present application provides a control device for a robot, comprising: a parameter acquisition module, used to acquire historical operating parameters of a historical period during the operation of the robot; wherein the end moment of the historical period is the current moment, and the duration of the historical period is less than a preset duration; a parameter processing module, used to process the historical operating parameters to obtain the abnormal probability of the historical operating parameters, and determine that the historical operating parameters are abnormal parameters when the abnormal probability is greater than the preset probability; wherein the abnormal parameters include multiple types of parameters, and at least one type of parameter is an abnormal type parameter; a control module, used to correct the abnormal type parameters belonging to the preset parameter type among the abnormal parameters to obtain the target parameters corresponding to the abnormal parameters, and control the robot to work with the target parameters.
[0013] A third aspect of the present application provides an electronic device, comprising: a processor; and a memory for storing a computer program, wherein when the computer program is executed by the processor, any of the above-mentioned robot control methods is implemented.
[0014] A fourth aspect of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, a robot control method as described above is implemented.
[0015] The present application has at least the following beneficial technical effects: Based on the control method, device, electronic device and storage medium of the robot provided by the present application, the method includes: obtaining the historical operation parameters of the historical time period during the operation of the robot; wherein the end moment of the historical time period is the current moment, and the duration of the historical time period is less than the 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 the preset probability; wherein the abnormal parameters include multiple types of parameters, and at least one type of parameter is an abnormal type parameter; correcting the abnormal type parameters in the abnormal parameters that belong to the preset parameter type to obtain the target parameters corresponding to the abnormal parameters, and controlling the robot to work with the target parameters. Therefore, by correcting the abnormal type parameters in the abnormal parameters, a more accurate target parameter can be obtained, and when the robot works with the target parameters, some faults can be automatically resolved, thereby improving production efficiency.
[0016] The above description is only an overview of the technical solution of the embodiment of the present application. In order to more clearly understand the technical means of the embodiment of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present application. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:
[0018] Figure 1 It is a flowchart of an embodiment of a robot control method provided by the present application;
[0019] Figure 2 is a flow chart of another embodiment of the robot control method provided by the present application;
[0020] Figure 3 is a flow chart of another embodiment of the robot control method provided by the present application;
[0021] Figure 4 is a flow chart of another embodiment of the robot control method provided by the present application;
[0022] Figure 5 is a flow chart of another embodiment of the robot control method provided by the present application;
[0023] Figure 6 is a flow chart of another embodiment of the robot control method provided by the present application;
[0024] Figure 7 is a flow chart of another embodiment of the robot control method provided by the present application;
[0025] Figure 8 is a structural block diagram of an embodiment of a robot control device provided by the present application;
[0026] Fig. 9 It is a schematic diagram of the structural framework of an embodiment of the electronic device provided by the present application;
[0027] Fig.10 It is a schematic diagram of the structural framework of an embodiment of the computer-readable storage medium provided by the present application. DETAILED DESCRIPTION
[0028] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.
[0029] If there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features limited to "first" and "second" may explicitly or implicitly include at least one of the features. In addition, if the meaning of "and / or" appearing in the full text is to include three parallel schemes, taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.
[0030] In a first aspect, the present application provides a robot control method, which can be directly applied to the robot, and the robot control device can be used as an execution subject. This method can also be directly applied to a monitoring system connected to the robot, and the monitoring system can be used as an execution subject, and the monitoring system can realize data processing and robot control.
[0031] It should be understood that the robot described in this application may be a robot system, and the robot system may include a robot body, external devices of the robot, and a control device of the robot. Based on this method, some operating failures of the robot can be automatically solved, thereby improving production efficiency. Among them, the robot may be a relevant robot in a welding workshop of vehicle manufacturing.
[0032] Figure 1 1 is a flow chart of an embodiment of the robot control method provided by the present application. Figure 1 , the method comprises the following steps:
[0033] S101: Obtain 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.
[0034] Among them, the operating parameters of the robot during operation can be recorded by the robot itself or by other devices. In combination with the above content, the recorded data can be transmitted to the robot's control device or to the robot's monitoring system, so that the operating parameters can be received and processed. The preset duration of the historical period can be a shorter duration, so that the parameter status of the robot can be reflected in a timely manner.
[0035] Combined with the above content, the robot body is the core part of the robot system, the robot's external equipment is set on the robot body to achieve a certain function, and the control device is used to control the robot body and external equipment. Among them, the robot body can include shafts, motors, reducers, encoders, etc.; external equipment can include welding tongs, welding machines, grippers, pipeline packages, gun changers, fixtures, water and gas modules, etc.; control equipment can include network communication connection devices, power modules, drive devices, control modules, IO signal circuits, etc.
[0036] Accordingly, the operating parameters of the robot during operation may include parameters of the main body, peripheral parameters, and control parameters. These parameters can often reflect the working status of the corresponding equipment and the working status of the entire robot.
[0037] S102: Process the historical operating parameters to obtain the abnormal probability of the historical operating parameters, and determine that the historical operating parameters are abnormal parameters when the abnormal probability is greater than a preset probability; wherein the abnormal parameters include multiple types of parameters, and at least one type of parameter is an abnormal type parameter.
[0038] It should be understood that the historical operating parameters can reflect the working status of the robot in the historical period. If the historical operating parameters are abnormal, then the robot is likely to work abnormally in the historical period.
[0039] 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. Generally speaking, as long as the operating parameter fluctuation is small, the robot can be regarded as being in a normal working state. Moreover, even if the operating parameter fluctuation is large, the operating parameter is not necessarily abnormal, and the robot is not necessarily in an abnormal working state. Therefore, after this embodiment processes the historical operating parameters, 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 the abnormal probability of the robot's operation to a certain extent.
[0040] Among them, the preset probability is pre-set and can be set 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 means that there is a high possibility that there is a problem with the historical operating parameters. 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 likely to have a fault in 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 in the historical period and the preset faults.
[0041] It should be understood that since there are multiple operating parameters during the operation of the robot, there are also multiple types of parameters in the historical operating parameters, such as torque parameters, current parameters, etc. When there are multiple types of parameters in the historical operating parameters, each type of parameter can be processed separately, and whether the historical operating parameter is an abnormal parameter can be obtained based on the results of the separate processing.
[0042] S103: Correcting abnormal parameters belonging to preset parameter types among the abnormal parameters to obtain target parameters corresponding to the abnormal parameters, and controlling the robot to work with the target parameters.
[0043] Combined with the above content, there may be multiple types of parameters in the abnormal parameters that are abnormal parameters, that is, there are multiple types of abnormal parameters. Multiple types of abnormal parameters correspond to different parameter types. If the parameter type of a certain type of abnormal parameter is a preset parameter type, then the abnormal parameter is corrected, that is, the abnormal parameter is corrected to a normal parameter. Among them, other types of parameters in the abnormal parameters can remain unchanged, and the abnormal parameters before correction are replaced by the corrected abnormal parameters to obtain the target parameters corresponding to the abnormal parameters. At this time, since the abnormal parameters belonging to the preset parameter type in the target parameters are corrected, even if some of the abnormal parameters are still abnormal, the accuracy will be improved, and the probability of abnormality when the robot works with the target parameters will be reduced.
[0044] It should be understood that when certain types of operating parameters of the robot are abnormal, they can be automatically corrected by control instructions, but some types of operating parameter abnormalities cannot be automatically corrected by control instructions, but require external intervention to correct. In this embodiment, the type of parameter that can be automatically corrected by control instructions can be used as a preset parameter type. For example, welding current can be used as a preset parameter type, and when the welding current parameter is abnormal, the welding current parameter can be automatically corrected by a correction instruction.
[0045] In summary, by correcting the abnormal parameters among the abnormal parameters, more accurate target parameters can be obtained. When the robot works with the target parameters, it can automatically solve some faults, thereby improving production efficiency.
[0046] Figure 2 It is a flow chart of another embodiment of the robot control method provided in the present application.
[0047] Combination Figure 2 In some specific embodiments, the step of correcting the abnormal class parameters belonging to the preset parameter type in the abnormal parameters to obtain the target parameters corresponding to the abnormal parameters includes:
[0048] S201: Determine abnormal data values of abnormal class parameters belonging to a preset parameter type among abnormal parameters, and determine multiple groups of normal data values corresponding to the abnormal data values based on historical data before a historical period.
[0049] The abnormal data value of the abnormal parameter belonging to the preset parameter type may be the abnormal data value of the abnormal parameter when the robot executes a specific instruction and at a specific execution stage. For example, if the abnormal parameter is a welding current parameter, the abnormal data value may be the welding current value at a specific welding stage of a specific welding instruction.
[0050] The robot generally has a large amount of historical data before the historical period, and multiple groups of normal data values and abnormal data values can be obtained through these historical data. Among them, the abnormal data values and the normal data values are data values under the same instruction and the same execution stage. The number of groups of normal data values can be greater than the preset number, for example, the preset number of groups can be 50 groups.
[0051] S202: Determine fitting data values according to multiple groups of normal data values, and replace abnormal data values in abnormal parameters with the fitting data values to obtain target parameters corresponding to the abnormal parameters.
[0052] Among them, the fitting data values corresponding to the multiple groups of normal data values are all the groups of normal data values obtained in the above steps. The fitting data values determined by the normal data values of all groups can better represent the normal data values of all groups. The method of determining the fitting data values by multiple groups of data is not specifically limited in this embodiment, and can be a related method of data fitting in the prior art.
[0053] Therefore, the determined fitting data values can better represent the normal data values. After replacing the abnormal data values with the fitting data values, the abnormal parameters can be restored to normal parameters.
[0054] Figure 3 It is a flow chart of another embodiment of the robot control method provided by the present application.
[0055] Combination Figure 3 In some specific embodiments, the step of determining fitting data values according to multiple groups of normal data values, and replacing abnormal data values in abnormal class parameters with fitting data values to obtain target parameters corresponding to abnormal parameters includes:
[0056] S301: removing a preset number of groups of maximum normal data values and a preset number of groups of minimum normal data values from a plurality of groups of normal data values to obtain a plurality of corrected groups of normal data values, and obtaining an average data value of the plurality of corrected groups of normal data values.
[0057] It should be understood that multiple groups of normal data values are generally not consistent, but rather uneven, but the data values are within a certain range. In this embodiment, the first preset number and the last preset number of normal data values are removed from all normal data values sorted from large to small, and then the average data value of all data values after removing these data values is obtained.
[0058] S302: replacing the abnormal data value in the abnormal class parameter by the average data value to obtain the target parameter corresponding to the abnormal parameter.
[0059] It should be understood that after removing the normal data values with larger and smaller data values, the average data value obtained is more consistent with the normal standard data value. At this time, by replacing the abnormal data values in the abnormal class parameters with the average data value, the target parameters obtained will be more accurate.
[0060] Figure 4 It is a flow chart of another embodiment of the robot control method provided by the present application.
[0061] Combination Figure 4 In some specific embodiments, the step of processing the historical operating parameters to obtain the abnormal probability of the historical operating parameters, and determining that the historical operating parameters are abnormal parameters when the abnormal probability is greater than the preset probability, includes:
[0062] S401: Processing each type of parameter in the historical operating parameters respectively to obtain the abnormal probability corresponding to each type of parameter, and comparing the abnormal probability of each type of parameter with the corresponding preset probability.
[0063] This embodiment defines how to determine whether a historical operating parameter is an abnormal parameter when the historical operating parameter has multiple types of parameters.
[0064] Among them, each type of parameter can be set with a preset probability. After the abnormal probability corresponding to a certain type of parameter is determined, the abnormal probability can be compared with the preset probability corresponding to the type of parameter.
[0065] S402: If the abnormal probability of any type of parameter is greater than the corresponding preset probability, the parameters of the corresponding category are taken as abnormal class parameters, and the historical operation parameters are taken as abnormal parameters.
[0066] In this embodiment, as long as the abnormal probability of a certain type of parameter is greater than the corresponding preset probability, the corresponding type of parameter is used as an abnormal type parameter. In addition, as long as one type of parameter is an abnormal type parameter, the historical operating parameters are used as abnormal parameters. However, in other embodiments, the historical operating parameters can be used as abnormal parameters only when multiple types of parameters are abnormal type parameters, and no specific limitation is made here.
[0067] Figure 5It is a flow chart of another embodiment of the robot control method provided by the present application.
[0068] Combination Figure 5 In some specific embodiments, after the step of processing the historical operating parameters to obtain the abnormal probability of the historical operating parameters, and determining that the historical operating parameters are abnormal parameters when the abnormal probability is greater than the preset probability, the method includes:
[0069] S501: If the abnormal parameters include abnormal parameters of non-preset parameter types and there is no alarm information in the historical period, the warning level is determined according to the probability value of the abnormal probability: wherein different warning levels correspond to non-overlapping probability value ranges.
[0070] It should be understood that since abnormal parameters of non-preset parameter types cannot be automatically corrected to normal parameters through correction instructions, if there are abnormal parameters of non-preset parameter types in the abnormal parameters, the abnormal parameters cannot be corrected to normal parameters. At this time, there may still be abnormal parameters in the subsequent periods of the historical period, which may affect the working status of the robot. If there is no alarm information in the historical period, the user cannot be informed and cannot perform targeted processing.
[0071] At this time, in order to let users know that the robot may be abnormal, early warning information will be generated in the subsequent process. This step first determines the early warning level according to the probability value of the abnormal probability, and the higher the average probability value of the probability value range corresponding to the abnormal probability value, the higher the corresponding early warning level, in order to meet actual needs.
[0072] S502: Generate corresponding warning information based on the warning level to issue a warning.
[0073] When the warning level is high, the corresponding warning information can achieve a more significant reminder effect. For example, at a low warning level, a text warning can be issued, and at a high warning level, a text plus voice warning can be issued.
[0074] Figure 6 It is a flow chart of another embodiment of the robot control method provided by the present application.
[0075] Combination Figure 6 In some specific embodiments, the step of processing the historical operating parameters to obtain the abnormal probability of the historical operating parameters includes:
[0076] S601: Outputting standard parameters corresponding to the historical period through a preset statistical model; wherein the preset statistical model is obtained by training the historical parameters before the historical period.
[0077] The preset statistical mode may be an ARIMA model, but is not limited thereto. At this time, the ARIMA model may be trained using normal historical parameters before the historical period, so that the trained ARIMA model can output standard parameters corresponding to the history.
[0078] It should be understood that the standard parameters of the historical period, that is, the theoretical standard normal parameters, can be used as reference parameters in the process of judging whether the actual parameters are normal parameters.
[0079] S602: Compare the standard parameters with the historical operating parameters to obtain the similarity between the two, and determine the abnormal probability of the historical operating parameters according to the similarity; wherein there is a preset corresponding relationship between the abnormal probability and the similarity.
[0080] When comparing the standard parameters with the historical operating parameters, multiple feature values of the historical operating parameters may be compared with multiple feature values corresponding to the standard parameters, and the similarity between the standard parameters and the historical operating parameters may be determined by the similarity of the feature values. Of course, the method of obtaining the similarity is not limited to this.
[0081] Among them, when the similarity is higher, the corresponding abnormal probability can be smaller to comply with the actual application rules.
[0082] Figure 7 It is a flow chart of another embodiment of the robot control method provided by the present application.
[0083] Combination Figure 7 In some specific embodiments, the step of processing the historical operating parameters to obtain the abnormal probability of the historical operating parameters includes:
[0084] S701: Output prediction parameters corresponding to the historical period through a preset deep learning model; wherein the preset deep learning model is obtained by training the historical parameters before the historical period.
[0085] The preset deep learning model may be an LSTM model, but is not limited thereto. At this time, the LSTM model may be trained using normal historical parameters before the historical period, so that the trained LSTM model can output prediction parameters corresponding to the historical period.
[0086] Similarly, the forecast parameters corresponding to the historical period are relatively standard normal parameters and can be used as reference parameters in the process of judging whether the actual parameters are normal parameters.
[0087] S702: Compare the predicted parameters with the historical operating parameters to obtain the degree of differentiation between the two, and determine the abnormal probability of the historical operating parameters according to the degree of differentiation; wherein there is a corresponding relationship between the degree of differentiation and the abnormal probability.
[0088] The degree of differentiation between historical operating parameters and predicted parameters will reflect the degree of differentiation between historical operating parameters and normal parameters. Moreover, the higher the degree of differentiation, the greater the difference between historical operating parameters and normal parameters, and the greater the probability of abnormality of historical operating parameters.
[0089] Therefore, there is a corresponding relationship between the degree of differentiation and the probability of abnormality. The higher the degree of differentiation, the greater the corresponding probability of abnormality.
[0090] A second aspect of the present application provides a robot control device 20, Figure 8 It is a structural block diagram of an embodiment of the robot control device 20 provided in the present application.
[0091] Combination Figure 8 , the robot control device 20 includes a parameter acquisition module 21, a parameter processing module 22 and a control module 23. The parameter acquisition module 21 is used to obtain the historical operation parameters of the 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 the preset duration. The parameter processing module 22 is used to process the historical operation parameters to obtain the abnormal probability of the historical operation parameters, and determine that the historical operation parameters are abnormal parameters when the abnormal probability is greater than the preset probability; wherein the abnormal parameters include multiple types of parameters, and at least one type of parameter is an abnormal parameter. The control module 23 is used to correct the abnormal parameters belonging to the preset parameter type in the abnormal parameters to obtain the target parameters corresponding to the abnormal parameters, and control the robot to work with the target parameters.
[0092] A third aspect of the present application provides an electronic device, comprising: a processor; and a memory for storing a computer program, wherein when the computer program is executed by the processor, the robot control method in any of the above embodiments is implemented.
[0093] Fig. 9 It is a schematic diagram of the structural framework of an embodiment of the electronic device 500 provided in the present application.
[0094] Combination Fig. 9In some specific embodiments, the electronic device 500 includes a central processing unit (CPU) 501 and a read-only memory (ROM) 502, wherein the central processing unit 501 is a processor and the read-only memory (ROM) 502 is a memory. The central processing unit 501 can perform 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 to the random access memory (RAM) 503, such as executing the method in the above embodiment. In the RAM 503, various programs and data required for system operation are also stored. The CPU 501, the ROM 502 and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.
[0095] 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 needed. 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 needed so that a computer program read therefrom is installed into the storage section 508 as needed.
[0096] In particular, 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, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 509, and / or installed from a 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.
[0097] A fourth aspect of the present application provides a computer-readable storage medium 40, Fig.10It is a schematic diagram of the structural framework of an embodiment of the computer-readable storage medium 40 provided in the present application.
[0098] Combination Fig.10 A computer program 41 is stored on the computer-readable storage medium 40. When the computer program 41 is executed by the processor, the robot control method in any of the above embodiments is implemented.
[0099] It should be noted that the computer-readable medium 40 shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as a part of a carrier wave, wherein a computer-readable computer program is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0100] In summary, based on the control method, device, electronic device and storage medium of the robot provided by the present application, the method includes: obtaining the historical operation parameters of the historical time period during the operation of the robot; wherein the end moment of the historical time period is the current moment, and the duration of the historical time period is less than the 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 the preset probability; wherein the abnormal parameters include multiple types of parameters, and at least one type of parameter is an abnormal type parameter; correcting the abnormal type parameters belonging to the preset parameter type in the abnormal parameters to obtain the target parameters corresponding to the abnormal parameters, and controlling the robot to work with the target parameters. Therefore, by correcting the abnormal type parameters in the abnormal parameters, a more accurate target parameter can be obtained, and when the robot works with the target parameters, some faults can be automatically solved, thereby improving production efficiency.
[0101] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. A person skilled in the art can easily make corresponding changes or modifications based on the main concept and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.
Claims
1. A robot control 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 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; wherein the abnormal parameters include multiple types of parameters, and at least one type of parameter is an abnormal type parameter; The abnormal type parameters belonging to the preset parameter type among the abnormal parameters are corrected to obtain the target parameters corresponding to the abnormal parameters, and the robot is controlled to work with the target parameters.
2. The robot control method according to claim 1, characterized in that: The step of correcting the abnormal type parameters belonging to the preset parameter type among the abnormal parameters to obtain the target parameters corresponding to the abnormal parameters includes: Determine the abnormal data value of the abnormal class parameter belonging to the preset parameter type among the abnormal parameters, and determine multiple groups of normal data values corresponding to the abnormal data value according to the historical data before the historical period; A fitting data value is determined according to the multiple groups of normal data values, and the abnormal data value in the abnormal type parameter is replaced by the fitting data value to obtain a target parameter corresponding to the abnormal parameter.
3. The robot control method according to claim 2, characterized in that: The step of determining fitting data values according to the multiple groups of normal data values, and replacing the abnormal data values in the abnormal class parameters with the fitting data values to obtain target parameters corresponding to the abnormal parameters includes: Removing a preset number of groups of maximum normal data values and a preset number of groups of minimum normal data values from the multiple groups of normal data values to obtain a corrected multiple groups of normal data values, and obtaining an average data value of the corrected multiple groups of normal data values; The abnormal data value in the abnormal parameter is replaced by the average data value to obtain the target parameter corresponding to the abnormal parameter.
4. The robot control 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, and determining that the historical operating parameters are abnormal parameters when the abnormal probability is greater than a preset probability, comprises: Processing each type of parameter in the historical operating parameters respectively to obtain the abnormal probability corresponding to each type of parameter, and comparing the abnormal probability of each type of parameter with the corresponding preset probability; If the abnormal probability of any type of parameter is greater than the corresponding preset probability, the parameters of the corresponding category are taken as abnormal type parameters, and the historical operation parameters are taken as abnormal parameters.
5. The robot control method according to claim 1, characterized in that: After the step of processing the historical operating parameters to obtain the 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, the method further comprises: If the abnormal parameters include the abnormal type parameters that are not the preset parameter types, and there is no alarm information in the historical period, the warning level is determined according to the probability value of the abnormal probability: wherein different warning levels correspond to non-overlapping probability value ranges; Based on the warning level, corresponding warning information is generated to issue a warning.
6. The robot control 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: Outputting the standard parameters corresponding to the historical period through a preset statistical model; wherein the preset statistical model is obtained by training the historical parameters before the historical period; The standard parameters are compared with the historical operating parameters to obtain the similarity between the two, and the abnormal probability of the historical operating parameters is determined according to the similarity; wherein there is a preset corresponding relationship between the abnormal probability and the similarity.
7. The robot control 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: Outputting prediction parameters corresponding to the historical period through a preset deep learning model; wherein the preset deep learning model is obtained by training the historical parameters before the historical period; The predicted parameters are compared with the historical operating parameters to obtain the degree of differentiation between the two, and the abnormal probability of the historical operating parameters is determined according to the degree of differentiation; wherein there is a corresponding relationship between the degree of differentiation and the abnormal probability.
8. A robot control device, characterized in that: include: A parameter acquisition module, used to acquire 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; a parameter processing module, configured to process the historical operating parameters to obtain an abnormal probability of the historical operating parameters, and determine that the historical operating parameters are abnormal parameters when the abnormal probability is greater than a preset probability; wherein the abnormal parameters include multiple types of parameters, and at least one type of parameter is an abnormal type parameter; The control module is used to correct the abnormal parameters belonging to the preset parameter type among the abnormal parameters to obtain the target parameters corresponding to the abnormal parameters, and control the robot to work with the target parameters.
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 control method according to any one of claims 1 to 7.
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 control method according to any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Data center operation and maintenance robot control method based on large model
CN120928698A