CN-122008260-A - Control method and related device for industrial robot

Abstract

The embodiment of the application relates to the technical field of industrial control, and provides a control method and a related device of an industrial robot, wherein the method comprises the steps of determining application scene information according to the current transaction to be processed; determining operation precision information and operation configuration information according to the application scene information, determining reference operation parameter information according to the operation precision information and the operation configuration information, generating parameter correction information according to the target state information, correcting the reference operation parameter information by adopting the parameter correction information to obtain the target operation parameter information, controlling the industrial robot according to the target operation parameter information, generating corresponding target operation parameter information by combining the current transaction to be processed and the target state information of the industrial robot, and finally controlling by adopting the target operation parameter information, thereby improving the accuracy of determining the target operation parameter and further improving the accuracy of controlling the industrial robot.

Inventors

• Huang Zhuofei
• Tai Yunxin

Assignees

• 跨维(深圳)智能数字科技有限公司

Dates

Publication Date

20260512

Application Date

20260415

Claims (10)

1. 1. A method of controlling an industrial robot, the method comprising: Acquiring a current transaction to be processed of an industrial robot and acquiring target state information of the industrial robot; Determining application scene information according to the current transaction to be processed; Determining operation precision information and operation configuration information according to the application scene information; determining reference operation parameter information according to the operation precision information and the operation configuration information; Generating parameter correction information according to the target state information; Correcting the reference operation parameter information by adopting the parameter correction information to obtain the target operation parameter information; And controlling the industrial robot according to the target operation parameter information.
2. 2. The control method of an industrial robot according to claim 1, wherein acquiring target state information of the industrial robot comprises: extracting abnormal data in historical operation data of the industrial robot to obtain an abnormal data set; performing data equalization processing on the abnormal data in the abnormal data set to obtain a target data set; extracting features of the target data set to obtain a target feature vector; and predicting the state of the industrial robot according to the target feature vector and the real-time operation data of the industrial robot to obtain target state information.
3. 3. The method for controlling an industrial robot according to claim 2, wherein the performing data equalization processing on the abnormal data in the abnormal data set to obtain the target data set includes: denoising the abnormal data set to obtain a first data set; clustering the first data in the first data set to obtain M sub-data sets; determining the corresponding classification size of each sub-data set in the M sub-data sets to obtain a classification size information set; and carrying out data equalization processing on the M sub-data sets according to the classification size information in the classification size information set to obtain a target data set.
4. 4. The method for controlling an industrial robot according to claim 3, wherein performing data equalization processing on the M sub-data sets according to the classification size information in the classification size information set to obtain the target data set comprises: Determining a target test set corresponding to each sub-data set in the M sub-data sets to obtain M target test sets; Calculating the error rate corresponding to each target test set in the M target test sets to obtain M target error rate sets; calculating the average error rate of each sub-data set according to the target error rates in the M target error rate sets to obtain M average error rates; Determining the number of operation data to be synthesized for each sub-data set in M sub-data sets according to M average error rates and classification size information in the classification size information sets to obtain a first number set; And carrying out data synthesis on each sub-data set in the M sub-data sets according to the first quantity in the first quantity set to obtain a target data set.
5. 5. The method for controlling an industrial robot according to claim 4, wherein determining the target test set corresponding to each of the M sub-data sets, to obtain M target test sets, comprises: Selecting a preset number of operation data from each of the M sub-data sets as training sets of the corresponding sub-data sets to obtain M reference training sets; determining a test set corresponding to each reference training set in M reference training sets to obtain M reference test sets; And performing iterative linear classification training on each of the M reference test sets to obtain M target test sets.
6. 6. The method according to claim 5, wherein the performing feature extraction on the target data set to obtain a target feature vector includes: extracting time sequence characteristic information of a target data set to obtain a first characteristic vector; and carrying out associated feature extraction on the target data set according to the first feature vector to obtain a target feature vector.
7. 7. A control device for an industrial robot, the device comprising: The system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a current transaction to be processed of the industrial robot and acquiring target state information of the industrial robot; The system comprises a determining unit, a parameter correcting unit and a processing unit, wherein the determining unit is used for determining application scene information according to the current transaction to be processed, determining operation precision information and operation configuration information according to the application scene information, determining reference operation parameter information according to the operation precision information and the operation configuration information, generating parameter correcting information according to the target state information, and correcting the reference operation parameter information by adopting the parameter correcting information to obtain the target operation parameter information; and the control unit is used for controlling the industrial robot according to the target operation parameter information.
8. 8. The control device of an industrial robot according to claim 7, wherein in acquiring the target state information of the industrial robot, the acquisition unit is specifically configured to: extracting abnormal data in historical operation data of the industrial robot to obtain an abnormal data set; performing data equalization processing on the abnormal data in the abnormal data set to obtain a target data set; extracting features of the target data set to obtain a target feature vector; and predicting the state of the industrial robot according to the target feature vector and the real-time operation data of the industrial robot to obtain target state information.
9. 9. An industrial robot comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is adapted to store a computer program comprising program instructions, the processor being configured to execute the steps of the control method of an industrial robot according to any one of claims 1 to 6, and to invoke the program instructions.
10. 10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the steps of the control method of an industrial robot according to any one of claims 1 to 6.

Description

Control method and related device for industrial robot Technical Field The application relates to the technical field of industrial control, in particular to a control method and a related device of an industrial robot. Background As core equipment in the field of intelligent manufacturing, an industrial robot is usually required to manually configure corresponding operation parameters during operation, for example, on a configuration interface of a display, the operation parameters of the industrial robot are configured in a manual configuration mode, for example, identification precision during operation and the like, and due to manual processing, related transaction attributes and the like of the industrial robot during transaction processing cannot be accurately distinguished, so that accuracy during configuration of the operation parameters is low, and further accuracy during control of the industrial robot is low. Disclosure of Invention The embodiment of the application provides a control method and a related device for an industrial robot, which can combine the current transaction to be processed and target state information of the industrial robot to generate corresponding target operation parameter information, and finally control the industrial robot by adopting the target operation parameter information, thereby improving the accuracy of determining the target operation parameter and further improving the accuracy of controlling the industrial robot. A first aspect of an embodiment of the present application provides a control method of an industrial robot, the method including: Acquiring a current transaction to be processed of an industrial robot and acquiring target state information of the industrial robot; Determining application scene information according to the current transaction to be processed; Determining operation precision information and operation configuration information according to the application scene information; determining reference operation parameter information according to the operation precision information and the operation configuration information; Generating parameter correction information according to the target state information; Correcting the reference operation parameter information by adopting the parameter correction information to obtain the target operation parameter information; And controlling the industrial robot according to the target operation parameter information. In one possible implementation, obtaining the target state information of the industrial robot includes: extracting abnormal data in historical operation data of the industrial robot to obtain an abnormal data set; performing data equalization processing on the abnormal data in the abnormal data set to obtain a target data set; extracting features of the target data set to obtain a target feature vector; and predicting the state of the industrial robot according to the target feature vector and the real-time operation data of the industrial robot to obtain target state information. In one possible implementation manner, the performing data equalization processing on the abnormal data in the abnormal data set to obtain a target data set includes: denoising the abnormal data set to obtain a first data set; clustering the first data in the first data set to obtain M sub-data sets; determining the corresponding classification size of each sub-data set in the M sub-data sets to obtain a classification size information set; and carrying out data equalization processing on the M sub-data sets according to the classification size information in the classification size information set to obtain a target data set. In one possible implementation manner, a method for performing data equalization processing on M sub-data sets according to classification size information in a classification size information set to obtain a target data set includes: Determining a target test set corresponding to each sub-data set in the M sub-data sets to obtain M target test sets; Calculating the error rate corresponding to each target test set in the M target test sets to obtain M target error rate sets; calculating the average error rate of each sub-data set according to the target error rates in the M target error rate sets to obtain M average error rates; Determining the number of operation data to be synthesized for each sub-data set in M sub-data sets according to M average error rates and classification size information in the classification size information sets to obtain a first number set; And carrying out data synthesis on each sub-data set in the M sub-data sets according to the first quantity in the first quantity set to obtain a target data set. In one possible implementation manner, a method for determining a target test set corresponding to each of M sub-data sets to obtain M target test sets includes: Selecting a preset number of operation data from each of the M sub-data sets as training sets of th