Method and apparatus for determining operating state parameter of robot, and computer device

Abstract

The present application relates to a method and apparatus for determining an operating state parameter of a robot, and a computer device. The method comprises: acquiring candidate operating state parameters of a target robot having an operating state parameter to be determined; determining a preset number of candidate operating condition categories for the target robot; on the basis of a first similarity between the candidate operating state parameters and clustering center data that corresponds to the preset number of candidate operating condition categories, determining a target operating condition category for the target robot; acquiring an association relationship between energy consumption data and operating state data, wherein the association relationship is pre-constructed on the basis of historical operating state data of the robot in the target operating condition category and historical energy consumption data of the robot in the target operating condition category; and on the basis of a preset energy consumption condition and the association relationship, determining target operating state data from the candidate operating state parameters. By using the method, the degree of refinement of an operating state parameter of a robot can be improved.

Description

Method, device and computer equipment for determining operating state parameters of robot Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a method, apparatus, and computer equipment for determining operating status parameters of a robot. Background Art

[0002] With the development of science and technology, the automation, robotization and intelligence of automobile welding production lines are also constantly developing. Welding robots are often used in automobile welding production lines. During the operation of welding robots, corresponding operating status parameters need to be set, and corresponding energy consumption data will be generated. A large amount of operating status data and energy consumption data of welding robots are collected and stored.

[0003] The current method for determining the operating status data of an industrial robot is usually to adjust the operating status data setting of the welding robot according to the welding task and robot model of the robot.

[0004] However, the inventors discovered during implementation that the existing method for determining the operating status parameters of a robot is not very sophisticated.

[0005] Summary of the Invention

[0006] Based on this, it is necessary to provide a method, device and computer equipment for determining the operating status parameters of a robot that can improve the degree of refinement of the operating status parameters of the robot in order to address the above technical problems.

[0007] In a first aspect, the present application provides a method for determining operating state parameters of a robot, the method comprising:

[0008] Obtaining candidate operating state parameters of the target robot for which the operating state parameters are to be determined;

[0009] Determining a preset number of candidate working condition categories for the target robot;

[0010] Determining a target operating condition category of the target robot based on a first similarity between the candidate operating state parameter and cluster center data corresponding to a preset number of candidate operating condition categories;

[0011] Obtaining a correlation between energy consumption data and operating status data; the correlation is pre-established based on the robot's historical operating status data in the target working condition category and its historical energy consumption data in the target working condition category;

[0012] Based on the preset energy consumption conditions and association relationships, target operating state data is determined from candidate operating state parameters.

[0013] In one embodiment, obtaining the correlation between energy consumption data and operating status data includes:

[0014] Obtain target historical operating state data and target historical energy consumption data determined according to the robot identification and program identification of the robot;

[0015] Clustering the target historical operating status data to determine historical operating status data corresponding to a plurality of preset operating condition categories, and determining historical energy consumption data corresponding to a plurality of operating condition categories based on the target historical energy consumption data;

[0016] The historical operating status data and the corresponding historical energy consumption data corresponding to each operating condition category are correlated and analyzed to obtain the correlation relationship between the energy consumption data and the operating status data corresponding to each operating condition category.

[0017] In one embodiment, correlation analysis is performed on the historical operating status data and the corresponding historical energy consumption data corresponding to each operating condition category to obtain the correlation relationship between the energy consumption data and the operating status data corresponding to each operating condition category, including:

[0018] Determine historical operating status sub-data corresponding to multiple operating condition categories based on the target historical operating status data, and determine historical energy consumption sub-data corresponding to multiple operating condition categories based on the target historical energy consumption data;

[0019] Discretize the historical operating status sub-data and historical energy consumption sub-data of each operating condition category to obtain a discretized data set corresponding to each operating condition category;

[0020] The association analysis process is performed on the discrete data sets corresponding to each operating condition category to obtain the association relationship between the energy consumption data and the operating status data corresponding to each operating condition category.

[0021] In one embodiment, the historical operating status sub-data and historical energy consumption sub-data of each operating condition category are discretized to obtain a discretized data set corresponding to each operating condition category, including:

[0022] Get the current working condition category from multiple working condition categories;

[0023] Obtain the current sub-data corresponding to the current operating condition category; wherein the current sub-data is the historical operating status sub-data or the historical energy consumption sub-data;

[0024] Get the mean and standard deviation of the current sub-data;

[0025] According to the mean and standard deviation of the current sub-data, the current sub-data is discretized to obtain the discretized data set corresponding to the current working condition category.

[0026] In one embodiment, a correlation analysis is performed on the discretized data sets corresponding to each operating condition category to obtain a correlation relationship between the energy consumption data and the operating status data corresponding to each operating condition category, including:

[0027] Get the preset minimum support and confidence;

[0028] According to the minimum support and confidence, the discrete operating status data and discrete energy consumption data contained in the discretized data set corresponding to each operating condition category are subjected to correlation analysis to obtain the correlation relationship between the energy consumption data and operating status data corresponding to each operating condition category.

[0029] In one embodiment, determining a preset number of candidate working condition categories for a target robot includes:

[0030] Obtain the robot ID of the target robot and the program ID of the program to be executed by the target robot;

[0031] According to the robot identifier and the program identifier, a preset number of candidate working condition categories corresponding to the target robot are determined.

[0032] In one embodiment, determining a target operating condition category of a target robot based on a first similarity between a candidate operating state parameter and cluster center data corresponding to a preset number of candidate operating condition categories includes:

[0033] The candidate operating condition category corresponding to the smallest first similarity degree is used as the pre-selected operating condition category;

[0034] Obtaining multiple sample operating status data corresponding to a preselected operating condition category;

[0035] obtaining a second similarity between the candidate operating state parameter and the plurality of sample operating state data;

[0036] If the first similarity level corresponding to the preselected operating condition category is less than a preset number of second similarities, the preselected operating condition category is used as the target operating condition category.

[0037] In a second aspect, the present application further provides a device for determining operating state parameters of a robot, the device comprising:

[0038] A candidate operating parameter acquisition module is used to obtain candidate operating state parameters of the target robot whose operating state parameters are to be determined;

[0039] a candidate working condition category determination module, configured to determine a preset number of candidate working condition categories for a target robot;

[0040] a target operating condition category determination module, configured to determine a target operating condition category of a target robot based on a first similarity between a candidate operating state parameter and cluster center data corresponding to a preset number of candidate operating condition categories;

[0041] The correlation relationship acquisition module is used to obtain the correlation relationship between energy consumption data and operating status data; the correlation relationship is pre-established based on the historical operating status data of the robot in the target working condition category and the historical energy consumption data in the target working condition category;

[0042] The target operation data determination module is used to determine the target operation state data from the candidate operation state parameters based on the preset energy consumption conditions and association relationships.

[0043] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0044] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0045] The above-mentioned method, apparatus, and computer device for determining operating state parameters of a target robot for which operating state parameters are to be determined obtain candidate operating state parameters for the target robot; determine a preset number of candidate operating condition categories for the target robot; and determine the target operating condition category of the target robot based on a first degree of similarity between the candidate operating state parameters and cluster center data corresponding to the preset number of candidate operating condition categories, thereby improving the accuracy of determining the target operating condition category of the target robot. The method, apparatus, and computer device for determining operating state parameters of a target robot improve the accuracy of determining the target operating condition category of the target robot by obtaining a correlation between energy consumption data and operating state data; the correlation is pre-established based on the robot's historical operating state data in the target operating condition category and its historical energy consumption data in the target operating condition category. The method, apparatus, and computer device for determining operating state parameters of a target robot improve the accuracy of determining the target operating state data by determining the target operating state data from the candidate operating state parameters based on the preset energy consumption conditions and the correlation. Compared with conventional technologies, the present application can determine target operating state data from candidate operating state parameters that meet the energy consumption conditions based on the correlation between energy consumption data and operating state data. In this way, the target operating state data for recommendation can be accurately determined based on the potential association rules in the operating state data and energy consumption data, thereby improving the refinement of the target operating state data. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] FIG1 is a schematic flow chart of a method for determining operating state parameters of a robot according to one embodiment;

[0048] FIG2 is a flow chart of steps for obtaining an association between energy consumption data and operating status data in one embodiment;

[0049] FIG3 is a flow chart showing the steps of associating energy consumption data and operating status data corresponding to each operating condition category in one embodiment;

[0050] FIG4 is a flow chart illustrating the steps of obtaining a discretized data set corresponding to each operating condition category in one embodiment;

[0051] FIG5 is a flow chart of a method for determining operating state parameters of a robot according to another embodiment;

[0052] FIG6 is a block diagram of a device for determining operating state parameters of a robot according to an embodiment;

[0053] FIG7 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0055] In an exemplary embodiment, as shown in FIG1 , a method for determining operating state parameters of a robot is provided. This embodiment uses the method applied to a server as an example for illustration. It is understood that the method can also be applied to a terminal, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. This embodiment includes the following steps S102 to S110.

[0056] S102, obtaining candidate operating state parameters of a target robot whose operating state parameters are to be determined.

[0057] The target robot can be a robot whose operating state parameters are to be determined, a robot whose operating program is to be executed, or a welding robot used for welding on a user's car. Candidate operating state parameters can be operating state parameters of the target robot to be determined for a specific program. Candidate operating state parameters can be multiple operating state parameters to be determined, and the target operating state parameters of the target robot can be determined from the candidate operating state parameters. Operating state data can include current, voltage, resistance, pulse width, stability factor, etc.

[0058] For example, the server may obtain the robot identifier (e.g., robot code) of the target robot for which the operating state parameters are to be determined, and may also obtain the program identifier (e.g., program number) of the program executed by the target robot. Based on the robot identifier of the target robot and the program identifier of the program executed by the target robot, the server may obtain candidate operating state parameters for the target robot. In this manner, the target robot for which the operating state parameters are to be determined can be accurately determined, and the candidate operating state parameters for the target robot can be obtained.

[0059] S104: Determine a preset number of candidate working condition categories for the target robot.

[0060] The candidate operating condition category may be an operating condition category determined based on the robot identification and program identification of the robot. For example, a plurality of different operating conditions may correspond to a certain robot executing a certain program. Different operating state parameters may be set for different operating condition categories. The robot's operating conditions may include factors such as the robot's workload, operating time, operating temperature, operating humidity, operating pressure, and operating speed. The candidate operating condition category may be a type of operating condition to be determined for the robot. There may be multiple candidate operating condition categories, and the target operating condition type of the target robot may be determined from the candidate operating condition categories.

[0061] For example, the server may determine a preset number of candidate operating condition categories based on the robot identifier of the target robot and the program identifier of the program being executed by the target robot. For example, the number of candidate operating condition categories may be three, and the three candidate operating condition categories may each have a corresponding edge label. For example, j = 1, 2, and 3 may represent the category labels of the three candidate operating condition categories, respectively.

[0062] S106 , determining a target operating condition category of the target robot according to a first similarity between the candidate operating state parameters and cluster center data corresponding to a preset number of candidate operating condition categories.

[0063] Among them, the cluster center data can be the cluster center data of the cluster corresponding to the candidate working condition category, and can be the center data contained in the candidate working condition category. The cluster center data can be the operating state data of the cluster to form the candidate working condition category. The first similarity level can be the similarity between the candidate operating state parameters and the cluster center data, and the similarity can be represented by distance. The first similarity level can be the distance between the candidate operating state parameters and the cluster center data, for example, it can be the two-norm distance, the Euclidean distance, etc. The target working condition category can be the working condition category determined for the target robot, that is, the target working condition category can be the working condition category of the program to be executed by the target robot.

[0064] Exemplarily, the server can obtain the similarity between the candidate operating state parameters and the cluster center data corresponding to a preset number of candidate operating condition categories as the first similarity. For example, the server can obtain the distance between the candidate operating state parameters and the cluster center data of each candidate operating condition category as the first similarity. The server can determine the target operating condition category of the target robot based on the first similarity between the candidate operating state parameters of the target robot and the cluster center data corresponding to each candidate operating condition category. For example, the candidate operating condition category corresponding to the smallest similarity can be used as the target operating condition category of the target robot. In this way, the target operating condition category can be accurately determined from multiple candidate operating condition categories through the similarity between the candidate operating state parameters and the cluster center data corresponding to the candidate operating condition categories, thereby improving the accuracy of the operating state parameters of the target robot.

[0065] S108, obtaining the association relationship between the energy consumption data and the operating status data; the association relationship is pre-constructed based on the historical operating status data of the robot in the target working condition category and the historical energy consumption data in the target working condition category.

[0066] The association relationship may be an association relationship between the energy consumption data and the operating status parameters of the robot under the target working condition category.

[0067] Exemplarily, the server can obtain the robot's historical operating status data under the target operating condition category and the historical energy consumption data under the target operating condition category. The server can construct an association relationship between the energy consumption data and the operating status data based on the historical operating status data and the historical energy consumption data. For example, the FP-growth (Frequent Pattern Tree-growth) association rule analysis model can be used to construct an association relationship between the energy consumption data and the operating status data. When determining the operating status parameters of the target robot, the server can obtain the pre-constructed association relationship between the energy consumption data and the operating status data, and further determine the target operating status parameters of the target robot based on the pre-constructed association relationship. In this way, the operating status parameters of the robot can be determined based on the potential association rules in the operating status data and energy consumption data under the target operating condition category, thereby improving the accuracy of the robot's operating status parameters.

[0068] S110 , determining target operating state data from candidate operating state parameters based on preset energy consumption conditions and association relationships.

[0069] The energy consumption condition may be a condition set for energy consumption data. For example, the energy consumption condition may represent the minimum energy consumption of the robot or the energy consumption at which the robot performs at its best performance.

[0070] For example, the server can determine the energy consumption data required by the target robot based on pre-set energy consumption conditions. Furthermore, based on the correlation between the energy consumption data and the operating status data, the server can determine the operating status data corresponding to the required energy consumption data as the target operating status data. For example, based on the minimum energy consumption data required by the target robot and the correlation between the energy consumption data and the operating status data, the server can determine the operating status data corresponding to the minimum energy consumption data as the target operating status data. In this way, the server can determine the operating status parameters corresponding to the energy consumption data required by the robot based on the potential correlation rules between the operating status data and energy consumption data under the target working condition category, thereby improving the accuracy of the robot's operating status parameters.

[0071] In this embodiment, candidate operating state parameters of a target robot whose operating state parameters are to be determined are obtained; a preset number of candidate operating condition categories are determined for the target robot; and the target operating condition category of the target robot is determined based on a first degree of similarity between the candidate operating state parameters and cluster center data corresponding to the preset number of candidate operating condition categories, thereby improving the accuracy of determining the target operating condition category of the target robot. A correlation between energy consumption data and operating state data is obtained; the correlation is pre-established based on the robot's historical operating state data in the target operating condition category and its historical energy consumption data in the target operating condition category; and the target operating state data can be determined from the candidate operating state parameters based on the preset energy consumption conditions and the correlation, thereby improving the accuracy of determining the target operating state data. Compared with traditional technologies, the present application releases the value of data by mining the correlation between operating status data and energy consumption data; and saves the strong correlation rules obtained by mining to the welding process knowledge base, which can provide quantifiable recommendation information for the setting of the target robot operating status parameters. The present application can determine the target operating status data from the candidate operating status parameters that meet the energy consumption conditions through the correlation between energy consumption data and operating status data. In this way, the target operating status data for recommendation can be accurately determined based on the potential correlation rules in the operating status data and energy consumption data, thereby improving the degree of refinement of the target operating status data.

[0072] In an exemplary embodiment, as shown in FIG2 , obtaining the association relationship between energy consumption data and operating status data includes S202 to S206 , wherein:

[0073] S202 , obtaining target historical operating state data and target historical energy consumption data determined according to the robot identification and program identification of the robot.

[0074] Among them, the robot identifier can be used as a unique identifier of the robot, for example, it can be a robot code. The program identifier can be a unique identifier of the robot executing the program, for example, it can be a program number. The target historical operating status data can be the historical operating status data when a certain robot executes a certain program; for example, it can be the historical operating status data when the i-th robot executes the p-th program number. The target historical energy consumption data can be the historical energy consumption data when a certain robot executes a certain program; for example, it can be the historical energy consumption data when the i-th robot executes the p-th program number. The target historical energy consumption data and the target historical operating status data can be corresponding data, that is, the target historical energy consumption data and the target historical operating status data can be historical data when the same robot executes the same program.

[0075] S204 , clustering the target historical operating status data to determine historical operating status data corresponding to a plurality of preset operating condition categories, and determining historical energy consumption data corresponding to a plurality of operating condition categories based on the target historical energy consumption data.

[0076] The operating condition category may be a pre-set operating condition category, and the operating condition category corresponding to each operating condition data may be determined by performing cluster analysis on the operating status data, that is, the operating condition category to which the operating status data belongs may be determined by cluster analysis. Multiple operating condition categories may serve as the candidate operating condition categories.

[0077] S206 , performing correlation analysis on the historical operating status data and the corresponding historical energy consumption data corresponding to each operating condition category, and obtaining a correlation relationship between the energy consumption data and the operating status data corresponding to each operating condition category.

[0078] The correlation relationship may be the relationship between energy consumption data and operating status data under a certain operating condition category.

[0079] For example, the server can obtain the robot identification of the robot and determine the program identification of the robot executing a certain program. The server can determine the target historical operating status data and target historical energy consumption data corresponding to the robot identification and program identification based on the robot identification and the program identification. For example, the server groups the data set according to the welding robot number and program number to obtain G i，p , where i is the robot number and p is the program number, i = 1, 2…n, p = 1, 2…m.

[0080] The server can cluster the target historical operating status data based on the target historical operating status data, and divide the target historical operating status data into a plurality of preset working condition categories. The server can determine the historical operating status data contained in each working condition category. It is understandable that the historical operating status data contained in the working condition category can be the target historical operating status data after clustering and classification. The server can also determine the historical energy consumption data contained in each working condition category through the above clustering results and the correspondence between the target historical operating status data and the target historical energy consumption data. It is understandable that the server can cluster and classify the target historical operating status data and the target historical energy consumption data based on the target historical operating status data, and classify both the target historical operating status data and the target historical energy consumption data. Each working condition category obtained can correspond to historical operating status data and historical energy consumption data. For example, the server can perform clustering and classification on the data set G i,p Perform clustering to obtain the data set G i,p Datasets D for different working conditions i,p,j , where the dataset D i,p,j It can include historical operating status data and historical energy consumption data.

[0081] The server can build an association rule analysis model, and through the association rule analysis model, perform association rule mining on the historical operating status data and the corresponding historical energy consumption data corresponding to each working condition category, and obtain the association relationship between the energy consumption data and the operating status data under each working condition category. For example, the server can build an FP-growth association rule analysis model, set the minimum support MinSup and confidence MinConf, and perform association rule mining on the energy consumption data and the operating status data under each working condition category to obtain the association rule data set R i,p,j .

[0082] In this embodiment, by clustering the target historical operating status data, it is possible to determine the historical operating status data corresponding to multiple preset operating condition categories, and to determine the historical energy consumption data corresponding to multiple operating condition categories based on the target historical energy consumption data. Furthermore, by performing association analysis on the historical operating status data and the corresponding historical energy consumption data corresponding to each operating condition category, it is possible to obtain the correlation between the energy consumption data and operating status data corresponding to each operating condition category. In this way, association rules can be mined for the historical operating status data and historical energy consumption data for each operating condition type, allowing for the recommendation of operating status data based on the association rules, thereby improving the refinement of the robot's operating status data.

[0083] In an exemplary embodiment, as shown in FIG3 , correlation analysis is performed on the historical operating status data and the corresponding historical energy consumption data corresponding to each operating condition category to obtain a correlation relationship between the energy consumption data and the operating status data corresponding to each operating condition category, including S302 to S306, wherein:

[0084] S302, determining historical operating status sub-data corresponding to a plurality of operating condition categories based on the target historical operating status data, and determining historical energy consumption sub-data corresponding to a plurality of operating condition categories based on the target historical energy consumption data;

[0085] S304, discretizing the historical operating status sub-data and historical energy consumption sub-data of each operating condition category to obtain a discretized data set corresponding to each operating condition category;

[0086] S306 , performing correlation analysis on the discretized data sets corresponding to each operating condition category to obtain correlation relationships between energy consumption data and operating status data corresponding to each operating condition category.

[0087] The historical operating status sub-data may be operating status data included in the operating condition category, and the historical operating status sub-data may be data obtained by clustering the target historical operating status data. That is, the target historical operating status data may be clustered to obtain the historical operating status sub-data for each operating condition category. The historical energy consumption sub-data may be energy consumption data included in the operating condition category, and may be energy consumption data for each operating condition category obtained by clustering the target historical energy consumption data. The discretized data set may be a set of discrete data, and the discretized data set may include the discretized historical operating status sub-data and the discretized historical energy consumption sub-data.

[0088] For example, the server can determine the historical operating status sub-data contained in each operating condition category based on the clustered target historical operating status data, and can also determine the historical energy consumption sub-data contained in each operating condition category based on the clustered target historical energy consumption data. The server can discretize the historical operating status sub-data for each operating condition category, and discretize the historical energy consumption sub-data for each operating condition category, to obtain a discretized data set corresponding to each operating condition category. The server can construct an association rule analysis model, and, using the association rule analysis model, perform association analysis on the discretized data set corresponding to each operating condition category, to obtain association rules between the energy consumption data and operating status data corresponding to each operating condition category.

[0089] Optionally, the server can use the 6σ method to convert the dataset D i,p,j Each continuous data variable in is divided into 14 intervals, and then the data set D i,p,j Perform discretization processing to obtain the discretization matrix E i,p,j The server can build an FP-growth association rule analysis model, set the minimum support MinSup and confidence MinConf, and perform the analysis on the discretized data matrix E i,p,j Perform association rule mining to obtain the association rule dataset R i,p,j The server can parse the association rules to obtain the numerical action range between the operating status data and the energy consumption data of the working condition j.

[0090] In this embodiment, by discretizing the historical operating status sub-data and historical energy consumption sub-data of each working condition category, a discrete data set corresponding to each working condition category is obtained; the discrete data set corresponding to each working condition category is subjected to association analysis processing to obtain the association relationship between the energy consumption data and the operating status data corresponding to each working condition category, which can effectively and accurately determine the association rule relationship between the energy consumption data and the operating status data under each working condition category, thereby improving the refinement of the robot's operating status data recommendation.

[0091] In an exemplary embodiment, as shown in FIG4 , the historical operating status sub-data and the historical energy consumption sub-data of each operating condition category are discretized to obtain a discretized data set corresponding to each operating condition category, including S402 to S408, wherein:

[0092] S402, obtaining a current working condition category from multiple working condition categories;

[0093] S404, obtaining current sub-data corresponding to the current operating condition category; wherein the current sub-data is historical operating status sub-data or historical energy consumption sub-data;

[0094] S406, obtaining the mean and standard deviation of the current sub-data;

[0095] S408 , discretizing the current sub-data according to the mean and standard deviation of the current sub-data to obtain a discretized data set corresponding to the current working condition category.

[0096] The current operating condition category may be any one of multiple operating condition categories. For each operating condition category, the discretized data set corresponding to the operating condition category may be determined using the method provided in this embodiment. For multiple operating condition categories, this embodiment uses the current operating condition category as an example for illustration.

[0097] The current sub-data may be historical operating status sub-data or historical energy consumption sub-data. The historical operating status sub-data or historical energy consumption sub-data may be discretized using the method provided in this embodiment. This embodiment uses the current sub-data as an example to illustrate the method for processing the historical operating status sub-data or historical energy consumption sub-data.

[0098] For example, the server may select any one of multiple operating condition categories as the current operating condition category. For any operating condition category, the server may obtain historical operating status sub-data or historical energy consumption sub-data corresponding to the current operating condition category as the current sub-data for the current operating condition category. The server may determine the mean and standard deviation of the current sub-data. Furthermore, the server may determine a discretization interval based on the mean and standard deviation of the current sub-data. The server may then discretize the current sub-data based on the determined interval to obtain a discretized data set corresponding to the current operating condition category.

[0099] Optionally, the server may use the 6σ method to convert the dataset D i,p,j Each continuous data variable in is divided into 14 intervals, and then the data set D i,p,j Perform discretization processing to obtain the discretization matrix E i,p,j For example, for the working condition data set D 1,101,1 , the resistance data matrix is ​​X c=[x c，0 , x c，1 ,…,x c,t ,...,x c,r ], where c indicates that the cth continuous variable is current, and r indicates that there are r data samples in the resistance data matrix. X is calculated. c The mean u c is 9.5319, standard deviation σ c is 0.0094; for any x c,t , if x c,t In [u c +6σ c , +∞) interval, the discretization code is p101_99, if x c,t In (u c +6σ c ,u c +5σc] interval, the discretization code is p101_100, and so on. If x c,t In [u c -6σ c , -∞) interval, the discretization code is p101_112; similarly, the discretization code of the energy consumption data is p101_169, p101_170, ..., p101_182; finally, the discretization matrix E is obtained 1,101，1 .

[0100] In this embodiment, by obtaining the mean and standard deviation of the current sub-data; discretizing the current sub-data according to the mean and standard deviation of the current sub-data, a discretized data set corresponding to the current operating condition category is obtained, which can accurately discretize the historical operating status sub-data and the historical energy consumption sub-data, thereby improving the refinement of the discretized data set, and further improving the refinement of the correlation between the operating status data and the energy consumption data.

[0101] In an exemplary embodiment, a correlation analysis process is performed on the discretized data sets corresponding to each operating condition category to obtain a correlation relationship between the energy consumption data and the operating status data corresponding to each operating condition category, including:

[0102] Get the preset minimum support and confidence;

[0103] According to the minimum support and confidence, the discrete operating status data and discrete energy consumption data contained in the discretized data set corresponding to each operating condition category are subjected to correlation analysis to obtain the correlation relationship between the energy consumption data and operating status data corresponding to each operating condition category.

[0104] The minimum support and confidence can be parameters used to construct an association rule analysis model. The minimum support can be a threshold for measuring support. The confidence can be a threshold for measuring the minimum reliability of an association rule.

[0105] Exemplarily, the server can determine the pre-set minimum support and confidence, and based on the pre-built association rule analysis model, can perform association rule mining analysis on the discrete operating status data contained in the discretized data set corresponding to each operating condition category and the discrete energy consumption data contained in the discretized data set according to the minimum support and confidence, to obtain the association relationship between the energy consumption data and the operating status data corresponding to each operating condition category.

[0106] Optionally, the server can construct an FP-growth association rule analysis model, set the minimum support MinSup = 0.3 and the confidence MinConf = 0.8, and perform the following analysis on the discretized data matrix E 1,101,1 Perform association rule mining to obtain the association rule dataset R 1,101,1 The server can send the dataset R 1,101,1 The discrete associated terms in the equation are resolved into numerical action intervals. For example, the rule antecedent [p101_105, p101_119] and the rule posterior [p101_175] occur 11425 times, with a support of 0.32 and a confidence of 0.9862. It can be seen from the analysis that when the resistance is in (u re -σ re ,u re ], that is (99.9146, 118.508], while the pulse width is (u pw -σ pw ,u pw ], that is, (31.5028, 33.7274], there is a 98.62% probability that the energy consumption is in (u eg -σ eg ,u eg ], that is (1479.63, 1712.26].

[0107] In this embodiment, by obtaining the pre-set minimum support and confidence; and performing correlation analysis on the discrete operating status data and discrete energy consumption data contained in the discrete data set corresponding to each operating condition category based on the minimum support and confidence, the correlation relationship between the energy consumption data and the operating status data corresponding to each operating condition category can be obtained effectively and accurately, thereby improving the determination of the correlation relationship between the energy consumption data and the operating status data, and further improving the degree of refinement of the robot's operating status data.

[0108] In an exemplary embodiment, determining a preset number of candidate working condition categories for a target robot includes:

[0109] Obtain the robot ID of the target robot and the program ID of the program to be executed by the target robot;

[0110] According to the robot identifier and the program identifier, a preset number of candidate working condition categories corresponding to the target robot are determined.

[0111] For example, the server may obtain a robot identifier (e.g., a robot code) of a target robot for which operating state parameters are to be determined. The server may also obtain a program identifier (e.g., a program code) of a program to be executed by the target robot. The server may determine a preset number of candidate operating condition categories corresponding to the target robot based on the robot identifier of the target robot and the program identifier of the program to be executed by the target robot. The server may further determine a target operating condition category for the target robot from the candidate operating condition categories.

[0112] Optionally, the server can obtain the data of the welding robot and determine the data group G according to the robot number and program number. i，p , and determine the group G i，p Each candidate working condition category and each cluster center C under i，p，j .

[0113] In this embodiment, by obtaining the robot identification of the target robot and the program identification of the program to be executed by the target robot; determining a preset number of candidate working condition categories corresponding to the target robot based on the robot identification and the program identification, the candidate working condition categories corresponding to the target robot can be accurately determined, which is conducive to determining the target working condition category from the candidate working condition categories, thereby improving the refinement of the robot's operating status parameters.

[0114] In an exemplary embodiment, determining a target operating condition category of a target robot based on a first similarity between a candidate operating state parameter and cluster center data corresponding to a preset number of candidate operating condition categories includes:

[0115] The candidate operating condition category corresponding to the smallest first similarity degree is used as the pre-selected operating condition category;

[0116] Obtaining multiple sample operating status data corresponding to a preselected operating condition category;

[0117] obtaining a second similarity between the candidate operating state parameter and the plurality of sample operating state data;

[0118] If the first similarity level corresponding to the preselected operating condition category is less than a preset number of second similarities, the preselected operating condition category is used as the target operating condition category.

[0119] The preselected operating condition category may be an operating condition category selected from candidate operating condition categories, and further determination may be made as to whether the preselected operating condition category satisfies the target operating condition category. The sample operating state data may be sample data used to determine whether the operating state data is normal. The second similarity may be the similarity between the candidate operating state parameter and the sample operating state data. The second similarity may be the distance between the candidate operating state parameter and the sample operating state data, such as a two-norm distance, a Euclidean distance, or the like.

[0120] For example, the server may obtain a first degree of similarity between the candidate operating state parameter and the cluster center data corresponding to multiple candidate operating condition categories, and use the candidate operating condition category corresponding to the minimum value among the multiple first similarities as the preselected operating condition category. The server may also obtain multiple sample operating state data corresponding to the preselected operating condition category, and obtain a second degree of similarity between the candidate operating state parameter and the multiple sample operating state data. If the number of times the first degree of similarity is less than a certain value among the multiple second similarities exceeds a preset number, the preselected operating condition category may be used as the target operating condition category, and the candidate operating state parameter may be confirmed as a normal sample. Otherwise, if the number of times the first degree of similarity is less than a certain value among the multiple second similarities does not exceed a preset number, the candidate operating state parameter is confirmed as an abnormal sample and an alarm is issued.

[0121] For example, the server can calculate the candidate running state data of the target robot and the group G 1,101 Each cluster center C under 1,101，j The distance {d c1 , d c2 , d c3} and the distance sequence d = {d c1，1 , d c1，2 ,…,d c1，z1 , d c2，1 , d c2，2 ,…,d c2，z2 , d c3，1 , d c3，2 ,…,d c3，z3}, where z1, z2, and z3 are the numbers of sample operating status data corresponding to the three candidate operating condition categories respectively;

[0122] The server can obtain the minimum value of the three distances min(d c1 , d c2 , d c3 )=d c1 , if d c1 Less than {d c1，1 , d c1，2 ,...,d c1，z1} exceeds a certain proportion, then the candidate running state data of the target robot is a normal sample and belongs to working condition D 1,101,1 , R 1,101,1 The numerical range obtained by parsing the association rule data set is used as the recommendation result; otherwise, it is regarded as an abnormal sample and an alarm is issued.

[0123] In this embodiment, the candidate operating condition category corresponding to the smallest first similarity is used as the pre-selected operating condition category; multiple sample operating status data corresponding to the pre-selected operating condition category are obtained; the second similarity between the candidate operating status parameters and the multiple sample operating status data is obtained; if the first similarity corresponding to the pre-selected operating condition category is less than a preset number of second similarities, the pre-selected operating condition category is used as the target operating condition category, which can accurately obtain the target operating condition category, which is conducive to determining the operating status parameters of the robot according to the association relationship corresponding to the target operating condition category, thereby improving the refinement of the operating status parameters.

[0124] In an exemplary embodiment, as shown in FIG5 , a method for determining operating state parameters of a robot is provided, which can be applied to an automotive welding robot, including:

[0125] S501, obtaining the welding robot number, program number, operating status historical data and energy consumption historical data, wherein the operating status data includes welding current, voltage, resistance, pulse width, stability factor, etc.

[0126] S502, grouping the data set according to the welding robot number and program number to obtain G i,p , where i is the robot number and p is the program number, i = 1, 2…n, p = 1, 2…m.

[0127] S503, extract the data set G of the pth program number of the i-th robot i,p , delete rows with missing values.

[0128] For example, extract the data sample set of the 101st program number of the first robot, delete the samples with vacant values, and obtain the data set G 1,101 ;

[0129] S504, construct a kernel density clustering algorithm, set the number of neighborhood samples MinPts, and perform clustering on the dataset G i,p Perform clustering to obtain the data set G i,p Datasets D for different working conditions i,p,j , the cluster center C of each category i,p,j , each sample category label, where j = 1, 2…q, q is the number of working conditions; if the sample category label is -1, it will be eliminated as an abnormal sample.

[0130] For example, a kernel density clustering algorithm is constructed, and the number of neighborhood samples MinPts is set to 15. 1,101 Perform clustering to obtain three different category data sets D 1,101,j (i.e. three different working conditions), the cluster centers C of the three categories of data sets 1,101,j And the sample category label sequence (-1, 0, 1, 2), where j = 1, 2, 3; if the sample category label is -1, it will be removed as an abnormal sample.

[0131] S505, using the 6σ method, the dataset D i,p,j Each continuous data variable in is divided into 14 intervals, and then the data set D i,p,j Perform discretization processing to obtain the discretization matrix E i,p,j .

[0132] For example, the dataset D is transformed into i,p,j Each continuous data variable in is divided into 14 intervals, and then the data set D i,p,j Perform discretization processing to obtain the discretization matrix E i,p,j For example, for the working condition data set D 1,101,1 , the resistance data matrix is ​​X c =[x c,0 , x c,1 ,...,x c,t ,...,x c,r ], where c indicates that the cth continuous variable is current, and r indicates that there are r data samples in the resistance data matrix. X is calculated. c The mean u c is 9.5319, standard deviation σ c is 0.0094; for any x c,t , if x c,t In [u c +6σ c , +∞) interval, the discretization code is p101_99, if x c,t In (u c +6σ c ,u c +5σ c ] interval, the discretization code is p101_100, and so on. If x c,t In [u c -6σ c , -∞) interval, the discretization code is p101_112; similarly, the discretization code of the energy consumption data is p101_169, p101_170, ..., p101_182; finally, the discretization matrix E is obtained 1,101,1 .

[0133] S506, set the minimum support MinSup and confidence MinConf, and the discretized data matrix E i,p,j Perform association rule mining to obtain the association rule dataset R i,p,j .

[0134] For example, the FP-growth association rule analysis model is constructed, and the minimum support MinSup=0.3 and the confidence MinConf=0.8 are set. 1,101,1 Perform association rule mining to obtain the association rule dataset R 1,101,1 .

[0135] S507 , analyzing the association rules to obtain a numerical action range between the operating status data and the energy consumption data of the working condition j.

[0136] For example, the dataset R 1,101,1 The discrete associated terms in the equation are resolved into numerical action intervals. For example, the rule antecedent [p101_105, p101_119] and the rule posterior [p101_175] occur 11425 times, with a support of 0.32 and a confidence of 0.9862. It can be seen from the analysis that when the resistance is in (u re -σ re ,u re ], that is (99.9146, 118.508], while the pulse width is (u pw -σ pw ,u pw ], that is, (31.5028, 33.7274], there is a 98.62% probability that the energy consumption is in (u eg -σ eg ,u eg ], that is (1479.63, 1712.26].

[0137] S508, obtaining candidate operating state data of the welding robot whose operating state parameters are to be determined, and determining the data group G according to the robot number and program number. i,p .

[0138] For example, candidate operating state data of the welding robot is obtained, for example, the data is determined to belong to group G according to the robot number and program number. 1，101

[0139] S509, calculating the candidate operating state data of the welding robot and the group G i,p Each cluster center C under i,p,j The distance between the running status data of each sample.

[0140] For example, the candidate operating state data of the welding robot and the group G are calculated.1，101 Each cluster center C under 1，101，j The distance {d c1 , d c2 , d c3} and the distance sequence d = {d c1，1 , d c1，2 ,…,d c1，z1 , d c2，1 , d c2，2 ,…,d c2，z2 , d c3，1 , d c3，2 ,…,d c3，z3}, z1, z2, and z3 are the numbers of sample operating status data corresponding to the three candidate operating condition categories.

[0141] S510: Determine whether the candidate operating state data of the welding robot is an abnormal sample. If so, execute S511 to generate an alarm.

[0142] For example, the minimum value min(d c1 , d c2 , d c3 )=d c1 , if d c1 Less than {d c1，1， d c1，2 ,...,d c1，z1} exceeds a certain proportion, then the candidate running state data of the target robot is a normal sample and belongs to working condition D 1，101，1 , R 1，101，1 The numerical range obtained by parsing the association rule data set is used as the recommendation result; otherwise, it is regarded as an abnormal sample and an alarm is issued.

[0143] If not, execute S512 to screen strong association rules from the association rule data set in combination with the welding process, analyze the strong association rules, and obtain corresponding numerical action intervals as recommendation results.

[0144] In this embodiment, the operating conditions of the automobile welding robot under different program numbers can be identified, and potential association rules in the operating status data and energy consumption data under different operating conditions can be mined to enrich the welding process knowledge base and provide recommended information for the setting of the welding robot operating status parameters.

[0145] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0146] Based on the same inventive concept, embodiments of the present application also provide a robot operating state parameter determination device for implementing the aforementioned robot operating state parameter determination method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of the one or more robot operating state parameter determination device embodiments provided below can be found in the limitations of the robot operating state parameter determination method described above and will not be repeated here.

[0147] In an exemplary embodiment, as shown in FIG6 , a device for determining operating state parameters of a robot is provided, comprising: a candidate operating parameter acquisition module 610 , a candidate working condition category determination module 620 , a target working condition category determination module 630 , an association relationship acquisition module 640 , and a target operating data determination module 650 , wherein:

[0148] A candidate operating parameter acquisition module 610 is used to acquire candidate operating state parameters of a target robot for which operating state parameters are to be determined;

[0149] A candidate working condition category determination module 620 is used to determine a preset number of candidate working condition categories for the target robot;

[0150] a target operating condition category determination module 630 for determining a target operating condition category of a target robot based on a first similarity between a candidate operating state parameter and cluster center data corresponding to a preset number of candidate operating condition categories;

[0151] The association relationship acquisition module 640 is used to obtain the association relationship between the energy consumption data and the operating status data; the association relationship is pre-established based on the historical operating status data of the robot in the target working condition category and the historical energy consumption data in the target working condition category;

[0152] The target operation data determination module 650 is configured to determine target operation state data from candidate operation state parameters based on preset energy consumption conditions and association relationships.

[0153] In an exemplary embodiment, the association relationship acquisition module includes a historical data acquisition unit, a data clustering unit, and an association analysis unit.

[0154] The historical data acquisition unit is configured to acquire target historical operating status data and target historical energy consumption data determined based on the robot identification and program identification of the robot. The data clustering unit is configured to cluster the target historical operating status data to determine historical operating status data corresponding to a plurality of preset operating condition categories, and to determine historical energy consumption data corresponding to a plurality of operating condition categories based on the target historical energy consumption data. The correlation analysis unit is configured to perform correlation analysis on the historical operating status data and the corresponding historical energy consumption data corresponding to each operating condition category, to determine a correlation between the energy consumption data and operating status data corresponding to each operating condition category.

[0155] In an exemplary embodiment, the association analysis unit includes a sub-data determination unit, a discretization data acquisition unit, and an association relationship acquisition unit.

[0156] The sub-data determination unit is used to determine the historical operating status sub-data corresponding to multiple operating condition categories based on the target historical operating status data, and to determine the historical energy consumption sub-data corresponding to multiple operating condition categories based on the target historical energy consumption data. The discretized data acquisition unit is used to discretize the historical operating status sub-data and historical energy consumption sub-data for each operating condition category to obtain a discretized data set corresponding to each operating condition category. The association relationship acquisition unit is used to perform association analysis on the discretized data set corresponding to each operating condition category to obtain the association relationship between the energy consumption data and operating status data corresponding to each operating condition category.

[0157] In an exemplary embodiment, the discretization data acquisition unit includes a current category determination unit, a current sub-data determination unit, and a discretization processing unit.

[0158] Get the current working condition category from multiple working condition categories;

[0159] Obtain the current sub-data corresponding to the current operating condition category; wherein the current sub-data is the historical operating status sub-data or the historical energy consumption sub-data;

[0160] Get the mean and standard deviation of the current sub-data;

[0161] According to the mean and standard deviation of the current sub-data, the current sub-data is discretized to obtain the discretized data set corresponding to the current working condition category.

[0162] In an exemplary embodiment, the association relationship acquisition unit includes a support confidence acquisition unit and an association relationship analysis unit.

[0163] The support confidence acquisition unit is used to obtain a preset minimum support and confidence level. The association analysis unit is used to perform association analysis on the discrete operating state data and discrete energy consumption data contained in the discretized data set corresponding to each operating condition category based on the minimum support and confidence level, and obtain the association relationship between the energy consumption data and operating state data corresponding to each operating condition category.

[0164] In an exemplary embodiment, the candidate operating condition category determination module includes an identification acquisition unit and a candidate operating condition category acquisition unit.

[0165] The identification acquisition unit is used to acquire the robot identification of the target robot and the program identification of the program to be executed by the target robot. The candidate working condition category acquisition unit is used to determine a preset number of candidate working condition categories corresponding to the target robot according to the robot identification and the program identification.

[0166] In an exemplary embodiment, the target operating condition category determination module includes a preselected operating condition category determination unit, a sample operation data acquisition unit, a second similarity degree acquisition unit, and a similarity degree comparison unit.

[0167] The preselected operating condition category determination unit is configured to select the candidate operating condition category corresponding to the smallest first similarity as the preselected operating condition category. The sample operation data acquisition unit is configured to acquire a plurality of sample operation status data corresponding to the preselected operating condition category. The second similarity acquisition unit is configured to acquire a second similarity between the candidate operation status parameter and the plurality of sample operation status data. The similarity comparison unit is configured to select the preselected operating condition category as the target operating condition category if the first similarity corresponding to the preselected operating condition category is less than a preset number of second similarities.

[0168] Each module in the aforementioned device for determining the operating state parameters of a robot may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0169] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in Figure 7. The computer device includes a processor, a memory, an input / output (I / O) interface, and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store candidate operating state parameters. The I / O interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method for determining the operating state parameters of a robot.

[0170] Those skilled in the art will understand that the structure shown in FIG7 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0171] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0172] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0173] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0174] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0175] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0176] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0177] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for determining operating state parameters of a robot, characterized in that: The method comprises: Obtaining candidate operating state parameters of the target robot whose operating state parameters are to be determined; Determining a preset number of candidate working condition categories for the target robot; Determining a target operating condition category of the target robot according to a first similarity between the candidate operating state parameter and the cluster center data corresponding to the preset number of candidate operating condition categories; Acquire the association relationship between energy consumption data and operating status data; the association relationship is pre-constructed based on the historical operating status data of the robot in the target working condition category and the historical energy consumption data in the target working condition category; Based on the preset energy consumption condition and the association relationship, target operating state data is determined from the candidate operating state parameters.

2. The method according to claim 1, characterized in that The obtaining of the correlation between the energy consumption data and the operating status data includes: Acquire target historical operating state data and target historical energy consumption data determined according to the robot identification and program identification of the robot; Clustering the target historical operating status data to determine historical operating status data corresponding to a plurality of preset operating condition categories, and determining historical energy consumption data corresponding to the plurality of operating condition categories according to the target historical energy consumption data; The historical operating status data and the corresponding historical energy consumption data corresponding to each of the operating condition categories are subjected to correlation analysis to obtain the correlation relationship between the energy consumption data and the operating status data corresponding to each of the operating condition categories.

3. The method according to claim 2, characterized in that The correlation analysis of the historical operating status data and the corresponding historical energy consumption data corresponding to each of the operating condition categories is performed to obtain the correlation relationship between the energy consumption data and the operating status data corresponding to each of the operating condition categories, including: Determine the historical operating status sub-data corresponding to the multiple operating condition categories according to the target historical operating status data, and determine the historical energy consumption sub-data corresponding to the multiple operating condition categories according to the target historical energy consumption data; Discretizing the historical operating status sub-data and historical energy consumption sub-data of each of the operating condition categories to obtain a discretized data set corresponding to each of the operating condition categories; The discrete data sets corresponding to the various working condition categories are subjected to association analysis to obtain the association relationship between the energy consumption data and the operating status data corresponding to the various working condition categories.

4. The method according to claim 3, characterized in that The discretization processing of the historical operating status sub-data and the historical energy consumption sub-data of each of the operating condition categories is performed to obtain a discretized data set corresponding to each of the operating condition categories, including: Obtaining a current operating condition category from the multiple operating condition categories; Obtain the current sub-data corresponding to the current operating condition category; wherein the current sub-data is the historical operating state sub-data According to or described historical energy consumption data; Obtaining the mean and standard deviation of the current sub-data; The current sub-data are discretized according to the mean and standard deviation of the current sub-data to obtain a discretized data set corresponding to the current operating condition category.

5. The method according to claim 3, characterized in that: The performing of association analysis on the discrete data sets corresponding to each of the working condition categories to obtain the association relationship between the energy consumption data and the operating status data corresponding to each of the working condition categories includes: Get the preset minimum support and confidence; According to the minimum support and the confidence, a correlation analysis is performed on the discrete operating status data and the discrete energy consumption data contained in the discretized data set corresponding to each operating condition category to obtain the correlation relationship between the energy consumption data and the operating status data corresponding to each operating condition category.

6. The method according to claim 1, characterized in that The determining of a preset number of candidate working condition categories for the target robot includes: Obtaining a robot identifier of the target robot and a program identifier of a program to be executed by the target robot; A preset number of candidate working condition categories corresponding to the target robot are determined according to the robot identifier and the program identifier.

7. The method according to any one of claims 1 to 6, characterized in that: The step of determining the target operating condition category of the target robot according to the first similarity between the candidate operating state parameter and the cluster center data corresponding to the preset number of candidate operating condition categories comprises: The candidate operating condition category corresponding to the smallest first similarity degree is used as the pre-selected operating condition category; Acquire a plurality of sample operating status data corresponding to the preselected operating condition category; Acquire a second similarity between the candidate operating state parameter and the plurality of sample operating state data; If the first similarity level corresponding to the pre-selected operating condition category is less than a preset number of second similarities, the pre-selected operating condition category is used as the target operating condition category.

8. A device for determining operating state parameters of a robot, characterized in that: The device comprises: A candidate operating parameter acquisition module is used to acquire candidate operating state parameters of a target robot whose operating state parameters are to be determined; A candidate working condition category determination module, used to determine a preset number of candidate working condition categories for the target robot; a target operating condition category determination module, configured to determine the target operating condition category of the target robot according to a first similarity between the candidate operating state parameter and the cluster center data corresponding to the preset number of candidate operating condition categories; The association relationship acquisition module is used to obtain the association relationship between energy consumption data and operating status data; the association relationship is based on the machine The robot's historical operating status data in the target operating condition category and historical energy consumption data in the target operating condition category are pre-built; The target operation data determination module is used to determine the target operation status data from the candidate operation status parameters based on the preset energy consumption conditions and the association relationship.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images