Industrial robot health degree real-time evaluation method and device fusing multiple indexes

Abstract

The invention provides an industrial robot health degree real-time evaluation method and device fusing multiple indexes. The method comprises the steps that data of all indexes of an industrial robot are collected and obtained in real time; performing operational analysis on the indexes through a machine learning algorithm, and screening to obtain a plurality of key indexes influencing the health degree of the industrial robot; calculating and analyzing the weight of each key index in health degree scoring by using an analytic hierarchy process; scoring the key indexes according to the acquired data of the key indexes and respective scoring rules of the key indexes to obtain scores of the key indexes; according to the weights of the key indexes and the scores of all the key indexes, the health degree score of the industrial robot is obtained through comprehensive operation; and evaluating the health degree score of the industrial robot to obtain a health degree evaluation result of the industrial robot. Requirements of real-time monitoring of the operation condition, the health degree and the operation trend of the industrial robot are met, and safe and stable operation of the industrial robot is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of industrial robots, and in particular to a method and device for real-time evaluation of the health of an industrial robot integrating multiple indicators. Background Art

[0002] The unmanned operation of industry is inseparable from the application of industrial intelligent robots. The more important the role of industrial robots in industrial scenarios, the more attention should be paid to their own safety and reliability. Once a problem occurs with the robot, at the very least, production will be suspended, resulting in loss of economic benefits; at worst, it will cause major accidents such as personal safety and production safety. Therefore, it is necessary to understand the "health" of the industrial robot itself in real time.

[0003] Robots are widely used in a wide range of fields, and the tasks involved are also complex and diverse. Usually, a large number of parameters and indicators are needed to fully describe the working status of the robot. The traditional robot health assessment method obtains fixed analysis indicators, does not consider the complexity of the robot's operating conditions, and cannot accurately reflect the robot's true health status. Therefore, the evaluation results obtained are quite different from the actual situation. How to obtain the key indicators that affect the health of industrial robots from these complex data, and how to accurately assess the current health status of industrial robots are issues that need to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide a method and device for real-time evaluation of the health of an industrial robot that integrates multiple indicators, thereby realizing the requirements of real-time monitoring of the operating status, health level, and operating trend of the industrial robot, so that managers can timely grasp the situation of each industrial robot in the factory environment and ensure its safe and stable operation.

[0005] In a first aspect, an embodiment of the present application provides a method for real-time evaluation of the health of an industrial robot integrating multiple indicators, the method comprising: Collect and obtain data on various indicators of industrial robots in real time; The indicators are analyzed and calculated using a machine learning algorithm to screen out multiple key indicators; Scoring the key indicators according to the collected data of the key indicators and the scoring rules of the key indicators to obtain scores of the key indicators; Use the analytic hierarchy process to calculate and analyze the weight of each key indicator in the health score; According to the weight of the key indicators and the scores of the key indicators, a comprehensive calculation is performed to obtain a health score of the industrial robot; The health score of the industrial robot is evaluated to obtain a health assessment result of the industrial robot.

[0006] Furthermore, the machine learning algorithm includes using the XGBosst algorithm to evaluate the indicators and screen out key indicators. The formula is expressed as: ,in is the loss function, and its parameters are the true value and predicted value of the sample data, Indicates complexity.

[0007] Furthermore, the key indicators include key operating indicators of the industrial robot, and the scoring rules include scoring based on the degree of deviation between the real-time data of the key operating indicators collected when the industrial robot is working and the rated value; and / or scoring based on the degree of deviation between the real-time data and the operating baseline of the normal operation of the industrial robot.

[0008] Furthermore, the key operating indicators of the industrial robot include: memory utilization, and / or axis real-time current, and / or axis operating temperature, and / or robot arm load rate, and / or energy consumption rate, and / or coordinate positioning deviation.

[0009] Furthermore, the key indicator includes a remaining life indicator of the industrial robot, and the scoring rule includes scoring according to the operating time of the industrial robot and the length of time until the specified scrapping time of the industrial robot.

[0010] Furthermore, the key indicator includes the number of overhauls of the industrial robot, and the scoring rule includes scoring according to the number of overhauls of the industrial robot.

[0011] Furthermore, the calculation formula of the health score is expressed as:

[0012] Among them, H represents the health score of the robot, Ei represents each indicator, and Wi represents the indicator weight.

[0013] In a second aspect, an embodiment of the present application provides a device for real-time evaluation of the health of an industrial robot integrating multiple indicators, the device comprising: Data acquisition module, used to collect data of various indicators of industrial robots in real time; A key indicator screening module is used to perform calculation and analysis on the indicators through a machine learning algorithm to screen out multiple key indicators; A key indicator scoring module is used to score the key indicators according to the collected key indicator data and the scoring rules of the key indicators to obtain the scores of the key indicators; The key indicator weight analysis module is used to calculate and analyze the weight of each key indicator in the health score using the hierarchical analysis method; A health score module, used for obtaining a health score of the industrial robot by comprehensive calculation based on the weights of the key indicators and the scores of the key indicators; The health evaluation module is used to evaluate the health score of the industrial robot and obtain the health evaluation result of the industrial robot.

[0014] In a third aspect, an embodiment of the present application provides a target device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for real-time assessment of the health of an industrial robot integrating multiple indicators as described in any one of the first aspects above is implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the real-time assessment method of the health of an industrial robot integrating multiple indicators as described in any one of the first aspects above.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a target device, the target device executes the real-time assessment method for the health of an industrial robot integrating multiple indicators as described in any one of the first aspects above.

[0017] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0018] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the present application removes useless or redundant features from a large amount of data generated during the operation of the industrial robot through a machine learning algorithm, and screens out key indicators that affect the health of the industrial robot, thereby achieving a good balance between the comprehensiveness and economy of the health assessment indicators, and avoiding the problem that the health assessment caused by fixed key indicators cannot accurately reflect the true health status of the robot; by establishing a scoring mechanism for key indicators and calculating the overall health of the robot through weighted synthesis, the results of the health assessment are more accurate, so that the health assessment of the industrial robot can be realized in a timely, accurate and efficient manner, and abnormal situations can be discovered and checked as early as possible, thereby ensuring the healthy and stable operation of the robot and improving the economic benefits of industrial production. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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.

[0020] Figure 1 It is a detailed flowchart of a method for real-time evaluation of the health of an industrial robot integrating multiple indicators provided in an embodiment of the present application; Figure 2 This is a schematic diagram of key indicator scoring rules for a real-time health assessment method for an industrial robot integrating multiple indicators provided in an embodiment of the present application; Figure 3 This is a brief flowchart of a method for real-time evaluation of the health of an industrial robot integrating multiple indicators provided in an embodiment of the present application; Figure 4 This is a hierarchical model structure diagram of the real-time evaluation of the health of an industrial robot provided in one embodiment of the present application; Figure 5 It is a schematic diagram of the Santy scale provided in an embodiment of the present application; Figure 6 This is a schematic diagram of a criterion layer judgment matrix for real-time evaluation of the health of an industrial robot provided in an embodiment of the present application; Figure 7 It is a schematic diagram of the usage of the Santy scale provided in one embodiment of the present application; Figure 8 This is a schematic diagram of the result of the criterion layer judgment matrix for real-time evaluation of the health of an industrial robot provided in one embodiment of the present application; Fig. 9 This is a representation of the RI value provided in an embodiment of the present application; Fig.10 This is a schematic diagram of a device for real-time evaluation of the health of an industrial robot integrating multiple indicators provided in one embodiment of the present application; Fig.11 This is a real-time assessment trend chart of the health of an industrial robot integrating multiple indicators provided in an embodiment of the present application; Fig.12 It is a host schematic diagram of a method for real-time assessment of the health of an industrial robot integrating multiple indicators provided in one embodiment of the present application. DETAILED DESCRIPTION

[0021] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0022] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0023] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0024] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0025] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0026] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0027] The embodiment of the present invention provides a method and device for real-time evaluation of the health of industrial robots integrating multiple indicators, which can make full use of the comprehensive data collection capabilities of industrial robots now and in the future, and collect various data generated during the production and operation of industrial robots in real time, thereby realizing the comprehensiveness of the health evaluation indicators of industrial robots; the algorithm of the present application summarizes and organizes the above-mentioned large number of data indicators with different attributes, different standards, and different sources, and screens out the key indicators that affect the health of industrial robots, thereby realizing the economy of the health evaluation of industrial robots; and then further uses the analytic hierarchy process to perform a comprehensive calculation on the weights of the key indicators and the scores obtained according to the scoring rules of the key indicators to obtain the health score as the health measurement standard of the industrial robot, thereby realizing the accuracy of the health evaluation of the industrial robot. It perfectly solves the deficiencies of the existing passive operation and maintenance management methods for industrial robots in terms of prevention and predictability, improves the level of health management of industrial robots, and provides a basis for proactive industrial robot operation and maintenance management with the goal of predicting risk issues in advance.

[0028] The target device may include, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The target device may also be implemented using an independent server or a server cluster consisting of multiple servers. In other words, the target device may be, for example, Fig.12 Computer equipment shown.

[0029] The present invention is described in detail below through specific embodiments.

[0030] Figure 3 The following is a brief flow chart of the method for managing the health of industrial robots in a smart park provided by the present application. As an example but not a limitation, the method specifically includes the following steps: S101: Real-time collection and acquisition of data on various indicators of industrial robots; S102: Performing calculation analysis through machine learning algorithms to screen out multiple key indicators that affect the health of industrial robots; S103: Score the key indicators according to their respective scoring rules to obtain scores for each key indicator; S104: Use the analytic hierarchy process to calculate and analyze the weight of each key indicator in the health score; S105: Obtaining a health score of the industrial robot through comprehensive calculation according to the weight of the key indicator and the score of each key indicator; S106: Evaluate the health score of the industrial robot.

[0031] Combination Figure 1The detailed flowchart further describes the implementation process of the above steps of the real-time evaluation method for the health of industrial robots: S101: Real-time collection of data on various indicators of industrial robots: Industrial robots can generate a large amount of data during operation. For example, a certain brand of robot will generate more than 60 indicators during the production process, including the robot's manufacturer, model, axis information, output log information, load, axis name, axis status, etc. In this step, the system obtains these data indicators through various types of collection equipment or product manuals / instructions. This comprehensive data collection using a variety of data collection methods is the basis for accurate health judgment. In the existing technology, it is often based on past experience or requirements. A few fixed key indicators are selected for long-term evaluation. However, with the evolution of industrial robots and the continuous changes in scenarios, some of these key indicators can no longer meet the requirements of health assessment. Therefore, only comprehensive data collection and dynamic screening of these data can meet the requirements for accurate assessment of the health of industrial robots.

[0032] S102: Through machine learning algorithms, we perform computational analysis and screen out multiple key indicators that affect the health of industrial robots: The comprehensive data of various indicators of industrial robots cannot be directly used for health assessment, because a large amount of data is irrelevant to the health of the robot. These impurity data need to be removed to ensure the accuracy of health assessment. This application uses the XGBoost algorithm of machine learning to obtain key indicators related to health assessment. The specific method is as follows: All the properties and indicators of the robot equipment and the operating data generated under normal operation are used as data sources to train the XGBoost feature selection algorithm. The goal is to select the key indicators that affect the normal operation of the robot.

[0033] The XGBoost algorithm defines an objective function that takes into account the complexity and prediction error of the model. Each time a node splits, the gain before and after the split is calculated. If the gain is greater than 0, it means that the model after the split is better than the model before the split, so the feature with the largest gain is selected for splitting. The calculation of this gain involves performing a second-order Taylor expansion on the objective function. The optimal leaf node weight is determined by solving the minimum value of the quadratic function, and then the gain before and after the split is evaluated.

[0034] In terms of feature selection, XGBoost uses an exact greedy algorithm and an approximate algorithm to process continuous variables. The exact greedy algorithm traverses all possible split points of continuous features, calculates the gain of each split point, and selects the one with the largest gain as the split point of the feature; while the approximate algorithm improves the computational efficiency by selecting a part of the candidate split points based on the exact greedy algorithm. These candidate split points can be selected by a quantile-based method.

[0035] In general, the principle of feature selection in the XGBoost algorithm is mainly based on the optimization of the objective function. It determines whether to split each feature by calculating the gain after splitting, thereby achieving model optimization and feature selection. The objective function formula of the algorithm is expressed as: , for the objective function obj(θ), including two terms, is the loss function, and its parameters are the true value and predicted value of the sample data. After comparing the true value with the predicted value, the smaller the difference, the more accurate it is; Represents complexity, which is expanded into , where T in λT represents the number of leaf nodes in a tree. The larger the number of leaf nodes, the higher the complexity. The complexity of the leaf nodes can be controlled by adjusting the λ value; w represents the vector composed of the output values ​​of the leaf nodes. The smaller the value, the more stable the result.

[0036] The XGBoost algorithm is an improvement on the gradient boosting tree. The main idea is to construct a regression tree with given sample data, such as the normal operation sample data of the robot in this case, including memory utilization time series data, axis real-time current time series data, and operating voltage time series data, and perform node splitting. By performing a second-order Taylor expansion on the objective function, the minimum value of the quadratic function is solved to determine the optimal leaf node weight, and then evaluate the gain before and after the split. If the gain is greater than 0, it means that the model after the split is better than the model before the split. Continue to split until the gain is less than 0, so as to select the key indicators.

[0037] In one embodiment, we use the XGBoost algorithm to find that the key indicators that affect the health of industrial robots mainly include key operating indicators of industrial robots, remaining life indicators of industrial robots, and the number of overhauls of industrial robots. Among them, the key operating indicators include: memory utilization, and / or real-time current of the axis, and / or axis operating temperature, and / or mechanical arm load rate, and / or energy consumption rate, and / or coordinate positioning deviation. In this example, eight key indicators are selected as the core indicators of the robot, namely: memory utilization, real-time current of the axis, axis operating temperature, mechanical arm load rate, energy consumption rate, coordinate positioning deviation, remaining life of the robot, and number of major overhauls of the robot. These indicators can be arbitrarily combined in other embodiments.

[0038] In other embodiments, according to the characteristics of the industrial robot, the collected data, or the different application scenarios, through the machine learning results of the above XGBoost algorithm, it is found that other indicators are more likely to affect the health evaluation results, then these other key indicators are selected as possible evaluation basis. This also shows the flexibility of the health evaluation of this method, which is reflected in the ability to select more suitable key indicators according to changes in the actual environment.

[0039] S103: Score the key indicators according to their respective scoring rules to obtain scores for each key indicator: like Figure 2 As shown, in this example, the key indicators of the health of industrial robots are scored using different scoring rules. Specifically, according to the characteristics of the eight key indicators mentioned above, there are three different scoring rules according to the different categories, as described below: Scoring Rule 1: The scoring rules for the key operating indicators of the industrial robot include scoring based on the degree of deviation between the real-time data of the key operating indicators collected when the industrial robot is operating and the rated value; and / or scoring based on the degree of deviation between the real-time data and the operating baseline of the normal operation of the industrial robot. Such indicators mainly include: memory utilization, and / or real-time current of the axis, and / or operating temperature of the axis, and / or load rate of the robot arm, and / or energy consumption rate, and / or coordinate positioning deviation.

[0040] For a robot in this example, the memory utilization, real-time current of the axis, the axis operating temperature, the load of the robot arm, the energy consumption, and the coordinate positioning all have rated values ​​(normal operating range); in addition, through real-time monitoring of the data of these indicators, an operating law curve, namely the operating baseline, can be summarized, which can be used as a reference for real-time data in a year-on-year / month-on-month manner. Assuming that each indicator is implemented in a percentage system, for real-time data, every deviation from the rated value will be deducted ten points; every time it exceeds / is lower than the baseline data by x% (customizable), 5 points will be deducted, and the scoring is completed.

[0041] Scoring Rule 2: The scoring rules for the remaining life indicators of industrial robots include scoring based on the operating time of the industrial robot and the length of time until the specified scrapping time of the industrial robot. For example, for the service life of the robot, a custom life countdown is set, such as 12 months. For every month that passes, 1 / 12 of the score of the indicator is deducted (out of 100).

[0042] Scoring Rule 3: The scoring rules for the number of overhauls of industrial robots include scoring according to the number of overhauls of the industrial robots. For example, the number of major overhauls of the robot can be deducted (on a percentage basis). Based on the experience value, the judgment basis for major overhauls is determined, and each time an overhaul occurs, the corresponding custom score is deducted from the indicator.

[0043] Scoring according to the characteristics of different indicators can accurately calibrate the actual health status of each key indicator, laying the foundation for the accuracy of the subsequent overall evaluation of industrial robots.

[0044] S104: Use the analytic hierarchy process to calculate and analyze the weight of each key indicator in the health score: In this embodiment, the weight assignment of each key indicator in the health score is calculated using the AHP (Analytic Hierarchy Process).

[0045] AHP is a multi-index comprehensive evaluation algorithm. As the algorithm is simple and practical, it is widely used in business management or in real life. It generally has two uses: one is indicator weighting, and the other is quantitative solution selection.

[0046] The application of the hierarchical analysis method in this example mainly includes the following four main steps, as follows: S1. Constructing a hierarchical model: like Figure 4As shown, a hierarchical model is first constructed. In this embodiment, the hierarchy is divided into two layers, namely, a target layer and a criterion layer. The target layer is the robot health score, and the criterion layer is composed of 8 key indicators selected in step S102.

[0047] S2. Construct judgment matrix: The judgment matrix of this embodiment is constructed by comparing each element with each other and determining the weight of each criterion layer to the target layer. In simple terms, the indicators of the criterion layer are judged pairwise and given using Santy's 1-9 scale method. For details, please refer to Figure 5 , which describes in detail the Santy scale diagram of this example.

[0048] For the criterion layer A, we can construct a matrix:

[0049] The elements in A satisfy:

[0050] Simply put, for example, for the criterion layer: memory utilization, axis real-time current, axis operating temperature, load rate, energy consumption rate, coordinate positioning deviation, robot remaining life, robot major overhaul times, we can construct such a Figure 6 The 8*8 judgment matrix shown.

[0051] The diagonal line represents the judgment of each indicator. For example, the importance of "memory utilization" and "memory utilization" is 1, because the comparison between the indicators themselves is definitely 1:1. For the second row and the first column, that is, the comparison between "axis real-time current" and "memory utilization", in this embodiment, it is agreed that "axis real-time current" is obviously more important than "memory utilization", so the value can be 5 (see Figure 7 ).

[0052] for Figure 6 Each element in the judgment matrix of is further obtained by using the above-mentioned labeling method. Figure 8 The final criterion layer judgment matrix is ​​shown.

[0053] S3. Hierarchical single sorting and its consistency test.

[0054] Hierarchical single sorting and its consistency test The hierarchical single sorting and its consistency test is to determine the weight of the indicators. The specific process is as follows: Calculate the mth power of the product of each row of matrix A to obtain an m-dimensional vector (in this example, the value of m is 8):

[0055] Normalize the vector to get the weight vector, that is, the weight:

[0056] At the same time, the maximum characteristic root is solved, and its formula is:

[0057] According to the CI value formula, the CI value is calculated:

[0058] Solve the CR value based on the CI and RI values ​​to determine whether its consistency is passed.

[0059] The RI value table is as follows: Fig. 9 The following is the random consistency index obtained by Satty simulation 1000 times.

[0060] Therefore, when CR<0.1, it indicates that the consistency of the judgment matrix A is considered to be within the allowable range, and the eigenvector of A can be used to perform weight vector calculation.

[0061] S4. Hierarchical total ordering and consistency test: Because this example does not involve total hierarchical ranking and there is no decision-making layer, the weights of the eight indicator indexes can be obtained through the above steps, and this step is omitted.

[0062] S105: According to the weight of the key indicator and the score of each key indicator, a comprehensive calculation is performed to obtain the health score of the industrial robot: Finally, the robot health score is:

[0063] Among them, H represents the health score of the robot, Ei represents the score of each indicator, and Wi represents the indicator weight.

[0064] S106: Evaluate the health score of the industrial robot: According to the robot health scores obtained in the above steps, complete the health assessment. The assessment standards refer to:

[0065] In another embodiment, the above evaluation method is used to perform real-time health scoring of robots in the factory area, forming a real-time evaluation trend chart of the health of industrial robots. The trend chart can provide an overall understanding of the trend of the health of the managed robots, and can help managers to conduct early human intervention or maintenance for robots with continuously low health or downward trends, so as to discover problems as early as possible and prevent production accidents.

[0066] In one embodiment, Fig.11 As shown, the industrial robot health assessment method described in the above embodiment is used to manage multiple industrial robots in the jurisdiction at the same time, and the health scores of different industrial robots are statistically analyzed according to the time dimension to form a health trend chart of industrial robots in the jurisdiction. According to the chart, managers can grasp the health change trend of different industrial robots and compare the health differences of different industrial robots, which provides a basis for active health maintenance and facilitates the reasonable assignment of tasks according to the operating status of each robot. This trend chart can only be perfectly presented on the basis of the design concept of the present invention, and is a manifestation of effectively utilizing the industrial robot health management method of the present invention to improve the level of production management.

[0067] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0068] In one embodiment, corresponding to the real-time assessment method for the health of an industrial robot integrating multiple indicators described in the above embodiment, Fig.10 The structure block diagram of the real-time health evaluation device for industrial robots integrating multiple indicators provided by the embodiment of the present application is shown. For the sake of convenience, only the part related to the embodiment of the present application is shown. Fig.10 , the device comprises: The data acquisition module 801 is used to acquire data of various indicators of the industrial robot in real time; The key indicator screening module 802 is used to perform operation analysis on the indicators through a machine learning algorithm to screen and obtain multiple key indicators; The key indicator scoring module 803 is used to score the key indicators according to the collected key indicator data and the scoring rules of the key indicators to obtain the scores of the key indicators; The key indicator weight analysis module 804 is used to calculate and analyze the weight of each key indicator in the health score using the hierarchical analysis method; A health score module 805 is used to obtain a health score of the industrial robot by comprehensive calculation according to the weight of the key indicators and the scores of each key indicator; The health evaluation module 806 is used to evaluate the health score of the industrial robot and obtain a health evaluation result of the industrial robot.

[0069] This embodiment can make full use of the data collection capabilities of current and future advanced industrial robot ancillary equipment by using effective and reasonable algorithms, and summarize and organize the above-mentioned large number of data indicators with different attributes, different standards, and different sources, so that not only can multi-dimensional data indicators be used in the evaluation system, but also the results of health analysis are very accurate. This method perfectly solves the shortcomings of existing passive operation and maintenance management methods for industrial robots in terms of prevention and prediction, improves the level of health management of industrial robots, and provides a basis for proactive operation and maintenance management with the goal of predicting risk issues in advance. It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0070] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0071] An embodiment of the present application further provides a target device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in any of the above-mentioned method embodiments when executing the computer program.

[0072] This embodiment makes full use of the comprehensive industrial robot data collection capabilities of the present and future, and collects various data generated by the industrial robot during production and operation in real time, thereby achieving the comprehensiveness of the industrial robot health assessment indicators; the algorithm of this application summarizes and organizes the above-mentioned large number of data indicators with different attributes, different standards, and different sources, and screens out the key indicators that affect the health of the industrial robot, thereby achieving the economy of the health assessment of the industrial robot; then further uses the hierarchical analysis method to perform a comprehensive calculation on the weights of the key indicators and the scores obtained according to the scoring rules of each key indicator to obtain a health score as a measure of the health of the industrial robot, thereby achieving the accuracy of the health assessment of the industrial robot.

[0073] By using effective and reasonable algorithms, we can make full use of the data collection capabilities of current and future advanced industrial robot ancillary equipment, summarize and organize the above-mentioned large number of data indicators with different attributes, different standards, and different sources, so that not only can multi-dimensional data indicators be used in the evaluation system, but also this dynamic key indicator management makes the results of health analysis very accurate. This method perfectly solves the shortcomings of the existing passive operation and maintenance management methods for industrial robots in terms of prevention and predictiveness, improves the producer's industrial robot health management level, and provides a basis for proactive operation and maintenance management with the goal of predicting risk issues in advance.

[0074] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0075] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0076] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / target device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0077] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0078] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0079] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0080] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A real-time evaluation method for the health of an industrial robot integrating multiple indicators, characterized in that: The method comprises: Collect and obtain data on various indicators of industrial robots in real time; The indicators are analyzed and calculated using a machine learning algorithm to screen out multiple key indicators that affect the health of the industrial robot; Scoring the key indicators according to the collected data of the key indicators and the scoring rules of the key indicators to obtain scores of the key indicators; Use the analytic hierarchy process to calculate and analyze the weight of each key indicator in the health score; According to the weight of the key indicators and the scores of the key indicators, a comprehensive calculation is performed to obtain a health score of the industrial robot; The health score of the industrial robot is evaluated to obtain a health assessment result of the industrial robot.

2. The real-time assessment method for the health of an industrial robot integrating multiple indicators as claimed in claim 1 is characterized in that: The machine learning algorithm includes using the XGBosst algorithm to evaluate the indicators and screen out key indicators. The formula is: ,in is the loss function, and its parameters are the true value and predicted value of the sample data, Indicates complexity.

3. The real-time assessment method for the health of an industrial robot integrating multiple indicators as claimed in claim 1 is characterized in that: The key indicators include key operating indicators of the industrial robot, and the scoring rules include scoring based on the degree of deviation from the rated value of the real-time data of the key operating indicators collected when the industrial robot is running; And / or scoring is performed based on the degree of deviation between the real-time data and an operating baseline of the industrial robot under normal operation.

4. The real-time assessment method for the health of an industrial robot integrating multiple indicators as claimed in claim 3 is characterized in that: The key operating indicators of the industrial robot include: memory utilization, and / or axis real-time current, and / or axis operating temperature, and / or robot arm load rate, and / or energy consumption rate, and / or coordinate positioning deviation.

5. The real-time assessment method for the health of an industrial robot integrating multiple indicators as claimed in claim 1 is characterized in that: The key indicator includes a remaining life indicator of the industrial robot, and the scoring rule includes scoring according to the operating time of the industrial robot and the length of time until the specified scrapping time of the industrial robot.

6. The real-time assessment method for the health of an industrial robot integrating multiple indicators as claimed in claim 1 is characterized in that: The key indicator includes the number of overhauls of the industrial robot, and the scoring rule includes scoring according to the number of overhauls of the industrial robot.

7. The real-time assessment method for the health of an industrial robot integrating multiple indicators as claimed in any one of claims 3 to 6, characterized in that: The calculation formula of the health score is expressed as: Among them, H represents the health score of the robot, Ei represents each indicator, and Wi represents the indicator weight.

8. A real-time health evaluation device for industrial robots integrating multiple indicators, characterized in that: The device comprises: Data acquisition module, used to collect data of various indicators of industrial robots in real time; A key indicator screening module is used to perform calculation and analysis on the indicators through a machine learning algorithm to screen out multiple key indicators that affect the health of the industrial robot; A key indicator scoring module is used to score the key indicators according to the collected key indicator data and the scoring rules of the key indicators to obtain the scores of the key indicators; The key indicator weight analysis module is used to calculate and analyze the weight of each key indicator in the health score using the hierarchical analysis method; A health score module, used for obtaining a health score of the industrial robot by comprehensive calculation based on the weights of the key indicators and the scores of the key indicators; The health evaluation module is used to evaluate the health score of the industrial robot and obtain the health evaluation result of the industrial robot.

9. A target device, characterized in that: The target device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for real-time assessment of the health of an industrial robot integrating multiple indicators as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for real-time assessment of the health of an industrial robot integrating multiple indicators as described in any one of claims 1 to 7 is implemented.

Images