An intelligent diagnosis system for robot rotation units

Through integrated energy field analysis, infrared thermal image analysis, micro deformation recognition and finite element methods, potential faults of the rotating unit are identified and performance optimized, solving the problem of insufficient fault recognition in traditional technology, and achieving high efficiency of the rotating unit Reliable operation.

CN118734662BActive Publication Date: 2024-11-12JIANGSU XINAI LUO TECH R & D CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411233977.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-04
Publication Date
2024-11-12
Estimated Expiration
2044-09-04

AI Technical Summary

Technical Problem

Traditional intelligent fault diagnosis technology has shortcomings in timely identifying tiny deformations and early performance degradation, and cannot effectively warn and prevent potential faults and safety risks, resulting in increased downtime and maintenance costs of the robot rotating unit.

Method used

The energy field analysis module, infrared thermal image analysis module, micro deformation identification module, performance impact assessment module, fault mode identification module, optimization strategy formulation module and real-time monitoring and adjustment module are adopted, and through simulation analysis, temperature monitoring, digital image processing, limited Meta-methods, gradient descent methods and other technologies monitor and optimize the performance of the rotating unit in real time, identify potential failure modes and formulate optimization strategies.

Benefits of technology

It significantly improves the monitoring and diagnosis capabilities of the rotating unit, can identify potential faults early, reduce downtime and maintenance costs, and ensures efficient and reliable operation of the robot system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118734662B_ABST
    Figure CN118734662B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of intelligent fault diagnosis technology, specifically to an intelligent diagnosis system for a robot rotating unit, which includes an energy field analysis module, an infrared thermal imaging analysis module, a micro-deformation recognition module, a performance impact assessment module, a fault mode identification module, an optimization strategy formulation module, and a real-time monitoring and adjustment module. In the present invention, by integrating advanced data analysis and simulation technologies, the monitoring and diagnosis capabilities of the rotating unit are significantly improved, and judgment logic is introduced, such as structural deformation analysis and precision degradation warning based on temperature anomalies, which can identify small deformations and performance degradation signs that may lead to serious faults at an early stage, and at the same time, the gradient descent method is used to optimize the design and working parameters, and the fault mode is specifically solved, and then through real-time monitoring and dynamic adjustment, the performance of the rotating unit is continuously optimized to ensure the efficient and reliable operation of the robot system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent fault diagnosis, and in particular to an intelligent diagnosis system for a robot rotation unit. Background Art

[0002] The field of intelligent fault diagnosis technology focuses on using advanced data analysis, machine learning, artificial intelligence algorithms, and signal processing technologies to monitor, predict, diagnose, and prevent faults in mechanical equipment and systems in real time. The core goal is to improve equipment reliability and efficiency, reduce unexpected downtime, and reduce maintenance costs. In robotics, especially for robotic systems that rely on precise rotating units to perform operations, the application of intelligent fault diagnosis technology is particularly critical. It can analyze data from rotating units (such as vibration signals, temperature readings, and motor currents) to identify potential signs of failure, thereby providing early warning and intervention before the problem becomes a serious failure.

[0003] Among them, the Robot Rotary Unit Intelligent Diagnosis System is an advanced system specially designed to monitor and diagnose potential faults in the robot's rotary unit (such as joints, gearboxes and drive motors). Its main purpose is to maximize the robot's operating efficiency and reliability through real-time performance monitoring and fault analysis. By detecting signs of failure early, the system aims to prevent failures from occurring, thereby reducing the robot's downtime and maintenance costs, and helping to improve the safety and production efficiency of the production line, because problems with the rotary unit can be identified and resolved in a timely manner, avoiding potential safety risks and production delays.

[0004] Traditional intelligent fault diagnosis technology has obvious shortcomings in timely identifying minor deformations and early performance degradation. Analysis and processing usually begin only after a fault occurs. The delayed fault handling mechanism cannot effectively prevent the occurrence of faults, increasing the system's downtime and maintenance costs. There is a lack of real-time response to early signs of faults, especially early warning of structural deformation and decreased rotation accuracy caused by abnormal temperature, which makes it impossible to prevent potential faults and safety risks, thereby affecting production efficiency and safety. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an intelligent diagnosis system for a robot rotation unit.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A robot rotation unit intelligent diagnosis system comprises:

[0007] The energy field analysis module simulates and analyzes the electromagnetic field and mechanical vibration energy field, captures the comprehensive impact on the performance of the rotating unit, analyzes the temperature changes caused by the electromagnetic field when the motor is working, and the effects of vibration energy on bearings and gears, and obtains the energy field analysis results;

[0008] The infrared thermal imaging analysis module uses infrared thermal imaging technology to perform real-time temperature monitoring on the rotating unit based on the temperature change data in the energy field analysis result, analyzes the temperature distribution and its change trend, and obtains a temperature anomaly distribution map;

[0009] The micro-deformation recognition module analyzes the motion trajectory and micro-deformation corresponding to the temperature anomaly distribution map based on the motion image of the rotating unit captured by the high-speed camera through digital image processing technology, determines whether the temperature anomaly causes structural deformation, and generates a micro-deformation index;

[0010] The performance impact assessment module uses the finite element method to analyze the impact of micro-deformation on the performance of the rotation unit based on the micro-deformation index, including the reduction of rotation accuracy and material fatigue, predicts the long-term impact of micro-deformation on the overall performance, and obtains a performance impact assessment record;

[0011] The fault mode identification module identifies potential fault modes of the rotating unit based on the performance impact assessment record, including bearing damage or gear wear caused by motor overheating, and obtains a fault mode identification result;

[0012] The optimization strategy formulation module uses a gradient descent method based on the fault mode identification result to adjust the design parameters and operating parameters, including optimizing the motor winding layout and adjusting the bearing material selection, to obtain a performance optimization strategy solution;

[0013] The real-time monitoring and adjustment module implements real-time monitoring and dynamic adjustment of the rotating unit based on the performance optimization strategy, optimizes the performance of the rotating unit in real time by adjusting the working parameters, and generates an optimized operation record of the rotating unit.

[0014] As a further solution of the present invention, the energy field analysis results include electromagnetic field intensity distribution, vibration energy spectrum, and energy field interaction points; the temperature anomaly distribution diagram includes the position of the highest temperature point, the average temperature value, and the temperature distribution unevenness index; the micro-deformation index includes the specific value of the deformation amount, the area of ​​the affected area, and the deformation trend type; the performance impact assessment record specifically refers to the percentage of operating efficiency decrease and the change of key performance parameters; the fault mode identification results include the fault name, fault impact level, and a list of potential fault causes; the performance optimization strategy scheme specifically includes the recommended replacement component type and the expected performance improvement range; the rotating unit optimization operation record includes the real-time data update frequency and a list of executed adjustment measures.

[0015] As a further solution of the present invention, the energy field analysis module includes an electromagnetic field simulation submodule, a vibration energy analysis submodule, and an impact analysis submodule;

[0016] The electromagnetic field simulation submodule performs electromagnetic field simulation analysis based on the input current and voltage parameters of the motor when it is working, simulates the distribution and intensity of the electromagnetic field under different operating conditions, and obtains an electromagnetic field distribution diagram;

[0017] The vibration energy analysis submodule analyzes the influence of mechanical vibration caused by the electromagnetic field on the rotating unit including bearings and gears based on the electromagnetic field distribution diagram, simulates the vibration frequency and energy transfer, and obtains the vibration energy influence record;

[0018] The impact analysis submodule is based on the vibration energy impact record, combined with the temperature change caused by the electromagnetic field and the effect of the vibration energy on the bearing and gear, to reveal the overall impact on the performance of the rotating unit and obtain the energy field analysis result.

[0019] As a further solution of the present invention, the infrared thermal image analysis module includes a temperature data capture submodule, a temperature distribution analysis submodule, and an abnormal trend identification submodule;

[0020] The temperature data capture submodule uses infrared thermal imaging technology to perform real-time temperature monitoring on the rotating unit according to the temperature change data in the energy field analysis result, captures the real-time temperature data of the rotating unit surface, and obtains the real-time temperature index;

[0021] The temperature distribution analysis submodule analyzes the temperature distribution of the entire rotating unit based on the real-time temperature index, identifies the uniformity of the temperature distribution and the abnormally high temperature area, and generates the temperature distribution analysis result;

[0022] The abnormal trend identification submodule identifies abnormal patterns in the temperature change trend based on the temperature distribution analysis results, including areas with sharp temperature rise or sustained high temperature, determines the actual location and potential trend of the temperature anomaly, and obtains a temperature anomaly distribution map.

[0023] As a further solution of the present invention, the micro-deformation recognition module includes an image capture submodule, an image processing submodule, and a deformation judgment submodule;

[0024] The image capture submodule is based on a high-speed camera to capture the motion image of the rotating unit in a working state, ensure image clarity, and obtain a high-speed motion image set;

[0025] The image processing submodule uses digital image processing technology to perform contrast enhancement and edge detection based on the high-speed motion image set. If the image shows an obvious temperature abnormality area, the image features of the area are extracted to generate a temperature abnormality image feature set.

[0026] The deformation judgment submodule is based on the temperature anomaly image feature set and the temperature anomaly distribution map, and compares and analyzes the slight deformation in the image by setting a threshold. If the feature change exceeds the threshold, it is judged as structural deformation, otherwise it is marked as no obvious deformation, and a slight deformation index is obtained.

[0027] As a further solution of the present invention, the performance impact assessment module includes a deformation impact analysis submodule, a rotation accuracy assessment submodule, and a material fatigue prediction submodule;

[0028] The deformation impact analysis submodule uses the finite element method to simulate the influence of small deformation on the rotating unit structure based on the small deformation index, analyzes the stress and strain distribution in the deformation area, and generates the deformation impact analysis results;

[0029] The finite element method, according to the formula:

[0030] s = E ( T f a c t o r , D f a c t o r ) e ( L r a t e , A f a c t o r ) ( 1 + n ( T f a c t o r ) ) ( 1 − 2 n ( T f a c t o r ) ) [ 1 − n n n n 1 − n n n n 1 − n ] e

[0031] Calculate the stress and strain distribution of the structure after a small deformation and generate deformation effect analysis results, where: is the elastic modulus, is Poisson's ratio, is stress, For strain, is the temperature influence factor, is the minor defect coefficient, is the loading rate, is the material anisotropy coefficient;

[0032] The rotation accuracy assessment submodule assesses the influence of small deformation on the rotation accuracy of the rotation unit based on the deformation influence analysis result, calculates the extent of the accuracy reduction, and if the accuracy reduction exceeds a preset threshold, it is marked as performance degradation, and a rotation accuracy reduction assessment record is obtained;

[0033] The material fatigue prediction submodule predicts the material fatigue life caused by small deformation based on the rotation accuracy degradation assessment record, applies material fatigue theory, analyzes the performance degradation degree after long-term operation, and obtains the performance impact assessment record.

[0034] As a further solution of the present invention, the fault mode identification module includes a performance data analysis submodule, a potential fault identification submodule, and a fault mode classification submodule;

[0035] The performance data analysis submodule analyzes the performance of the rotating unit under different working conditions based on the performance impact assessment record, identifies abnormal working conditions with large performance deviations, and generates a performance deviation data set;

[0036] The potential fault identification submodule reveals the potential fault factors corresponding to the performance deviation according to the performance deviation data set by comparing the historical fault data with the fault mode library, and obtains a list of potential fault factors;

[0037] The fault mode classification submodule classifies the fault factors based on the potential fault factor list and matches them with the fault mode. If the match is successful, the fault mode is determined to obtain a fault mode recognition result.

[0038] As a further solution of the present invention, the optimization strategy formulation module includes a parameter adjustment submodule, a winding layout optimization submodule, and a material selection evaluation submodule;

[0039] The parameter adjustment submodule uses a gradient descent method to make preliminary adjustments to the operating parameters of the rotating unit based on the fault mode recognition result, including current and voltage settings, to reduce the possibility of fault occurrence and obtain a preliminary adjustment parameter set;

[0040] The gradient descent method, according to the formula:

[0041]

[0042] Calculate the working parameter adjustment of the rotating unit and obtain the preliminary adjustment parameter set, where: is the parameter set after the next iteration, is the parameter set of the current iteration, is the learning rate, is the cost function About parameters The gradient of is the current setting, For voltage setting, is the rotation speed, is the working temperature, are the weight coefficients of current, voltage, rotation speed, and temperature;

[0043] The winding layout optimization submodule optimizes the layout of the motor windings based on the preliminary adjustment parameter set, and generates a winding layout optimization plan by simulating the impact of different layouts on performance, avoiding motor overheating problems caused by improper winding layouts;

[0044] The material selection and evaluation submodule analyzes and selects the optimal bearing and gear materials based on the winding layout optimization scheme, improves the wear resistance of the rotating unit and reduces fatigue damage, and obtains a performance optimization strategy scheme.

[0045] As a further solution of the present invention, the real-time monitoring and adjustment module includes a performance monitoring submodule, a dynamic adjustment submodule, and an optimization effect analysis submodule;

[0046] The performance monitoring submodule implements real-time performance monitoring of the rotating unit based on the performance optimization strategy scheme to continuously monitor key indicators, including temperature, vibration frequency and motor load, capture performance fluctuations and abnormal conditions, and obtain real-time performance monitoring data;

[0047] The dynamic adjustment submodule is based on real-time performance monitoring data. If it is detected that the performance deviation exceeds the preset range, the working parameters are dynamically adjusted by the gradient descent method immediately, including adjusting the current intensity or changing the type of bearing lubricant, and generating parameter adjustment records;

[0048] The optimization effect analysis submodule analyzes the performance changes of the rotating unit after dynamic adjustment based on the parameter adjustment record, compares the operating efficiency, stability and durability before and after the adjustment, verifies the effectiveness of the optimization measures, and obtains the optimized operation record of the rotating unit.

[0049] Compared with the prior art, the advantages and positive effects of the present invention are:

[0050] In the present invention, by integrating advanced data analysis and simulation technologies, the monitoring and diagnostic capabilities of the rotating unit are significantly improved, and judgment logic is introduced, such as structural deformation analysis and accuracy degradation warning based on temperature anomalies, which can identify small deformations and performance degradation signs that may lead to serious failures at an early stage. At the same time, the gradient descent method is used to optimize the design and operating parameters, and the failure mode is solved in a targeted manner. Then, through real-time monitoring and dynamic adjustment, the performance of the rotating unit is continuously optimized to ensure the efficient and reliable operation of the robot system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a system flow chart of the present invention;

[0052] Figure 2 It is a schematic diagram of the system framework of the present invention;

[0053] Figure 3 This is a flow chart of the energy field analysis module of the present invention;

[0054] Figure 4 This is a flow chart of the infrared thermal imaging analysis module of the present invention;

[0055] Figure 5 It is a flow chart of the micro-deformation recognition module of the present invention;

[0056] Figure 6 It is a flow chart of the performance impact assessment module of the present invention;

[0057] Figure 7 This is a flow chart of the fault mode identification module of the present invention;

[0058] Figure 8Formulate a module flow chart for the optimization strategy of the present invention;

[0059] Figure 9 It is a flow chart of the real-time monitoring and adjustment module of the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. Embodiment 1

[0062] See also Figure 1 and Figure 2 ,A robot rotation unit intelligent diagnosis system includes an energy field analysis module, an infrared thermal image analysis module, a micro-deformation recognition module, a performance impact evaluation module, a fault mode identification module, an optimization strategy formulation module, and a real-time monitoring and adjustment module;

[0063] The energy field analysis module simulates and analyzes the electromagnetic field and mechanical vibration energy field, captures the comprehensive impact on the performance of the rotating unit, analyzes the temperature changes caused by the electromagnetic field when the motor is working, and the effects of vibration energy on bearings and gears, and obtains the energy field analysis results;

[0064] The infrared thermal imaging analysis module uses infrared thermal imaging technology to monitor the temperature of the rotating unit in real time based on the temperature change data in the energy field analysis results, analyze the temperature distribution and its change trend, and obtain the temperature anomaly distribution map;

[0065] The micro-deformation recognition module uses digital image processing technology to analyze the motion trajectory and micro-deformation corresponding to the temperature anomaly distribution map based on the motion image of the rotating unit captured by the high-speed camera, determines whether the temperature anomaly causes structural deformation, and generates micro-deformation indicators;

[0066] The performance impact assessment module uses the finite element method to analyze the impact of micro-deformation on the performance of the rotation unit based on the micro-deformation index, including the reduction of rotation accuracy and material fatigue, predicts the long-term impact of micro-deformation on the overall performance, and obtains the performance impact assessment record;

[0067] The fault mode identification module identifies potential fault modes of the rotating unit based on the performance impact assessment records, including bearing damage or gear wear caused by motor overheating, and obtains fault mode identification results;

[0068] The optimization strategy formulation module uses the gradient descent method to adjust the design parameters and operating parameters based on the fault pattern recognition results, including optimizing the motor winding layout and adjusting the bearing material selection to obtain a performance optimization strategy solution;

[0069] The real-time monitoring and adjustment module implements real-time monitoring and dynamic adjustment of the rotating unit based on the performance optimization strategy. By adjusting the working parameters, the performance of the rotating unit is optimized in real time and the optimized operation record of the rotating unit is generated.

[0070] The energy field analysis results include the electromagnetic field intensity distribution, vibration energy spectrum, and energy field interaction points. The temperature anomaly distribution diagram includes the location of the highest temperature point, the average temperature value, and the temperature distribution unevenness index. The micro-deformation index includes the specific value of the deformation, the area of ​​the affected area, and the type of deformation trend. The performance impact assessment record specifically refers to the percentage of operating efficiency decrease and the change of key performance parameters. The fault mode identification results include the fault name, fault impact level, and a list of potential fault causes. The performance optimization strategy plan specifically includes the recommended replacement component type and the expected performance improvement range. The rotating unit optimization operation record includes the real-time data update frequency and a list of implemented adjustment measures.

[0071] See also Figure 2 and Figure 3 ,The energy field analysis module includes an electromagnetic field simulation submodule, a vibration energy analysis submodule, and an impact analysis submodule;

[0072] The electromagnetic field simulation submodule performs electromagnetic field simulation analysis based on the input current and voltage parameters of the motor when it is working, simulates the distribution and intensity of the electromagnetic field under different operating conditions, and obtains the electromagnetic field distribution diagram;

[0073] In the energy field analysis module, the electromagnetic field simulation submodule uses Ansys Maxwell software to simulate and analyze the electromagnetic field based on the input current and voltage parameters of the motor when it is working. The current input range is set to 0-10A and the voltage input range is set to 0-220V. The distribution and intensity changes of the electromagnetic field under different working conditions are analyzed. The grid division accuracy is adjusted to 0.1mm to improve the accuracy of the simulation results and generate an electromagnetic field distribution map.

[0074] The vibration energy analysis submodule analyzes the impact of mechanical vibration caused by electromagnetic field on rotating units including bearings and gears based on the electromagnetic field distribution diagram, simulates vibration frequency and energy transfer, and obtains vibration energy impact records;

[0075] The vibration energy analysis submodule is based on the electromagnetic field distribution diagram and uses vibration analysis software (such as the VibraImage system) to set the vibration sampling frequency to 1000 Hz and the sampling time to 10 seconds. It analyzes the vibration frequency and energy transfer of the rotating unit caused by the change in the electromagnetic field, simulates the forces on the bearings and gears, and sets the vibration energy transfer threshold to 5J. If the vibration energy exceeds this value, it is recorded as significant vibration, and a vibration energy impact record is obtained.

[0076] The impact analysis submodule is based on the vibration energy impact record, combined with the temperature changes caused by the electromagnetic field and the effects of vibration energy on bearings and gears, to reveal the overall impact on the performance of the rotating unit and obtain the energy field analysis results;

[0077] The impact analysis submodule is based on the vibration energy impact record and adopts the multi-physics field coupling analysis method (COMSOL Multiphysics software). Combined with the temperature change data caused by the electromagnetic field, the temperature analysis range is set to -20°C to 120°C. The impact of electromagnetic field and mechanical vibration energy on bearings and gears is comprehensively analyzed. By setting the time step of the physical field interaction analysis to 0.01 seconds, the changes in the energy field in the transient process are captured, the overall impact on the performance of the rotating unit is revealed, and the energy field analysis results are generated.

[0078] See also Figure 2 and Figure 4 ,The infrared thermal image analysis module includes a temperature data capture ,submodule, a temperature distribution analysis submodule, and an ,abnormal trend identification submodule;

[0079] The temperature data capture submodule uses infrared thermal imaging technology to monitor the real-time temperature of the rotating unit based on the temperature change data in the energy field analysis results, captures the real-time temperature data of the rotating unit surface, and obtains the real-time temperature index;

[0080] In the temperature data capture submodule, based on the energy field analysis results of the rotating unit, infrared thermal imaging technology is used. The FLIR toolkit is used to connect to the infrared thermal imaging instrument. The data capture frequency is set to 10 frames per second and the resolution is set to 640x480. The rotating unit is scanned continuously to capture the radiation energy of each pixel. The radiation energy is converted into a temperature value through the Planck law conversion algorithm. The emissivity is set to 0.95 and the ambient temperature is preset to 25°C. The temperature data on the surface of the rotating unit is calculated in real time to generate a real-time temperature index.

[0081] The temperature distribution analysis submodule analyzes the temperature distribution of the entire rotating unit based on real-time temperature indicators, identifies the uniformity of temperature distribution and abnormally high temperature areas, and generates temperature distribution analysis results;

[0082] In the temperature distribution analysis submodule, based on the real-time temperature index, the hotspot analysis algorithm is adopted, and the temperature data is processed using Python language combined with the NumPy library. First, the temperature data is spatially interpolated, and the RBF (radial basis function) interpolation method is used with the parameter set to ε=1.5 to obtain a continuous temperature field. Then, the Getis-Ord Gi statistical method in the hotspot analysis algorithm is applied with the parameter set to a neighborhood distance of 50 pixels to identify the uniformity of the temperature distribution and abnormally high temperature areas. This process does not involve data cleaning or feature extraction commands to generate temperature distribution analysis results.

[0083] The abnormal trend identification submodule identifies abnormal patterns in the temperature change trend based on the temperature distribution analysis results, including areas with sharp temperature rise or sustained high temperature, determines the actual location and potential trend of temperature anomalies, and obtains a temperature anomaly distribution map;

[0084] In the abnormal trend identification submodule, based on the temperature distribution analysis results, an anomaly detection algorithm is adopted. The Isolation Forest algorithm is implemented using Python language combined with the Scikit-learn library. The parameters are set to 100 trees and 256 sampling sizes. This algorithm constructs a random tree forest to isolate abnormal temperature points and identify them as points with abnormal trends. Based on the distribution of these points, the least squares linear regression is applied. The response variable is preset as temperature value and the explanatory variable is time. Abnormal patterns in temperature change trends, such as a sharp rise in temperature or a continuous high temperature area, are identified to generate a temperature anomaly distribution map.

[0085] See also Figure 2 and Figure 5 ,The micro-deformation recognition module includes an image capturing submodule, an image processing submodule, and a deformation judging submodule;

[0086] The image capture submodule is based on a high-speed camera to capture the motion image of the rotating unit in the working state, ensure the image clarity, and obtain a high-speed motion image set;

[0087] In the image capture submodule, based on a high-speed camera, the camera parameters are set to a shooting speed of 1000 frames per second, a resolution of 1920x1080, a CMOS sensor, and an aperture of f / 2.8 to ensure sufficient light passing through. A continuous shooting mode is adopted to capture the motion image of the rotating unit in the working state. The autofocus technology is used to maintain the clarity of the image at different speeds. The image data is stored in JPEG format to generate a high-speed motion image set.

[0088] The image processing submodule uses digital image processing technology to perform contrast enhancement and edge detection based on the high-speed motion image set. If the image shows an obvious temperature abnormality area, the image features of the area are extracted to generate a temperature abnormality image feature set.

[0089] In the image processing submodule, based on the high-speed motion image set, digital image processing technology is used. First, the cv2.equalizeHist() function in the OpenCV library is applied for contrast enhancement. This function equalizes the histogram of each image. Then the Canny edge detection algorithm is used, and the double thresholds are set to 100 and 200. The Gaussian filter is used with a kernel size of 5x5 to reduce image noise. After edge detection, if the image shows obvious temperature abnormality areas, the SURF algorithm is used, and the Hessian threshold is set to 400. The key points and descriptors of the area are detected and extracted to generate a temperature abnormality image feature set.

[0090] The deformation judgment submodule is based on the temperature anomaly image feature set and the temperature anomaly distribution map. It compares and analyzes the slight deformation in the image by setting a threshold. If the feature change exceeds the threshold, it is judged as structural deformation. Otherwise, it is marked as no obvious deformation, and the slight deformation index is obtained.

[0091] In the deformation judgment submodule, based on the temperature anomaly image feature set and the temperature anomaly distribution map, a machine learning algorithm, especially a support vector machine (SVM), is used. The svm.SVC() function in the Scikit-learn library is used, the kernel function is set to the radial basis function (RBF), the penalty parameter C is set to 1.0, the data set is segmented by the cross-validation method, and the model is trained. The temperature anomaly image feature set is used as input, and the threshold between deformation and non-deformation is set to a temperature change of more than 2°C. The SVM model is used to compare and analyze the slight deformation in the image. If the feature change exceeds the threshold, it is judged as structural deformation, otherwise it is marked as no obvious deformation, and a slight deformation index is generated.

[0092] See also Figure 2 and Figure 6 ,The performance impact evaluation module includes the deformation impact analysis submodule, the rotation accuracy evaluation submodule, and the material fatigue prediction submodule;

[0093] The deformation impact analysis submodule uses the finite element method to simulate the impact of small deformation on the rotating unit structure based on the small deformation index, analyzes the stress and strain distribution in the deformation area, and generates deformation impact analysis results;

[0094] Finite element method, according to the formula:

[0095] s = E ( T f a c t o r , D f a c t o r ) e ( L r a t e , A f a c t o r ) ( 1 + n ( T f a c t o r ) ) ( 1 − 2 n ( T f a c t o r ) ) [ 1 − n n n n 1 − n n n n 1 − n ] e

[0096] Calculate the stress and strain distribution of the structure after a small deformation and generate deformation effect analysis results, where: is the elastic modulus, which indicates the material's ability to resist deformation when subjected to external forces. Poisson's ratio describes the ratio of transverse strain to longitudinal strain when the material is subjected to axial stress. Stress is the distribution of forces inside the material that resist deformation caused by external forces. is strain, the ratio of the deformation of the material after being subjected to force to its original size. is the temperature influence factor, which reflects the influence of temperature change on the elastic modulus and Poisson’s ratio of the material. is the micro defect coefficient, which indicates the influence of micro defects inside the material on its elastic modulus and Poisson’s ratio. The loading rate refers to the rate at which the loading (force) changes over time, which affects the strain response of the material. is the material anisotropy coefficient, which describes the degree of difference in the properties of the material (such as elastic modulus and Poisson's ratio) in different directions.

[0097] The execution process is as follows:

[0098] Parameter collection and analysis, first, collect relevant material properties such as elastic modulus through experiments and literature research and Poisson's ratio Temperature dependent data, as well as the effects of small defects, loading rates and anisotropy of the material.

[0099] Determination of weight coefficient, for temperature influence factor and micro defect coefficient The collected data were used to determine their effects on the elastic modulus through regression analysis. and Poisson's ratio The influence weight of and the material anisotropy coefficient The experimental data also determine their effect on strain The influence weight of .

[0100] In the application of the model, the parameters and weight coefficients are substituted into the improved formula for calculation, and the finite element analysis is performed to simulate the influence of small deformation on the rotating unit structure and obtain the stress and strain distribution.

[0101] In this way, creative parameters are introduced and the improved formula takes into account more practical influencing factors, which can more accurately predict the performance of the rotating unit structure in actual environment.

[0102] The rotation accuracy assessment submodule assesses the impact of small deformations on the rotation accuracy of the rotation unit based on the deformation impact analysis results, and calculates the extent of the accuracy drop. If the accuracy drop exceeds a preset threshold, it is marked as performance degradation, and a rotation accuracy drop assessment record is obtained;

[0103] In the rotation accuracy evaluation submodule, based on the deformation influence analysis results, the error analysis method is adopted, and MATLAB software is used for calculation. A script is written to calculate the difference between the theoretical rotation center offset and the actual measured value of the rotation unit at different rotation speeds. The rotation speed range is set to 1000 to 3000 rpm, and the calculation is performed every 500 rpm. If the accuracy drops by more than the preset threshold, the preset threshold is set to 0.01 mm of rotation center offset, then it is marked as performance degradation, and the rotation accuracy degradation evaluation record is obtained.

[0104] The material fatigue prediction submodule uses the material fatigue theory to predict the material fatigue life caused by small deformation based on the rotation accuracy degradation assessment record, analyzes the performance degradation degree after long-term operation, and obtains the performance impact assessment record;

[0105] In the material fatigue prediction submodule, based on the rotation accuracy degradation evaluation record, the material fatigue theory is used to calculate using the Paris law, and the script is written in Python language to set the material fatigue crack extension parameter C to 1.25×10 -10 m / cycle and m are 3.2. By analyzing the maximum stress intensity factor range and crack growth rate of the rotating unit, the crack propagation life is calculated, and the performance impact assessment record is obtained by considering the performance degradation degree of the rotating unit after long-term operation.

[0106] See also Figure 2 and Figure 7 ,The fault mode identification module includes a performance data analysis submodule, a potential fault identification submodule, and a fault mode classification submodule;

[0107] The performance data analysis submodule analyzes the performance of the rotating unit under different working conditions based on the performance impact assessment records, identifies abnormal working conditions with large performance deviations, and generates a performance deviation data set;

[0108] In the performance data analysis submodule, based on the performance impact assessment records, the statistical analysis method is used to process the performance data using the Pandas library in Python. First, the performance impact assessment record file is read and the data is stored in the DataFrame structure. Then, the data is grouped according to different working conditions using the groupby method. The standard deviation of the performance indicator is calculated for each group of data using the std method, and the mean value is calculated using the mean method. The performance deviation threshold is set to twice the standard deviation, and the working conditions with a standard deviation greater than the threshold are screened out to generate a performance deviation data set.

[0109] The potential fault identification submodule reveals the potential fault factors corresponding to the performance deviation based on the performance deviation data set by comparing the historical fault data and the fault mode library, and obtains a list of potential fault factors;

[0110] In the potential fault identification submodule, based on the performance deviation data set, a pattern matching algorithm is adopted and implemented using the Scikit-learn library in Python. The historical fault data and fault pattern library are loaded, and the performance deviation data set is used as input. The K nearest neighbor algorithm is used, and the number of neighbors is set to 5. The Euclidean distance between each data item in the performance deviation data set and each data item in the historical fault data is calculated, and the five historical fault data items with the closest distance are selected. According to the majority voting principle, the potential fault factors corresponding to the performance deviation are revealed, and a list of potential fault factors is obtained.

[0111] The fault mode classification submodule classifies the fault factors based on the potential fault factor list and matches them with the fault mode. If the match is successful, the fault mode is determined and the fault mode recognition result is obtained;

[0112] In the fault mode classification submodule, based on the list of potential fault factors, a cluster analysis method is adopted. The K-means algorithm is executed using the Scikit-learn library in Python. The number of clusters is set to the number of fault modes in the fault mode library. The initialization method selects K-means++, and the maximum number of iterations is set to 300. Cluster analysis is performed on the list of potential fault factors. Each potential fault factor is assigned to the nearest cluster center according to its characteristics. These cluster centers correspond to the fault modes in the fault mode library. If the potential fault factor is successfully assigned to a cluster, the fault mode corresponding to the potential fault factor is determined, and the fault mode recognition result is obtained.

[0113] See also Figure 2 and Figure 8 ,The optimization strategy formulation module includes the parameter adjustment submodule, the winding layout optimization submodule, and the material selection evaluation submodule;

[0114] Based on the fault pattern recognition results, the parameter adjustment submodule uses the gradient descent method to make preliminary adjustments to the operating parameters of the rotating unit, including current and voltage settings, to reduce the possibility of faults and obtain a preliminary adjustment parameter set;

[0115] Gradient descent method, according to the formula:

[0116]

[0117] Calculate the working parameter adjustment of the rotating unit and obtain the preliminary adjustment parameter set, where: is the parameter set after the next iteration, including the current and voltage The latest settings, is the parameter set for the current iteration, including the current and voltage The current settings, is the learning rate, which controls the step size of parameter updates, is the cost function About parameters The gradient of , which indicates how to adjust the value of the cost function to the maximum extent under the current parameters, that is, to reduce the possibility of failure. It is the current setting, which directly affects the working state of the rotating unit. The voltage setting also directly affects the working state of the rotating unit. The rotation speed affects the performance and stability of the rotating unit. The working temperature affects the reliability and failure rate of the rotating unit. The weight coefficients of current, voltage, rotation speed, and temperature are used to quantify the influence of these parameters on the performance of the rotation unit, thus helping to make more precise parameter adjustments.

[0118] The execution process is as follows:

[0119] Data collection, collecting performance data of the rotating unit under different operating parameters, including failure rates;

[0120] Parameter analysis, using statistical or machine learning methods to analyze the impact of different parameters on performance and determine the importance of each parameter;

[0121] Weight determination: Based on the results of parameter analysis, the weight coefficient of each parameter is determined through optimization algorithms (such as linear regression, neural network, etc.) .

[0122] Through the above formula, we can introduce , , , and its weight coefficient, the operating parameters of the rotating unit can be adjusted more accurately to optimize its performance and reduce the probability of failure.

[0123] The winding layout optimization submodule optimizes the layout of the motor windings based on the preliminary adjustment parameter set, simulates the impact of different layouts on performance, avoids motor overheating caused by improper winding layout, and generates a winding layout optimization plan;

[0124] In the winding layout optimization submodule, based on the preliminary adjustment parameter set, a genetic algorithm is used to optimize the motor winding layout using the DEAP library in Python. First, the fitness function is defined as the evaluation criterion for the impact of the winding layout on the performance of the rotating unit, including motor efficiency and temperature distribution. Then the population is initialized with a population size of 50, and each individual represents a winding layout scheme. Through crossover, mutation, and selection operations, the natural selection process is simulated. The number of iterations is set to 100 generations, the crossover probability is set to 0.7, and the mutation probability is set to 0.2. Finally, the winding layout scheme with the highest motor efficiency and the most uniform temperature distribution is selected to generate the winding layout optimization scheme.

[0125] The material selection and evaluation submodule analyzes and selects the optimal bearing and gear materials based on the winding layout optimization scheme to improve the wear resistance of the rotating unit and reduce fatigue damage, and obtain a performance optimization strategy scheme;

[0126] In the material selection and evaluation submodule, based on the winding layout optimization scheme, the multi-attribute decision analysis method (MADM) is adopted to evaluate the bearing and gear materials using the PyMCDM library in Python. First, the properties of the evaluation materials are defined, including wear resistance, fatigue strength and cost. Then, weights are set for each attribute, with the wear resistance weight set to 0.4, the fatigue strength weight set to 0.4, and the cost weight set to 0.2. Then, the TOPSIS method is used. This method selects the scheme closest to the ideal solution and farthest from the negative ideal solution based on the distance measurement. By calculating the distance between each material scheme and the ideal solution, the optimal bearing and gear materials are selected to obtain the performance optimization strategy scheme.

[0127] See also Figure 2 and Figure 9 ,The real-time monitoring and adjustment module includes a performance monitoring submodule, a dynamic adjustment submodule, and an optimization effect analysis submodule;

[0128] The performance monitoring submodule implements real-time performance monitoring of the rotating unit based on the performance optimization strategy and continuously monitors key indicators, including temperature, vibration frequency, and motor load, to capture performance fluctuations and abnormal conditions and obtain real-time performance monitoring data;

[0129] In the performance monitoring submodule, based on the performance optimization strategy, real-time data acquisition technology is adopted, and Python language combined with NumPy library is used to continuously monitor key indicators such as temperature, vibration frequency and motor load. First, the temperature, vibration frequency and motor load data of the rotating unit are collected in real time through sensors, and the sensor sampling frequency is set to 100 times per second. Then, the numpy.array function is used to convert the collected data into an array format for subsequent processing. The collected data is analyzed in real time. By setting abnormal thresholds, such as temperature exceeding 100°C, vibration frequency exceeding the threshold or motor load exceeding 10% of the rated value, performance fluctuations and abnormal conditions are identified to obtain real-time performance monitoring data.

[0130] The dynamic adjustment submodule is based on real-time performance monitoring data. If it detects that the performance deviation exceeds the preset range, it will immediately use the gradient descent method to dynamically adjust the working parameters, including adjusting the current intensity or changing the type of bearing lubricant, and generate parameter adjustment records;

[0131] Based on real-time performance monitoring data, the gradient descent method is used to dynamically adjust the working parameters using the optimize.minimize function of the SciPy library in the Python language. First, the adjustment objective function is defined as minimizing the performance deviation, that is, minimizing the difference between the real-time monitoring data and the data under normal working conditions. Then, the initial adjustment value of the current intensity is set to the current current intensity minus 5A. If the bearing lubricant type is replaced, a more suitable lubricant is selected according to the real-time performance monitoring data. The basis for selecting the lubricant type is the matching degree between the most recent performance monitoring data and the lubricant performance parameters. The parameters are dynamically adjusted through the optimize.minimize function in order to minimize the performance deviation and generate parameter adjustment records.

[0132] The optimization effect analysis submodule analyzes the performance changes of the rotating unit after dynamic adjustment based on the parameter adjustment records, compares the operating efficiency, stability and durability before and after the adjustment, verifies the effectiveness of the optimization measures, and obtains the optimized operation records of the rotating unit;

[0133] In the optimization effect analysis submodule, based on the parameter adjustment records, the effect evaluation algorithm is adopted, and the Python language is combined with the Pandas library and the Matplotlib library to analyze the performance changes of the rotating unit after dynamic adjustment. First, the parameter adjustment records and the performance monitoring data before and after the adjustment are read, and the data is sorted using pandas.DataFrame. Then, the changes in operating efficiency, stability, and durability before and after the adjustment are calculated. The operating efficiency is calculated by the ratio of motor power output to input, the stability is calculated by the standard deviation of the vibration frequency, and the durability is estimated by analyzing the accumulation of fatigue damage. Finally, matplotlib.pyplot is used to draw a comparison chart of the performance changes before and after the adjustment to verify the effectiveness of the optimization measures and obtain the optimized operation record of the rotating unit.

[0134] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A robot rotation unit intelligent diagnosis system, characterized in that: The robot rotation unit intelligent diagnosis system comprises: The energy field analysis module simulates and analyzes the electromagnetic field and mechanical vibration energy field, captures the comprehensive impact on the performance of the rotating unit, analyzes the temperature changes caused by the electromagnetic field when the motor is working, and the effects of vibration energy on bearings and gears, and obtains the energy field analysis results; The infrared thermal imaging analysis module uses infrared thermal imaging technology to perform real-time temperature monitoring on the rotating unit based on the temperature change data in the energy field analysis result, analyzes the temperature distribution and its change trend, and obtains a temperature anomaly distribution map; The micro-deformation recognition module analyzes the motion trajectory and micro-deformation corresponding to the temperature anomaly distribution map based on the motion image of the rotating unit captured by the high-speed camera through digital image processing technology, determines whether the temperature anomaly causes structural deformation, and generates a micro-deformation index; The performance impact assessment module uses the finite element method to analyze the impact of micro-deformation on the performance of the rotation unit based on the micro-deformation index, including the reduction of rotation accuracy and material fatigue, predicts the long-term impact of micro-deformation on the overall performance, and obtains a performance impact assessment record; The fault mode identification module identifies potential fault modes of the rotating unit based on the performance impact assessment record, including bearing damage or gear wear caused by motor overheating, and obtains a fault mode identification result; The optimization strategy formulation module uses a gradient descent method based on the fault mode identification result to adjust the design parameters and operating parameters, including optimizing the motor winding layout and adjusting the bearing material selection, to obtain a performance optimization strategy solution; The real-time monitoring and adjustment module implements real-time monitoring and dynamic adjustment of the rotating unit based on the performance optimization strategy, optimizes the performance of the rotating unit in real time by adjusting the working parameters, and generates an optimized operation record of the rotating unit; The energy field analysis results include electromagnetic field intensity distribution, vibration energy spectrum, and energy field interaction points. The temperature anomaly distribution diagram includes the location of the highest temperature point, the average temperature value, and the temperature distribution unevenness index. The micro-deformation index includes the specific value of the deformation, the area of ​​the affected area, and the type of deformation trend. The performance impact assessment record specifically refers to the percentage of operating efficiency decrease and the change of key performance parameters. The fault mode identification results include the fault name, fault impact level, and a list of potential fault causes. The performance optimization strategy plan specifically includes the recommended replacement component type and the expected performance improvement range. The rotation unit optimization operation record includes the real-time data update frequency and a list of implemented adjustment measures.

2. The intelligent diagnosis system for the robot rotation unit according to claim 1, characterized in that: The energy field analysis module includes an electromagnetic field simulation submodule, a vibration energy analysis submodule, and an impact analysis submodule; The electromagnetic field simulation submodule performs electromagnetic field simulation analysis based on the input current and voltage parameters of the motor when it is working, simulates the distribution and intensity of the electromagnetic field under different operating conditions, and obtains an electromagnetic field distribution diagram; The vibration energy analysis submodule analyzes the influence of mechanical vibration caused by the electromagnetic field on the rotating unit including bearings and gears based on the electromagnetic field distribution diagram, simulates the vibration frequency and energy transfer, and obtains the vibration energy influence record; The impact analysis submodule is based on the vibration energy impact record, combined with the temperature change caused by the electromagnetic field and the effect of the vibration energy on the bearing and gear, to reveal the overall impact on the performance of the rotating unit and obtain the energy field analysis result.

3. The intelligent diagnosis system for the robot rotation unit according to claim 1, characterized in that: The infrared thermal image analysis module includes a temperature data capture submodule, a temperature distribution analysis submodule, and an abnormal trend identification submodule; The temperature data capture submodule uses infrared thermal imaging technology to perform real-time temperature monitoring on the rotating unit according to the temperature change data in the energy field analysis result, captures the real-time temperature data of the rotating unit surface, and obtains the real-time temperature index; The temperature distribution analysis submodule analyzes the temperature distribution of the entire rotating unit based on the real-time temperature index, identifies the uniformity of the temperature distribution and the abnormally high temperature area, and generates the temperature distribution analysis result; The abnormal trend identification submodule identifies abnormal patterns in the temperature change trend based on the temperature distribution analysis results, including areas with sharp temperature rise or sustained high temperature, determines the actual location and potential trend of the temperature anomaly, and obtains a temperature anomaly distribution map.

4. The intelligent diagnosis system for the robot rotation unit according to claim 1, characterized in that: The micro-deformation recognition module includes an image capture submodule, an image processing submodule, and a deformation judgment submodule; The image capture submodule is based on a high-speed camera to capture the motion image of the rotating unit in a working state, ensure image clarity, and obtain a high-speed motion image set; The image processing submodule uses digital image processing technology to perform contrast enhancement and edge detection based on the high-speed motion image set. If the image shows an obvious temperature abnormality area, the image features of the area are extracted to generate a temperature abnormality image feature set. The deformation judgment submodule is based on the temperature anomaly image feature set and the temperature anomaly distribution map, and compares and analyzes the slight deformation in the image by setting a threshold. If the feature change exceeds the threshold, it is judged as structural deformation, otherwise it is marked as no obvious deformation, and a slight deformation index is obtained.

5. The intelligent diagnosis system for the robot rotation unit according to claim 1, characterized in that: The performance impact assessment module includes a deformation impact analysis submodule, a rotation accuracy assessment submodule, and a material fatigue prediction submodule; The deformation impact analysis submodule uses the finite element method to simulate the influence of small deformation on the rotating unit structure based on the small deformation index, analyzes the stress and strain distribution in the deformation area, and generates the deformation impact analysis results; The finite element method, according to the formula: ; Calculate the stress and strain distribution of the structure after a small deformation and generate deformation effect analysis results, where: is the elastic modulus, is Poisson's ratio, is stress, For strain, is the temperature influence factor, is the minor defect coefficient, is the loading rate, is the material anisotropy coefficient; The rotation accuracy assessment submodule assesses the influence of small deformation on the rotation accuracy of the rotation unit based on the deformation influence analysis result, calculates the extent of the accuracy reduction, and if the accuracy reduction exceeds a preset threshold, it is marked as performance degradation, and a rotation accuracy reduction assessment record is obtained; The material fatigue prediction submodule predicts the material fatigue life caused by small deformation based on the rotation accuracy degradation assessment record, applies material fatigue theory, analyzes the performance degradation degree after long-term operation, and obtains the performance impact assessment record.

6. The robot rotation unit intelligent diagnosis system according to claim 1, characterized in that: The fault mode identification module includes a performance data analysis submodule, a potential fault identification submodule, and a fault mode classification submodule; The performance data analysis submodule analyzes the performance of the rotating unit under different working conditions based on the performance impact assessment record, identifies abnormal working conditions with large performance deviations, and generates a performance deviation data set; The potential fault identification submodule reveals the potential fault factors corresponding to the performance deviation according to the performance deviation data set by comparing the historical fault data with the fault mode library, and obtains a list of potential fault factors; The fault mode classification submodule classifies the fault factors based on the potential fault factor list and matches them with the fault mode. If the match is successful, the fault mode is determined to obtain a fault mode recognition result.

7. The robot rotation unit intelligent diagnosis system according to claim 1, characterized in that: The optimization strategy formulation module includes a parameter adjustment submodule, a winding layout optimization submodule, and a material selection evaluation submodule; The parameter adjustment submodule uses a gradient descent method to make preliminary adjustments to the operating parameters of the rotating unit based on the fault mode recognition result, including current and voltage settings, to reduce the possibility of fault occurrence and obtain a preliminary adjustment parameter set; The gradient descent method, according to the formula: ; Calculate the working parameter adjustment of the rotating unit and obtain a preliminary adjustment parameter set, where: is the parameter set after the next iteration, is the parameter set of the current iteration, is the learning rate, is the cost function About parameters The gradient of is the current setting, For voltage setting, is the rotation speed, is the working temperature, are the weight coefficients of current, voltage, rotation speed, and temperature; The winding layout optimization submodule optimizes the layout of the motor windings based on the preliminary adjustment parameter set, and generates a winding layout optimization plan by simulating the impact of different layouts on performance, avoiding motor overheating problems caused by improper winding layouts; The material selection and evaluation submodule analyzes and selects the optimal bearing and gear materials based on the winding layout optimization scheme, improves the wear resistance of the rotating unit and reduces fatigue damage, and obtains a performance optimization strategy scheme.

8. The robot rotation unit intelligent diagnosis system according to claim 1, characterized in that: The real-time monitoring and adjustment module includes a performance monitoring submodule, a dynamic adjustment submodule, and an optimization effect analysis submodule; The performance monitoring submodule implements real-time performance monitoring of the rotating unit based on the performance optimization strategy scheme to continuously monitor key indicators, including temperature, vibration frequency and motor load, capture performance fluctuations and abnormal conditions, and obtain real-time performance monitoring data; The dynamic adjustment submodule is based on real-time performance monitoring data. If it is detected that the performance deviation exceeds the preset range, the working parameters are dynamically adjusted by the gradient descent method immediately, including adjusting the current intensity or changing the type of bearing lubricant, and generating parameter adjustment records; The optimization effect analysis submodule analyzes the performance changes of the rotating unit after dynamic adjustment based on the parameter adjustment record, compares the operating efficiency, stability and durability before and after the adjustment, verifies the effectiveness of the optimization measures, and obtains the optimized operation record of the rotating unit.