AI-based pre-perception analysis method for the health status of IoT device terminals

Abstract

The present invention discloses an AI-based pre-perception analysis method for the health status of IoT device terminals, which relates to the technical field of device health management. The method collects operating data by deploying multiple types of sensors on key components, pre-processes the data to form a response data group, and performs collective processing to form a response data group set A. i , calculate the health status score index hss to perform operation health assessment, if the operation status is normal, then build a wear prediction model through the convolutional neural network model to obtain the aging wear prediction index wap, and generate the aging impact propagation coefficient w ip , combining the health status score index HSS and the aging wear prediction index WAP to calculate the aging response propagation index FPX; finally, the failure propagation probability of each component is accumulated to obtain the comprehensive failure risk prediction index SRR for comprehensive failure response evaluation, realizing real-time evaluation and early warning of the operating status of the industrial robot, ensuring stable operation of the equipment and extending its service life.

Description

Technical Field

[0001] The present invention relates to the technical field of device health management, and specifically to an AI-based pre-perception analysis method for the health status of IoT device terminals. Background Art

[0002] With the advancement of smart manufacturing, industrial intelligence, and digital transformation, society is increasingly relying on efficient, stable, and safe automated equipment. This is especially true in key sectors such as automotive manufacturing, semiconductor assembly, and high-end equipment, where demands for production continuity and equipment reliability are constantly increasing. At the same time, rising labor costs and a shortage of highly skilled talent are driving companies to increasingly rely on intelligent systems to replace traditional manual operation and maintenance. Faced with the strong demand for intelligent sensing and predictive capabilities for equipment operation driven by industrial upgrading, the transformation of industrial equipment from "post-repair" to "early warning" has become an inevitable trend in the digital development of the manufacturing industry.

[0003] Current approaches to monitoring the health of industrial robots generally rely on scheduled maintenance or single-parameter threshold-triggered early warning mechanisms. This approach suffers from significant hysteresis and localization, making it difficult to capture potential wear and tear behaviors and gradual deterioration processes at the device system level. Furthermore, existing methods, mostly based on conventional static parameters such as voltage, current, or temperature, lack a dynamic understanding of the device state evolution process, making it difficult to systematically assess the impact of aging propagation between components. Furthermore, current technologies face challenges at the data processing level, such as the difficulty in effectively extracting implicit features strongly correlated with health status from high-dimensional collected data and the lack of systematic filtering mechanisms for anomalous and noisy data, which can lead to model training bias and unstable prediction accuracy. Therefore, a systematic approach that integrates multidimensional time series signal processing, aging propagation modeling, and component-level functional coupling analysis is urgently needed to comprehensively improve the scientificity and reliability of industrial robot health monitoring and prediction. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides an AI-based pre-perception analysis method for the health status of IoT device terminals, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an AI-based pre-perception analysis method for the health status of IoT device terminals, comprising the following steps:

[0006] S1. Collecting the operating data of the industrial robot in real time based on the sensor group installed on the industrial robot, and transmitting it to the local server for pre-processing to obtain a response data group;

[0007] S2. The local server performs collective processing on the response data group to form a response data group set A. i, and based on the response data set A i Calculate the health status score index hss to conduct operational health assessment;

[0008] S3. When the equipment is running normally as assessed by the operation health assessment, a wear prediction model is constructed based on the convolutional neural network CNN, and the obtained response data set A is then i Input the wear prediction model to obtain the aging wear prediction index wap;

[0009] S4. The local server defines the functional relationship of components based on the electronic structure drawings and component work link diagrams of the industrial robot, and uses the historical collaborative fault data learning method to generate the aging impact propagation coefficient w ip , and then combine the health status score index hss and the aging wear prediction index wap to calculate the aging response propagation index fpx;

[0010] S5. The local server performs non-weighted accumulation of the fault propagation probability values ​​of all components of the industrial robot based on the obtained aging response propagation index fpx, and calculates the comprehensive fault risk prediction index SRR to perform comprehensive fault response evaluation.

[0011] Preferably, S1 includes S11 and S12;

[0012] S11. Install sensor groups on key components of the industrial robot, and collect operating data of the industrial robot in real time through the installed sensor groups;

[0013] The sensor group includes temperature sensor, piezoelectric sensor, vibration sensor, current sensor, voltage sensor and humidity sensor.

[0014] Preferably, S12, transmitting the operating data collected in real time by the sensor group to a local server via a wireless network, and the local server extracting feature data related to the health status of the industrial robot from the operating data using a principal component analysis technique;

[0015] Principal component analysis technology extracts feature data related to the health status of industrial robots from multiple original features of operating data through dimensionality reduction;

[0016] After obtaining the feature data, the local server performs data cleaning, denoising, outlier detection, and dimensionless processing on the feature data to obtain a response data group;

[0017] Data cleaning automatically removes outlier data through the set data quality threshold. Denoising uses the Kalman filter algorithm to weightedly fuse historical data with current feature data to filter out the noise in the feature data. Outlier detection uses a machine learning model combined with historical data to identify abnormal patterns in operating data. Dimensionless processing uses the Max-Min method to eliminate the dimensionality of operating data.

[0018] The response data set includes operating temperature wd, operating load fz, vibration amplitude zf, current intensity dl, voltage intensity yq and humidity sd.

[0019] Preferably, S2 includes S21;

[0020] S21: The local server aggregates the response data set of the same component i of the industrial robot collected at time t to form a response data set set A. i , expressed as: A i ⊇{wd, fz, zf, dl, yq, sd}, and store it in the data repository after marking the timestamp.

[0021] Preferably, S2 further includes S22;

[0022] S22, based on the obtained response data set A i Analyze the health status of each component of the industrial robot, and then analyze the health status of the industrial robot and perform a health assessment of the industrial robot, specifically including S221 and S222;

[0023] S221, the local server is based on the set A i Calculate and obtain the health status score index hss. The specific calculation formula is as follows;

[0024] ;

[0025] Where hss i (t) represents the health status score index of the i-th component at time t, m represents the total number of collected parameters, k i，j A represents the adjustment factor of the jth parameter on the health status score index of the i-th component, i，j (t) represents the jth parameter value collected in real time by the i-th component at time t, B i，j represents the standard value of the jth parameter of the i-th component under standard working conditions, λ j represents the time decay factor of the jth parameter, exp represents the exponential decay function, t represents the current time t, and t0 represents the initial time when the i-th component starts working.

[0026] Preferably, in S222, based on the healthy operation industry standard in the field of industrial robot equipment health management, a preset mechanical operation health threshold X is set, and then compared with the obtained health status score index hss to perform an operation health assessment. The specific assessment scheme is as follows;

[0027] When the health status score index hss ≤ the mechanical operation health threshold X, it indicates that there is a fault in the equipment. At this time, the robot control system controls the machine to stop immediately and generates a fault message. The fault information is transmitted to the relevant personnel user end via wireless communication to remind the machine fault that maintenance is required.

[0028] When the health status score index hss> the mechanical operation health threshold X, it means that the equipment is operating normally, and the equipment prediction instruction is executed at this time.

[0029] Preferably, S3 includes S31 and S32;

[0030] S31. When the operation health assessment shows that the equipment is operating normally, the local server builds a wear prediction model based on the convolutional neural network CNN and queries the time series response data set A of the historical industrial robot equipment in the data repository. i , analyze the time series characteristics of the historical response data group, then extract the frequency components in the equipment vibration signal through fast Fourier transform, analyze the changes of the historical response data group in different frequency ranges, obtain the historical time series characteristic response data set, input the historical time series characteristic response data set into the wear prediction model for model training, and optimize the wear prediction model;

[0031] S32, the response data set A obtained in real time i The trained wear prediction model is input to predict equipment aging. The wear prediction model outputs the aging wear prediction index wap. The specific formula for analyzing the aging and wear of industrial robot equipment is as follows;

[0032] ;

[0033] Where wap i (t) represents the aging wear prediction index of the i-th component at time t, m represents the total number of collected parameters, α i represents the adjustment coefficient of the wear rate of the i-th component, α i，0 represents the initial wear coefficient of the i-th component, e represents the exponential function, γ i represents the time decay coefficient of the i-th component.

[0034] Preferably, S4 includes S41 and S42;

[0035] S41. After executing the equipment aging prediction, the local server defines the functional dependency and physical conduction relationship between the various components of the industrial robot based on the electronic structure drawings and component work link diagrams of the industrial robot, uses the system modeling language and BOM structure list to identify the hierarchy and coupling relationship between equipment modules, and uses the historical collaborative fault data learning method to generate the aging impact propagation coefficient w ip , specifically as follows;

[0036] ;

[0037] w ip represents the causal strength of the impact on component p when component i fails;

[0038] S42, the local server obtains the health status score index hss, the aging wear prediction index wap and the aging impact propagation coefficient w ip Perform comprehensive calculations to obtain the aging response propagation index fpx and analyze the impact of single component aging on the operation of the entire robot;

[0039] ;

[0040] Where, fpx p (t) represents the propagation index of the failure response of the aging component to the p-th component at time t, N represents the total number of robot components, and e represents the exponential function.

[0041] Preferably, S5 includes S51;

[0042] S51. The local server performs non-weighted accumulation of the fault propagation probability values ​​of all components of the industrial robot based on the obtained aging response propagation index fpx, calculates and obtains the comprehensive fault risk prediction index SRR, and analyzes the overall fault risk of the industrial robot. The specific formula is as follows;

[0043] ;

[0044] Where, (t) represents the mean of the aging response propagation index of all components at time t.

[0045] Preferably, S5 further includes S52;

[0046] S52. Collect the comprehensive fault risk prediction index SRR of the industrial robot in normal and fault conditions in each historical period, calculate the mean of the historical comprehensive fault risk prediction index SRR based on the statistical method, and preset the operation fault response threshold V based on the mean. Then, compare it with the obtained comprehensive fault risk prediction index SRR to conduct a comprehensive fault response evaluation of the industrial robot. The specific evaluation plan is as follows;

[0047] When the comprehensive fault risk prediction index SRR ≥ the operating fault response threshold V, it means that the industrial robot has aging components, and the aging components affect the normal operation of other components. At this time, the robot control system controls the machine to stop immediately, and generates component aging information and transmits it to the relevant personnel user end through wireless communication to remind the equipment to replace the aging components.

[0048] When the comprehensive fault risk prediction index SRR is less than the operating fault response threshold V, it means that the robot components are normal and maintain normal monitoring.

[0049] The present invention provides an AI-based pre-perception analysis method for the health status of IoT device terminals. It has the following beneficial effects:

[0050] (1) This method realizes the comprehensive collection of operating data of key components of industrial robots by installing multiple sensors, and extracts and preprocesses the data features through principal component analysis to obtain response data groups that are highly correlated with the health status of the equipment, providing a data basis for subsequent analysis. Based on the response data groups, a response data set A is constructed. i By calculating the health status score index hss, the current health level of the equipment is quantified, and the preliminary assessment of the equipment operation status and fault judgment are achieved based on the set mechanical operation health threshold X.

[0051] (2) This method builds a wear prediction model based on a convolutional neural network (CNN), introduces Fourier transform to extract vibration frequency features, and trains and optimizes the model based on historical response data sets to output an aging wear prediction index (wap) to comprehensively evaluate the wear trend of the equipment under the influence of different parameters. Next, the electronic structure diagram of the equipment and the component link structure are introduced to construct the aging propagation path between components, and the aging influence propagation coefficient (w) is established through the historical collaborative fault data learning method. ip , thereby further calculating the aging response propagation index fpx, effectively revealing the potential impact of the aging of a certain component on other modules, and providing a theoretical basis for achieving accurate prediction.

[0052] (3) This method performs a non-weighted accumulation of the aging response propagation index fpx of all components to form a comprehensive fault risk prediction index SRR. It then sets the operational fault response threshold V based on historical operating samples to complete the quantitative judgment of the equipment-level fault response. This method can identify aging trends and trigger alarms in advance before the equipment actually fails, guiding the adjustment and implementation of equipment maintenance strategies, avoiding fault propagation and system downtime, effectively extending equipment service life, and improving the stability and operation and maintenance efficiency of industrial robots. The overall solution implements a fully closed-loop health management process from perception, assessment, prediction, to response, and is an important support for the integrated development of intelligent manufacturing and equipment status perception. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a schematic diagram of the steps of the AI-based IoT device terminal health status pre-perception analysis method of the present invention;

[0054] Figure 2 This is a schematic diagram of a line chart of comprehensive fault response evaluation according to the present invention;

[0055] Figure 3 This is a schematic diagram of the process framework of the AI-based IoT device terminal health status pre-perception analysis method of the present invention. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0057] Example 1

[0058] See also Figure 1 The present invention provides an AI-based pre-perception analysis method for the health status of IoT device terminals. To achieve the above objectives, the present invention is implemented through the following technical solutions: comprising the following steps:

[0059] S1. Collecting the operating data of the industrial robot in real time based on the sensor group installed on the industrial robot, and transmitting it to the local server for pre-processing to obtain a response data group;

[0060] S2. The local server performs collective processing on the response data group to form a response data group set A. i , and based on the response data set A i Calculate the health status score index hss to conduct operational health assessment;

[0061] S3. When the equipment is running normally as assessed by the operation health assessment, a wear prediction model is constructed based on the convolutional neural network CNN, and the obtained response data set A is then i Input the wear prediction model to obtain the aging wear prediction index wap;

[0062] S4. The local server defines the functional relationship of components based on the electronic structure drawings and component work link diagrams of the industrial robot, and uses the historical collaborative fault data learning method to generate the aging impact propagation coefficient w ip , and then combine the health status score index hss and the aging wear prediction index wap to calculate the aging response propagation index fpx;

[0063] S5. The local server performs non-weighted accumulation of the fault propagation probability values ​​of all components of the industrial robot based on the obtained aging response propagation index fpx, and calculates the comprehensive fault risk prediction index SRR to perform comprehensive fault response evaluation.

[0064] In this embodiment, S1 realizes high-frequency, multi-dimensional real-time data collection of the operating status of key components of industrial robots through various types of sensor groups, and pre-processes them through the local server to form a highly purified response data group, laying a solid foundation for subsequent intelligent processing. This stage significantly improves the timeliness and effectiveness of the operating data, and solves the problem of messy sensor data and difficulty in real-time processing in traditional solutions. In the S2 and S3 stages, the local server collects data based on the response data group set A. i Calculate the health status score index hss, and further determine whether the equipment is in a healthy state. Once it is determined that the equipment is operating normally, it automatically enters the wear prediction process based on the convolutional neural network CNN, and generates the aging wear prediction index wap through time series modeling and frequency analysis of historical data. Compared with the traditional passive strategy that relies on periodic manual maintenance, this method can actively predict the wear trend of components, greatly improve the foresight and pertinence of equipment maintenance, reduce the sudden failure rate of equipment, and realize the transformation from "fault response" to "wear prediction". In the S4 and S5 stages, the functional dependencies and physical conduction relationships between the various components of the industrial robot are further defined based on the electronic structure drawings and component working link diagrams of the industrial robot. The system modeling language and BOM structure list are used to identify the hierarchy and coupling relationship between equipment modules, and the historical collaborative fault data learning method is used to construct the aging propagation influence coefficient w between components. ip , and based on this, the aging response propagation index fpx is generated. Finally, the propagation indices of all components are unweightedly summed to obtain the comprehensive failure risk prediction index SRR, enabling a macro-risk assessment of the entire machine's operating status. Compared to current industry approaches that primarily rely on single-parameter indicators or simple alarm mechanisms, this method introduces a multi-parameter, multi-model fusion response propagation analysis mechanism, effectively improving the accuracy of risk assessment and the system's intelligent decision-making capabilities, further advancing industrial robots towards a highly reliable, autonomous, and efficient operational management model.

[0065] Example 2

[0066] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: S1 includes S11 and S12;

[0067] S11. Install sensor groups on key components of the industrial robot, and collect operating data of the industrial robot in real time through the installed sensor groups;

[0068] The sensor group includes a temperature sensor, a piezoelectric sensor, a vibration sensor, a current sensor, a voltage sensor, and a humidity sensor;

[0069] The temperature sensor is used to collect the operating temperature of the industrial robot in real time;

[0070] Piezoelectric sensors are used to collect the operating load of industrial robots in real time;

[0071] The vibration sensor is used to collect the vibration amplitude of the equipment in real time when the industrial robot is running;

[0072] The current sensor is used to detect the current intensity of the industrial robot in real time;

[0073] The voltage sensor is used to detect the voltage intensity of the industrial robot in real time;

[0074] The humidity sensor is used to collect the ambient humidity in real time.

[0075] S12, transmitting the operating data collected in real time by the sensor group to a local server via a wireless network, and the local server extracting feature data related to the health status of the industrial robot from the operating data using principal component analysis technology;

[0076] Principal component analysis technology extracts feature data related to the health status of industrial robots from multiple original features of operating data through dimensionality reduction;

[0077] After obtaining the feature data, the local server performs data cleaning, denoising, outlier detection, and dimensionless processing on the feature data to obtain a response data group;

[0078] Data cleaning automatically removes outlier data through the set data quality threshold. Denoising uses the Kalman filter algorithm to weightedly fuse historical data with current feature data to filter out the noise in the feature data. Outlier detection uses a machine learning model combined with historical data to identify abnormal patterns in operating data. Dimensionless processing uses the Max-Min method to eliminate the dimensionality of operating data.

[0079] The response data set includes operating temperature wd, operating load fz, vibration amplitude zf, current intensity dl, voltage intensity yq and humidity sd.

[0080] In this embodiment, by deploying sensor groups on key components of industrial robots, real-time collection of multi-dimensional parameters of equipment operation data is achieved, and the data is transmitted to a local server via a wireless network. The local server extracts characteristic factors highly correlated with health status from high-dimensional operation data based on principal component analysis technology, and combines multiple data optimization methods such as data cleaning, Kalman filtering denoising, outlier identification, and dimensionless processing to form a response data set with clear structure, low noise, and discriminant value. This method not only improves the accuracy and timeliness of operation data processing, but also effectively avoids the problems of data redundancy, weak feature correlation, and delayed evaluation in traditional methods. It significantly improves the reliability and response speed of subsequent health status assessment and aging prediction models, and provides a solid foundation for building an intelligent and predictable robot operation and maintenance system.

[0081] Example 3

[0082] This embodiment is explained in Example 2, please refer to Figure 1 , specifically: S2 includes S21 and S22;

[0083] S21: The local server aggregates the response data set of the same component i of the industrial robot collected at time t to form a response data set set A. i , expressed as: A i ⊇{wd, fz, zf, dl, yq, sd}, and store it in the data repository after marking the timestamp.

[0084] S22, based on the obtained response data set A i Analyze the health status of each component of the industrial robot, and then analyze the health status of the industrial robot and perform a health assessment of the industrial robot, specifically including S221 and S222;

[0085] S221, the local server is based on the set A i Calculate and obtain the health status score index hss. The specific calculation formula is as follows;

[0086] ;

[0087] Where hss i (t) represents the health status score index of the i-th component at time t, m represents the total number of collected parameters, k i，j A represents the adjustment factor of the jth parameter on the health status score index of the i-th component, which is used to adjust the sensitivity and importance of the parameter to the health status score. i，j (t) represents the jth parameter value collected in real time by the i-th component at time t, B i，j represents the standard value of the jth parameter of the i-th component under standard working conditions, λ jIt represents the time attenuation factor of the jth parameter, reflecting the attenuation of the influence of the jth parameter on the health status over time. It is extracted through the experimental data management system of the material manufacturer. exp represents the exponential attenuation function, t represents the current time t, and t0 represents the initial time when the i-th component starts working. It represents the effect of the jth parameter on the health status at the current time t, that is, the degree of deviation of the parameter, represents the time decay function of the jth parameter, describing the natural decay and boundary reduction effect of the jth parameter on the health status score index over time.

[0088] S222. Based on the healthy operation industry standard in the field of industrial robot equipment health management, a preset mechanical operation health threshold X is set and then compared with the obtained health status score index hss to perform an operation health assessment. The specific assessment plan is as follows;

[0089] When the health status score index hss ≤ the mechanical operation health threshold X, it indicates that there is a fault in the equipment. At this time, the robot control system controls the machine to stop immediately and generates a fault message. The fault information is transmitted to the relevant personnel user end via wireless communication to remind the machine fault that maintenance is required.

[0090] When the health status score index hss> the mechanical operation health threshold X, it means that the equipment is operating normally, and the equipment prediction instruction is executed at this time.

[0091] In this embodiment, S21 forms a standardized response data set A by aggregating the six key response parameters of the same component at the same time. i , and assign timestamp storage to ensure the temporal integrity of data; S22 further introduces the adjustment factor k i，j , time decay factor λ j And standard working condition parameters B i，j , calculates the health status score (HSS) index, accurately quantifies the health status of each component, and combines this with the industry's preset mechanical health threshold (X) to make judgments, enabling real-time, dynamic, and quantitative assessments of the operating status of industrial robots. This method not only breaks through traditional health assessment methods based on single parameters or manual judgment, but also enables early detection and rapid response to equipment failures. It also improves the reliability, safety, and operational efficiency of robots, laying the core technical foundation for building intelligent predictive maintenance systems.

[0092] Example 4

[0093] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: S3 includes S31 and S32;

[0094] S31. When the operation health assessment shows that the equipment is operating normally, the local server builds a wear prediction model based on the convolutional neural network CNN and queries the time series response data set A of the historical industrial robot equipment in the data repository. i , analyze the time series characteristics of the historical response data group, then extract the frequency components in the equipment vibration signal through fast Fourier transform, analyze the changes of the historical response data group in different frequency ranges, obtain the historical time series characteristic response data set, input the historical time series characteristic response data set into the wear prediction model for model training, and optimize the wear prediction model;

[0095] S32, the response data set A obtained in real time i The trained wear prediction model is input to predict equipment aging. The wear prediction model outputs the aging wear prediction index wap. The specific formula for analyzing the aging wear of industrial robot equipment is as follows;

[0096] ;

[0097] Where wap i (t) represents the aging wear prediction index of the i-th component at time t, which is used to describe the wear and aging of the i-th component at time t, m represents the total number of collected parameters, α i It represents the adjustment coefficient of the wear rate of the i-th component, describing the degree of wear of the component under different factors, and is extracted through the experimental data management system of the material manufacturer. i，0 represents the initial wear coefficient of the i-th component, which is extracted through the material supply manufacturer's material management system, e represents the exponential function, γ i It represents the time decay coefficient of the i-th component, which is used to describe the decay rate of the component over time and is extracted through the material manufacturer's experimental data management system. Indicates that at the current moment t, various wear factors A i，j (t) the immediate contribution to the wear state, Indicates the aging trend of a component due to material properties and long-term fatigue effects.

[0098] In this embodiment, by constructing a wear prediction model based on a convolutional neural network (CNN), combined with historical time series response data and frequency domain analysis technology, intelligent modeling and dynamic prediction of the wear and aging trends of key components of industrial robots are achieved. Not only is the historical vibration frequency characteristics fully extracted, but also the real-time input response data set A is used to i Perform prediction calculations and output the aging wear prediction index wap, effectively quantifying the aging degree of components at each moment. During the implementation process, by introducing the component material management system and the experimental data management system, the wear rate adjustment coefficient α is dynamically extracted through a dedicated API interface. iand the time decay coefficient γ i , enabling differentiated modeling of the wear behavior of different components. The Aging Wear Prediction Index (WAP) integrates real-time multi-source sensor data and material aging behavior. Using a segmented structure, it separately models the effects of immediate wear and time decay, enabling dynamic health assessment of key industrial robot components under complex operating conditions. Compared to traditional linear models, it is more physically reasonable and engineering-adaptable. It not only characterizes the decreasing impact of multiple wear factors over time, but also accurately simulates the irreversible aging process of materials that accumulates over operating cycles. Its clear structure, quantifiable parameters, and excellent computability and generalizability significantly improve the accuracy of equipment fault warnings and the scientific nature of maintenance strategies, offering outstanding practical value and innovation in industrial automation scenarios. This step significantly enhances industrial robots' ability to identify potential aging risks, shifting operation and maintenance strategies from "fixed-cycle maintenance" to "state-based predictive control," reducing equipment failure rates, and improving production line continuity and intelligent maintenance.

[0099] Example 5

[0100] This embodiment is explained in Example 4. Please refer to Figure 1 , specifically: S4 includes S41 and S42;

[0101] S41. After executing the equipment aging prediction, the local server defines the functional dependency and physical conduction relationship between the various components of the industrial robot based on the electronic structure drawings and component work link diagrams of the industrial robot, uses the system modeling language and BOM structure list to identify the hierarchy and coupling relationship between equipment modules, and uses the historical collaborative fault data learning method to generate the aging impact propagation coefficient w ip , specifically as follows;

[0102] ;

[0103] w ip represents the causal strength of the impact on component p when component i fails;

[0104] S42, the local server obtains the health status score index hss, the aging wear prediction index wap and the aging impact propagation coefficient w ip Perform comprehensive calculations to obtain the aging response propagation index fpx and analyze the impact of single component aging on the operation of the entire robot;

[0105] ;

[0106] Where, fpx p (t) represents the propagation index of the failure response of the aging component to the pth component at time t, N represents the total number of robot components, e represents the exponential function, represents the intrinsic failure tendency of component i, that is, the potential probability of triggering failure under the dual effects of the current state and historical wear of the component, It represents the transmission capability and efficiency of the risk from component i to the target component p, and analyzes the nonlinear and multi-time-scale transmission effects consistent with the actual system.

[0107] In this embodiment, the electronic structure drawings and component work link diagrams of industrial robots are used, combined with the system modeling language and BOM structure list to clarify the functional dependencies and coupling relationships between components, and the aging impact propagation coefficient w is generated based on historical collaborative failure data learning. ip ; Then, the health status score index hss, aging wear prediction index wap and aging impact propagation coefficient w are integrated ip A comprehensive calculation of the aging response propagation index fpx is performed to accurately quantify the chain reaction effect of any component aging on the operation of the entire system, achieving dynamic quantification of fault risks and multi-source propagation path modeling in the equipment system. By introducing a nonlinear time decay mechanism, the linkage diffusion characteristics of faults evolving over time in complex structural systems are effectively reflected. This improves the accuracy of latent fault identification and prediction, and also enables priority warning and closed-loop control of system-level risks for key components, significantly enhancing the reliability of equipment, the foresight of maintenance decisions, and the adaptability of operating systems. This implementation method not only establishes a dynamic feedback mechanism for component aging on system-level fault propagation, but also effectively overcomes the problem of traditional methods lacking structural conduction path modeling in aging analysis, achieving multi-dimensional mapping and deduction of aging risks from a single point to the system, significantly improving the systematicity, foresight, and decision-making accuracy of fault warnings, and providing a controllable and adjustable optimization path for equipment maintenance and health management.

[0108] Example 6

[0109] This embodiment is explained in Example 5, please refer to Figure 1 and Figure 2 ,Specifically: S5 includes S51 and S52;

[0110] S51. The local server performs non-weighted accumulation of the fault propagation probability values ​​of all components of the industrial robot based on the obtained aging response propagation index fpx, calculates and obtains the comprehensive fault risk prediction index SRR, and analyzes the overall fault risk of the industrial robot. The specific formula is as follows;

[0111] ;

[0112] Where, (t) represents the mean of the aging response propagation index of all components at time t.

[0113] S52. Collect the comprehensive fault risk prediction index SRR of the industrial robot in normal and fault conditions in each historical period, calculate the mean of the historical comprehensive fault risk prediction index SRR based on the statistical method, and preset the operation fault response threshold V based on the mean. Then, compare it with the obtained comprehensive fault risk prediction index SRR to conduct a comprehensive fault response evaluation of the industrial robot. The specific evaluation plan is as follows;

[0114] When the comprehensive fault risk prediction index SRR ≥ the operating fault response threshold V, it means that the industrial robot has aging components, and the aging components affect the normal operation of other components. At this time, the robot control system controls the machine to stop immediately, and generates component aging information and transmits it to the relevant personnel user end through wireless communication to remind the equipment to replace the aging components.

[0115] When the comprehensive fault risk prediction index SRR is less than the operating fault response threshold V, it means that the robot components are normal and maintain normal monitoring.

[0116] In this embodiment, after obtaining the aging response propagation index fpx, a comprehensive fault risk prediction index (SRR) is calculated using a non-weighted cumulative method. Furthermore, the operational fault response threshold (V) is set based on the average value of fpx under historical operating conditions, thereby achieving a quantitative risk assessment and accurate judgment of the overall operational status of the industrial robot. Specifically, when the comprehensive fault risk prediction index (SRR) is greater than or equal to the operational fault response threshold (V), a shutdown command is automatically generated and component aging information is pushed, triggering an early warning mechanism. If the comprehensive fault risk prediction index (SRR) is lower than the operational fault response threshold (V), the equipment is maintained in normal operation and continuously monitored. This method not only establishes a data-driven dynamic threshold assessment mechanism, avoiding the misjudgment problem of static alarms, but also achieves efficient closed-loop management from micro-component aging to macro-system risks, significantly improving the timeliness of fault prevention, the intelligence of equipment management, and overall operation and maintenance efficiency, ultimately achieving a comprehensive improvement effect of reducing equipment failure rates, extending service life, and optimizing maintenance cycles.

[0117] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An AI-based pre-perception analysis method for the health status of IoT device terminals, characterized by: The following steps are involved: S1. Collecting the operating data of the industrial robot in real time based on the sensor group installed on the industrial robot, and transmitting it to the local server for pre-processing to obtain a response data group; S2. The local server performs collective processing on the response data group to form a response data group set A. i , and based on the response data set A i Calculate the health status score index hss to conduct operational health assessment; S3. When the equipment is running normally as assessed by the operation health assessment, a wear prediction model is constructed based on the convolutional neural network CNN, and the obtained response data set A is then i Input the wear prediction model to obtain the aging wear prediction index wap; S4. The local server defines the functional relationship of components based on the electronic structure drawings and component work link diagrams of the industrial robot, and uses the historical collaborative fault data learning method to generate the aging impact propagation coefficient w ip , and then combine the health status score index hss and the aging wear prediction index wap to calculate the aging response propagation index fpx; ； Where, fpx p (t) represents the propagation index of the failure response of the aging component to the pth component at time t, N represents the total number of robot components, e represents the exponential function, hss i (t) represents the health status score index of the i-th component at time t, wap i (t) represents the aging wear prediction index of the i-th component at time t; S5. The local server performs non-weighted accumulation of the fault propagation probability values ​​of all components of the industrial robot based on the obtained aging response propagation index fpx, and calculates the comprehensive fault risk prediction index SRR to perform comprehensive fault response evaluation.

2. The AI-based pre-perception analysis method for IoT device terminal health status according to claim 1 is characterized by: S1 includes S11 and S12; S11. Install sensor groups on key components of the industrial robot, and collect operating data of the industrial robot in real time through the installed sensor groups; The sensor group includes temperature sensor, piezoelectric sensor, vibration sensor, current sensor, voltage sensor and humidity sensor.

3. The AI-based pre-perception analysis method for IoT device terminal health status according to claim 2 is characterized by: S12, transmitting the operating data collected in real time by the sensor group to a local server via a wireless network, and the local server extracting feature data related to the health status of the industrial robot from the operating data using principal component analysis technology; Principal component analysis technology extracts feature data related to the health status of industrial robots from multiple original features of operating data through dimensionality reduction; After obtaining the feature data, the local server performs data cleaning, denoising, outlier detection, and dimensionless processing on the feature data to obtain a response data group; Data cleaning automatically removes outlier data through the set data quality threshold. Denoising uses the Kalman filter algorithm to weightedly fuse historical data with current feature data to filter out the noise in the feature data. Outlier detection uses a machine learning model combined with historical data to identify abnormal patterns in operating data. Dimensionless processing uses the Max-Min method to eliminate the dimensionality of operating data. The response data set includes operating temperature wd, operating load fz, vibration amplitude zf, current intensity dl, voltage intensity yq and humidity sd.

4. The AI-based pre-perception analysis method for IoT device terminal health status according to claim 3 is characterized by: S2 includes S21; S21: The local server aggregates the response data set of the same component i of the industrial robot collected at time t to form a response data set set A. i , expressed as: A i {wd, fz, zf, dl, yq, sd}, and store it in the data repository after marking the timestamp.

5. The AI-based pre-perception analysis method for IoT device terminal health status according to claim 4 is characterized by: S2 also includes S22; S22, based on the obtained response data set A i Analyze the health status of each component of the industrial robot, and then analyze the health status of the industrial robot and perform a health assessment of the industrial robot, specifically including S221 and S222; S221, the local server is based on the set A i Calculate and obtain the health status score index hss. The specific calculation formula is as follows; ； Where hss i (t) represents the health status score index of the i-th component at time t, m represents the total number of collected parameters, k i，j A represents the adjustment factor of the jth parameter on the health status score index of the i-th component, i，j (t) represents the jth parameter value collected in real time by the i-th component at time t, B i，j represents the standard value of the jth parameter of the i-th component under standard working conditions, λ j represents the time decay factor of the jth parameter, exp represents the exponential decay function, t represents the current time t, and t0 represents the initial time when the i-th component starts working.

6. The AI-based pre-perception analysis method for IoT device terminal health status according to claim 5 is characterized by: S222. Based on the healthy operation industry standard in the field of industrial robot equipment health management, a preset mechanical operation health threshold X is set and then compared with the obtained health status score index hss to perform an operation health assessment. The specific assessment plan is as follows; When the health status score index hss ≤ the mechanical operation health threshold X, it indicates that there is a fault in the equipment. At this time, the robot control system controls the machine to stop immediately and generates a fault message. The fault information is transmitted to the relevant personnel user end via wireless communication to remind the machine fault that maintenance is required. When the health status score index hss> the mechanical operation health threshold X, it means that the equipment is operating normally, and the equipment prediction instruction is executed at this time.

7. The AI-based pre-perception analysis method for IoT device terminal health status according to claim 6 is characterized by: S3 includes S31 and S32; S31. When the operation health assessment shows that the equipment is operating normally, the local server builds a wear prediction model based on the convolutional neural network CNN and queries the time series response data set A of the historical industrial robot equipment in the data repository. i , analyze the time series characteristics of the historical response data group, then extract the frequency components in the equipment vibration signal through fast Fourier transform, analyze the changes of the historical response data group in different frequency ranges, obtain the historical time series characteristic response data set, input the historical time series characteristic response data set into the wear prediction model for model training, and optimize the wear prediction model; S32, the response data set A obtained in real time i The trained wear prediction model is input to predict equipment aging. The wear prediction model outputs the aging wear prediction index wap. The specific formula for analyzing the aging and wear of industrial robot equipment is as follows; ； Where wap i (t) represents the aging wear prediction index of the i-th component at time t, m represents the total number of collected parameters, α i represents the adjustment coefficient of the wear rate of the i-th component, α i，0 represents the initial wear coefficient of the i-th component, e represents the exponential function, γ i represents the time decay coefficient of the i-th component.

8. The AI-based pre-perception analysis method for the health status of IoT devices according to claim 7, characterized in that: S4 includes S41 and S42; S41. After executing the equipment aging prediction, the local server defines the functional dependency and physical conduction relationship between the various components of the industrial robot based on the electronic structure drawings and component work link diagrams of the industrial robot, uses the system modeling language and BOM structure list to identify the hierarchy and coupling relationship between equipment modules, and uses the historical collaborative fault data learning method to generate the aging impact propagation coefficient w ip , specifically as follows; ； w ip represents the causal strength of the impact on component p when component i fails; S42, the local server obtains the health status score index hss, the aging wear prediction index wap and the aging impact propagation coefficient w ip Comprehensive calculations are performed to obtain the aging response propagation index fpx and analyze the impact of the aging of a single component on the operation of the entire robot.

9. The AI-based pre-perception analysis method for IoT device terminal health status according to claim 8, characterized in that: S5 includes S51; S51. The local server performs non-weighted accumulation of the fault propagation probability values ​​of all components of the industrial robot based on the obtained aging response propagation index fpx, calculates and obtains the comprehensive fault risk prediction index SRR, and analyzes the overall fault risk of the industrial robot. The specific formula is as follows; ； Where, (t) represents the mean of the aging response propagation index of all components at time t.

10. The AI-based pre-perception analysis method for IoT device terminal health status according to claim 9 is characterized by: S5 also includes S52; S52. Collect the comprehensive fault risk prediction index SRR of the industrial robot in normal and fault conditions in each historical period, calculate the mean of the historical comprehensive fault risk prediction index SRR based on the statistical method, and preset the operation fault response threshold V based on the mean. Then, compare it with the obtained comprehensive fault risk prediction index SRR to conduct a comprehensive fault response evaluation of the industrial robot. The specific evaluation plan is as follows; When the comprehensive fault risk prediction index SRR ≥ the operating fault response threshold V, it means that the industrial robot has aging components, and the aging components affect the normal operation of other components. At this time, the robot control system controls the machine to stop immediately, and generates component aging information and transmits it to the relevant personnel user end through wireless communication to remind the equipment to replace the aging components. When the comprehensive fault risk prediction index SRR is less than the operating fault response threshold V, it means that the robot components are normal and maintain normal monitoring.

Images