CN-121997158-A - Cross-border Internet of things equipment fault diagnosis and prediction system based on artificial intelligence

CN121997158ACN 121997158 ACN121997158 ACN 121997158ACN-121997158-A

Abstract

The invention provides an artificial intelligence-based cross-border Internet of things equipment fault diagnosis and prediction system which comprises a data acquisition module, wherein the data acquisition module is used for collecting operation data of cross-border Internet of things equipment, and the data preprocessing module is used for cleaning, normalizing and extracting features of the acquired data so as to facilitate subsequent analysis and prediction. The invention utilizes machine learning and deep learning to more accurately identify the fault type of the equipment and predict the future fault occurrence probability, improves the efficiency of fault diagnosis and prediction, automatically completes the tasks of data acquisition, preprocessing, diagnosis and prediction, reduces manual intervention and error rate, intelligently optimizes the operation parameters of the equipment according to the fault diagnosis and prediction result, reduces the fault occurrence probability, improves the service life and the operation efficiency of the equipment, displays the fault diagnosis and prediction result and equipment optimization suggestion through a user interface, and helps a user to better understand and master the operation state of the equipment.

Inventors

Pang Yuxiong
LU WEIJUN
Pang Zhiyin

Assignees

广州金财智链数字科技有限公司

Dates

Publication Date: 20260508
Application Date: 20240131

Claims (10)

1. The system for diagnosing and predicting the faults of the cross-border Internet of things equipment based on the artificial intelligence is characterized by comprising a data acquisition module, wherein the data acquisition module is used for collecting operation data of the cross-border Internet of things equipment, the data acquisition module is in data connection with a data preprocessing module, and the data acquired by the data acquisition module is recorded as device= { x 1 .x 2 ...x n }; the data preprocessing module is used for cleaning, normalizing and extracting features of the acquired data so as to facilitate subsequent analysis and prediction, wherein each device is provided with a Feature code= { f 1 .f 2 ...f n } in the process of extracting the features; The AI-CIOT fault diagnosis engine module processes and analyzes the collected cross-border Internet of things equipment data and then uses a pre-stored fault diagnosis algorithm to identify and position equipment; Fault diagnosis mathematical formula n= (ax+by+c)/D; wherein N is the output error (noise), A is the numerator of the system function (transfer function), B is the denominator of the system function (transfer function), C is the input error (noise), D is the co-factor (e.g., gain) of the system function (transfer function); The AI-CIOT fault diagnosis engine module is in data connection with the fault diagnosis algorithm library module, wherein the fault diagnosis algorithm library module is provided with a fault diagnosis algorithm, and the fault diagnosis algorithm comprises a traditional statistical method, a machine learning algorithm and a deep learning algorithm; The fault diagnosis algorithm formula is Z=Y X (a); wherein Z is a fault characteristic equation, Y is a fault characteristic coefficient, X is an input signal (such as voltage and current), a is a fault characteristic index (reflecting the severity of the fault); The AI-CIOT fault diagnosis engine module is in data connection with the equipment state monitoring and predicting module, and the equipment state monitoring and predicting module monitors the state of equipment in real time by using the collected equipment data and a method in a fault diagnosis algorithm library; the equipment state monitoring and predicting module is in data connection with the equipment fault knowledge graph construction module, and the equipment fault knowledge graph construction module uses the collected equipment data and fault diagnosis results to construct an equipment fault knowledge graph for storing and learning the fault mode and rule of the equipment; The failure mode and rule formula is R=Σ (Xi x j)/(ΣXi 2)/(1/2) ΣXj (1/2), where R is the correlation coefficient (reflecting the linear relationship strength between the two variables), xi is the observed value of the first variable, and Xj is the observed value of the second variable.
2. The system for diagnosing and predicting the equipment failure of the cross-border internet of things based on artificial intelligence according to claim 1, wherein the data collected by the data collection module comprises equipment parameters, an operation state and environment parameters, the equipment failure knowledge graph construction module is in data connection with the deep learning capability integration module, and the deep learning capability integration module integrates a deep learning algorithm into the failure diagnosis system and uses a deep learning model to identify and predict the equipment failure.
3. The system for diagnosing and predicting the faults of the cross-border Internet of things equipment based on artificial intelligence according to claim 2, wherein the deep learning capacity integrated module is in data connection with the AI model prediction optimization module, the AI model prediction optimization module provides the interpretability of the AI model and helps a user understand how the AI model performs fault diagnosis and model optimization; K in the model optimization process =1/(1+e ((a+bx))); Wherein, K is an optimization function, a is a bias term, b is a weight, e is the bottom of natural logarithm; The real-time fault early warning module uses the results of equipment state monitoring and prediction to send out fault early warning to a user in real time, so as to help the user take measures in time to prevent equipment faults; the predictive formula is (precision Tree) y=f (X1, X2,., xn); y is a predicted value, X1, X2, xn is an input feature, and f is a decision tree model.
4. The system for diagnosing and predicting the equipment faults of the cross-border internet of things based on artificial intelligence according to claim 3 is characterized in that the real-time fault early warning module is in data connection with the equipment maintenance and repair module, the equipment maintenance and repair module provides corresponding equipment maintenance and repair suggestions according to the diagnosis results of equipment faults to help a user to improve the operation efficiency of the equipment and reduce the fault rate, the equipment maintenance and repair module is in data connection with the fault diagnosis model optimizing and updating module, and the fault diagnosis model optimizing and updating module collects new equipment data and fault diagnosis results and is used for optimizing and updating the fault diagnosis model to improve the accuracy and reliability of the system.
5. The system for diagnosing and predicting the faults of the cross-border Internet of things equipment based on artificial intelligence according to claim 4, wherein the fault diagnosis model optimizing and updating module is in data connection with a system security and privacy protection module, wherein the system security and privacy protection module protects the data security and privacy of a user and comprises aspects of data encryption, access control and data desensitization; the diagnostic function is y=f (w1×x1+ W2X 2 a. +wn X xn+b); Wherein Y is a predicted value, W1, W2, & gt, wn is a weight matrix, X1, X2, & gt, xn is an input feature, b is a bias term, f is an activation function; The system security and privacy protection module is in data connection with the cross-platform equipment compatibility module, and the cross-platform equipment compatibility module ensures that the system supports various types of cross-border Internet of things equipment no matter what communication protocol or data format is used by the system.
6. The system for diagnosing and predicting the equipment failure of the cross-border Internet of things based on artificial intelligence according to claim 5, wherein the cross-platform equipment compatibility module is in data connection with the user interface and the interaction module, and the user interface and the interaction module are used for setting a user interface and an interaction mode so that a user can easily use the system for diagnosing and predicting the equipment failure.
7. The system for diagnosing and predicting the faults of the cross-border Internet of things equipment based on artificial intelligence according to claim 6 is characterized in that the user interface and interaction module is in data connection with the data analysis and visualization module, and the data analysis and visualization module uses data analysis and visualization tools to help a user to understand the running condition and fault diagnosis results of the equipment more intuitively.
8. The system for diagnosing and predicting the faults of the cross-border Internet of things equipment based on artificial intelligence according to claim 7 is characterized in that the data analysis and visualization module is in data connection with the system performance evaluation and monitoring module, wherein the system performance evaluation and monitoring module is responsible for monitoring the performance of the system, including response time, accuracy and other key indexes, and is adjusted and optimized according to requirements; The adjustment probability formula is P (y|x) =p (x|y) ×p (Y)/P (X); wherein P (Y|X) is the conditional probability of a given input feature, P (X|Y) is the conditional probability of a given output, P (Y) is the prior probability of a class, and P (X) is the prior probability of an input feature.
9. The system for diagnosing and predicting the equipment failure of the cross-border Internet of things based on artificial intelligence according to claim 8, wherein the system performance evaluation and monitoring module is in data connection with the equipment failure prediction module, and the equipment failure prediction module uses historical equipment data and failure diagnosis results to construct an equipment failure prediction model for predicting failures occurring in the future.
10. The system for diagnosing and predicting equipment failure of cross-border internet of things based on artificial intelligence as recited in claim 9, wherein the equipment failure prediction module is in data connection with a data integration and synchronization module, wherein the data integration and synchronization module integrates data from different equipment and sources together, and synchronizes and updates the data.

Description

Cross-border Internet of things equipment fault diagnosis and prediction system based on artificial intelligence Technical Field The invention relates to the technical field of cross-border Internet of things equipment fault diagnosis and prediction, in particular to a cross-border Internet of things equipment fault diagnosis and prediction system based on artificial intelligence. Background With the development of internet of things, more and more devices are connected and data exchanged through the internet. The global distribution of these devices makes fault diagnosis and prediction more complex. The existing cross-border Internet of things equipment fault diagnosis process still needs to be improved, and the traditional fault diagnosis and prediction method is often dependent on manual operation, low in efficiency and easy to make mistakes. Therefore, the system is improved, and a cross-border Internet of things equipment fault diagnosis and prediction system based on artificial intelligence is provided, so that more efficient and accurate fault diagnosis and prediction can be realized. Disclosure of Invention The invention aims to solve the problems of the prior art. In order to achieve the aim, the invention provides the technical scheme that the cross-border Internet of things equipment fault diagnosis and prediction system based on artificial intelligence comprises a data acquisition module, wherein the data acquisition module is used for collecting operation data of the cross-border Internet of things equipment, the data acquisition module is in data connection with a data preprocessing module, and the data acquired by the data acquisition module is recorded as device= { x 1.x2...xn }; the data preprocessing module is used for cleaning, normalizing and extracting features of the acquired data so as to facilitate subsequent analysis and prediction, wherein each device is provided with a Feature code= { f 1.f2...fn } in the process of extracting the features; The AI-CIOT fault diagnosis engine module processes and analyzes the collected cross-border Internet of things equipment data and then uses a pre-stored fault diagnosis algorithm to identify and position equipment; Fault diagnosis mathematical formula n= (ax+by+c)/D; wherein N is the output error (noise), A is the numerator of the system function (transfer function), B is the denominator of the system function (transfer function), C is the input error (noise), D is the co-factor (e.g., gain) of the system function (transfer function); The AI-CIOT fault diagnosis engine module is in data connection with the fault diagnosis algorithm library module, wherein the fault diagnosis algorithm library module is provided with a fault diagnosis algorithm, and the fault diagnosis algorithm comprises a traditional statistical method, a machine learning algorithm and a deep learning algorithm; The fault diagnosis algorithm formula is Z=Y X (a); wherein Z is a fault characteristic equation, Y is a fault characteristic coefficient, X is an input signal (such as voltage and current), a is a fault characteristic index (reflecting the severity of the fault); The AI-CIOT fault diagnosis engine module is in data connection with the equipment state monitoring and predicting module, and the equipment state monitoring and predicting module monitors the state of equipment in real time by using the collected equipment data and a method in a fault diagnosis algorithm library; the equipment state monitoring and predicting module is in data connection with the equipment fault knowledge graph construction module, and the equipment fault knowledge graph construction module uses the collected equipment data and fault diagnosis results to construct an equipment fault knowledge graph for storing and learning the fault mode and rule of the equipment; The failure mode and rule formula is R=Σ (Xi x j)/(ΣXi 2)/(1/2) ΣXj (1/2), where R is the correlation coefficient (reflecting the linear relationship strength between the two variables), xi is the observed value of the first variable, and Xj is the observed value of the second variable. As a preferable technical scheme of the invention, the data acquired by the data acquisition module comprises equipment parameters, running states and environment parameters, the equipment fault knowledge map construction module is in data connection with the deep learning capability integration module, and the deep learning capability integration module integrates a deep learning algorithm into a fault diagnosis system and uses a deep learning model to identify and predict faults of equipment. The advanced learning capacity integrated module is in data connection with the AI model prediction optimization module, and the AI model prediction optimization module provides the interpretability of the AI model to help a user understand how the AI model performs fault diagnosis and model optimization; K in the model optimization process =1/(1+e ((a+bx)));