Fault Diagnosis Model of Information System Based on Joint Neural Network and Observability Technology
Yansheng Qu, Chao Ma, Shaosong Zhu, Weiting Zhao, Linlin Tang, Bintai Xu, Lingzhen Meng, Youxin Wang · 2024
The aim of this study is to develop an efficient fault diagnosis method for information systems by combining joint neural network and observability technology. Firstly, the operation data of the information system is collected and pre-processed to ensure data quality and consistency. Then, we design and train a joint neural network (JNN) that combines the advantages of convolutional neural networks (CNN) and long short-term memory networks (LSTM) for feature extraction and time series data modeling. Then, the observability analysis technology is used to determine the observable state variables of the system to ensure the accuracy and real-time fault diagnosis. Evaluate model performance with cross-validation and test data, including metrics such as accuracy, recall, and F1-score. The experimental results show that the fault diagnosis method combined with JNN and observability technology is significantly superior to the traditional method in feature extraction, fault detection and diagnosis accuracy.