A Multi-Fault Diagnosis Method for Sensor Systems Based on Principle Component Analysis

Sensors

Daqi Zhu¹  Jie Bai¹ 

[1] Laboratory of Underwater Vehicles and Intelligent Systems, Shanghai Maritime University, Shanghai, 200135, China

关键词: multi-fault diagnosis;    principal component analysis;    signal reconstruction;    fault detection;    fault isolation;   

DOI  :  10.3390/s100100241

来源: mdpi

【 摘 要 】

A model based on PCA (principal component analysis) and a neural network is proposed for the multi-fault diagnosis of sensor systems. Firstly, predicted values of sensors are computed by using historical data measured under fault-free conditions and a PCA model. Secondly, the squared prediction error (SPE) of the sensor system is calculated. A fault can then be detected when the SPE suddenly increases. If more than one sensor in the system is out of order, after combining different sensors and reconstructing the signals of combined sensors, the SPE is calculated to locate the faulty sensors. Finally, the feasibility and effectiveness of the proposed method is demonstrated by simulation and comparison studies, in which two sensors in the system are out of order at the same time.

【 授权许可】

CC BY   
©2010 by the authors; licensee Molecular Diversity Preservation International, Basel, Switzerland.