Status Self-Validation of Sensor Arrays Using Gray Forecasting Model and Bootstrap Method

Abstract

The reliability monitoring of sensor arrays is a challenging and critical issue that directly influences the performance of a measurement and control system. In this paper, a novel strategy based on gray forecasting model GM(1,1) coupled with the bootstrap method is proposed for status self-validation of sensor arrays. The proposed strategy focuses on fault detection, isolation, and recovery (FDIR), data validation and dynamic measurement uncertainty estimation of the sensor arrays. The FDIR scheme can effectively detect and isolate sensor abrupt faults and simultaneously accomplish fault recovery with high accuracy and good timeliness. Furthermore, the proposed FDIR scheme has the advantage of discriminating between fault-free signals with sudden changes and undoubted abrupt faults through the trust mechanism. The model GM(1,1) is updated continuously by a metabolism method to improve the adaptivity of the strategy for reliability monitoring. After signal reconstruction, the data validation and dynamic measurement uncertainty can be evaluated by the bootstrap method without any prior information about measurands. A real metal-oxide gas sensor array experimental system is designed to verify the excellent performance of the proposed strategy. The experimental results demonstrate that the proposed approach is capable of conducting the status self-validation of sensor arrays effectively and improving the reliability of sensor arrays in engineering applications.