Fault-tolerant control based on belief rule base expert system for multiple sensors concurrent failure in liquid launch vehicle

This paper develops a new fault-tolerant control (FTC) of wireless sensor network in vehicle that aims to solve three problems in engineering practice: lack of data in sensor failure state, high system complexity and multiple sensors concurrent failure. In the new FTC framework, a new belief rule base expert system for concurrent events is developed to aggregate the data and knowledge and handle the concurrent events. In the FTC framework, fault detection and diagnosis (FDD) part is firstly conducted, and then, the output of the failure sensors is reconstructed based on the output reconstruction strategy by the observation information from the available sensors. In the FDD model, the fault diagnosis strategy of proximity classification based on distance is applied in the FDD model. To further improve the performance of the FTC framework, a new optimization model is proposed. A case study is conducted to illustrate the effectiveness of the proposed framework.