基于自适应粒子群相关向量机的液体火箭发动机试车台故障检测

Selection of Relevance Vector Machine (RVM) kernel function parameter is one among ineffectively resolved issues, which is first resolved in the literature by adaptive Particle Swarm Optimization (APSO). This paper takes the advantage of APSO dramatically convergence to optimize and select the RVM kernel parameter, thus forming a novel APSO-RVM method. Furthermore, the method is proposed to the fault detection of engines test system. In order to verify the validity of dramatically effectiveness in fault detection, we demonstrate the proposed APSO-RVM approach by performing both simulations and experiments using Oxygen Valve Outlet Pressure (Pejy) database. The experimental results show that APSO-RVM approach can rapidly detect faults effectively and has a high practical value.