Dynamic multiple fault diagnosis based on HMM and QPSO

By analyzing the problems existed about dynamic multiple fault diagnosis (DMFD), a hidden Markov model (HMM) and a formal definition of DMFD are introduced to overcome the invalidation of static multiple fault diagnosis model in some situations. The optimal solution of the objective function is a traditional set covering problem, which belongs to NP completeness problems. This paper decomposes original DMFD problem into several separable subproblems, and solves each of them with binary particle swarm optimization algorithm. The optimal speed is higher than existing methods, and the overall computational complexity and time are reduced, thus the optimal results are also better.