Computational Intelligence-Based Prognosis for Hybrid Mechatronic System Using Improved Wiener Process

In this article, a fast krill herd algorithm is developed for prognosis of hybrid mechatronic system using the improved Wiener degradation process. First, diagnostic bond graph used to model and derive global analytical redundancy relations. Based on relations, fault signature matrix mode change isolation can be obtained. Second, in order determine true faults from suspected candidates after isolation, estimation method based adaptive square root cubature Kalman filter proposed when noise distributions are unknown. Then, process incorporating nonlinear term build incipient results. For prognosis, estimate unknown coefficients. After that, probability density function remaining useful life derived identified model. Finally, methods validated by simulations.