Product technical life prediction based on multi-modes and fractional Levy stable motion

Some equipment degradation processes have long-range dependence (LRD) and multi-modes characteristics. The multi-modes are caused by changes of the external environment, the operating conditions and the loads throughout the lifetime of the equipment. In the present paper, a multi-modal Fractional Levy Stable Motion (FLSM) degradation model is developed to predict the product technical life or remaining useful life (RUL) of equipment. The advantage of FLSM lies in its LRD characteristics and its ability to describe multiple stochastic distributions as the tail parameter a changes. Multi-modes, switching points and modal categories are identified by change point detection and clustering algorithms, and a Markov state transition matrix describes the modes switching law. The probability density function (PDF) of RUL is established by Monte Carlo Simulation. The effectiveness of the prediction model is verified by a practical example of a blast furnace. (C) 2021 Elsevier Ltd. All rights reserved.

Automated summary

This paper proposes a multi-modal FLSM degradation model for predicting the product technical life or remaining useful life of equipment. By identifying multi-modes, switching points, and modal categories, and utilizing Markov state transition matrix and Monte Carlo Simulation, the effectiveness of the prediction model is validated.