Approaches for component degradation modelling in time-varying environments with application to residual life prediction

This article explores two approaches for modelling the effect of time-varying environmental conditions on the degradation processes of systems subject to linear/exponential degradation, and derives the procedures for applying the approaches to real-time residual life prediction. The first approach, namely the look-up table (LUT) approach, accesses the effect of environmental conditions empirically from historical data without artificially imposing any additional term on the classical stochastic linear degradation model, provided that the historical training data covers all possible finite environmental conditions. The second approach, namely the multiplicative acceleration effect (MAE) approach, regards that the environmental condition has a multiplicative acceleration/deceleration effect on component degradation rate, and is applicable to the case when the historical data only partially covers the possible finite/infinite environmental conditions. In approach development, the parameter estimation algorithms are explicitly derived so that the historical training samples with time-varying environmental conditions can be used to estimate the prior distributions of component degradation rate. Several numerical experiments designed based on real degradation data of ball grid array solder joints are conducted to evaluate the proposed approaches. The experimental results verify the superiority of the proposed approaches over the classical approach which simply ignores the effect of environmental conditions. The LUT approach slightly outperforms the MAE approach when they are both applicable. On the other hand, the MAE approach still performs well in presence of new environmental conditions.