This paper explains the fusion of the physics-based material degradation mechanism with the statistics-based data modeling approach for predicting the degradation rate of photovoltaic (PV) modules. The degradation of PV module is mainly associated with the module construction type and climatic condition at its use location. The aim of this paper is to quantify the effect of dynamic environmental stresses (dynamic covariates) on the power degradation of the module over its lifetime. There are various physics-based models, such as Arrhenius model, for understanding the physical or chemical reaction-related root causes of PV degradation. But, to estimate the underlying material properties, such as activation energy (Ea), statistical modeling plays a key role. In addition, instead of being continuously monitored, the performance characteristics of PV modules are often measured only at intervals like quarterly or annually, which makes it difficult to model the complete degradation path of the module. On the other hand, the information on dynamic covariates is recorded more frequently with the development of sophisticated sensors and data acquisition systems. This information can be integrated through physics-based models to study the effects of environmental variables in degradation processes. Hence, in this paper, a cumulative exposure model is used to link the module degradation path and the environmental variables, including module temperature (both static and cyclic), ultraviolet radiation, and relative humidity, which are recorded as multivariate time series.

Onboard sensors, which constantly monitor the states of a system and its components, have made the predictive maintenance (PdM) of a complex system possible. To date, system reliability has been extensively studied with the assumption that systems are either single-component systems or they have a deterministic reliability structure. However, in many realistic problems, there are complex multi-component systems with uncertainties in the system reliability structure. This paper presents a PdM scheme for complex systems by employing discrete time Markov chain models for modelling multiple degradation processes of components and a Bayesian network (BN) model for predicting system reliability. The proposed method can be considered as a special type of dynamic Bayesian network because the same BN is repeatedly used over time for evaluating system reliability and the inter-time–slice connection of the same node is monitored by a sensor. This PdM scheme is able to make probabilistic inference at any system level, so PdM can be scheduled accordingly.

Reliability-based design optimization (RBDO) has a probabilistic constraint that is used for evaluating the reliability or safety of the system. In modern engineering design, this task is often performed by a computer simulation tool such as finite element method (FEM). This type of computer simulation or computer experiment can be treated a black box, as its analytical function is implicit. This paper presents an efficient sampling strategy on learning the probabilistic constraint function under the design optimization framework. The method is a sequential experimentation around the approximate most probable point (MPP) at each step of optimization process. Our method is compared with the methods of MPP-based sampling, lifted surrogate function, and nonsequential random sampling. We demonstrate it through examples.