Reliability Prediction of Partially Observable Mechanical Equipment Under Variable Operating Conditions

Mechanical equipment, such as the engine in fields of marine and nuclear energy, often works under variable operating conditions due to different task demands. Sensor signals reflecting the actual health status can be observed at discrete monitoring points. To consider these factors jointly, a novel approach to predict the reliability characteristics of mechanical equipment under variable operating conditions is presented in this paper. The equipment degradation is modeled by a dynamic Gamma process, with its shape parameter representing operating condition effect. The equipment age, degradation level and variable operating condition are formulated as the covariate of proportional hazard model. In order to make the evaluation feasible, a matrix-based approximate method is presented to calculate the closed-form solution of reliability characteristics for equipment. A numerical study is demonstrated to show the effectiveness of the model.