A Degradation Hidden Semi-Markov Model for Predicting Asset Health and Remaining Useful Life

An effective tactical asset management program, incorporating condition and degradation assessments, is essential for asset-intensive organizations to make informed decisions about maintenance and renewal. Since asset degradation is an inherently stochastic phenomenon, models based on stochastic processes are the most suitable approach for accurately predicting it. Asset condition assessment and event data are collected and recorded during inspection and maintenance activities to model equipment degradation. A degradation model that integrates these data associated with assets is highly desirable for predicting the effective and reliable remaining useful life (RUL). This study develops a novel Degradation Hidden Semi-Markov Model that uses both failure and condition data to predict RUL of critical pumps in the wastewater network of a regional town in South Australia. To evaluate the model's performance and outcomes, a portion of the condition data was reserved as the test dataset, while the remaining historical condition data was used for degradation and RUL modeling. In addition, the predicted RUL was validated using both forward-backward and Viterbi algorithms. Results showed not only the expected asset health state closely followed of the actual, but also the absolute prediction error of the estimated RUL using these algorithms was minimal.