Remaining Useful Life Estimation Using Fault to Failure Transformation in Process Systems

The remaining useful life (RUL) plays a significant role in the predictive maintenance of process systems. In recent years, data-driven approaches have been used to estimate the RUL. However, without a deeper understanding of process systems and their failure mechanisms, it is challenging to estimate the RUL for process systems. This demands an approach that integrates data with mechanistic understanding. This article proposes a model to estimate the RUL of process systems in real time by monitoring the system's fault condition. The fault is modeled using real-time observed data, while the progression of fault to failure is modeled using mechanistic understanding. These steps are carried out using a novel mixed model combining machine learning-based autonomous fault diagnosis with root cause analysis and a statistical degradation model. The autonomous RUL estimation method is then developed as a self-learning model. A fault dictionary is developed to store the fault patterns and failure margin for different failure conditions. The proposed approach is benchmarked using the Tennessee Eastman process.