Conception and implementation of a data-driven prognostics algorithm for safety–critical systems

Complex engineering systems suffer from internal wears and tears that cannot be measured by sensors. Sudden failure of such systems is hazardous and may endanger human life. To avoid sudden failures, a prognostics system that takes multivariate sensor data and infers system health and then projects the inferred system health into future based on damage progression for remaining useful life (RUL) estimation in real time is needed. Logisticians, engineers, project managers, and others can also benefit from prognostics information to improve performance and reduce cost. Our contribution in this paper is to present a data-driven prognostics approach for RUL estimation of aircraft turbofan engines that run onboard in real time. Kalman filter and neural network are used together to infer system health from several sensor readings. The inferred system health is then projected by another neural network till the end of life for RUL calculation. The algorithm is implemented on Raspberry Pi 2 single-board computer running Windows 10 Internet of Things Core to enable efficient development and deployment of onboard prognostics applications. Data from PHM08 data challenge competition are used for algorithm development and testing. The results show the applicability of this approach for RUL estimation onboard in real time.