Abstract
In recent years, there has been a growing interest in the connectivity of vehicles. This connectivity allows for the monitoring and analysis of large amount of sensor data from vehicles during their normal operations. In this paper, an approach is proposed for analyzing such data to determine a vehicle component’s remaining useful life named time-to-failure (TTF). The collected data is first used to determine the type of performance degradation and then to train a regression model to predict the health condition and performance degradation rate of the component using a machine learning algorithm. When new data is collected later for the same component in a different system, the trained model can be used to estimate the time-to-failure of the component based on the predicted health condition and performance degradation rate. To validate the proposed approach, a quarter-car model is simulated, and a machine learning algorithm is applied to determine the time-to-failure of a failing shock absorber. The results show that a tap-delayed nonlinear autoregressive network with exogenous input (NARX) can accurately predict the health condition and degradation rate of the shock absorber and can estimate the component’s time-to-failure. To the best of the authors’ knowledge, this research is the first attempt to determine a component’s time-to-failure using a machine learning algorithm.
Predicting Time-to-Failure of Plasma Etching Equipment using Machine Learning
