Constructing robust health indicators from complex engineered systems via anticausal learning

In prognostics and health management (PHM), the task of constructing comprehensive health indicators (HI) from huge amounts of condition monitoring data plays a crucial role. HIs may influence both the accuracy and reliability of remaining useful life (RUL) prediction, and ultimately the assessment of system’s degradation status. Most of the existing methods assume apriori an oversimplified degradation law of the investigated machinery, which in practice may not appropriately reflect the reality. Especially for safety–critical engineered systems with a high level of complexity that operate under time-varying external conditions, degradation labels are not available, and hence, supervised approaches are not applicable. To address the above-mentioned challenges for extrapolating HI values, we propose a novel anticausal-based framework with reduced model complexity, by predicting the cause from the causal models’ effects. Two heuristic methods are presented for inferring the structural causal models. First, the causal driver is identified from complexity estimate of the time series, and second, the set of the effect measuring parameters is inferred via Granger Causality. Once the causal models are known, off-line anticausal learning only with few healthy cycles ensures strong generalization capabilities that helps obtaining robust online predictions of HIs. We validate and compare our framework on the NASA’s N-CMAPSS dataset with real-world operating conditions as recorded on board of a commercial jet, which are utilized to further enhance the CMAPSS simulation model. The proposed framework with anticausal learning outperforms existing deep learning architectures by reducing the average root-mean-square error (RMSE) across all investigated units by nearly 65%.