Remaining Useful Life Estimation Under Uncertainty with Causal GraphNets
This work addresses the challenge of accurate RUL estimation under uncertainty for engineers and maintenance planners, particularly for systems with complex degradation patterns and irregular data.
This paper introduces a new method for Remaining Useful Life (RUL) estimation using Causal GraphNets, designed to handle large, non-equispaced time series with multi-scale features. The method implicitly learns system evolution at a state-vector level and represents prediction uncertainty as a Gamma distribution.
In this work, a novel approach for the construction and training of time series models is presented that deals with the problem of learning on large time series with non-equispaced observations, which at the same time may possess features of interest that span multiple scales. The proposed method is appropriate for constructing predictive models for non-stationary stochastic time series.The efficacy of the method is demonstrated on a simulated stochastic degradation dataset and on a real-world accelerated life testing dataset for ball-bearings. The proposed method, which is based on GraphNets, implicitly learns a model that describes the evolution of the system at the level of a state-vector rather than of a raw observation. The proposed approach is compared to a recurrent network with a temporal convolutional feature extractor head (RNN-tCNN) which forms a known viable alternative for the problem context considered. Finally, by taking advantage of recent advances in the computation of reparametrization gradients for learning probability distributions, a simple yet effective technique for representing prediction uncertainty as a Gamma distribution over remaining useful life predictions is employed.