Data-model interactive Rul prediction of stochastic degradation devices with multiple uncertainty quantification and multi-sensor information fusion

Abstract

This paper proposes an improved remaining useful life (RUL) prediction method for stochastic degradation devices monitored by multi-source sensors under data-model interactive framework. Firstly, the interrelationships among sensors are established using k-nearest neighbor (KNN), and the composite health index (CHI) is constructed by aggregating the multi-source sensor information through the graph convolutional network (GCN). Secondly, a stochastic degradation model with triple uncertainty at any initial degradation level is established to improve the matching degree between the stochastic degradation model and the actual degradation process. Then, a data-model interactive mechanism is proposed to form a closed-loop optimization between the CHI construction and the stochastic degradation model to enhance the RUL prediction accuracy of the device. Finally, experiments on aero-engine and tool datasets indicate that the proposed method can improve the comprehensive performance by at least 20% compared with the original method of the data-model interactive framework, which verifies its effectiveness and superiority.