Talks and presentations

Modern industrial equipments are in the rapid development towards enlargement, complication, and high precision, which poses challenges for ensuring the operating safety. As a key technology to assess system health, RUL prediction is capable of providing effective information for the formulation of maintenance strategy, with the reduction of economic loss caused by faults or anomalies accordingly. Subject to the stochastic uncertainty of failure mechanism and environmental interaction, the temporal correlation of degradation among whole life cycle of the system cannot be ignored. Based on the non-Markovian theoretical framework, we conduct some researches with regard to data-driven fractional degradation process modeling and RUL prediction.

According to a new type of state space-based model, we mainly develop an online RUL prediction method for the above system. In this model, the dependencies among different degradations can be reflected in a diffusion coefficient matrix. Considering that some industrial systems like blast furnaces are usually equipped with multi-sensors, an efficient information fusion strategy also plays an important role in predicting the RUL. Based on multi-dimensional observations, the hidden degradation states are identified through the sequential Kalman filtering. Meanwhile, the unknown parameters in the model are updated iteratively by the expectation maximization (EM) algorithm. At last, the RUL distributions are simulated through the Monte Carlo method, in which three types of failure structures with regard to the degradations are considered. The effectiveness of the proposed method is fully verified by a numerical example as well as a case study about the blast furnace.