Prognostic Modeling Utilizing a High-Fidelity Pressurized Water Reactor Simulator

Abstract

Abstract-Within power generation, ageing assets and an emphasis on more efficient operation of power systems and improved maintenance decision methods has led to a growing focus on asset prognostics. The main challenge facing the implementation of successful asset prognostics in power generation is the lack of available run-to-failure data. This paper proposes to overcome this issue by use of full scope high fidelity simulators to generate the run-to-failure data required. From this simulated failure data a similarity based prognostic approach is developed for estimating the Remaining Useful Life of a valve asset. Case study data is generated by initializing prebuilt industrial failure models within a 970MW Pressurized Water Reactor simulation. Such full scope high fidelity simulators are mainly operated for training purposes, allowing personnel to gain experience of standard operation as well as failures within a safe, simulated operating environment. This research repurposes such a high fidelity simulator to generate the type of data and affects that would be produced in the event of a fault. The fault scenario is then run multiple times to generate a library of failure events. This library of events was then split into training and test batches for building the prognostic model. Results are presented and conclusions drawn about the success of the technique and the use of high fidelity simulators in this manner.Index Terms-Model-based prognostics, remaining useful life, high fidelity simulation, power generation,

Predicting Remaining Useful Life Based on Hilbert–Huang Entropy with Degradation Model

“…Many scholars have proposed various similarity models for RUL. A similarity-based prognostic approach is developed for estimating the RUL of a valve asset using full-scope highfidelity simulators to generate the run-to-failure data [15]. A Bayesian hierarchical model-(BHM-) based prognostics approach is applied to analyze and predict the discharge behavior of Li-ion batteries with variable load profiles and variable amounts of available discharge data [16].…”