Improved Elman neural network in turbine blade fault diagnosis

Abstract

To remotely monitor and maintain large-scale complex equipment in real-time, it is required to create a comprehensive framework integrating remote data collection, transmission, storage, analysis and prediction. The framework is designed to provide manufacturers with proactive, systematic, integrated operation and maintenance service, where the data analysis and health forecasting are the most important part. This paper conducts health management for the turbine blades. An output-hidden feedback (OHF) Elman neural network is developed by adding a self-feedback factor in the context nodes. Thus, this improved method can increase the accuracy of the fault diagnosis for guide vane damage. Through the results, the applicability of this improved Elman neural network has been verified.