Prognosis of Blade Material Fatigue Using Elman Neural Networks

Ji Hong Yan; P.X. Wang

doi:10.4028/www.scientific.net/AMM.10-12.558

Paper Titles

Development of a Self-Feedback Adjustment Piezoelectric Ceramic Power Supply
p.538

Defect Identification and Classification for Digital X-Ray Images
p.543

A Cluster-Based Wavelet Feature Extraction Method for Machine Fault Diagnosis
p.548

Bearing Fault Diagnosis Using Gaussian Mixture Models (GMMs)
p.553

Prognosis of Blade Material Fatigue Using Elman Neural Networks
p.558

The Design of Software Platform of Data Transformation and Integration Based on J2EE Technology
p.563

A Study of Cutting State Monitoring System Based on Virtual Instrument
p.568

A Hybrid Feature Selection Based on Ant Colony Optimization and Probabilistic Neural Networks for Bearing Fault Diagnostics
p.573

Depth Control Method of AFM-Based Nanomachining with Diamond Tip in Deflection Mode
p.578

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 10-12Prognosis of Blade Material Fatigue Using Elman...

Prognosis of Blade Material Fatigue Using Elman Neural Networks

Abstract:

Prognosis of major components such as blades, rotors, valves of steam turbine is crucial to reducing operating and maintenance costs. Prognostic strategies can assist to detect, classify and predict developing faults, guarantee reliable, efficient and continuous operation of electric plants, and may even result in saving lives. In this paper, a recurrent neural network based strategy was developed for blade material degradation assessment and fatigue damage propagation prediction. Two Elman Neural Networks were developed for fatigue severity assessment and trend prediction correspondingly. The performance of the proposed prognostic methodology was evaluated by using blade material fatigue data collected from a material testing system. The prognostic method is found to be a reliable and robust material fatigue predictor.