A fault diagnosis method for gas turbines based on improved data preprocessing and an optimization deep belief network
Authors:
- Li-Ping YanLYLi-Ping Yan
- Xue-Zhi DongXDXue-Zhi Dong
- Tao WangTWTao Wang
- Qing GaoQGQing Gao
- Chun-Qing TanCTChun-Qing Tan
- De-Tang ZengDZDe-Tang Zeng
- Hua-Liang ZhangHZHua-Liang Zhang
- Hai-Sheng ChenHCHai-Sheng Chen
- 25 October 2019
- journal article
- research article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 31 (1) , 015015
Abstract
A classifier trained by a normalized simulation parameter could not identify an actual fault. In order to solve this problem, improved data preprocessing is proposed which normalizes the deviation of the simulation parameter, thus making preprocessed simulation data more accurate at revealing the performance of an actual gas turbine. Furthermore, an optimization deep belief network (DBN) based on a genetic algorithm is developed, which shows a good classification ability. The superiority of these two methods is validated respectively by a three-shaft gas turbine platform. It has also been found that based on the DBN optimization method, adding outlet temperature parameter T 3 to a high-pressure compressor can significantly improve diagnostic accuracy, increasing it by 10.1%. Finally, the fault experimental result validates the effectiveness of improved data preprocessing combined with an optimization DBN to diagnose faults in actual gas turbines.Keywords
Funding Information
- National Natural Science Foundation of China (51676182)
- National Key R&D Program of China (2018YFB0905101)
This publication has 24 references indexed in Scilit:
- Fault detection and isolation of gas turbine engines using a bank of neural networksJournal of Process Control, 2015
- A New Gas Path Fault Diagnostic Method of Gas Turbine Based on Support Vector MachineJournal of Engineering for Gas Turbines and Power, 2015
- FDI oriented modeling of an experimental SOFC system, model validation and simulation of faulty statesApplied Energy, 2014
- Multiple-Model Sensor and Components Fault Diagnosis in Gas Turbine Engines Using Autoassociative Neural NetworksJournal of Engineering for Gas Turbines and Power, 2014
- A Novel Gas Turbine Engine Health Status Estimation Method Using Quantum‐Behaved Particle Swarm OptimizationMathematical Problems in Engineering, 2014
- Failure diagnosis using deep belief learning based health state classificationReliability Engineering & System Safety, 2013
- Sparse Bayesian Learning for Gas Path DiagnosticsJournal of Engineering for Gas Turbines and Power, 2013
- Data-Driven Fault Detection in Aircraft Engines With Noisy Sensor MeasurementsJournal of Engineering for Gas Turbines and Power, 2011
- An expert system for the diagnosis of faults in rotating machinery using adaptive order-tracking algorithmExpert Systems with Applications, 2009
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006