Fault diagnosis of gas turbine based on partly interpretable convolutional neural networks

被引:125
作者
Zhou, Dengji [1 ]
Yao, Qinbo [1 ]
Wu, Hang [1 ]
Ma, Shixi [1 ]
Zhang, Huisheng [1 ]
机构
[1] Shanghai Jiao Tong Univ, Key Lab Power Machinery & Engn, Educ Minist, Shanghai 200240, Peoples R China
基金
中国国家自然科学基金;
关键词
Gas turbine; Fault diagnosis; Convolutional neural network; Extreme gradient boosting; Interpretation; Field data; PROGNOSTIC MODEL; ENERGY;
D O I
10.1016/j.energy.2020.117467
中图分类号
O414.1 [热力学];
学科分类号
摘要
The fault diagnosis of gas turbines plays a vital role in engine reliability and availability. The data-driven diagnostic model has been verified useful for identifying and characterizing engine degradation. But Convolution Neural Networks (CNN) is considered to perform poorly in the fault diagnosis for time-series signals. And most of the studies do not involve the interpretability of CNN, leading model hard to be optimized and integrated with physical mechanisms. For the fault diagnosis of the gas turbines, strong coupling often exists between gas path faults and sensor faults, making fault diagnosis difficult when both faults occur simultaneously. A novel method is proposed to improve the performance of typical CNN through optimizing the influence of input measurement parameter sequencing. Extreme Gradient Boosting (XGBoost) is used to make the effects of the sequencing on CNN diagnostic accuracy interpretable. In the simulation experiment, the diagnostic accuracy of CNN after optimization is 95.52%, higher than that of conventional CNN (accuracy rate 91.10%), RNN (accuracy rate 94.21%) and other methods. For the analysis of field data, the new method has shown stronger feature extraction ability and can detect typical gas path faults in advance. The new method performs well in precision, stability, and comprehensibility. (C) 2020 Elsevier Ltd. All rights reserved.
引用
收藏
页数:17
相关论文
共 41 条
[1]   Renewable and non-renewable energy, regime type and economic growth [J].
Adams, Samuel ;
Klobodu, Edem Kwame Mensah ;
Apio, Alfred .
RENEWABLE ENERGY, 2018, 125 :755-767
[2]   An ensemble of dynamic neural network identifiers for fault detection and isolation of gas turbine engines [J].
Amozegar, M. ;
Khorasani, K. .
NEURAL NETWORKS, 2016, 76 :106-121
[3]  
[Anonymous], 2017, P IEEE C COMPUTER VI
[4]  
[Anonymous], 2018, PHYS REV LETT
[5]   Identification of sensor faults on turbofan engines using pattern recognition techniques [J].
Aretakis, N ;
Mathioudakis, K ;
Stamatis, A .
CONTROL ENGINEERING PRACTICE, 2004, 12 (07) :827-836
[6]   Artificial intelligence for the diagnostics of gas turbines - Part I: Neural network approach [J].
Bettocchi, R. ;
Pinelli, M. ;
Spina, P. R. ;
Venturini, M. .
JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER-TRANSACTIONS OF THE ASME, 2007, 129 (03) :711-719
[7]  
Botros KK, 2000, ASME TURB EXP 2000 P
[8]   An Approach for Optimal Measurements Selection on Gas Turbine Engine Fault Diagnosis [J].
Chen, Min ;
Hu, Liang Quan ;
Tang, Hailong .
JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER-TRANSACTIONS OF THE ASME, 2015, 137 (07)
[9]  
Chen T., 2015, R PACKAGE VERSION 04
[10]  
Chen T, 2016, ery and Data Mining, V785, P785, DOI [DOI 10.1145/2939672.2939785, 10.1145/2939672.2939785]