Fault Diagnosis of Gas Turbine Based on Partly Interpretable Convolutional Neural Networks
Fault Diagnosis of Gas Turbine Based on Partly Interpretable Convolutional Neural Networks
复制标题
基于部分可解释卷积神经网络的燃气轮机故障诊断
DOI：
10.1016/j.energy.2020.117467
复制
发表时间：
2020-06
期刊：
影响因子：
9
通讯作者：
Huisheng Zhang
中科院分区：
文献类型：
--
作者：
Dengji Zhou;Qinbo Yao;Hang Wu;Shixi Ma;Huisheng Zhang
燃气轮机的故障诊断对发动机的可靠性和可用性起着至关重要的作用。数据驱动诊断模型已被证明对发动机退化的识别和表征是有用的。但是卷积神经网络（CNN）被认为在时序信号的故障诊断中表现不佳。而且大多数研究都没有涉及到CNN的可解释性，导致模型难以优化并与物理机制相结合。在燃气轮机的故障诊断中，气路故障与传感器故障之间往往存在强耦合，导致两种故障同时发生时故障诊断困难。提出了一种通过优化输入测量参数排序的影响来提高典型CNN性能的新方法。极端梯度增强（XGBoost）用于使排序对CNN诊断准确性的影响可解释。在仿真实验中，优化后的CNN诊断准确率为95.52%，高于常规CNN（准确率91.10%）、RNN（准确率94.21%）等方法。在现场数据分析中，新方法表现出较强的特征提取能力，能够提前发现典型气路故障。该方法具有精度高、稳定性好、可理解性好等优点。
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.
登录
查看更多内容
影响因子：
1.9
作者：
M. Zedda;Riti Singh
通讯作者：
M. Zedda;Riti Singh
影响因子：
6
作者：
S. S. Tayarani-Bathaie-S.;Z. N. S. Vanini;K. Khorasani
通讯作者：
S. S. Tayarani-Bathaie-S.;Z. N. S. Vanini;K. Khorasani
DOI：
10.1115/1.2431391
发表时间：
2007-07
影响因子：
1.5
作者：
R. Bettocchi;M. Pinelli;P. R. Spina;M. Venturini
通讯作者：
R. Bettocchi;M. Pinelli;P. R. Spina;M. Venturini
影响因子：
8.6
作者：
Xie, Tian;Grossman, Jeffrey C.
通讯作者：
Grossman, Jeffrey C.
DOI：
10.1007/978-3-540-72395-0_36
发表时间：
2007-06
期刊：
--
影响因子：
--
作者：
Weiqi Hu;Jingtao Hu
通讯作者：
Weiqi Hu;Jingtao Hu