苏静雷,王红军,王政博,刘淑聪,王 楠,张顺利.多通道卷积神经网络和迁移学习的燃气轮机转子故障诊断方法[J].电子测量与仪器学报,2023,37(3):132-140 |
多通道卷积神经网络和迁移学习的燃气轮机转子故障诊断方法 |
Fault diagnosis method of gas turbine rotor with multi-channel convolutional neural network and transfer learning |
|
DOI: |
中文关键词: 燃气轮机 多通道卷积 故障诊断 迁移学习方法 |
英文关键词:gas turbine multi-channel convolution fault diagnosis transfer learning method |
基金项目:国家自然科学基金(51975058)项目资助 |
|
Author | Institution |
Su Jinglei | 1. School of Mechanical and Electrical Engineering, Beijing Information Science & Technology University,2. High-End Equipment Intelligent Perception and Control Beijing International Scientific Cooperation Base, Beijing Information Science & Technology University,3. Beijing Key Laboratory of Measurement and Control of Mechanical and Electrical System, Beijing Information Science & Technology University |
Wang Hongjun | 1. School of Mechanical and Electrical Engineering, Beijing Information Science & Technology University,2. High-End Equipment Intelligent Perception and Control Beijing International Scientific Cooperation Base, Beijing Information Science & Technology University,3. Beijing Key Laboratory of Measurement and Control of Mechanical and Electrical System, Beijing Information Science & Technology University |
Wang Zhengbo | 1. School of Mechanical and Electrical Engineering, Beijing Information Science & Technology University,2. High-End Equipment Intelligent Perception and Control Beijing International Scientific Cooperation Base, Beijing Information Science & Technology University,3. Beijing Key Laboratory of Measurement and Control of Mechanical and Electrical System, Beijing Information Science & Technology University |
Liu Shucong | 1. School of Mechanical and Electrical Engineering, Beijing Information Science & Technology University,2. High-End Equipment Intelligent Perception and Control Beijing International Scientific Cooperation Base, Beijing Information Science & Technology University,3. Beijing Key Laboratory of Measurement and Control of Mechanical and Electrical System, Beijing Information Science & Technology University |
Wang Nan | 1. School of Mechanical and Electrical Engineering, Beijing Information Science & Technology University,2. High-End Equipment Intelligent Perception and Control Beijing International Scientific Cooperation Base, Beijing Information Science & Technology University,3. Beijing Key Laboratory of Measurement and Control of Mechanical and Electrical System, Beijing Information Science & Technology University |
Zhang Shunli | 1. School of Mechanical and Electrical Engineering, Beijing Information Science & Technology University,2. High-End Equipment Intelligent Perception and Control Beijing International Scientific Cooperation Base, Beijing Information Science & Technology University,3. Beijing Key Laboratory of Measurement and Control of Mechanical and Electrical System, Beijing Information Science & Technology University |
|
摘要点击次数: 1437 |
全文下载次数: 968 |
中文摘要: |
燃气轮机结构复杂,工况严苛,实际针对运行过程中转子系统故障样本难以获取,样本量少导致故障诊断精度低的问
题,提出一种多通道卷积神经网络(multi-channel convolutional neural network, MCCNN)深度迁移学习的燃气轮机转子故障诊断
方法。 该方法首先以轴承一维原始振动信号为输入,将数据重新排列组合模拟转换二维图像,有效避免实际转换图像的繁琐操
作。 用西储大学(CWRU)的公开轴承数据和西安交通大学(XJTU)公开轴承数据对 MCCNN 模型进行训练更新权重并诊断,取
得了 100%和 99. 95%的故障分类准确率。 以 CWRU 轴承故障数据集为源域,燃气轮机转子故障数据集为目标域,利用迁移学
习将从源域训练得到的模型参数保留,输入目标域数据集进行训练,并对燃气轮机故障数据进行分类,分类准确率达到
97. 78%,由实验结果可知多通道卷积神经网络和迁移学习适应任务需要,可以在转子系统故障样本量少的情况下解决问题。 |
英文摘要: |
In view of the complex structure and severe working conditions of gas turbine, a multi-channel convolutional neural network
(MCCNN) deep transfer learning gas turbine rotor fault diagnosis was proposed for the problem that it was difficult to obtain the rotor
system fault samples during operation and the fault diagnosis accuracy was low due to the small sample size. The method firstly, took the
one-dimensional raw vibration signal of the bearing as the input, then rearranged and combined the data to simulate the converted twodimensional image, effectively avoiding the tedious operation of the actual converted image. The MCCNN model was trained with the
public bearing data from Case Western Reserve University (CWRU) and Xi′an Jiaotong University (XJTU) to update the weights and
diagnose. The fault classification accuracy is up to 99. 95% ~ 100%. CWRU bearing fault datasets were used as the source domain and
the gas turbine rotor fault datasets were used as the target domain, the model parameters obtained from the source domain training were
retrained by using transfer learning method for the target domain datasets and the classification accuracy for the gas turbine fault data was
97. 78%. The experimental results demonstrated that multi-channel convolutional neural networks and transfer learning model is suitable
to the task needs and can solve the problem with a small sample size of rotor system. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|