在实际工况中，发电机中传感器采集到的故障样本数据有限，使用基于深度学习的方法进行故障诊断存在过拟合问题导致模型泛化能力较差以及诊断精度不高。为了解决这个问题，本文采用样本扩充的思路，提出了一种改进的辅助分类器条件深度卷积生成对抗网络(modified auxiliary classifier conditional deep convolutional generative adversarial network，MACDCGAN)的故障诊断方法。通过对采集的一维时序信号进行小波变换增强特征，构建简化结构参数的条件深度卷积生成对抗网络模型生成样本，并在模型中采用Wasserstein距离优化损失函数解决训练过程中存在模式崩塌和梯度消失的缺点；通过添加一个独立的分类器来改进分类模型的兼容性，并在分类器中引入学习率衰减算法增加模型稳定性。实验结果表明，该方法可以有效的提高故障诊断的精度，并且验证了所提模型具有良好的泛化性能。
Abstract
In actual working conditions, the fault sample data collected by sensors in the generator is limited, and there is over-fitting problem in fault diagnosis based on deep learning method, which leads to poor generalization ability of the model and low diagnosis accuracy. In order to solve this problem, this paper adopts the idea of sample expansion, and proposes an improved fault diagnosis method of auxiliary classifier Conditional Deep Convolutive Generative Adversarial Network (MACDCGAN). By enhancing the characteristics of the collected one-dimensional time series signals by wavelet transform, the conditional depth convolution of simplified structural parameters is constructed to generate the samples of the countermeasure network model, and the Wasserstein distance optimization loss function is used in the model to solve the shortcomings of pattern collapse and gradient disappearance in the training process. An independent classifier is added to improve the compatibility of the classification model, and the learning rate attenuation algorithm is introduced into the classifier to increase the stability of the model. The experimental results show that this method can effectively improve the accuracy of fault diagnosis, and verify that the proposed model has good generalization performance.
关键词
发电机 /
特征提取 /
生成对抗网络 /
卷积神经网络 /
故障诊断
{{custom_keyword}} /
Key words
Generator /
Feature extraction /
Generative Adversarial Networks /
Convolutional Neural Network /
Fault diagnosis
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Zhang Z， Li W，Jia X. CFD Investigation of a Mobula Birostris-Based Bionic Vortex Generator on Mitigating the Influence of Surface Roughness Sensitivity of a Wind Turbine Airfoil[J].IEEE Access，2020，8:223889 -223896.
[2] Yi C，Qin J，Xiao H，et al. Second-order Synchro squeezing Modified S Transform for wind turbine fault diagnosis[J]. Applied Acoustics，2022，189: 108614.
[3] Lim D H，Kim K S.Development of deep learning-based detection technology for vortex-induced vibration of a ship's propeller[J]. Journal of Sound and Vibration，2021: 116629.
[4] Zhang T，Liu S，Wei Y，et al. A novel feature adaptive extraction method based on deep learning for bearing fault diagnosis[J]. Measurement，2021，185: 110030.
[5] 陈保家,陈学力,沈保明,等.CNN-LSTM深度神经网络在滚动轴承故障诊断中的应用[J].西安交通大学学报，2021，55(06):28-36.
CHEN Baojia, CHEN Xueli, SHEN Baoming, et al. Xiao Nengqi. Application of CNN-LSTM deep neural network in fault diagnosis of rolling bearings [J]. Journal of Xi'an Jiaotong University, 2021, 55(06) :28-36.
[6] Huang K，Wu S，Li F，et al. Fault Diagnosis of Hydraulic Systems Based on Deep Learning Model With Multirate Data Samples[J]. IEEE Transactions on Neural Networks and Learning Systems，2021.
[7] Zou Y，Zhang Y，Mao H. Fault diagnosis on the bearing of traction motor in high-speed trains based on deep learning[J]. Alexandria Engineering Journal，2021，60(1): 1209-1219.
[8] Wang X，Mao D，Li X. Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network[J]. Measurement，2021，173: 108518.
[9] Saravanakumar R，Krishnaraj N，Venkatraman S，et al. Hierarchical symbolic analysis and particle swarm optimization based fault diagnosis model for rotating machineries with deep neural networks[J]. Measurement，2021，171: 108771.
[10] Zhou F，Yang S，Fujita H，et al. Deep learning fault diagnosis method based on global optimization GAN for unbalanced data[J]. Knowledge-Based Systems，2020，187: 104837.
[11] Liu H，Zhou J，Xu Y，et al. Unsupervised fault diagnosis of rolling bearings using a deep neural network based on generative adversarial networks[J].Neurocomputing， 2018，315: 412-424.
[12] Wang Z，Wang J，Wang Y. An intelligent diagnosis scheme based on generative adversarial learning deep neural networks and its application to planetary gearbox fault pattern recognition[J]. Neurocomputing，2018，310: 213-222.
[13] Zhu Y, Zhuang F, Wang J, et al. Deep subdomain adaptation network for image classification[J]. IEEE transactions on neural networks and learning systems, 2020, 32(4): 1713-1722.
[14] Jiefei G U，Yang Q I，Ziyi Z，et al. Fault diagnosis of rolling bearings based on generative adversarial network and convolutional denoising auto-encoder[J]. Journal of Advanced Manufacturing Science and Technology，2022，2(2): 2022009-2022009.
[15] 冯永,张春平,强保华,等.GP-WIRGAN：梯度惩罚优化的Wasserstein图像循环生成对抗网络模型[J].计算机学报,2020,43(02):190-205.
FENG Yong, ZHANG Chunping, QIANG Baohua, et al. GP-WIRGAN: Wasserstein Image Cyclic Generative Adversarial Network Model with Gradient Penalty Optimization [J]. Journal of Computer Science, 2020, 43(02): 190- 205.
[16] Wang X，Gupta A. Generative image modeling using style and structure adversarial networks[C] European conference on computer vision. Springer，Cham，2016: 318-335.
[17] Zhang D，Ning Z Q，Yang B，et al. Fault diagnosis of permanent magnet motor based on DCGAN-RCCNN[J]. Energy Reports，2022，8: 616-626.
[18] Zhu F, He M, Zheng Z. Data augmentation using improved cDCGAN for plant vigor rating[J]. Computers and Electronics in Agriculture, 2020, 175: 105603.
[19] Silik A，Noori M，Altabey W A，et al. Comparative analysis of wavelet transform for time-frequency analysis and transient localization in structural health monitoring[J]. Structural Durability & Health Monitoring，2021，15(1): 1.
[20] Cheng, Yiwei, et al. "Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network." Knowledge-Based Systems 216 (2021): 106796.
[21] Loshchilov I，Hutter F. Decoupled weight decay regularization[J].arXiv preprint arXiv:1711.05101，2017.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(2736 KB)
