北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2023, Vol. 46 ›› Issue (3): 62-66.

• 论文 • 上一篇    下一篇

优化GAN的风电机组齿轮箱故障诊断方法

许同乐,苏元浩,孟良,兰孝升,李云凤   

  1. 山东理工大学 机械工程学院
  • 收稿日期:2021-11-26 修回日期:2022-02-13 出版日期:2023-06-28 发布日期:2023-06-05
  • 通讯作者: 许同乐 E-mail:xutongle@163.com
  • 基金资助:

    国家自然科学基金项目(ZR2021ME221)

Fault Diagnosis Method of Wind Turbine Gearbox by Optimized GAN

XU Tongle, SU Yuanhao, MENG Liang, LAN Xiaosheng, LI Yunfeng   

  • Received:2021-11-26 Revised:2022-02-13 Online:2023-06-28 Published:2023-06-05

摘要:

针对风电机组齿轮箱故障诊断准确率低的问题,提出了一种逻辑回归与遗传算法优化生成对抗网络(GAN)的齿轮箱故障诊断方法。该方法采用逻辑回归与遗传算法优化GAN模型,首先,对输入信号向量化编码通过轮盘式选择对宏基因等位交叉;然后,用最小二乘变异替换等位编码串重构表征向量,并输入卷积网络进行二次迭代;最后,构建逻辑回归辅助分类器表征决策边界,依据回归曲线实现判别器的分类与诊断。实验结果表明,所提方法的故障诊断准确率达到99.72%,证明该方法实现了样本数据的增强和诊断准确率的提高。

关键词: font-family:宋体, ">生成对抗网络;遗传算法;逻辑回归;最小二乘变异;故障诊断font-family:", ">

Abstract:

To solve the issue that the low fault diagnosis accuracy of wind turbine gearbox, a gear fault diagnosis method based on logistic regression and genetic algorithm optimized generative adversarial networks (GAN) is proposed. The GAN model is optimized based on logistic regression and genetic algorithm. First, encoding the input signal to quantization coding by wheel selection on an acer for equipotential crossing. Then, the refactoring characterization vector is reconstructed by replacing the allelic coding string with least square variation, and the convolution network is input for the second iteration. Finally, the method builds auxiliary classifier characterization of decision boundary logistic regression. The discriminator achieves classification and diagnosis based on regression curves. Results show that the fault diagnosis accuracy of this method is up to 99.72%, which proves that the method can enhance the sample data and improve the diagnosis.

Key words: Generative adversarial network, genetic algorithm, logistic regression, least squares variation, fault diagnosis

中图分类号: