国家工程技术图书馆第一分馆 | 机械分馆 | 机械工业信息研究院 | library.gmachineinfo.com

Semi-supervised fault diagnosis of gearbox based on feature pre-extraction mechanism and improved generative adversarial networks under limited labeled samples and noise environment
参考中译:有限标记样本和噪音环境下基于特征预提取机制和改进生成对抗网络的变速箱半监督故障诊断

刊名：	Advanced engineering informatics
作者：	Lijie Zhang（School of Mechatronical and Electrical Engineering, Hebei Agricultural University） Bin Wang（School of Mechatronical and Electrical Engineering, Hebei Agricultural University） Pengfei Liang（School of Mechanical Engineering, Yanshan University） Xiaoming Yuan（School of Mechanical Engineering, Yanshan University） Na Li（School of Mechatronical and Electrical Engineering, Hebei Agricultural University）
刊号：	738C0037
ISSN：	1474-0346
出版年：	2023
年卷期：	2023, vol.58
页码：	102211-1--102211-14
总页数：	14
分类号：	TP18; TP3
关键词：	Fault diagnosis；Gearbox；Generative adversarial network；Wavelet transform
参考中译：	故障诊断;齿轮箱;生成对抗网络;子波变换
语种：	eng
文摘：	Gearboxes are the most widely used component to transfer speed and power in many industries, and high precision gearbox fault diagnosis (FD) is pretty crucial for ensuring the safe operation of the machine. However, traditional FD methods often need a great quantity of labeled data, and are prone to noise interference in practical work, resulting in a relatively low diagnosis accuracy. With the intention of overcoming these problems, this paper proposes a semi-supervised FD approach based on feature pre-extraction mechanism and improved generative adversarial network (IGAN). First, the data is preprocessed by the feature pre-extraction mechanism based on wavelet transform. Then, limited labeled samples and a large number of unlabeled samples are sent to the IGAN model. Finally, two typical gearbox fault datasets are utilized to evaluate the feasibility and effectiveness of the proposed approach in limited labeled samples and noise environment. Trial results denote that the proposed approach has better diagnosis accuracy and anti-noise robustness than other approaches.
参考中译：	变速箱是许多行业中应用最广泛的传递速度和动力的部件，而高精度的变速箱故障诊断是确保机器安全运行的关键。然而，传统的故障诊断方法往往需要大量的标注数据，并且在实际工作中容易受到噪声的干扰，导致诊断准确率相对较低。针对这些问题，本文提出了一种基于特征预提取机制和改进的生成对抗网络(IGAN)的半监督FD方法。首先，利用基于小波变换的特征预提取机制对数据进行预处理。然后，将有限的已标记样本和大量未标记样本发送到IGAN模型。最后，利用两个典型的齿轮箱故障数据集对该方法在有限标签样本和噪声环境下的可行性和有效性进行了评估。实验结果表明，与其他方法相比，该方法具有更好的诊断精度和抗噪能力。