|国家科技期刊平台
首页|期刊导航|计算机应用研究|标签噪声下结合对比学习与邻域样本分析的故障诊断方法

标签噪声下结合对比学习与邻域样本分析的故障诊断方法OA北大核心CSTPCD

Fault diagnosis method via contrastive learning and neighborhood sample analysis under label noise

中文摘要英文摘要

当前基于深度学习的故障诊断方法依赖于标注完备的训练样本,当数据集中存在噪声标签时,模型会对噪声数据过拟合,影响泛化能力.为实现模型在采用标签噪声进行训练的情况下对设备运行工况的精确识别,提出一种结合对比学习与邻域样本分析的故障诊断方法.首先采用对比学习方法对模型进行预训练,拉近模型特征空间中的相似样本映射距离,实现判别能力增强;随后,基于特征相似度寻找每个样本最相似的近邻用以计算训练标签可靠性并据此执行样本划分以及标签纠正,构建更为可靠的训练子集;最后在训练过程中引入标签重加权以及一致性正则化操作增强模型鲁棒性.此外,通过同时训练两个网络模型以交替构建训练子集用于另一网络训练过程,缓解单网络模型训练框架易引起的认知偏差问题.在公共数据集上进行实验验证,结果表明所提方法能够有效识别并纠正噪声标签,在较高噪声标签情况下仍能保持良好的诊断性能.

Nowadays due to the dependence of fault diagnosis method based on deep learning on well-labeled training dataset,which will lead to the problem that deep neural network can easily overfit those noisy labels and affect the generalization of net-work under the condition of label noise.In order to achieve accurate recognition of equipment operating conditions in the net-work trained with label noise,this paper proposed a fault diagnosis method via contrastive learning and neighborhood sample analysis.Firstly,the method used contrastive learning to pre-train the model,which could reduce the embedding distance of similar samples in the feature space and achieved improving the ability of optimizing the feature representation ability of the network.Then,the method utilized the feature similarity to find each sample's closest neighbors to estimate the reliability of training labels which could separate all training samples into a clean or noisy subset and implemented label correction on noisy subset.After that,it established a more reliable training subset.Iastly,the proposed method made use of label reweighting and con-sistency regularization to enhance robustness of network.In particular,two networks got trained simultaneously where each network used the dataset division from the other network during the training process,which could mitigate confirmation bias caused by single network model training framework.The experimental results on public dataset demonstrate that proposed method can verify and cor-rect the noisy labels impressively well and maintain great fault diagnosis performance under the condition of high-level noisy labels.

金泽中;叶春明

上海理工大学管理学院,上海 200093

机械工程

对比学习标签噪声标签纠正故障诊断

contrastive learningnoisy labellabel correctionfault diagnosis

《计算机应用研究》 2024 (010)

3044-3052 / 9

上海市哲学社会科学一般项目(2022BGL010);国家自然科学基金资助项目(71840003);上海市科学技术委员会"科技创新行动计划"软科学重点项目(20692104300)

10.19734/j.issn.1001-3695.2024.02.0036

评论