齿轮箱非平衡故障数据下的自适应诊断方法
Adaptive diagnosis method based on gearbox unbalanced fault data
田娟 1谢刚 1张顺 1王宇飞1
作者信息
- 1. 太原科技大学 电子信息工程学院,太原 030024;太原科技大学 先进控制与工业智能山西省重点实验室,太原 030024
- 折叠
摘要
[目的]现有智能故障诊断方法面临的挑战包括模型训练依赖于大量标签数据、故障数据获取困难且发生概率不同、对工况影响考虑不足等.为此,提出一种变工况下自适应类间和类内非平衡故障数据的齿轮箱诊断方法.[方法]首先,构建门控局部连接网络,有效降低对标签数据的依赖,直接从原始数据中挖掘数据分布本征特征;其次,设计外部注意力和内部注意力并行机制,考虑变工况下类间故障和类内故障分布差异,进一步调整提取特征权重;最后,采用焦点损失函数,更加关注少数类和困难类样本,实现高质量的非平衡诊断信息挖掘.[结果]经齿轮箱故障试验平台6组非平衡数据测试,验证了所提方法自适应识别非平衡故障数据的有效性和优越性.
Abstract
[Objective]The existing intelligent fault diagnosis methods face challenges,such as model training relying on a large amount of labeled data,difficulty in obtaining fault data with different occurrence probabilities,and insufficient consider-ation of the impact of operating conditions.To address these challenges,a novel gearbox diagnosis method for adaptive inter-class and intra-class unbalanced fault data under varying working conditions was proposed.[Methods]Firstly,a gated local con-nection network was utilized to reduce the reliance on the labeled data and extract intrinsic features directly from the original da-ta.Secondly,a parallel mechanism of external and internal attention was designed to consider the distribution differences among inter-class and intra-class faults under different working conditions,adjusting the weights of extracted features accordingly.Fi-nally,focal loss function was employed to focus on minority and challenging samples,enabling high-quality mining of unbal-anced diagnostic information.[Results]The proposed method is demonstrated by six unbalanced gearbox datasets,which shows great effectiveness and superiority in identifying unbalanced fault data.
关键词
故障诊断/类间和类内非平衡/门控局部连接网络/注意力并行机制/焦点损失Key words
Fault diagnosis/Inter-class and intra-class imbalances/Gated local connection network/Attention parallel mechanism/Focal loss引用本文复制引用
出版年
2025
NETL
NSTL
万方数据