基于加权子域自适应对抗网络的齿轮箱变工况故障诊断  

Fault diagnosis of gearbox under variable working condition based on weighted subdomain adaptive adversarial network

作　　者：张慧云[1] 左芳君 余熹 杨婷 ZHANG Huiyun;ZUO Fangjun;YU Xi;YANG Ting(School of Intelligent Manufacturing,Chengdu Technological University,Chengdu 610031,China;College of Mechanical Engineering,Sichuan University,Chengdu 610065,China)

机构地区：[1]成都工业学院智能制造学院,成都610031 [2]四川大学机械工程学院,成都610065

出　　处：《机械强度》2025年第3期96-103,共8页Journal of Mechanical Strength

基　　金：四川省自然科学基金面上项目(24NSFSC1295)。

摘　　要：实际工程中齿轮箱受复杂多变的运行环境影响,导致单一振动信号难以准确有效地表征齿轮箱在不同工况下的故障信息。为此,提出了一种基于加权子域自适应对抗网络的齿轮箱变工况故障诊断方法。首先,采用多源异构信号融合策略,将振动信号时频图、电流信号格拉姆矩阵和红外热力图转换为多通道数据集,从不同视角描述齿轮箱运行状态;其次,构建嵌入高效通道注意力机制(Efficient Channel Attention,ECA)的自校正卷积神经网络(Self-calibrated Convolutions Network,SCNet)作为特征提取器,动态调整多源异构信号间相互作用和依赖关系,平衡源域和目标域的多源异构数据间尺度差异;再次,在特征提取器和域判别器进行对抗训练的同时,引入最大均值差异(Maximum Mean Discrepancy,MMD)和线性判别分析(Linear Discriminant Analysis,LDA)衡量当前跨域任务特征表示的域对齐程度及诊断任务决策边界,并构造动态平衡因子实时调整域对齐损失和类分辨性损失,有效地对齐源域和目标域每个类空间。最后,通过采集的齿轮箱变工况故障数据集进行验证。结果表明,所提方法在不同工况的诊断精度均达到95%以上,证明了所提方法的可行性和有效性。In practical engineering,gearboxes are subject to complex and variable operating environments,which hinder the ability of a single vibration signal to accurately and effectively represent fault information under different working conditions.To address this issue,a gearbox fault diagnosis method for variable working conditions based on weighted subdomain adaptive adversarial networks was proposed.Initially,a multi-source heterogeneous signal fusion strategy was employed to transform vibration signal spectrograms,current signal Gramian matrices,and infrared thermograms into a multichannel dataset,offering diverse perspectives on gearbox operational states.Subsequently,a self-calibrated convolutions network(SCNet)incorporating an efficient channel attention(ECA)mechanism acted as a feature extractor,dynamically adjusting the interactions and dependencies between multi-source heterogeneous signals to balance the scale differences between the source and target domain heterogeneous data.Concurrently,during adversarial training of the feature extractor and domain discriminator,maximum mean discrepancy(MMD)and linear discriminant analysis(LDA)were introduced to measure the domain alignment degree of the current cross-domain task feature representation and the diagnostic task decision boundary.A dynamic balancing factor was constructed to real-time adjust domain alignment loss and class discriminability loss,effectively aligning each class space between the source and target domains.Finally,validated by a collected gearbox fault dataset under variable operating conditions.The results show that the proposed method achieves diagnostic accuracy exceeding 95%across different conditions,demonstrating its feasibility and effectiveness.

关 键 词：齿轮箱 不同工况 故障诊断 数据融合 域自适应 

分 类 号：TH165.3[机械工程—机械制造及自动化] TP18[自动化与计算机技术—控制理论与控制工程]