Peng Rongrong, Zhang Xingzhong, Shi Peiming
Nonlinear Dynamics and Application Research Center, Nanchang Institute of Science and Technology, Nanchang 330108, China.
National Engineering Research Center for Equipment and Technology of Cold Rolled Strip, Yanshan University, Qinhuangdao 066004, China.
Entropy (Basel). 2022 Dec 31;25(1):83. doi: 10.3390/e25010083.
The multi-process manufacturing of steel rolling products requires the cooperation of complicated and variable rolling conditions. Such conditions pose challenges to the fault diagnosis of the key equipment of the rolling mill. The development of transfer learning has alleviated the problem of fault diagnosis under variable working conditions to a certain extent. However, existing diagnosis methods based on transfer learning only consider the distribution alignment from a single representation, which may only transfer part of the state knowledge and generate fuzzy decision boundaries. Therefore, this paper proposes a multi-representation domain adaptation network with duplex adversarial learning for hot rolling mill fault diagnosis. First, a multi-representation network structure is designed to extract rolling mill equipment status information from multiple perspectives. Then, the domain adversarial strategy is adopted to match the source and target domains of each pair of representations for learning domain-invariant features from multiple representation networks. In addition, the maximum classifier discrepancy adversarial algorithm is adopted to generate target features that are close to the source support, thereby forming a robust decision boundary. Finally, the average value of the predicted probabilities of the two classifiers is used as the final diagnostic result. Extensive experiments are conducted on an experimental platform of a four-high hot rolling mill to collect the fault state data of the reduction gearbox and roll bearing. The experimental results reveal that the method can effectively realize the fault diagnosis of rolling mill equipment under variable working conditions and can achieve average diagnostic rates of up to 99.15% and 99.40% on the data sets of the rolling mill gearbox and bearing, which are respectively 2.19% and 1.93% higher than the rates achieved by the most competitive method.
钢材轧制产品的多工序制造需要复杂多变的轧制条件相互配合。这些条件给轧机关键设备的故障诊断带来了挑战。迁移学习的发展在一定程度上缓解了可变工况下的故障诊断问题。然而，现有的基于迁移学习的诊断方法仅从单一表征考虑分布对齐，这可能只传递部分状态知识并产生模糊的决策边界。因此，本文提出一种用于热轧机故障诊断的具有双重对抗学习的多表征域自适应网络。首先，设计一种多表征网络结构，从多个角度提取轧机设备状态信息。然后，采用域对抗策略对每对表征的源域和目标域进行匹配，以便从多个表征网络中学习域不变特征。此外，采用最大分类器差异对抗算法生成接近源支持的目标特征，从而形成鲁棒的决策边界。最后，将两个分类器预测概率的平均值作为最终诊断结果。在四辊热轧机实验平台上进行了大量实验，以采集减速箱和轧辊轴承的故障状态数据。实验结果表明，该方法能够有效实现可变工况下轧机设备的故障诊断，在轧机齿轮箱和轴承数据集上的平均诊断率分别达到99.15%和99.40%，分别比最具竞争力的方法高出2.19%和1.93%。
