该系列研究聚焦于小样本条件下的工业过程故障诊断，提出了一种通用转移框架，通过自适应mixup方法增强样本，确保诊断稳定性和准确性。随着故障样本增加，采用变换矩阵减少诊断误差，无需重新训练框架。实验数据集涉及磁通泄露检测、TEP和跨域多模式监控。另一篇工作则关注零样本故障诊断，利用属性转移实现有效诊断。关键词包括小样本学习、故障诊断、自适应方法、变换矩阵和跨域学习。
1 A General Transfer Framework based on Industrial Process Fault Diagnosis under Small Samples
创新点：
(1)解决小样本迁移；
(2)the adaptive mixup (Admixup) method is presented, which can adaptively expand the fault samples and make the shared distribution smoother to guarantee the stability and accuracy of the fault diagnosis results
(3)transformation matrix is used as an evolutionary channel to reduce the fault diagnosis errors without retraining the framework as fault samples increase.
实验数据集：Magnetic flux leakage detection process,TEP
2 Fault Description Based Attribute Transfer for Zero-Sample Industrial Fault Diagnosis
创新点：零样本过程故障诊断
实验数据集：TEP.TPP
3 Transfer Dictionary Learning Method for Cross-Domain Multi-mode Process Monitoring and Fault Isolation
在第一阶段对数据的处理值得借鉴
实验数据集：CSTH和Industrial Wind Turbine System Monitoring Case
扫一扫
978
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
