文献类型：期刊文献

中文题名：基于特征加权的化工过程中未见模式的故障诊断

英文题名：Fault Diagnosis of Unseen Modes in Chemical Processes Based on Feature Weighted

作者：易瓅[1];侍洪波[1];宋冰[1];陶阳[1]

机构：[1]华东理工大学信息科学与工程学院,上海200237

年份：2025

卷号：51

期号：5

起止页码：693

中文期刊名：华东理工大学学报(自然科学版)

外文期刊名：Journal of East China University of Science and Technology

收录：;北大核心:【北大核心2023】；

基金：国家自然科学基金(62073141,62073140,62103149)。

语种：中文

中文关键词：故障诊断;深度神经网络;领域泛化;领域偏移;田纳西-伊士曼工艺

外文关键词：fault diagnosis;deep neural networks;domain generalization;domain shift;Tennessee-Eastman process

摘要：故障诊断是化工行业确保生产安全和产品质量的关键。现有的基于深度神经网络的故障诊断模型利用特定条件下的样本训练,忽视了其领域泛化能力,导致在复杂多变的场景中诊断性能出现明显下降。针对这一问题,提出了一种基于加权的领域特定特征去除网络(Weighted-Based Domain-Specific Feature Removal Network,WBDSFRN)。WBDSFRN包含一个基于加权的领域特定特征去除模块,在训练阶段区分领域不变特征和领域特定特征;在测试阶段尽量将目标域特定特征去除,从而减轻领域偏移的影响。最后,利用田纳西-伊士曼工艺(Tennessee-Eastman Process,TEP)进行实验。结果表明,WBDSFRN的性能优于现有方法,在复杂多变的操作条件下也能表现出稳健的诊断性能。
Fault diagnosis is critical for ensuring production safety and product quality within the chemical industry.Existing fault diagnosis models that leverage deep neural networks are typically trained using samples from specific operating conditions,neglecting the domain generalization capabilities of these models.This leads to a significant decline in diagnostic performance in complex and variable scenarios.To address this issue,a weightedbased domain-specific feature removal network(WBDSFRN)is proposed.WBDSFRN incorporates a weighted-based domain-specific feature removal module,which effectively discriminates between domain-invariant and domainspecific features during the training phase.In the testing phase,the model largely eliminates domain-specific features of the target domain to mitigate domain shift effects.Finally,experiments are conducted using the Tennessee-Eastman process(TEP).The results demonstrate that WBDSFRN significantly outperforms existing approaches and exhibits robust diagnostic performance even under complex and variable operating conditions.