Physically-consistent-WGAN based small sample fault diagnosis for industrial processes  

作　　者：Siyu Tang Hongbo Shi Bing Song Yang Tao Shuai Tan 

机构地区：[1]Key Laboratory of Smart Manufacturing in Energy Chemical Process,Ministry of Education,East China University of Science and Technology,Shanghai 200237,China

出　　处：《Chinese Journal of Chemical Engineering》2025年第2期163-174,共12页中国化学工程学报(英文版)

摘　　要：In real industrial scenarios, equipment cannot be operated in a faulty state for a long time, resulting in a very limited number of available fault samples, and the method of data augmentation using generative adversarial networks for smallsample data has achieved a wide range of applications. However, the current generative adversarial networks applied in industrial processes do not impose realistic physical constraints on the generation of data, resulting in the generation of data that do not have realistic physical consistency. To address this problem, this paper proposes a physical consistency-based WGAN, designs a loss function containing physical constraints for industrial processes, and validates the effectiveness of the method using a common dataset in the field of industrial process fault diagnosis. The experimental results show that the proposed method not only makes the generated data consistent with the physical constraints of the industrial process, but also has better fault diagnosis performance than the existing GAN-based methods.

关 键 词：Chemical processes Fault diagnosis Physical consistency Generative adversarial networks Small sample data 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]