arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.18528cs.LG
收藏

基于迁移学习的输入-输出解耦网络生成不相关残差变量用于化工过程故障诊断

Generation of Uncorrelated Residual Variables for Chemical Process Fault Diagnosis via Transfer Learning-based Input-Output Decoupled Network

Xiangjiang Laboratory(湘江实验室);School of Automation, Central South University(中南大学自动化学院);School of Computer Science, Hunan University of Technology and Business(湖南工商大学计算机学院);Department of Automation, Shanghai Jiao Tong University(上海交通大学自动化系)

Zhuofu Pan, Qingkai Sui, Yalin Wang, Jiang Luo, Jie Chen, Hongtian Chen

AI总结:

本文提出基于迁移学习的输入-输出解耦网络(TDN),通过IDN与预训练VAE结合生成不相关残差变量,实现故障到正常映射,同时完成故障检测与信号估计,并经数值与化学仿真验证有效。

摘要:

过去几十年中,结构解耦在基于模型的故障隔离与估计中发挥了重要作用,其对角传递矩阵设计有助于实现准确的故障定位与重构。然而,传统方法在建模高维非线性和大数据方面效果有限,且解耦思想在数据驱动框架中未得到充分重视。深度学习以处理大数据和复杂特征提取能力著称,近期被用于开发残差生成模型,但仍缺乏与解耦相关的诊断设计。为此,本文提出一种基于迁移学习的输入-输出解耦网络(TDN)用于诊断,它由输入-输出解耦网络(IDN)和预训练的变分自编码器(VAE)组成。在IDN中,通过对角化和并行计算操作生成不相关残差变量。在迁移学习阶段,根据VAE的损失和最大均值差异损失提供正常状态的知识,以指导IDN的训练。训练完成后,IDN学习从故障到正常的映射,从而同时作为故障检测指标和估计的故障信号。最后,通过一个数值例子和一个化学仿真验证了所开发的TDN的有效性。

英文摘要:

Structural decoupling has played an essential role in model-based fault isolation and estimation in past decades, which facilitates accurate fault localization and reconstruction thanks to the diagonal transfer matrix design. However, traditional methods exhibit limited effectiveness in modeling high-dimensional nonlinearity and big data, and the decoupling idea has not been well-valued in data-driven frameworks. Known for big data and complex feature extraction capabilities, deep learning has recently been used to develop residual generation models. Nevertheless, it lacks decoupling-related diagnostic designs. To this end, this paper proposes a transfer learning-based input-output decoupled network (TDN) for diagnostic purposes, which consists of an input-output decoupled network (IDN) and a pre-trained variational autocoder (VAE). In IDN, uncorrelated residual variables are generated by diagonalization and parallel computing operations. During the transfer learning phase, knowledge of normal status is provided according to VAE's loss and maximum mean discrepancy loss to guide the training of IDN. After training, IDN learns the mapping from faulty to normal, thereby serving as the fault detection index and the estimated fault signal simultaneously. At last, the effectiveness of the developed TDN is verified by a numerical example and a chemical simulation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑