An EPS-kNN Fault Propagation Analysis Method for Industrial Processes Based on the Fusion of Knowledge and Data

被引：0

作者：

Wang, Lixin ^{[1
]}

Qian, Xiaoyi ^{[1
]}

Feng, Yanliang ^{[2
]}

Dai, Ziheng ^{[1
]}

Kang, Changsheng ^{[1
]}

Guan, Shuai ^{[1
]}

Zhao, Yi ^{[1
]}

机构：

[1] Shenyang Inst Engn, Liaoning Key Lab Power Grid Energy Conservat & Con, Shenyang 110036, Peoples R China

[2] Yingkou Power Supply Co, State Grid Liaoning Elect Power Co Ltd, Yingkou 115000, Peoples R China

来源：

IEEE ACCESS | 2025年 / 13卷

关键词：

Fault diagnosis; Vectors; Process monitoring; Data models; Principal component analysis; Complex networks; Nearest neighbor methods; Mathematical models; Distributed databases; Computational modeling; Complex network model; fault propagation path; k-nearest neighbors; subblock interaction monitoring; IDENTIFICATION; CAUSALITY; NETWORKS; MODEL;

D O I：

10.1109/ACCESS.2025.3558631

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

To reduce the false connections resulting from numerous redundant paths in the fault propagation analysis for industrial processes, an equal probability symbolized k-nearest neighbors (EPS-kNN) fault propagation analysis method based on the fusion of fault data and process knowledge is proposed. Subblock interaction monitoring is introduced to identify potential fault areas and eliminate redundant variables. The complex network model is incorporated into the EPS-kNN-based fault propagation path identification to improve accuracy and interpretability. Different types of faults in the Tennessee Eastman process and Ammonia synthesis process are applied to verify the effectiveness, and the result shows that the proposed method can identify the fault propagation path more effectively and reduce the occurrence of false connections compared with the traditional methods.

引用

页码：78335 / 78347

页数：13

共 37 条

[1] Situated Information Flow between Food Commodity and Regional Equity Markets: An EEMD-Based Transfer Entropy Analysis [J].