Process alarm log mining and modeling based on complex networks
- 22 September 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
To analyze the correlation between alarm logs generated during complex chemical processes, a mining and modeling method of process alarm logs is proposed in this paper. The proposed method mines the correlation between alarm logs based on the Word2Vec and Pearson correlation coefficient, and establishes a quantitative modeling based on the complex networks. Firstly, the alarm variables are mapped to real-valued vectors using the Word2Vec. Then, the association relationships among the alarm logs are analyzed using the Pearson correlation analysis, and the Pearson correlation coefficient matrix and its Boolean matrix are obtained. The Boolean matrix is set as the adjacency matrix, and complex networks can be quantitatively modelled. Finally, the effectiveness of the proposed method is verified by an actual case.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 15 references indexed in Scilit:
- Functional importance evaluation approach for cloud manufacturing services based on complex network and evidential reasoning ruleComputers & Industrial Engineering, 2022
- Intelligent HAZOP analysis method based on data miningJournal of Loss Prevention in the Process Industries, 2022
- A fault diagnosis method for complex chemical process based on multi-model fusionChemical Engineering Research and Design, 2022
- One step forward for smart chemical process fault detection and diagnosisComputers & Chemical Engineering, 2022
- A new unsupervised data mining method based on the stacked autoencoder for chemical process fault diagnosisComputers & Chemical Engineering, 2020
- Data mining and clustering in chemical process databases for monitoring and knowledge discoveryJournal of Process Control, 2018
- Industrial alarm systems: Challenges and opportunitiesJournal of Loss Prevention in the Process Industries, 2017
- An Overview of Industrial Alarm Systems: Main Causes for Alarm Overloading, Research Status, and Open ProblemsIEEE Transactions on Automation Science and Engineering, 2015
- Monitoring of chemical industrial processes using integrated complex network theory with PCAChemometrics and Intelligent Laboratory Systems, 2015
- A combined analysis of plant connectivity and alarm logs to reduce the number of alerts in an automation systemJournal of Process Control, 2013