Abstract
There are many unknown abnormal working conditions in industrial production. It is difficult to identify unknown abnormal working conditions because there are few relative sample and experience in this field. To solve this problem, a new identification method combining two-step clustering analysis and signed directed graph (TSCA-SDG) is proposed. Firstly, through correlation analysis and R-type clustering analysis, the variables are effectively selected and extracted. Then, a two-step clustering analysis was carried out on the selected variables to obtain the cluster results. Through the establishment of the signed directed graph (SDG) model, the causes of abnormal working conditions and their mutual influence are deduced from the mechanism. The application of the TSCA-SDG method in the catalytic cracking process shows that this method has good performance for abnormal condition identification.
Highlights
This paper proposes a method for identifying unknown abnormal conditions in the catalytic cracking process by combining the two-step clustering analysis with the signed directed graph (SDG)
This paper proposes a feature extraction and selection method that comprehensively considers correlation analysis and R-type clustering analysis to effectively solve this problem
For the two-step clustering method, the optimal number of classifications is judged according to the Schwarz Bayesian Information Criterion (BIC) and Akaike Information according to the Schwarz Bayesian Information Criterion (BIC) and Akaike Information
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. With the rapid development of industrial big data and computer technology, data-based fault diagnosis technology is more and more widely applied [10,11,12,13]. TSC is a clustering method recently developed It occupies fewer memory resources and has a fast computing speed for large datasets. In the identification of working conditions of industrial big data, TSC can accurately identify and cluster data of abnormal working condition. The above cluster methods have received in-depth development, their analysis of specific industrial mechanism is insufficient. This paper proposes a method for identifying unknown abnormal conditions in the catalytic cracking process by combining the two-step clustering analysis with the SDG model (TSCA-SDG). TSCA-SDG method is introduced in detail, followed the principles of two-step clustering analysis andand
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
