Research on Correlation Mining of Compressor Failure Factors based on Apriori Algorithm
Year: 2024
Type: article
Abstract: In order to reduce the influence of uncertainty factors during the operation of centrifugal compressors, text data mining method is used to extract text data from 942 fault records of centrifugal compressors of a pipeline. The 942 data were classified by 5M1E analysis, and the data set was scanned several times based on Apriori algorithm, and the support, confidence and boost of the itemsets were calculated to discover all the frequent itemsets, so as to generate association rules. The results show that by setting the thresholds of support and confidence, 22 strong association rules are obtained, and "the degree of aging of compressor components" and "the degree of performance degradation of compressor components" are found to have higher support and more association rules, which provides a good solution for the evaluation and control of the factors affecting compressor failure. This provides an effective reference for evaluating and controlling the factors affecting compressor failure.
DOI: 10.54691/e7pfgx04
Authors: Kai Zhang, Liqiong Chen, Sisi Zhang, Weihe Huang
Institution: Southwest Petroleum University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4401792585