Design and realization of compressor data abnormality safety monitoring and inducement traceability expert system

Salvato in:
Dettagli Bibliografici
Pubblicato in:PLoS One vol. 20, no. 1 (Jan 2025), p. e0315917
Autore principale: Wang, Yuan
Altri autori: Hu, Shaolin
Pubblicazione:
Public Library of Science
Soggetti:
Accesso online:Citation/Abstract
Full Text
Full Text - PDF
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!

MARC

LEADER 00000nab a2200000uu 4500
001 3156421470
003 UK-CbPIL
022 |a 1932-6203 
024 7 |a 10.1371/journal.pone.0315917  |2 doi 
035 |a 3156421470 
045 2 |b d20250101  |b d20250131 
084 |a 174835  |2 nlm 
100 1 |a Wang, Yuan 
245 1 |a Design and realization of compressor data abnormality safety monitoring and inducement traceability expert system 
260 |b Public Library of Science  |c Jan 2025 
513 |a Journal Article 
520 3 |a Centrifugal compressors are widely used in the oil and natural gas industry for gas compression, reinjection, and transportation. Fault diagnosis and identification of centrifugal compressors are crucial. To promptly monitor abnormal changes in compressor data and trace the causes leading to these data anomalies, this paper proposes a security monitoring and root cause tracing method for compressor data anomalies. Additionally, it presents an intelligent system design method for fault tracing in compressors and localization of faults from different sources. This method starts from petrochemical big data and consists of three parts: fault dynamic knowledge graph construction, instrument data sliding fault-tolerant filtering, and the fusion and reasoning of fault dynamic knowledge graph and instrument data variation monitoring. The results show that this method effectively overcomes the problems of false alarms and missed alarms based on fixed threshold alarm methods, and achieves 100% classification of two types of faults: non starting of the drive machine and low oil pressure by constructing a PCA (Principal Component Analysis)—SPE (Square Prediction Error)—CNN (Convolutional Neural Network) classifier. Combined with dynamic knowledge graph and NLP (Natural Language Processing) inference, it achieves good diagnostic results. 
653 |a Software 
653 |a Deep learning 
653 |a Fuzzy sets 
653 |a Big Data 
653 |a Expert systems 
653 |a Principal components analysis 
653 |a Oil and gas industry 
653 |a Artificial neural networks 
653 |a Fault tolerance 
653 |a Neural networks 
653 |a Systems design 
653 |a Gas industry 
653 |a Localization 
653 |a Natural gas industry 
653 |a Monitoring 
653 |a Fault detection 
653 |a Knowledge representation 
653 |a Risk assessment 
653 |a Petrochemicals 
653 |a Fault diagnosis 
653 |a Data compression 
653 |a False alarms 
653 |a Reinjection 
653 |a Knowledge 
653 |a Process controls 
653 |a Support vector machines 
653 |a Classification 
653 |a Natural gas 
653 |a Information processing 
653 |a Algorithms 
653 |a Anomalies 
653 |a Tracing 
653 |a Natural language processing 
653 |a Centrifugal compressors 
653 |a Economic 
700 1 |a Hu, Shaolin 
773 0 |t PLoS One  |g vol. 20, no. 1 (Jan 2025), p. e0315917 
786 0 |d ProQuest  |t Health & Medical Collection 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3156421470/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3156421470/fulltext/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3156421470/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch