Review of Machine Learning Based Fault Detection for Centrifugal Pump Induction Motors
Обзор методов обнаружения неисправностей асинхронных двигателей центробежных насосов на основе машинного обучения
2022-01-01
SCID: 54.1/pda5xgz2
Discuss with AI
centrifugal pump condition monitoringinduction motor faultsmachine learning-based fault diagnosismotor current signature analysispump fault detection
Figures from the paper
Abstract (AI)
Centrifugal pumps are an integral part of many industrial processes and are used extensively in water supply, sewage, heating and cooling systems. While there are several review papers on machine learning-based fault diagnosis on induction motors, its application to centrifugal pumps has received relatively little attention. This work attempts to summarize and review recent research and development in machine learning-based pump condition monitoring and fault diagnosis. The paper starts with a brief explanation of pump operation including common pump faults and the main principles of the motor current signature analysis (MCSA) method. This is followed by a detailed explanation of various machine learning-based methods including the types of detected faults, experimental details and reported accuracies. The performances of different approaches are then presented systematically in a unified table. Finally, the authors discuss practical aspects and challenges related to data collection, storage and real-world implementation.
Key Findings
1
A unified table compares the reported performance of different machine-learning approaches for pump fault diagnosis.
2
It summarizes common centrifugal-pump faults and explains motor current signature analysis as a principal monitoring method.
3
Practical challenges involving data collection, data storage, and real-world implementation are identified as important barriers to deployment.
4
The paper systematically reviews machine-learning methods, detected fault types, experimental setups, and reported diagnostic accuracies.
5
The review addresses the relatively understudied application of machine learning to condition monitoring and fault diagnosis in centrifugal pump induction motors.
Research Object
centrifugal pump induction motors and their pump systems
Research Subject
machine-learning-based condition monitoring and fault diagnosis, including detected fault types, performance, and practical implementation challenges
Publication Details
Publication Date
2022-01-01
Journal
Publisher
ISSN
Cited by
115
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest