Review of Machine Learning Based Fault Detection for Centrifugal Pump Induction Motors

Обзор методов обнаружения неисправностей асинхронных двигателей центробежных насосов на основе машинного обучения
Vladan Velisavljević, Vladimir Dyo, Cem Ekin Sunal
2022-01-01

centrifugal pump condition monitoringinduction motor faultsmachine learning-based fault diagnosismotor current signature analysispump fault detection
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.
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.

centrifugal pump induction motors and their pump systems

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
Access Type
Author Information
Authors
Vladan Velisavljević
Vladimir Dyo
Cem Ekin Sunal
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%