
Citation: Khalid, S.; Jo, S.-H.; Shah,
S.Y.; Jung, J.H.; Kim, H.S. Artificial
Intelligence-Driven Prognostics and
Health Management for Centrifugal
Pumps: A Comprehensive Review.
Actuators 2024,13, 514. https://
doi.org/10.3390/act13120514
Academic Editor: Zhuming Bi
Received: 30 October 2024
Revised: 22 November 2024
Accepted: 9 December 2024
Published: 10 December 2024
Copyright: © 2024 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Review
Artificial Intelligence-Driven Prognostics and Health
Management for Centrifugal Pumps: A Comprehensive Review
Salman Khalid 1, Soo-Ho Jo 1, Syed Yaseen Shah 2, Joon Ha Jung 2,* and Heung Soo Kim 1,*
1Department of Mechanical, Robotics, and Energy Engineering, Dongguk University, 30 Pil-dong 1 Gil,
2Department of Industrial Engineering, Ajou University, Suwon 16499, Republic of Korea;
Abstract: This comprehensive review explores data-driven methodologies that facilitate the prog-
nostics and health management (PHM) of centrifugal pumps (CPs) while utilizing both vibration
and non-vibration sensor data. This review investigates common fault types in CPs, while placing a
specific emphasis on artificial intelligence (AI) approaches, including machine learning (ML) and
deep learning (DL) techniques, for fault diagnosis and prognosis. A key innovation of this review is
its in-depth analysis of cutting-edge methods, such as adaptive thresholding, hybrid models, and
advanced neural network architectures, aimed at accurately predicting the remaining useful life
(RUL) of CPs under varying operational conditions. This review also addresses the limitations and
challenges of the current AI-driven methodologies, offering insights into potential solutions. By
synthesizing these methodologies and presenting practical applications through case studies, this
review provides a forward-looking perspective to empower industry professionals and researchers
with effective strategies to ensure the reliability and efficiency of centrifugal pumps. These findings
could contribute to optimizing industrial processes and advancing health management strategies for
critical components.
Keywords: centrifugal pumps (CPs); fault diagnosis; prognostics; artificial intelligence; machine
learning; deep learning
1. Introduction
A centrifugal pump (CP) is a piece of mechanical equipment that transports a fluid
from one place to another. Since manufacturing facilities and power plants use fluids often,
CPs are widely used in many industrial sites [
1
,
2
]. A survey by an energy organization
underscored that electric motor-driven machines, particularly CPs, are responsible for
65% of the energy consumption in industry [
3
]. However, CPs are prone to mechanical
failure because they have rotational parts that interact with fluids. The features of the
fluids in the CPs vary, and the fluid demand fluctuates, which generates faults and failures
in the pumps [
4
–
6
]. Cavitation and hydraulic instability occur frequently, and system-
related concerns can be generated as well [
7
–
9
]. Additionally, inadequate maintenance,
insufficient lubrication, misalignment, imbalances, and seal leakages decrease the reliability
of CPs
[10–14]
. If the malfunctions of pumps are not managed in a suitable period of
time, these failures and faults will lead to significant maintenance costs, energy waste,
disruptions in manufacturing processes, and potential safety hazards [15].
Effective health monitoring for CPs is essential in maintaining the optimal performance
of the machines. Traditional maintenance strategies, which perform maintenance after
severe faults are identified, have limitations [
16
,
17
]. However, recent advancements in PHM
for engineering systems have been modifying the maintenance strategies for CPs
[18–20]
.
As the cost of data acquisition has been decreased, the continuous online monitoring of
CPs has facilitated proactive maintenance strategies, such as data-driven PHM.
Actuators 2024,13, 514. https://doi.org/10.3390/act13120514 https://www.mdpi.com/journal/actuators