<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE ArticleSet PUBLIC "-//NLM//DTD PubMed 2.7//EN" "https://dtd.nlm.nih.gov/ncbi/pubmed/in/PubMed.dtd">
<ArticleSet>
<Article>
<Journal>
				<PublisherName>Iran Center for Management Studies</PublisherName>
				<JournalTitle>Journal of Industrial Engineering and Management Studies</JournalTitle>
				<Issn>2476-308X</Issn>
				<Volume>13</Volume>
				<Issue>1</Issue>
				<PubDate PubStatus="epublish">
					<Year>2026</Year>
					<Month>07</Month>
					<Day>01</Day>
				</PubDate>
			</Journal>
<ArticleTitle>Data-Driven Prognostics of Industrial Pumps: Condition Assessment and Time to Change Estimation Using Ensemble Methods</ArticleTitle>
<VernacularTitle></VernacularTitle>
			<FirstPage>47</FirstPage>
			<LastPage>62</LastPage>
			<ELocationID EIdType="pii">247074</ELocationID>
			
<ELocationID EIdType="doi">10.22116/jiems.2026.556663.1623</ELocationID>
			
			<Language>EN</Language>
<AuthorList>
<Author>
					<FirstName>Ehsan</FirstName>
					<LastName>Heydari</LastName>
<Affiliation>Department of Industrial Engineering, University of Kurdistan</Affiliation>
<Identifier Source="ORCID">0009-0005-1637-4116</Identifier>

</Author>
<Author>
					<FirstName>Seyyed Mojtaba</FirstName>
					<LastName>Tabatabaei</LastName>
<Affiliation>Department of Mechanical Engineering, Islamic Azad University, Science and Research Branch, Tehran</Affiliation>

</Author>
</AuthorList>
				<PublicationType>Journal Article</PublicationType>
			<History>
				<PubDate PubStatus="received">
					<Year>2025</Year>
					<Month>11</Month>
					<Day>01</Day>
				</PubDate>
			</History>
		    <Abstract>AbstractUnplanned pump failures inflict high operational costs, rendering traditional maintenance strategies ‎inefficient. While Machine Learning (ML) has advanced fault diagnosis, a critical gap remains in ‎simultaneously classifying operational states and predicting the &quot;Time Remaining until a State Change&quot; ‎‎(TRSC) using real-world, imbalanced data. This study addresses this necessity by developing an integrated ‎predictive maintenance framework for industrial centrifugal pumps. Leveraging a four-year vibration ‎dataset (2020–2024), we employ Random Forest (RF), XGBoost, and Multi-Layer Perceptron (MLP), ‎utilizing SMOTE and jittering augmentation to mitigate data scarcity and imbalance. The study makes two ‎primary contributions: (1) accurate classification of four operational states (Normal to Failure), and (2) ‎precise regression of TRSC to optimize spare parts logistics. Results indicate that ensemble models ‎‎(RF/XGBoost) achieve classification accuracies exceeding 92% and TRSC prediction with an RMSE ‎below 25 days, significantly outperforming MLP. Furthermore, SHAP analysis reveals that horizontal and ‎axial vibrations are the dominant precursors to failure. These findings offer a robust, interpretable tool for ‎shifting towards condition-based maintenance, ensuring reliability and cost efficiency.‎</Abstract>
		<ObjectList>
			<Object Type="keyword">
			<Param Name="value">Keywords: Pump</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Random forest</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Extreme gradient boosting</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Multilayer Perceptron</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Vibration Analysis</Param>
			</Object>
		</ObjectList>
<ArchiveCopySource DocType="pdf">https://jiems.icms.ac.ir/article_247074_53c86595b8b2d03a96933e2d82674be8.pdf</ArchiveCopySource>
</Article>
</ArticleSet>
