Robust Estimation of Fuel Pump Volumetric Efficiency Using Tree-Based Ensembles

Basit Öğe Kaydı
dc.contributor.authorDoylan, Elif
dc.contributor.authorBilgin, Turgay Tugay
dc.contributor.authorKenar, Zeynep Dilara
dc.contributor.authorAkyuz, Yigit
dc.contributor.authorYildiz, Erhan
dc.date.accessioned2026-02-08T15:11:11Z
dc.date.available2026-02-08T15:11:11Z
dc.date.issued2025
dc.departmentBursa Teknik Üniversitesi
dc.description2025 Innovations in Intelligent Systems and Applications Conference, ASYU 2025 -- 2025-09-10 through 2025-09-12 -- Bursa -- 214381
dc.description.abstractVolumetric efficiency (VE) measurement in highpressure fuel pumps, specifically at 35 MPa (LG35), is critical for diagnosing leakage and wear. To analyze pressure traces, conventional methods rely on manual analysis, which is timeconsuming and requires expert intervention. We propose a machine learning-based alternative that estimates LG35 from routinely logged cycle-level metrics such as stroke length, shaft speed, system pressure, and temperature. Using a dataset of 4,139 real-world pump cycles, we benchmark seven regression models and demonstrate that tree-based ensembles, particularly Gradient Boosting, significantly outperform linear baselines. A voting ensemble combining multiple models achieves a mean absolute error of 3.04 % on a hold-out set simulating unseen stroke conditions. SHAP analysis confirms that model predictions align with physical intuition. Our approach enables real-time, expert-free diagnostics, offering a scalable solution for fuel system testing in automotive manufacturing. © 2025 IEEE.
dc.identifier.doi10.1109/ASYU67174.2025.11208323
dc.identifier.isbn9798331597276
dc.identifier.scopus2-s2.0-105022471536
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/ASYU67174.2025.11208323
dc.identifier.urihttps://hdl.handle.net/20.500.12885/5297
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzScopus_KA_20260207
dc.subjectensemble learning
dc.subjectfuel pump testing
dc.subjectgradient boosting
dc.subjectregression models
dc.subjectVolumetric efficiency
dc.titleRobust Estimation of Fuel Pump Volumetric Efficiency Using Tree-Based Ensembles
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu