Spectroscopic Characterization and AI-Based Classification of Engine Oil Degradation in Internal Combustion Engines

Basit Öğe Kaydı
dc.contributor.authorKaynakli, Metin
dc.contributor.authorAlbayrak, Ahmet
dc.contributor.authorIşcan, Bahattin
dc.date.accessioned2026-07-01T11:36:27Z
dc.date.available2026-07-01T11:36:27Z
dc.date.issued2025
dc.departmentDüzce Üniversitesi
dc.description9th International Artificial Intelligence and Data Processing Symposium, IDAP 2025 -- 6 September 2025 through 7 September 2025 -- Malatya -- 215321
dc.description.abstractThis study aims to evaluate the degradation level of engine oils used in internal combustion engines by analyzing the physicochemical changes they undergo over time using FTIR (Fourier Transform Infrared) spectroscopy. Four different engine oil samples (collected from gasoline and diesel engines) were taken at specific mileage intervals and analyzed using the FTIR method. In the FTIR analysis, key variables such as oxidation, water/fuel contamination, and additive depletion in the engine oil were interpreted through wavelength absorption peaks. Specifically, absorption regions associated with carbonyl (C=O), hydroxyl (O-H), sulfate (S=O), and phosphate (P-O) groups were evaluated to determine the aging and degradation levels of each sample. The study also employed machine learning techniques (Random Forest, Logistic Regression, SVM, Naive Bayes, KNN) to classify the condition of the engine oil. In univariate analyses (using only absorbance values), oxidation levels were predicted, while multiclass models aimed to classify conditions such as 'Good', 'Moderate', and 'Poor'. Random Forest models generally provided the most successful results. The KNN algorithm was used to group oils with similar structures based on their FTIR spectra. The results demonstrate that FTIR spectra are not only useful for interpretive analysis but also serve as powerful data sources suitable for numerical modeling. This study highlights that, instead of relying solely on mileage-based oil changes, condition-based maintenance strategies can be more accurately planned using FTIR data and AI-supported analysis. © 2025 IEEE.
dc.identifier.doi10.1109/IDAP68205.2025.11222280
dc.identifier.isbn979-833158990-5
dc.identifier.scopus2-s2.0-105025023990
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/IDAP68205.2025.11222280
dc.identifier.urihttps://hdl.handle.net/20.500.12684/23041
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartof9th International Artificial Intelligence and Data Processing Symposium, IDAP 2025
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_Scopus_20260623
dc.subjectCondition-Based Maintenance
dc.subjectEngine Oil Degradation
dc.subjectFTIR Spectroscopy
dc.subjectMachine Learning Classification
dc.titleSpectroscopic Characterization and AI-Based Classification of Engine Oil Degradation in Internal Combustion Engines
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu