/ Makaleler / Scopus Detay

Scopus 🔓 Açık Erişim YÖKSİS DOI Eşleşti SJR Q1

Comparison of machine learning algorithms for predicting diesel/biodiesel/iso-pentanol blend engine performance and emissions

Heliyon · Kasım 2023

YÖKSİS Kayıtları

Heliyon · 2023 SCI-Expanded

Doç. Dr. SEDA ŞAHİN →

YÖKSİS Kayıtları — ISSN Eşleşmesi

The effect of curcumin on some cytokines, antioxidants and liver function tests in rats induced by Aflatoxin B1

2022 ISSN: 2405-8440 SCI-Expanded Q2

Doç. Dr. DURMUŞ HATİPOĞLU →

10.1016/j.heliyon.2022.e09890

Circular economy model for developing countries: evidence from Bangladesh

2022 ISSN: 2405-8440 SCI-Expanded Q2

Prof. Dr. HAKAN ACET →

10.1016/j.heliyon.2022.e09530

The effect of curcumin on some cytokines, antioxidants and liver function tests in rats induced by Aflatoxin B1

2022 ISSN: 2405-8440 SCI-Expanded Q2

Prof. Dr. ERCAN KESKİN →

10.1016/j.heliyon.2022.e09890

The impact of Artificial Intelligence in academia: Views of Turkish academics on ChatGPT

2023 ISSN: 2405-8440 SCI-Expanded Q2

Arş. Gör. SÜHEYLA AYVAZ →

10.1016/j.heliyon.2023.e19688

Comparison of machine learning algorithms for predicting diesel/biodiesel/iso-pentanol blend engine performance and emissions

2023 ISSN: 2405-8440 SCI-Expanded Q2

Doç. Dr. SEDA ŞAHİN →

10.1016/j.heliyon.2023.e21365

Ancient Schwannoma as an exceptional thoracic spinal tumor: A case report

2022 ISSN: 2405-8440 SCI

Dr. Öğr. Üyesi AHMET GÖRGEL →

10.1016/j.heliyon.2022.e10286

Social media use and social capital: Social media usage habits and perceptions of school administrators

2024 ISSN: 2405-8440 SCI-Expanded Q2

Doç. Dr. NAGİHAN TUFAN YENİÇIKTI →

10.1016/j.heliyon.2023.e23293

Predicting deep well pump performance with machine learning methods during hydraulic head changes

2024 ISSN: 2405-8440 SCI-Expanded Q1

Doç. Dr. NURİ ORHAN →

10.1016/j.heliyon.2024.e31505

Evaluation of outstanding theories in outsourcing with practices in the public health sector: The case of Türkiye

2024 ISSN: 2405-8440 SCI-Expanded Q1

Doç. Dr. MEHMET YORULMAZ →

10.1016/j.heliyon.2024.e28773

Citizen attitudes towards e-government services during the COVID-19 pandemic: A case in Türkiye

2024 ISSN: 2405-8440 SCI-Expanded Q1

Prof. Dr. NESLİHAN İYİT →

10.1016/j.heliyon.2024.e35041

Determining factors of university students binge-watching attitudes

2024 ISSN: 2405-8440 SCI-Expanded Q1

Doç. Dr. MURAT AYTAŞ →

10.1016/j.heliyon.2024.e39642

Perspectives on drone journalism in Turkiye: Journalists views on the use of drones

2024 ISSN: 2405-8440 Scopus

Arş. Gör. SÜHEYLA AYVAZ →

10.1016/j.heliyon.2024.e39790

Factors influencing the longevity of posterior composite restorations: A dental university clinic study

2024 ISSN: 2405-8440 SCI-Expanded Q1

Prof. Dr. NİMET ÜNLÜ →

10.1016/j.heliyon.2024.e27735

Gastroprotective activity of Jervine alkaloid from Veratrum album on gastric ulcer in rat

2025 ISSN: 2405-8440 SCI-Expanded Q1

Dr. Öğr. Üyesi MUHAMMED YAYLA →

10.1016/j.heliyon.2025.e43491

Makale Bilgileri

Dergi Heliyon

ISSN24058440

Yayın TarihiKasım 2023

Cilt / Sayfa9

DOI10.1016/j.heliyon.2023.e21365

Scopus ID2-s2.0-85175295272

Erişim🔓 Açık Erişim

Özet In this study, machine learning techniques, namely artificial neural network (ANN), support vector machine (SVM), and extreme gradient boosting (XGBoost), were used to comprehensively evaluate engine performance and exhaust emissions for different fuel blends. To obtain valuable insights on optimizing engine performance and emissions for alternative fuel blends and thus contribute to the advancement of knowledge in this field, we focused on iso-pentanol ratios while maintaining the biodiesel ratios constant. The maximum brake thermal efficiency (BTE) values for the diesel (30.13 %), D85B10P5 (29.92 %), D80B10P10 (29.89 %), and D70B10P20 (29.79 %) blends were achieved at 1600 rpm. At 1600 rpm, the brake-specific fuel consumption (BSFC) values for the diesel, D85B10P5, D80B10P10, and D70B10P20 blends were 189.93, 200.93, 202.93, and 203.95 g kWh−1, respectively. In engine performance prediction, the ANN model exhibited superior performance, yielding regression coefficient (R2), root mean square error, and mean absolute error values of 0.984, 0.411 %, and 0.112 %, respectively, in BTE prediction, and 0.958 %, 6.9 %, and 2.95 %, respectively, in BSFC prediction. In exhaust gas temperature prediction, the SVM model exhibited the best performance, yielding an R2 value of 0.981. Although all models successfully predicted NOx emissions, the ANN model exhibited the best performance, achieving an R2 value of 0.959. In CO2 and hydrocarbon estimation, the XGBoost model exhibited the best performance, yielding R2 values of 0.956 and 0.973, respectively. Therefore, the ANN model can be used to accurately predict engine performance, and the XGBoost model can be used to accurately predict emission parameters.