Environmental and energy performance assessment of a methanol–diesel RCCI engine through explainable machine learning

The transition toward sustainable transportation requires cleaner combustion technologies capable of improving efficiency while reducing environmental impacts. This study experimentally investigates the combustion, performance, and emission characteristics of a methanol–diesel Reactivity Controlled Compression Ignition (RCCI) engine equipped with a Common Rail Direct Injection (CRDI) system. Experiments were conducted on a single‐cylinder Kirloskar TV1 engine at injection pressures of 400–600 bar and injection timings of 21°–25° BTDC under full‐load operation. Methanol was supplied through port fuel injection to create a partially premixed charge, while diesel was directly injected as the high‐reactivity fuel. RCCI operation improved brake thermal efficiency to 29.8%, while reducing brake‐specific fuel consumption, CO, UHC, and smoke emissions; among tested conditions, the best performance was achieved at 23° BTDC and 500 bars. However, NO x emissions increased with higher in‐cylinder temperatures, reflecting the well‐known efficiency–NO x trade‐off in RCCI combustion. Net environmental benefit therefore depends on how this trade‐off is weighted, and on factors beyond the present scope such as after‐treatment and methanol production pathway. Among five machine learning models developed for performance prediction, Support Vector Regression achieved the highest accuracy ( R 2 = 0.9696), while SHAP analysis provided interpretable insights into parameter influence. The findings demonstrate the potential of RCCI and explainable artificial intelligence to support cleaner energy systems and contribute to Sustainable Development Goals SDG 7 (Affordable and Clean Energy) and SDG 13 (Climate Action).

Authors

Institutions

Publication Details

Journal
Environmental Progress & Sustainable Energy
Published
2026-11-20
DOI
https://doi.org/10.1002/ep.70808
Primary Topic
Advanced Combustion Engine Technologies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Environmental and energy performance assessment of a methanol–diesel RCCI engine through explainable machine learning

Jibitesh Kumar Panda, Uttam Kumar Bera, Shweta Kumari, Arnab Deb et al.
Environmental Progress & Sustainable Energy
Advanced Combustion Engine Technologies
article

Environmental and energy performance assessment of a methanol–diesel RCCI engine through explainable machine learning

Jibitesh Kumar Panda, Uttam Kumar Bera, Shweta Kumari, Arnab Deb, Madhujit Deb, Varadharajan Srinivasan, Chiranjit Bhowmik, Sandip Mandal, S. P. Samal
article en

Abstract

The transition toward sustainable transportation requires cleaner combustion technologies capable of improving efficiency while reducing environmental impacts. This study experimentally investigates the combustion, performance, and emission characteristics of a methanol–diesel Reactivity Controlled Compression Ignition (RCCI) engine equipped with a Common Rail Direct Injection (CRDI) system. Experiments were conducted on a single‐cylinder Kirloskar TV1 engine at injection pressures of 400–600 bar and injection timings of 21°–25° BTDC under full‐load operation. Methanol was supplied through port fuel injection to create a partially premixed charge, while diesel was directly injected as the high‐reactivity fuel. RCCI operation improved brake thermal efficiency to 29.8%, while reducing brake‐specific fuel consumption, CO, UHC, and smoke emissions; among tested conditions, the best performance was achieved at 23° BTDC and 500 bars. However, NO x emissions increased with higher in‐cylinder temperatures, reflecting the well‐known efficiency–NO x trade‐off in RCCI combustion. Net environmental benefit therefore depends on how this trade‐off is weighted, and on factors beyond the present scope such as after‐treatment and methanol production pathway. Among five machine learning models developed for performance prediction, Support Vector Regression achieved the highest accuracy ( R 2 = 0.9696), while SHAP analysis provided interpretable insights into parameter influence. The findings demonstrate the potential of RCCI and explainable artificial intelligence to support cleaner energy systems and contribute to Sustainable Development Goals SDG 7 (Affordable and Clean Energy) and SDG 13 (Climate Action).

Environmental Progress & Sustainable Energy
Manipal Academy of Higher Education (IN), National Institute of Technology Agartala (IN), Advanced Numerical Research and Analysis Group (IN), National Institute of Technology Arunachal Pradesh (IN), Saveetha University (IN)
Advanced Combustion Engine Technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon