Highlights
•
Diesel engine models are built using advanced machine learning techniques and verified based on experimental data.
•
A new hybrid inference is proposed for the selection of hyperparameters of kernel based extreme learning machine.
•
Problems of data scarcity and exponentiality are eased by using logarithmic transformation of dependent variables to pre-process the data.
•
A comparison among the models built by advanced and traditional methods is conducted.
•
The models developed by advanced methods with the hybrid inference and logarithmic transformation are more accurate than traditional ones.
