Multi-input multi-output machine learning predictive model for engine performance and stability, emissions, combustion and ignition characteristics of diesel-biodiesel-gasoline blends

In this research, a multi-input multi-output artificial neural network (MIMO-ANN) is developed, in which 14 features associated with the engine performance and stability, emissions, combustion ignition characteristics of diesel-biodiesel-gasoline mixtures are meant to be modelled by diverse combination engine/combustion parameters. The selected targets comprise brake specific fuel consumption (BSFC), thermal efficiency (BTE), efficiency, coefficient variance (COV), NOx, CO2, CO HC exhaust temperature (Texh), in-cylinder pressure (Pcyl), maximum rise rate (MPRR), heat release (HRR), duration (CD) delay (ID). inputs variables entail load, speed, compression ratio, gasoline, biodiesel diesel ratios, crank angle (CA), injection (Tinj), (Pinj), mean effective (BMEP) start (SOI). Sensitivity analysis outlier detection applied order eliminate less-effective inputs/data points. prepared data sets then used train test ANN model, conjunction benchmarking model outcomes using determination (R2), average absolute relative deviation (AARD) squared errors (RMSE). R2 ranged within 0.9804–0.9998, close unity, proving that proposed accurately capable predicting intended characteristics.