Freddie Liswaniso Inambao

Excessive exhaust backpressure (EBP) in modern diesel engines disrupts gas exchange, increases residual gas fraction (RGF), and reduces combustion efficiency. Traditional experimental approaches, including simulations and bench testing, are often time-consuming and costly, which has driven growing interest in artificial neural networks (ANNs) for accurately modelling complex engine behavior. This research introduces an ANN model designed to predict the impact of EBP on the performance and emissions of a diesel engine across varying compression ratio (CR) of 12, 14, 16, and 18 and engine load (25%, 50%, 75%, and 100%) conditions. The ANN model was developed and optimised using genetic algorithms (GA) and particle swarm optimisation (PSO). It was then trained using data from an experimentally validated one-dimensional computational fluid dynamics (1D-CFD) model developed through GT-Power GT-ISE v2024, simulating engine responses under variation CR, load, and EBP conditions. The optimised ANN architecture, featuring an optimal (3-14-10) configuration, was trained using the Levenberg–Marquardt back propagation algorithm. The performance of the model was assessed using statistical criteria, including the coefficient of determination (R²), root mean square error (RMSE), and k-fold cross-validation, by comparing its predictions with both experimental and simulated data. Results indicate that the optimised ANN model outperformed the baseline ANN and other machine learning (ML) models, attaining an R² of 0.991 and an RMSE of 0.011. It reliably predicts engine performance and emissions under varying EBP conditions while offering insights for engine control, optimisation, diagnostics, and thermodynamic mechanisms. The overall prediction error ranged from 1.911% to 2.972%, confirming the model’s robustness in capturing performance and emission outcomes.

The increasing demand for efficient and environmentally friendly diesel engines necessitates advanced simulation tools, with Gamma Technologies’ GT-POWER emerging as a leading software suite for this purpose. This review paper examines the capabilities of GT-POWER for modelling diesel engines, exploring its fundamental principles, user interface, modelling techniques, and simulation capabilities, alongside comparisons with other formidable simulation tools. Moreover, various case studies from the literature are presented to illustrate its application. While there are some shortfalls within the context of GT-POWER, such as the need for further exploration of underutilized areas, the current focus on primarily 1D and multi-zone modelling requires expansion. Coupling GT-POWER with other simulation software for multiphysics analyses—such as CFD for combustion, structural analysis for component stress, fluid flow, and heat transfer—offers significant potential; however, this integration remains largely unexploited. Despite its limitations, the results consistently reveal the software’s versatility in optimizing engine performance across diverse applications, including component design, alternative fuel evaluations, and integration with various technologies such as MATLAB/Simulink, Artificial Neural Networks, and Python. The consistent findings across multiple studies further confirm GT-POWER’s effectiveness as a leading simulation tool for advancing diesel engine technology. Ultimately, this study bridges the gap between theoretical understanding and practical application, making it a valuable resource for researchers and engineers in the field of internal combustion engine optimization.

This study evaluated the performance of a diesel engine operated with waste plastic biodiesel fuel (WPPO) blends. Findings were that at all engine loads (from idling to full load) the emissions of carbon monoxide (CO), unburnt hydrocarbon (UHC) and carbon dioxide (CO2) were low compared to conventional diesel (PD), although the emissions of NOX were higher. The brake specific fuel consumption (BSFC) for the blends dropped while the brake thermal efficiency (BTE) increased with load for all blends until intermediate load when it decreased. WPPO blends had a higher viscosity compared to PD. CO emissions for blend 95/WPPO5 at all engine speed idling modes were 285 ppm, 298 ppm, 320ppm, and 388 ppm while PD emissions were 270 ppm, 295 ppm, 315 ppm and 365 ppm respectively. The values for UHC for blend 95/WPPO5 at all modes were 35 ppm, 28 ppm, 22 ppm, and 18 ppm compared to PD fuel with 20ppm, 25 ppm, 30 ppm, and 40ppm respectively. The NOX emissions for PD fuel at all modes were 175 ppm, 225 ppm, 300 ppm and 375 ppm compared to blend 95/WPPO5 at 195 ppm, 245 ppm, 335 ppm, and 397 ppm. The BSFC values for blend 95/WPPO5 at all modes were 0.48 kg/kW.h, 0.41 kg/kW.h, 0.35 kg/kW.h and 0.4 kg/kW.h compared to PD at 0.45 kg/kW.h, 0.39 kg/kW.h, 0.33 kg/kW.h and 035 kg/kW.h respectively.