A Bayesian regularization back propagation (BRBP) neural network model for prediction of the effect of using Al2O3–Fe2O3 hybrid nano fuels on the performance and emissions of diesel engines
摘要
The present study investigates the effect of adding Al2O3, Fe2O3, and Al2O3–Fe2O3 hybrid nanoparticles to diesel fuel. To this end two methods are employed: experimental research and Bayesian regularization back propagation (BRBP) neural network model. Adding nano particles increases the heating value of the desired mixed fuel causing an increase in torque and power of the engine, while decreasing NOx and SO2 emissions. Based on the experimental results, a Bayesian regularization back propagation (BRBP) neural network model is designed to predict the performance and emissions of the diesel engine under the influence of nano particles. The results show that hybrid nano fuel produces more torque and brake power and less CO emission, while increasing NOx and SO2 emissions. In general, hybrid nano fuel has better performance in terms of torque, power, thermal efficiency,… compared to non-hybrid fuels, such that 11% increase in brake power can be observed due to using hybrid nano fuel in 1600 RPM speeds. Furthermore, CO emission decreases (up to 20%), while NOx and SO2 emissions increase by using hybrid nano fuel.
Graphical abstract