Prediction of CI Engine Emissions Fueled with Multiwalled Carbon Nanotube-Doped Waste Cooking Oil Biodiesel using Multilayer Neural Network

Nanocatalysts play a significant role to improve the thermal and physical properties of biodiesel. In present work, multiwalled carbon nanotubes (MWCNTs) as an additive with fraction 30, 40, 50 ppm are dispersed different biodiesel–diesel blends 10%, 30%, 50% waste cooking oil (WCO)-based biodiesel (B10, B30, B50) for prediction four-stroke compression ignition (CI) engine emissions using multilayer neural network (MLNN) model. An MLNN model uses backpropagation algorithm map input output parameters. The parameters load, blends, MWCNTs in ppm. On other hand, HC, CO, NOx. results optimum topological structure 3-10-3 denoted mean square error (MSE) equal 0.095 that capable predicting operating conditions. Thereafter, developed is tested on experimental setup consisting single-cylinder CI emission analyzer. characteristics predicted by called be nearly measurements reasonable accuracy it depicts good “R” values 0.95, 0.96, 0.976 NOx, respectively, also gives average relative 0.83%, 1.01%, 1.05%, respectively. Further, suitable engines, thus minimizing cost, time, labor effort.