Enhancing performance of diesel engine with the collective impact of ternary nano fuel blends using DBO-vCANN approach

The rising global population is driving an increasing energy demand, primarily met by fossil fuels. This manuscript presents a hybrid approach for enhancing diesel engine performance and emissions characteristics of ternary nanofuelblends (TNFB). The proposed hybrid technique is the joint execution of dung beetle optimiser (DBO) and viscoelastic constitutive artificial neural networks (vCANN). Hence, named as DBO-vCANN technique. The main objective of proposed technique is to improve engine performance and minimise emission characteristics. The DBO method optimises biodiesel production parameters, while vCANN model forecasts engine performance and emissions. The performance of proposed system is run on the MATLAB platform and is compared with existing methods. The proposed model accurately predicted compression ignition (CI) engine performance and emissions. The proposed approach provides better outcomes in existing particle swarm optimisation (PSO), Salp swarm algorithm (SSA), and ant lion optimisation (ALO), methods. The proposed method achieves efficiency of 98%, demonstrating improved system performance.