Sampled-data model validation: An algorithm and experimental setup of dual fuel IC engine

Abstract

This research work investigates the usage of hybrid based Artificial Neural Network-Harris Hawks and whale optimization algorithm (ANN-HHOWOA) for forecast of emission properties and performance of small utility single cylinder direct injection (DI) diesel engine inlet with rice bran biodiesel blends under dual fuel mode along with biogas. This Artificial Neural Network based hybrid Harris Hawks and whale optimization algorithm was developed and optimized to forecast the values of brake thermal efficiency (BTE), hydrocarbon (HC), carbon monoxide (CO) and carbon dioxide (CO2) based on the gathered input data from the experimental setup of dual fuel engine by varying engine operating load, blends of rice bran biodiesel, air fuel ratio and injection timings. To experimentally validate the results by using hybrid based Artificial Neural Network-Harris Hawks and whale optimization algorithm (ANN-HHOWOA), 500 trial runs were performed on objective functions of gathered data to find optimal solution. 70% of data were used for training, 15% for testing and other 15% were used for validation. It has been concluded that hybrid based Artificial Neural Network-Harris Hawks and whale optimization algorithm (ANN-HHOWOA) gave remarkable results with classification rate 98.6667% which is much better than other meta-heuristic algorithms. It is found that Artificial Neural Network based hybrid Harris Hawks and whale optimization algorithm is a very useful tool for prediction and optimization of combustion performance and emissions properties of dual fuel engine fuelled with biogas-biodiesel blends.