The variability of specific heats, internal irreversibility, heat and frictional losses are neglected in air-standard analysis for different internal combustion engine cycles. In this paper, the performance of an air-standard Diesel cycle with considerations of internal irreversibility described by using the compression and expansion efficiencies, variable specific heats, and losses due to heat transfer and friction is investigated by using finite-time thermodynamics. Artificial neural network (ANN) is proposed for predicting the thermal efficiency and power output values versus the minimum and the maximum temperatures of the cycle and also the compression ratio. Results show that the first-law efficiency and the output power reach their maximum at a critical compression ratio for specific fixed parameters. The first-law efficiency increases as the heat leakage decreases; however the heat leakage has no direct effect on the output power. The results also show that irreversibilities have depressing effects on the performance of the cycle. Finally, a comparison between the results of the thermodynamic analysis and the ANN prediction shows a maximum difference of 0.181% and 0.194% in estimating the thermal efficiency and the output power. The obtained results in this paper can be useful for evaluating and improving the performance of practical Diesel engines.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.