摘要
The carbon neutrality of existing internal combustion engines can be significantly enhanced through the use of sustainable e-fuels;thus,their price has to be reduced.Artificial intelligence(AI)offers a promising pathway to streamline and accelerate fuel development by enabling faster and more efficient model creation compared to conventional physicochemical simulations.Despite the apparent advantages,state-of-the-art research typically limits the application of AI to basic predictions within narrow operating ranges.This study introduces a novel AIbased fuel design tool capable of accurately predicting detailed engine performance across a broad range of operating conditions,using comprehensive physicochemical fuel properties as input.The proposed approach provides greater detail and precision than existing state-of-the-art methods.Building on a cost-efficient AI development strategy established in our previous work,the tool was constructed using 17 single-output multi-layer perceptron networks.The tool was validated using engine dynamometer measurements with various test fuels,and then it was applied to a fuel optimization task to demonstrate its effectiveness.The results indicate that the tool’s predictions closely match actual engine performance.Specifically,10 out of the 17 models achieved a mean absolute percentage error of<3%.In the optimization scenario,the optimized fuel had a predicted engine operating score of 40.51%,while the actual score was 41.3%,demonstrating the tool’s potential for accurate fuel design.Thus,this novel approach can support the development of low-cost e-fuels,enabling economically viable,carbon-neutral mobility across a wide range of transport applications.
基金
supported by the European Union within the framework of the National Laboratory for Autonomous Systems(RRF-2.3.1-21-2022-00002)
supported by AVL Hungary Kft.
