The actual trade-off among engine emissions and performance requires detailed investigations into exhaust system configurations. Correlations among engine data acquired by sensors are susceptible to artificial intelligence (AI)-driven performance assessment. The influence of exhaust back pressure (EBP) on engine performance, mainly on effective power, was investigated on a turbocharged diesel engine tested on an instrumented dynamometric test-bench. The EBP was externally applied at steady state operation modes defined by speed and load. A complete dataset was collected to supply the statistical analysis and machine learning phases—the training and testing of all the AI solutions developed in order to predict the effective power. By extending the cloud-/edge-computing model with the cloud AI/edge AI paradigm, comprehensive research was conducted on the algorithms and software frameworks most suited to vehicular smart devices. A selection of artificial neural networks (ANNs) and regressors was implemented and evaluated. Two proof-of concept smart devices were built using state-of-the-art technology—one with hardware acceleration for “complete cycle” AI and the other with a compact code and size (“AI in a nut-shell”) with ANN coefficients embedded in the code and occasionally offline “statistical re-calibration”.

This work presents an experimental energy and exergy analysis for the operation of a multi-cylinder four-stroke direct injection turbocharged and intercooled commercial diesel engine. A simplified model of an extended thermodynamic cycle over compressor-intercooler-engine and turbine was adapted, and then being calibrated with engine dynamometric bench measurements. For two representative engine operation modes - rated power and maximum torque - at full load, second law terms were assessed in function of chemical diesel fuel availability. The result was an integrated method for a reliable assessment of availability losses, which becomes a useful tool to evaluate the further improvement of process efficiency and of the energy harvesting potential.