Abstract

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”.

Highlights

  • Nowadays, diesel engines are the prime movers in commercial transportation, power generation, and off-road applications

  • The solutions presented in this paper demonstrate that state-of-the-art technologies enable de-centralized decisions via “edge artificial intelligence (AI)” (Figure 4)

  • Within the2 limits of the based on an artificial neural networks (ANNs) trained with the L–M algorithm, that can be assessed by the R benchmark, R Squared—the ratio between the variance of the predicted values and the variance of the unpredicted values

Read more

Summary

Introduction

Diesel engines are the prime movers in commercial transportation, power generation, and off-road applications. Their major advantages compared to other common alternatives are a better fuel economy, a lower carbon footprint, and an increased reliability. The demands on engine performance indicators—increased power output, lower fuel consumption, and emissions—require a better understanding of engine processes, further experimental investigations, and the implementation of control strategies based on numerical models. In four-stroke engines, the process of gas exchange requires a very rapid and total release of exhaust gas from cylinders into the atmosphere, which is evaluated by exhaust back pressure (EBP), a flow resistance indicator on the exhaust duct. Unsteady friction and inertial forces, which are.

Objectives
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call