Abstract
Fuel composition plays an important role both in efficiency and effectiveness of engines. Combined with the engine variables, fuel can span a wide range of composition space, which makes it demanding to find an optimal composition. Artificial intelligence (AI) algorithms are attracting significant interest for predicting complex phenomenon. In this chapter, a discussion is presented on exploiting the advantages presented by machine learning algorithms for fuel formulation. The present fuel modeling scenario and a holistic approach necessary for fuel optimization is first presented. A wealth of AI algorithms are available to make use of in fuel formulation. These algorithms are discussed in line with their application to fuel formulation and the literature of the explored space in this area is presented. Additionally, a discussion is presented on how AI also helps in assisting the traditional computational fluid dynamic and chemical kinetic analysis for an elaborate study of fuels. Fuel development is just a step in the entire engine innovation cycle, and a perspective of how the AI fits in to this scenario is presented.
| Original language | English (US) |
|---|---|
| Title of host publication | Artificial Intelligence and Data Driven Optimization of Internal Combustion Engines |
| Publisher | Elsevier |
| Pages | 47-67 |
| Number of pages | 21 |
| ISBN (Electronic) | 9780323884570 |
| ISBN (Print) | 9780323884587 |
| DOIs | |
| State | Published - Jan 1 2022 |
Keywords
- Combustion
- Fuel design
- Kinetics
- Machine learning
- Neural networks
ASJC Scopus subject areas
- General Engineering