A comparative analysis of adaptive energy management for a hybrid electric vehicle via five driving condition recognition methods

Bin Xu and Hanchen Wang

Energy, 2023, vol. 269, issue C

Abstract: – Adaptive powertrain control is of great importance to a high energy efficient vehicle and varying parameter recognition is the first step of adaptive control. However, a comparative study on different driving condition recognition methods is lacking in literature. In this study, five recognition methods are introduced and compared, namely fuzzy logic, clustering, Markov Decision Process, and supervised learning and navigation-based method. Three driving conditions are considered as recognition target, which are urban, suburban and highway conditions. 29 driving cycles and 4 driving cycles are used in training and validation, respectively. The training results show that all five methods have training accuracy above 86% with supervised learning leading the accuracy at 91.37%. The validation results from a hybrid electric vehicle show that the five prediction methods improve the fuel economy by 2.47%–4.58% in the four validation driving cycles when compared with constant prediction method. Based on the analysis of complexity and fuel economy performance, the navigation-based and clustering methods are recommended to apply in vehicle concept and production phase, respectively. This study can be used as a guidance to select driving condition recognition method for adaptive vehicle energy management.

Keywords: Driving condition recognition; Supervised learning; Markov decision process; Clustering; Fuzzy logic (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223001263
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:269:y:2023:i:c:s0360544223001263

DOI: 10.1016/j.energy.2023.126732

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().