Development of heavy-duty vehicle representative driving cycles via decision tree regression. (June 2021)

• Record Type: Journal Article
• Authors: Zhang, Chen; Kotz, Andrew; Kelly, Kenneth; Rippelmeyer, Luke
• Is Part Of: Transportation research. Volume 95(2021)
• Publication Date: 2021-06
• Subjects: Heavy-duty vehicle -- Powertrain electrification -- Decision tree regression -- Representative driving cycle -- On-road data; Transportation -- Research -- Periodicals; Transportation -- Environmental aspects -- Periodicals; 354.76
• DOI: 10.1016/j.trd.2021.102843
• Languages: English
• ISSNs: 1361-9209

Abstract

Highlights: Characterized driving behaviors for multiple heavy-duty vocations via on-road data. Illustrated critical metric distributions from on-road data for each vocation. Applied decision tree regression to derive the most representative driving cycle. Considered engine power and fuel rate as metrics while identifying the cycles. Accounted each metric's different influence on the objective of representatives. Abstract: Previously, researchers who developed representative driving cycles mainly focused on light-duty vehicles and only considered vehicle speed and related derivations. In this paper, we propose a novel approach to develop representative cycles for heavy-duty vehicles. By implementing decision tree regression (DTR) to the Fleet DNA on-road vehicle data, a broader set of metrics, such as engine power and fuel consumption, can be used for more robust cycle development. Additionally, the influence of each metric on the regression target is also accounted for by a weighted number derived through the DTR to enhance the representativenss of the developed cycle. As case studies, we applied the proposed method to five heavy-duty vocations (drayage, long haul, regional haul, local delivery, and transit bus) and derived the most representative cycle, as well as four extreme cycles (maximal energy consumption, maximal power-weighted work, maximal fraction of high speed, and minimal fuel economy) to advance the related alternative powertrain design.