Development of a novel engine power model to estimate heavy-duty truck fuel consumption

Abstract

An accurate heavy-duty truck (HDT) fuel consumption model is essential for estimating the truck energy consumption and evaluating energy-saving strategies. However, based on recent truck field tests, we noticed that the estimation discrepancies of several published models were considerable since they were only developed for light-duty vehicles and cannot accurately estimate the HDT engine operation states. This inspired us to develop a generic approach for HDT engine-power estimation with a deep learning approach based on numerous tests. The results show that the proposed approach enables a more accurate estimation of HDT engine power, and when applied as the input to the fuel consumption models (e.g. Virginia-Tech model), the average estimation error is reduced to 13.71% from 28.9%. Besides, once calibrated, the proposed model could be applied to various scenarios without re-calibration. In addition, it can depict the fuel consumption during engine braking, which is largely missing in conventional HDT models.

KEYWORDS:

• Heavy duty truck
• fuel consumption model
• power modeling
• deep learning

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This research was partially supported by the U.S. Department of Energy (DOE) Vehicle Technologies Office (VTO) under the Systems and Modeling for Accelerated Research in Transportation (SMART) Mobility Laboratory Consortium, an initiative of the Energy Efficient Mobility Systems (EEMS) Program under the direction of Mr. David Anderson who is gratefully acknowledged, the project number is DOE/VTO  EEMS031. It was also partially supported by CSC (China Scholarship Council, No: 201706320100) funding support of the first author’s visit at U. C. Berkeley in 2018, during which most of the research work was done.