Search Results

This paper presents multiple methods for predicting heavy/medium-duty vehicle fuel consumption based on driving cycle information. A polynomial model, a black box artificial neural net model, a polynomial neural network model, and a multivariate adaptive regression splines (MARS) model were developed and verified using data collected from chassis testing performed on a parcel delivery diesel truck operating over the Heavy Heavy-Duty Diesel Truck (HHDDT), City Suburban Heavy Vehicle Cycle (CSHVC), New York Composite Cycle (NYCC), and hydraulic hybrid vehicle (HHV) drive cycles. Each model was trained using one of four drive cycles as a training cycle and the other three as testing cycles. By comparing the training and testing results, a representative training cycle was chosen and used to further tune each method.

Understanding the real-world power demand of modern automobiles is of critical importance to engineers using modeling and simulation in the design of increasingly efficient powertrains. Increased use of global positioning system (GPS) devices has made large-scale data collection of vehicle speed (and associated power demand) a reality. While the availability of real-world GPS data has improved the industry's understanding of in-use vehicle power demand, relatively little attention has been paid to the incremental power requirements imposed by road grade. This analysis quantifies the incremental efficiency impacts of real-world road grade by appending high-fidelity elevation profiles to GPS speed traces and performing a large simulation study. Employing a large, real-world dataset from the National Renewable Energy Laboratory's Transportation Secure Data Center, vehicle powertrain simulations are performed with and without road grade under five vehicle models.