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.

Data has been gathered using the West Virginia University Heavy Duty Transportable Emissions Laboratories from buses operating on diesel and a variety of alternate fuels in the field. Typically, the transportable chassis dynamo meter is set up at a local transit agency and the selected buses are tested using the fuel in the vehicle at the time of the test. The dynamometer may be set up to operate indoors or outdoors depending on the space available at the site. Samples of the fuels being used at the site are collected and sent to the laboratory for analysis and this information is then sent together with emissions data to the Alternate Fuels Data Center at the National Renewable Energy Laboratory. Emissions data are acquired from buses using the Central Business District cycle reported in SAE Standard J1376; this cycle has 14 ramps with 20 mph (32.2 km/h) peaks, separated by idle periods.