Vehicular emissions prediction with CART-BMARS hybrid models |
| |
Institution: | 1. Department of Physics, College of William and Mary,Box 8795, Williamsburg, VA, USA;2. Department of Environmental, Earth, and Atmospheric Sciences, University of Massachusetts Lowell, Lowell MA, USA;3. Laboratoire de Météorologie Dynamique, IPSL, CNRS UMR 8539, Sorbonne Universités, UPMC Univ. Paris 06, Paris 75252, France;4. Science Directorate, NASA Langley Research Center, Hampton, VA, USA;5. Pacific Northwest National Laboratory, Richland, WA, USA;1. Centre Automatique et Systèmes, MINES ParisTech, PSL Research University, Paris 75006, France;2. Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim N-7491, Norway |
| |
Abstract: | Vehicular emission models play a key role in the development of reliable air quality modeling systems. To minimize uncertainties associated with these models, it is essential to match the high-resolution requirements of emission models with up-to-date information. However, these models are usually based on average trip speed, not on environmental parameters like ambient temperature, and vehicle’s motion characteristics, such as speed, acceleration, load and power. This contributes to the degradation of its predictive performance. In this paper, we propose to use the non-parametric Classification and Regression Trees (CART), the Boosting Multivariate Adaptive Regression Splines (BMARS) algorithm and a combination of them in hybrid models to improve the accuracy of vehicular emission prediction using on-board measurements and the chassis dynamometer testing. The experimental comparison between the proposed CART-BMARS hybrid model with the BMARS and artificial neural networks (ANNs) algorithms demonstrates its effectiveness and efficiency in estimating vehicular emissions. |
| |
Keywords: | Vehicular emissions On-board emission measurement Chassis dynamometer testing CART-BMARS ANNs |
本文献已被 ScienceDirect 等数据库收录! |
|