Refine Your Search

Search Results

Viewing 1 to 2 of 2
Technical Paper

A Configuration for a Continuously Variable Power-Split Transmission in Hybrid-Electric Vehicle Applications

Continuously variable transmissions (CVTs) are usually used in small vehicles due to power limitations on the variable elements. Continuously variable power-split transmissions (CVPST) were developed in order to reduce the fraction of power passing through the variable elements [1,2]. The configuration presented in this paper includes a planetary gear train (PGT), which in combination with the CVT allows the power to be split and therefore increase the power envelope of the system. The PGT also provides a branch that can be used in a hybrid electric vehicle (HEV) operation through an electric motor. A conceptual design of a CVPST for a HEV is presented in this paper. The objectives are to show the different operational modes, with diagrams, perform a power analysis, develop the velocity and force equations and finally show the performance of the system with an example application.
Technical Paper

Weighting of Parameters in Artificial Neural Network Prediction of Heavy-Duty Diesel Engine Emissions

The use of Artificial Neural Networks (ANNs) as a predictive tool has been shown to have a broad range of applications. Earlier work by the authors using ANN models to predict carbon dioxide (CO2), carbon monoxide (CO), oxides of nitrogen (NOx), and particulate matter (PM) from heavy-duty diesel engines and vehicles yielded marginal to excellent results. These ANN models can be a useful tool in inventory prediction, hybrid vehicle design optimization, and incorporated into a feedback loop of an on-board, active fuel injection management system. In this research, the ANN models were trained on continuous engine and emissions data. The engine data were used as inputs to the ANN models and consisted of engine speed, torque, and their respective first and second derivatives over a one, five, and ten second time range. The continuous emissions data were the desired output that the ANN models learned to predict through an iterative training process.