Economic and Efficient Hybrid Electric Vehicle Fuel Economy and Emissions Modeling Using an Artificial Neural Network

Paper #:
  • 2018-01-0315

Published:
  • 2018-04-03
Abstract:
High accuracy hybrid electric vehicle (HEV) fuel economy (FE) and emissions models used in practice today are the product of years of research, are physics based, and bear a large computational cost. However, it may be possible to replace these models with a non-physics based, higher accuracy, and computationally efficient version. In this research, an alternative method is developed by training and testing a time series artificial neural network (NN) using real world, on-road vehicle velocity and battery state of charge data to predict instantaneous FE and emissions. First, city and highway real world drive cycles were developed. These drive cycles were then driven in a HEV and velocity, battery state of charge, FE and emissions data were recorded. From the velocity data, FE was determined using a custom developed vehicle simulation model created in Modelica and using the Autonomie vehicle modeling software. Next, NNs were trained first using velocity and battery state of charge as inputs and FE as a target and then using velocity as an input and emissions as a target. To study FE prediction accuracy, the custom Modelica model results, Autonomie results, NN model results, and the actual FE results were compared. To study emissions prediction accuracy, the NN model results were directly compared to the actual emissions results. The results show that the NN model was computationally faster and predicted FE within a mean absolute error of 0-5%. For emissions prediction the NN model had a mean absolute error of 0-8% across CO2, CO, and NOx aggragate predicted concentrations. Overall, these results indicate that NN models could be used for a variety of research applications due to their economic and computational benefits such as derivation of vehicle control strategies to improve FE and emissions.
Access
Now
SAE MOBILUS Subscriber? You may already have access.
Buy
Attention: This item is not yet published. Pre-Order to be notified, via email, when it becomes available.
Select
Price
List
Download
$22.00
Mail
$22.00
Members save up to 36% off list price.
Share
HTML for Linking to Page
Page URL

Related Items

Event
2018-04-10
Technical Paper / Journal Article
2011-05-17