Browse Prior Art Database

A Neural Network based Method for PHEV Distance Between Fill-up Estimation Disclosure Number: IPCOM000248381D
Publication Date: 2016-Nov-22
Document File: 2 page(s) / 57K

Publishing Venue

The Prior Art Database

This text was extracted from a Microsoft Word document.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 52% of the total text.

A Neural Network Based Method for PHEV Distance Between Fill-up Estimation

Plug In Electric Vehicles (PHEVs) typically have an EV mode driving range which can cover some or all of a customer’s daily driving distance.  This EV mode driving range impacts the distance between fuel fill-ups compared to conventional vehicles.  For a conventional vehicle, generally the distance between fuel fill-up is dependent on tank size and fuel economy, while for PHEVs, distance between fuel-fill up is dependent on tank size, fuel economy, and EV driving range.  Furthermore, for PHEVs, the fraction of EV driving varies with customer trip lengths.  Hence, it becomes critical to use real world customer usage pattern to estimate distance between fill up and size the fuel tank accordingly.

We can assume that distance between fill-up for a PHEV is a function of three inputs variables: EV range, hybrid MPG, and tank size.  A linear model to estimate this was previously proposed.  However, to capture the nonlinearity of the estimation, and make the model more accurate over a wider usage range, an artificial neural network-based estimation model is proposed.


The objective of the work is to propose a customer data driven estimation model for distance between fuel fill-ups on PHEVs.  For PHEVs, distance between fill-ups is assumed as a function as follows -



 is the distance between fill ups

 is the fuel tank volume

 is the fuel economy in miles per gallon in charge sustaining mode once the battery is d...