By Topic

Estimating Soc in Lead-Acid Batteries Using Neural Networks in a Microcontroller-Based Charge-Controller

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Valdez, M.A.C. ; Inst. of Electr. Res., Morelos ; Orozco Valera, J.A. ; Arteaga, M.J.O.

Accurate state-of-charge (SOC) estimation in lead-acid batteries is an ever-increasing necessity in an industry that demands low-maintenance costs and highly available systems. If the batteries are charged by photovoltaic panels and are installed in remote sites and exposed to aggressive environmental conditions, the problem of extending the batteries' useful life becomes a challenge. Modern charge-controllers can do a very good job extending the batteries' life, but any charge-controller is as good as the measurements taken to feed the control algorithm. Estimating SOC in lead-acid batteries is generally acknowledged as a difficult problem. This paper presents a method to estimate SOC by means of an artificial neural network First, the network is trained using precise measurements of voltage, current and temperature under different charge-regimes. Ampere-counting (A-C) is used during training to determine SOC. Once the training is completed, the neural network can accurately estimate SOC using precise measurements of voltage and temperature and rough measurements of current. This method has the advantage of requiring no precise current measurements. Accurate current measurements tend to increase the cost of the controller. The resulting neural network has been implemented in a microcontroller-based charge-controller.

Published in:

Neural Networks, 2006. IJCNN '06. International Joint Conference on

Date of Conference:

0-0 0