End of discharge prediction;
SMART BATTERY MANAGEMENT
Results
The proposed system is able to predict the end of discharge event with an average accuracy of 6 min. for an event that may occur in up to 10 hrs (the prediction is made after the first minute of use). 61% of the predictions leads to an error less than 5 minutes.
Results obtained: predicted vs actual discharge time
This system has been implemented onboard a prototype of a FLUKE multimeter, which demonstrates also that neural network methods can be useful in difficult situation such as portable equipments.
Last update:
(comments)