Method for estimating internal resistance of secondary battery and anomaly detection system of secondary battery
View Patent ↗An electric automobile incorporating a secondary battery has a disadvantage such as a difficulty in knowing the remaining capacity accurately and in predicting the time when the remaining capacity becomes zero because of deterioration of the secondary battery. The internal resistance is estimated with high accuracy even when the secondary battery deteriorates. Data used for learning or estimation is a data group (also referred to as data with regenerative charging) that is limited to data acquired within a certain time range around the end of regenerative charging. Such data within the limited range is extracted, used for learning, and subjected to the estimation. Thus, a value of the internal resistance can be output with high accuracy, specifically, with a mean error rate of 1% or less.
1. A method for estimating internal resistance of a secondary battery in an electric vehicle,
wherein a vehicle comprises a secondary battery, a learned neural network portion for estimating internal resistance of the secondary battery, a regenerative brake for performing regenerative charging on the secondary battery, and a charging circuit for the regenerative charging of the secondary battery,
wherein the method comprises:
performing regenerative charging of the secondary battery when a brake of the vehicle runs;
measuring data of the secondary battery while the electric vehicle is stopped with regenerative charging not running;
inputting the data of the secondary battery to the learned neural network portion; and
outputting estimated internal resistance of the secondary battery from the learned neural network portion, and
wherein the data of the secondary battery is data limited within a first time range around an end of the regenerative charging.
2. The method for estimating internal resistance of a secondary battery in an vehicle according to claim 1 , wherein the first time range comprises a point of time before the end of regenerative charging and a point of resting time later than the end of regenerative charging.
3. The method for estimating internal resistance of a secondary battery in an vehicle according to claim 1 , wherein each of learning data to prepare the learned neural network portion and the data of the secondary battery includes one or more selected from a temperature, a voltage, a power, a current and a voltage.
4. A method for detecting an anomaly of a secondary battery in an electric vehicle,
wherein a vehicle comprises a secondary battery, a learned neural network portion for estimating internal resistance of the secondary battery, a regenerative brake for performing regenerative charging on the secondary battery, and a charging circuit for the regenerative charging of the secondary battery,
wherein the method comprises:
performing regenerative charging of the secondary battery when a brake of the vehicle runs;
measuring data of the secondary battery while the electric vehicle is stopped with regenerative charging not running;
inputting the data of the secondary battery to the learned neural network portion;
outputting estimated internal resistance of the secondary battery from the learned neural network portion; and
comparing a value of the estimated internal resistance with a reference value stored in advance as a range of a normal internal resistance in a memory.