Apparatus and method for estimating state of charge in battery using fuzzy algorithm implemented as neural network

1. An apparatus for estimating a state of charge (SOC) in a battery, the apparatus comprising:

a detector unit including a current detector for detecting current from a battery cell, a voltage detector for detecting voltage from the battery cell, and a temperature detector for detecting temperature from the battery cell;

a soft computing unit for calculating and outputting a battery SOC estimation value by processing the current, the voltage and the temperature detected by the detector unit using a computing algorithm, which is a fuzzy algorithm implemented as a neural network, the soft computing unit storing the battery SOC estimation value in a memory; and

a comparator operably coupled to the soft computing unit and a charger-discharger, the charger-discharger being further operably coupled to the battery cell, the comparator comparing the battery SOC estimation value with a predetermined target value that varies with charging or discharging of the battery, the comparator further providing an algorithm update signal to the soft computing unit to update the computing algorithm based on a learning algorithm when a difference between the battery SOC estimation value and the predetermined target value is outside of a critical range,

wherein the fuzzy algorithm has a form expressed as F=Φ(P,X)W, where Φ is one of a fuzzy radial function, a radial basis function, and an activation function in the neural network, P is a learning parameter, X is an input, and W is a weight to be updated during learning.

2. The apparatus according to claim 1 , wherein the predetermined target value is a reference value obtained through a corresponding test on a specific condition.

3. The apparatus according to claim 1 , wherein the learning algorithm is any one of a back propagation learning algorithm, a Kalman filter, a genetic algorithm, and a fuzzy learning algorithm.

4. A method for estimating a state of charge (SOC) in a battery, the method comprising the steps of:

detecting current, voltage and temperature from a battery cell, utilizing a current detector, a voltage detector, and a temperature detector, respectively;

calculating a battery SOC estimation value by processing the detected current, voltage and temperature using a computing algorithm, which is a fuzzy algorithm implemented as a neural network, utilizing a soft computing unit;

storing the battery SOC estimation value in a memory utilizing the soft computing unit;

calculating a difference value between the calculated battery SOC estimation value and a predetermined target value varying with charging or discharging of the battery utilizing a comparator operably coupled to the soft computing unit and a charger-discharger;

sending an algorithm update signal from the comparator to the soft computing unit when a difference between the battery SOC estimation value and the predetermined target value is outside of a critical range; and

updating the computing algorithm based on a learning algorithm utilizing the soft computing unit in response to the algorithm update signal,

wherein the fuzzy algorithm has a form expressed as F=Φ(P,X)W, where Φ is one of a fuzzy radial function, a radial basis function, and an activation function in the neural network, P is a learning parameter, X is an input, and W is a weight to be updated during learning.

5. The method according to claim 4 , wherein the predetermined target value is a reference value obtained through a corresponding test on a specific condition.

6. The method according to claim 4 , wherein the learning algorithm is any one of a back propagation learning algorithm, a Kalman filter, a genetic algorithm, and a fuzzy learning algorithm.