Abstract: A neural network type of apparatus is provided to detect an internal state of a secondary battery implemented in a battery system. The apparatus comprises a detecting unit, producing unit and estimating unit. The detecting unit detects electric signals indicating an operating state of the battery. The producing unit produces, using the electric signals, an input parameter required for estimating the internal state of the battery. The input parameter reflects calibration of a present charged state of the battery which is attributable to at least one of a present degraded state of the battery and a difference in types of the battery. The estimating unit estimates an output parameter indicating the charged state of the battery by applying the input parameter to neural network calculation.

Abstract: In a proposed apparatus and method, constant-voltage charge is performed with an in-vehicle secondary battery immediately after start of a vehicle or during running of the vehicle. A quantity relevant to polarization caused in the battery immediately after start of the constant-voltage charge is calculated using data of the charge current. It is determined whether or not a change rate of the calculated polarization-relevant quantity is less than a given threshold. When the change rate is less than the given threshold, a plurality of data of the charge current sampled and held during a predetermined period of time are acquired. A value of the charge current to be accumulated until the charge current reaches a given final value is calculated using the plurality of data of the charge current. The internal electric state of the battery is estimated based on the accumulated value of the charge current.

Abstract: An apparatus for estimating state variables of a secondary battery as an estimation target performs so that a neural network unit studies a true value of a battery temperature, a temperature large value which is larger than the true value of the battery temperature by an approximating temperature sensor detection error, and a temperature small value which is smaller than the true value of the battery temperature by the approximating temperature sensor detection error. After completion of the learning of those values, the neural network unit inputs a battery temperature detected by the temperature sensor, and performs a neural network based calculation to calculate a SOC (state of charge) of the secondary battery. This can drastically increase the calculation accuracy of the SOC of the secondary battery.

Abstract: A current Ibe and a voltage Vbe before a large current discharge in a secondary battery are stored in a memory. Plural voltage-current pairs are detected and stored in the memory during the large current discharge. Next, a regression curve (or a regression line) is obtained based on the plural voltage-current pairs stored in the memory using a well-known method. A discharge current Ip which exceeds a current-sensor detectable range is input in the regression curve to obtain a voltage Vp. A maximum discharge coordinate is set using the discharge current Ip and the voltage Vp. An internal resistance Rin of the secondary battery is calculated based on an inclination of a line that connects the coordinates (Ibe, Vbe) and (Ip, Vp).

Abstract: An apparatus is provided to calculate a quantity indicating a charged state of an on-vehicle battery. The battery powers a starter starting up an on-vehicle engine. In the apparatus, a plurality of pairs of data consisting of current and voltage of the battery are acquired at predetermined sampling intervals during a cranking period of the engine in response to starting up the starter. At intervals, a value of an internal resistance of the battery is calculated based on the plurality of pairs of data of current and voltage. The internal resistance is one kind of the charged-state indicating quantity. An open voltage difference is calculated, which is a difference between a pseudo circuit-open voltage of the battery given before starting up the starter and a pseudo circuit-open voltage of the battery given after the cranking period. The value of the internal resistance is corrected using the open voltage difference.

Abstract: An apparatus is provided to control a power voltage on a power-supplying line extending from a generator and connecting to a battery and eclectic loads. The apparatus is mounted on a vehicle and comprises a detecting device, a calculator, and a controller. The detecting device detects pairs of voltage and current of the battery. The calculator calculating a control current on the basis of the detected pairs of voltage and current and a target voltage for the power voltage. The pairs of voltage and current are used to calculate an internal resistance and/or a regression line of the battery. The controller controlling a charge and discharge current of the battery on the basis of the control current so that the power voltage is controlled to the target voltage.

Abstract: A charged state detecting apparatus for a secondary battery is provided, which can suppress deterioration in the accuracy of detecting a charged state, such as an SOC, the deterioration being caused by variation of a polarization state of a battery. The charged state detecting apparatus stabilizes an amount of polarization of the battery, stops power generation upon confirmation of the stabilization of the polarization amount, and sufficiently alters the current of the battery to sample a required number of data pairs of voltage and current of the battery. Using these data pairs, the charged state detecting apparatus detects a charged state, such as the SOC, of the battery.

Abstract: An apparatus and method of neural network type are provided to detect an internal state of a secondary battery implemented in a battery system. Electric signals indicating an operating state of the battery is detected and, using the electric signals, information indicating the internal state of the battery is calculated on the basis of neural network calculation, in which the information reflects a reduction in an effect of polarization of the secondary battery. Using the electric signals, input parameters required for calculating the internal state of the battery is calculated. The input parameters may include, as one input parameter, a polarization-related quantity to correct the effect of the polarization in an output parameter (such as SOC and/or SOH) from the neural network. Further, the input parameters may include, as one input parameter, a functional value already subjected to the correction for correcting the effect of the polarization.

Abstract: A neural network type of apparatus is provided to detect an internal state of a secondary battery implemented in a battery system. The apparatus comprises a detecting unit, producing unit and estimating unit. The detecting unit detects electric signals indicating an operating state of the battery. The producing unit produces, using the electric signals, an input parameter required for estimating the internal state of the battery. The input parameter reflects calibration of a present charged state of the battery which is attributable to at least one of a present degraded state of the battery and a difference in types of the battery. The estimating unit estimates an output parameter indicating the charged state of the battery by applying the input parameter to neural network calculation.

Abstract: An internal condition detection system detects a charging and discharging current and a terminal voltage of a charge accumulating device, and learns the internal condition quantity of the charge accumulating device through a neural network based on the current values and the terminal voltage values. The current values and the terminal voltage values are stored in a buffer and supplied as time-series data so that historical information is included. Further the neural network is fed with type information of the charge accumulating device. The type information is stored in a memory.