System monitoring the discharging period of the charging/discharging cycles of a rechargeable battery, and host device including a smart battery

• US 5,936,385 A
• Filed: 10/30/1996
• Issued: 08/10/1999
• Est. Priority Date: 10/31/1995
• Status: Expired due to Fees

• Current Assignee: US Philips Corporation (Koninklijke Philips N.V.)
• Original Assignee: US Philips Corporation (Koninklijke Philips N.V.)
• Inventors: Nadal, Jean-Pierre, D'Alche-Buc, Florence, Patillon, Jean-Noel
• Primary Examiner(s): Wong, Peter S.
• Assistant Examiner(s): SHIN, KYUNG E
• Application Number:
  US08/739,770
• Time in Patent Office: 1,014 Days
• Field of Search: 320/106, 320/107, 320/134, 320/135, 320/136, 320/132, 320/DIG. 21, 320/151, 320/152, 320/130
• US Class Current: 320/136
• CPC Class Codes: G01R 31/367 Software therefor, e.g. for battery testing using modelling or look-up tables
• CPC Class Codes: H02J 7/0063 with circuits adapted for supplying loads from the battery

Abstract

A system for monitoring the discharging/charging cycles of a rechargeable battery which includes adaptive calculation means for providing a predictive indication of when the battery will reach a critical discharge voltage. The adaptive calculation means includes parameters which can be modified by other adaptive calculation means so as to optimize the monitor'"'"'s performance depending on the battery'"'"'s actual use. The adaptive calculation means may be neural networks formed by a microprocessor and memory, and the monitor system may be coupled to a host system.

Claims

1. A monitoring system for monitoring the discharging period of the charging/discharging cycles of a battery, coupled to a rechargeable battery which has charging periods alternating with discharging periods as a function of charging/discharging cycles, this system comprising:

first adaptive calculation means which are arranged for collecting, at an initial instant (to) at the beginning of a discharging period of a charging/discharging cycle of the battery, a predetermined value of a critical discharge voltage threshold (V_TH), and for calculating and providing a predictive indication of a critical instant (t_TH) at which the battery will reach this predetermined critical discharge voltage threshold (V_TH),

second adaptive calculation means coupled to the first calculation means, which are arranged for collecting, at the initial instant (to), a measured value of an initial voltage (Vo), of an initial variation (Δ

Vo) of the voltage at a later instant (t'"'"'o) after a short lapse of time (Δ

to) starting from this initial instant (to) onwards, and of the initial number (No) of charging/dischargirg cycles of this battery effected before this initial instant (to), and arranged for calculating and producing from the instant (to+Δ

to) of said discharging period at which the initial values are available onwards, operating parameters which are automatically adapted to the values of the initial measurements and imposed on the first calculation means to improve the accuracy thereof.

2. A monitoring system as claimed in claim 1, in which the first adaptive calculation means are also arranged for collecting, at a current instant (t) during the respective discharging period of the charging/discharging cycle of the battery in operation, a temperature measurement (Tt), and for calculating and providing at this current instant (t) a predictive indication of a critical instant (t_TH) at which the battery will reach the predetermined critical discharge voltage threshold (V_TH).

3. A monitoring system as claimed in claim 1, in which:

the first adaptive calculation means are also arranged for calculating and providing at each current instant (t) a predictive indication of the lapse of time (Δ

t_TH) that is left from this current instant (t) onwards until the critical instant (t_TH) at which the battery will reach the predetermined critical discharge voltage threshold (V_TH), or a predictive indication of this critical instant (t_TH).

4. A monitoring system as claimed in claim 1, in which the adaptive calculation means are formed by:

a first neural network (NN1A) arranged for calculating and providing at each current instant (t) a predictive indication of the critical instant (t_TH) at which the battery will reach this predetermined critical discharge voltage threshold (V_TH), on the basis of the predetermined critical discharge voltage threshold (V_TH),

a second neural network (NN2A), combined in series with the first neural network, arranged for calculating and providing automatically adapted synaptic weights (WjB) imposed on the first neural network, on the basis of the initial measurement of the voltage values (Vo), of the initial voltage variation (Δ

Vo) and of the initial number of cycles (No), with each start of a discharging period of each discharging cycle, from the instant (to+Δ

to) of the respective period onwards at which the initial measurements are available.

5. A monitoring system as claimed in claim 2, in which the adaptive calculation means are formed by:

a first neural network (NN1B) arranged for calculating and providing at each current instant (t) a predictive indication of the critical instant (t_TH) at which the battery will reach this predetermined critical discharge voltage threshold (V_TH), on the basis of the predetermined critical discharge voltage threshold (V_TH), and on the basis of the temperature measurement (Tt),

a second neural network (NN2B), combined in series with the first neural network, arranged for calculating and providing automatically adapted synaptic weights (WjB) imposed on the first neural network, on the basis of the initial measurement of the voltage values (Vo), of the initial voltage variation (Δ

Vo) and of the initial number of cycles (No), with each start of a discharging period of each discharging cycle, from the instant (to+Δ

to) of the respective period onwards at which the initial measurements are available.

6. A monitoring system as claimed in claim 4, in which:

the first neural network is arranged for calculating and providing at each current instant (t) a predictive indication of the lapse of time (Δ

t_TH) that is left from this current instant (t) onwards until the critical instant (t_TH) at which the battery will reach this predetermined critical discharge voltage threshold (V_TH), on the basis of the predetermined critical discharge voltage threshold (V_TH), and possibly on the basis of the temperature measurement (Tt).

7. A monitoring system as claimed in claim 4, in which the first neural network (NN1) has three layers, of which one layer of two or three input cells for a threshold, a voltage value and possibly a temperature value respectively, one layer of hidden cells and an output cell, the cells of the hidden layer having a sigmoidal activating function with different slopes from one cell to another, and the cell of the output layer having a linear activating function.

8. A monitoring system as claimed in claim 7, in which the second neural network has three neural cell layers, of which one layer of four input cells for a threshold, and each of the initial values respectively, one layer of hidden cells, and one layer of output cells, the cells of the hidden layer having a sigmoidal activating function with different slopes from one cell to another, and the cells of the output layer having a like quantity to the number of synaptic coefficients which are necessary for the operation of the first neural network and having a sigmoidal activating function.

9. A monitoring system as claimed in claim 4, this system being coupled to a host device, and in this host device to a rechargeable battery, to time measuring means, voltage measuring means, and optionally to temperature measuring means, and to display means arranged for providing either an indication of the critical instant (t_TH) at which the battery will reach the critical voltage threshold (vt_TH), or an indication of the lapse of time (Δ

t_TH) that is left from a current instant of use (t) onwards until the instant (t_TH) at which the battery will reach a predetermined critical voltage threshold (Vt_TH), or the two indications, and optionally an indication of the end of the recharging period of the battery.

10. A monitoring system as claimed in claim 9, comprising a microprocessor for carrying out the calculations, and memory areas for storing the data, these memory areas being accessible via the microprocessor and including a ROM memory area for storing the structure data of the neural networks, the fixed parameters and the synaptic coefficients of the second neural network, and a RAM memory area for recording or producing the variable measurements and the synaptic coefficients of the first neural network.

11. A host device supplied with power by a rechargeable battery, coupled to a monitoring system as claimed in claim 1, this device further including, coupled to this system, time measuring means, voltage measuring means, optionally temperature measuring means, and display means arranged for providing either an indication of the critical instant (t_TH) at which the battery will reach the critical voltage threshold (vt_TH), or an indication of the lapse of time (Δ

t_TH) that is left from a current instant of use (t) onwards until the instant at which the battery will reach a predetermined critical voltage threshold (V_TH), or the two indications, and arranged for providing an indication of the end of the charging of the battery in a recharging period.

12. A host device as claimed in claim 11, in which the monitoring system comprises, for realizing the first and second calculation means, a microprocessor for carrying out the calculations, and memory areas for storing the data, these memory areas being accessible via the microprocessor and including a ROM memory area for storing the structure data of the first and second calculation means, the fixed parameters and the operation parameters of the second calculation means, and a RAM memory area for recording or producing the variable measurements and the operation parameters of the first calculation means.

13. A method of producing neural networks of the monitoring system as claimed in claim 7, comprising in a learning period:

the learning by the first neural network, of discharging time curves (t) as a function of the discharge voltage (Vt) and possibly the temperature (Tt) as parameters, during which period discharge voltages (Vt) are imposed on the input of the first neural network normally intended for the voltage value, and the corresponding instants are imposed on the output for forming a data base formed by vectors of the synaptic coefficients (WjA,WjB) of this first neural network,

the learning by the second neural network of relations between the initial values (Vo, Δ

Vo, No) and the synaptic coefficients (WjA,WjB) determined in its learning period of the first neural network, for determining and fixing its own synaptic coefficients.

14. A monitoring system as claimed in claim 2, in which:

the first adaptive calculation means are also arranged for calculating and providing at each current instant (t) a predictive indication of the lapse of time (Δ

t_TH) that is left from this current instant (t) onwards until the critical instant (t_TH) at which the battery will reach the predetermined critical discharge voltage threshold (V_TH), or a predictive indication of this critical instant (t_TH).

15. A monitoring system as claimed in claims 5, in which:

the first neural network is arranged for calculating and providing at each current instant (t) a predictive indication of the lapse of time (Δ

t_TH) that is left from this current instant (t) onwards until the critical instant (t_TH) at which the battery will reach this predetermined critical discharge voltage threshold (V_TH), on the basis of the predetermined critical discharge voltage threshold (V_TH), and possibly on the basis of the temperature measurement (Tt).

16. A monitoring system as claimed in claim 15, in which the first neural network has three layers, of which one layer of two or three input cells for a threshold, a voltage value and possibly a temperature value respectively, one layer of hidden cells and an output cell, the cells of the hidden layer having a sigmoidal activating function with different slopes from one cell to another, and the cell of the output layer having a linear activating function.

17. A monitoring system as claimed in claim 16, in which the second neural network has three neural cell layers, of which one layer of four input cells for a threshold, and each of the initial values respectively, one layer of hidden cells, and one layer of output cells, the cells of the hidden layer having a sigmoidal activating function with different slopes from one cell to another, and the cells of the output layer having a like quantity to the number of synaptic coefficients which are necessary for the operation of the first neural network and having a sigmoidal activating function.

18. A monitoring system as claimed in claim 17, this system being coupled to a host device, and in this host device to a rechargeable battery, to time measuring means, voltage measuring means, and optionally to temperature measuring means, and to display means arranged for providing either an indication of the critical instant (t_TH) at which the battery will reach the critical voltage threshold (vt_TH), or an indication of the lapse of time (Δ

t_TH) that is left from a current instant of use (t) onwards until the instant (t_TH) at which the battery will reach a predetermined critical voltage threshold (Vt_TH), or the two indications, and optionally an indication of the end of the recharging period of the battery.

19. A host device supplied with power by a rechargeable battery, coupled to a monitoring system as claimed in claim 10, this device further including, coupled to this system, time measuring means, voltage measuring means, optionally temperature measuring means, and display means Arranged for providing either an indication of the critical instant (t_TH) at which the battery will reach the critical voltage threshold (vt_TH), or an indication of the lapse of time (Δ

t_TH) that is left from a current instant of use (t) onwards until the instant at which the battery will reach a predetermined critical voltage threshold (V_TH), or the two indications, and arranged for providing an indication of the end of the charging of the battery in a recharging period.

20. A method of producing neural networks of the monitoring system as claimed in claim 17, comprising in a learning period:

the learning by the first neural network, of discharging time curves (t) as a function of the discharge voltage (Vt) and possibly the temperature (Tt) as parameters, during which period discharge voltages (Vt) are imposed on the input of the first neural network normally intended for the voltage value, and the corresponding instants are imposed on the output for forming a data base formed by vectors of the synaptic coefficients (WjA,WjB) of this first neural network,

the learning by the second neural network of relations between the initial values (Vo, Δ

Vo, No) and the synaptic coefficients (WjA,WjB) determined in its learning period of the first neural network, for determining and fixing its own synaptic coefficients.