Professional diagnosis method of battery performance analysis

• US 8,306,781 B2
• Filed: 04/17/2008
• Issued: 11/06/2012
• Est. Priority Date: 04/20/2007
• Status: Active Grant

• Current Assignee: Hangzhou Gold Electronic Equipment Company Limited
• Original Assignee: Hangzhou Gold Electronic Equipment Company Limited
• Inventors: Xu, Jianhong, Yuan, Ling, Zheng, Yi
• Primary Examiner(s): Nghiem, Michael
• Assistant Examiner(s): RIVERA VARGAS, MANUEL A
• Application Number:
  US12/596,163
• Publication Number:
  US 20110054815A1
• Time in Patent Office: 1,664 Days
• Field of Search: 702/183, 702 63- 35, 320/132, 320/134, 324425-434
• US Class Current: 702/183
• CPC Class Codes: G01R 31/367 Software therefor, e.g. for battery testing using modelling or look-up tables
• CPC Class Codes: G01R 31/382 Arrangements for monitoring battery or accumulator variables, e.g. SoC

Abstract

The present invention discloses a professional diagnosis method of battery performance analysis, Through the overall evaluation of experiential data library, several parameters about the battery are input into the artificial neural network, outputting capacity prediction and service life prediction of each battery, etc. and giving useful advices for each battery. Therefore the result is much more in conformity with the real condition of the battery. Besides, it designs an adaptive learning function of the abovementioned artificial neural network. This invention effectively avoids the defect of evaluating the VRLA battery performance at single moment, from single perspective and by single method, and it does the real-time monitoring and evaluating for the performance of the battery during VRLA battery working period, which is easy to operate, and avoids checking discharge test to the battery so that it doesn'"'"'t affect the cycle life of the VRLA battery.

Claims

1. A professional diagnosis method of battery performance analysis comprising the steps of:

measuring parameters of a battery set with two or more batteries by a measuring device, the parameters including maximum voltage of each battery in an equalized charge period, minimum voltage of each battery in an equalized charge period, float voltage dispersion ratio of a single battery, float voltage dispersion ratio of the battery set, battery conductance at end of a discharge r(i), voltage of each battery at end of a short-term discharge, voltage difference and temperature of each battery during a short-term charge and discharge;

then inputting the parameters to an artificial neural network including a computer which calculates and outputs predicted battery performance and gives relevant operating advices;

wherein said float voltage dispersion ration of a single battery is calculated by equation (3);

2. The professional diagnosis method of battery performance analysis according to claim 1, wherein discharge battery conductance at the end of the discharge is calculated by equation (5):

r(i)=[U_ij−

U_ij+2]/I 

 

(5)

where, I is the discharge current, and U_ij is the voltage of the battery i at the moment j in the discharge process, U_ij+2 is the voltage of the battery i at the moment j+2 in the discharge process, which satisfy the condition;

(U_ij−

U_ij+2)>

0.002.

3. The professional diagnosis method of battery performance analysis according to claim 2, wherein the modifying conductance of each battery is used as the input of the artificial neural network, modifying conductance of each battery is calculated by equation (6):

R(i)=40.404×

[r(i)−

r]²+0.5836371 

 

(6)

where, r is the average conductance of the battery set.

4. The professional diagnosis method of battery performance analysis according to claim 1, wherein the artificial neural network has an adaptive learning function, and the network automatically changes a learning set, restarts learning and training, and then forms a new evaluation system under special condition when a valve-regulated lead-acid battery goes through full or half capacity checking discharge testing.

5. The professional diagnosis method of battery performance analysis according to claim 4, wherein specific procedures to change the learning set are as follows:

(1) sorting the battery by performance according to checking discharge testing result;

(2) when the battery number is above twelve, choosing the first, last and middle four of sorting results at an end voltage of the checking discharge testing, and replacing corresponding parameters in original learning set;

calculating storage place of the middle four batteries by equation (7);

initial position=num\2−

1 

 

(7)

wherein, num is the battery number of the battery set;

when the battery number is below twelve, choosing a voltage at end of the checking discharge testing and replacing corresponding parameters in the battery original set;

marking specimens which are not replaced, then replacing them at next checking discharge testing;

(3) replacing other parameters in the learning set as follows;

reading the float voltage dispersion ratio of a single battery, the float voltage dispersion ratio of the battery set, the maximum equalized charge voltage, the minimum equalized charge voltage, the conductance calculated from dynamic discharge, the voltage of each battery at the end of the short-term discharge, the voltage difference and temperature of each battery during the short-term charge and discharge, which are at the closest moment to the checking discharge testing of a chosen battery in procedure and then replacing original values of relevant parameters in the learning set;

(4) replacing a teacher set by reading the network-calculated predicted capacity and service life of the chosen batteries in step (2) after the checking discharge testing and replacing the original value of relevant parameters in the teacher set; and

(5) after getting new learning set and teacher set, restarting learning of the network and forming a set of new evaluation rules for the battery performance.

6. A professional diagnosis method of battery performance analysis comprising the steps of:

measuring parameters of a battery set with two or more batteries by a measurement device, the parameters including maximum voltage of each battery in an equalized charge period, minimum voltage of each battery in an equalized charge period, float voltage dispersion ratio of a single battery, float voltage dispersion ratio of the battery set, battery conductance at end of a discharge r(i), voltage of each battery at end of a short-term discharge, voltage difference and temperature of each battery during a short-term charge and discharge; and

inputting the parameters to an artificial neural network including a computer which calculates and outputs predicted battery performance and gives relevant operating advices;

wherein said float voltage dispersion ratio of a single battery is calculated by equation (3);

7. The professional diagnosis method of battery performance analysis according to claim 6, wherein the artificial neural network has an adaptive learning function, and the network automatically changes a learning set, restarts learning and training, and then forms a new evaluation system under special condition when a valve-regulated lead-acid battery goes through full or half capacity checking discharge testing.

8. The professional diagnosis method of battery performance analysis according to claim 7, wherein specific changing learning set procedures are as follows:

(1) sorting the battery by performance according to checking discharge testing result;

(2) when the battery number is above twelve, choosing the first, last and middle four of sorting results at an end voltage of the checking discharge testing, and replacing corresponding parameters in original learning set;

calculating storage place of the middle four batteries by equation (7);

initial position=num\2−

1 

 

(7)

wherein, num is the battery number of the battery set;

when the battery number is below twelve, choosing a voltage at end of the checking discharge testing and replacing corresponding parameters in the battery original set;

marking specimens which are not replaced, then replacing them at next checking discharge testing;

(3) replacing other parameters in the learning set is as follows;

reading the float voltage dispersion ratio of a single battery, the float voltage dispersion ratio of the battery set, the maximum equalized charge voltage, the minimum equalized charge voltage, the conductance calculated from dynamic discharge, the voltage of each battery at the end of the short-term discharge, the voltage difference and temperature of each battery during the short-term charge and discharge, which are at the closest moment to the checking discharge testing of a chosen battery in procedure and then replacing original values of relevant parameters in the learning set;

(4) replacing a teacher set by reading the network-calculated predicted capacity and service life of the chosen batteries in step (2) after the checking discharge test and replacing the original value of relevant parameters in the teacher set; and

(5) after getting new learning set and teacher set, restarting learning of the network and forming a set of new evaluation rules for the battery performance.

9. The professional diagnosis method of battery performance analysis according to claim 6, wherein uses the modifying conductance of each battery as the input of the artificial neural network, modifying conductance of each battery is calculated by equation (6):

R(i)=40.404×

[r(i)−

r]²+0.5836371 

 

(6)

where, r is the average conductance of the battery set.