Method and system for predicting vehicle battery health using a collaborative vehicle battery health model

• US 9,058,038 B2
• Filed: 03/29/2012
• Issued: 06/16/2015
• Est. Priority Date: 03/29/2012
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Zhang, Yilu, Howell, Mark N., Tang, Xidong, Bai, Fan, Du, Xinyu, Singh, Satnam
• Primary Examiner(s): Shah, Kamini S
• Assistant Examiner(s): COOK, BRIAN S
• Application Number:
  US13/433,644
• Publication Number:
  US 20130262067A1
• Time in Patent Office: 1,174 Days
• Field of Search: 703/2, 702/63
• US Class Current: 1/1
• CPC Class Codes: G01R 31/367 Software therefor, e.g. for battery testing using modelling or look-up tables
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C

Abstract

A method includes collecting vehicle health data from a plurality of vehicles. A peer group is identified among the plurality of vehicles. The collected vehicle health data from the peer group into a collaborative vehicle health model, the collaborative vehicle health model being applicable to a current vehicle to predict a state of at least a component of the current vehicle.

Claims

1. A method for predicting replacement time of a vehicle battery comprising:

providing a processor configured to;

collect battery performance data from a plurality of vehicles though a wireless receiver;

identify the battery performance data associated with vehicles belonging to a peer group defined by a mutual year of manufacture;

apply a statistical operation to the battery performance data so as to calculate an adjustment parameter reflecting the mutual year of manufacture;

use a collaborative health model incorporating the adjustment factor to predict a replacement date of a battery of a vehicle associated with the peer group, the collaborative health model implemented as

C_deg(t)=C_Ne<sup>−

cz(1-Zw(t)/1.6ZIEC)</sup>,

wherein C_deg(t) is time dependent, battery capacity, C_N is nominal battery capacity, Z_w(t) is time dependent, weighted throughput, Z_IEC is a standard throughput value, and c_z is the adjustable parameter.

2. The method of claim 1, wherein peer group is further defined by a common model of the vehicles.

3. The method of claim 2, wherein the peer group is further defined by a common geographical area of operation.

4. The method of claim 2, wherein the peer group is further defined by a common climate to which the vehicles are subject.

5. The method of claim 2, wherein the peer group is further defined by similar operational conditions.

6. The method of claim 1, wherein the statistical operation includes a least mean square error operation.

7. The method of claim 1, the statistical operation is selected from the group consisting of application of a restricted maximum likelihood method, a quasi-maximum likelihood estimator, a posteriori estimator, a method of support, a generalized method of moments, or a maximum spacing estimation.

8. A system for predicting a replacement time of a vehicle battery, the system comprising:

a processor in communication with a wireless network, the processor configured to;

collect battery performance data from a plurality of vehicles though a wireless receiver;

identify the battery performance data associated with vehicles belonging to a peer group defined by a mutual year of manufacture;

apply a statistical operation to the battery performance data so as to calculate an adjustment parameter reflective of the mutual year of manufacture;

use a collaborative health model incorporating the adjustment factor to predict a replacement date of a battery of a vehicle associated with the peer group, the collaborative health model implemented as C_deg (t)=C_Ne<sup>−

cz(1-Zw(t)/1.6ZIEC),</sup>

wherein C_deg(t) is time dependent, battery capacity, C_N is nominal battery capacity, Z_w(t)is time dependent, weighted throughput, Z_IEC is a standard throughput value, and c_z is the adjustable parameter.

9. The system of claim 8, wherein peer group is further defined by a common model of the vehicles.

10. The system of claim 9, wherein the peer group is defined by a common geographical area of operation.

11. The system of claim 9, wherein the peer group is further defined by a common climate to which the vehicles are subject.

12. The system of claim 9, wherein the peer group is further defined by similar operational conditions.

13. The system of claim 8, wherein the statistical operation includes a least mean square error operation.

14. The system of claim 8, wherein the statistical operation is selected from the group consisting of application of a restricted maximum likelihood method, a quasi-maximum likelihood estimator, a posteriori estimator, a method of support, a generalized method of moments, or a maximum spacing estimation.