Systems and methods for determining vehicle battery health

• US 10,197,631 B2
• Filed: 06/01/2015
• Issued: 02/05/2019
• Est. Priority Date: 06/01/2015
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Inventors: Barfield, Jr., James Ronald, Welch, Stephen Christopher, Taylor, Thomas Steven
• Primary Examiner(s): Alrobaie, Khamdan N.
• Application Number:
  US14/727,238
• Publication Number:
  US 20160349330A1
• Time in Patent Office: 1,345 Days
• CPC Class Codes: G01R 31/3648 comprising digital calculation means, e.g. for performing an algorithm
• CPC Class Codes: G01R 31/367 Software therefor, e.g. for battery testing using modelling or look-up tables
• CPC Class Codes: G01R 31/389 Measuring internal impedance, internal conductance or related variables
• CPC Class Codes: G01R 31/392 Determining battery ageing or deterioration, e.g. state of health
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction
• CPC Class Codes: G07C 5/085 using electronic data carriers

Abstract

Techniques described herein may be used to provide a driver of a vehicle with an accurate assessment of the remaining life of the vehicle battery. An on-board device may collect information from one or more sensors or devices within the vehicle. The information may be processed to generate a data set that accurately describes the current status and operating conditions of the battery. The data set may be used to evaluate the health of the battery and make predictions regarding the future performance of the battery, which may be communicated to the driver of the vehicle. Machine-learning techniques may be implemented to improve upon methodologies to evaluate the health of the battery and make predictions regarding battery performance.

Claims

1. A method performed by one or more computing devices, comprising:

receiving, by the one or more computing devices, information corresponding to internal resistances of a battery of a vehicle;

receiving, by the one or more computing devices, information corresponding to at least one other operating condition, in addition to the internal resistances, corresponding to the vehicle;

receiving, by the one or more computing devices, information corresponding to an identity of a driver of the vehicle, the information originating from a mobile user device associated with the driver;

determining, by the one or more computing devices and based on the identity, driving habits that are based on historic driving data associated with the driver;

receiving, by the one or more computing devices, a machine learning model that was trained, over time, based on internal resistances of a plurality of vehicles, other operating conditions of the plurality of vehicles, and driving habits of a plurality of drivers associated with the plurality of vehicles;

evaluating, by the one or more computing devices, the machine learning model based on the internal resistances of the battery of the vehicle, the at least one other operating condition, and the driving habits of the driver to produce a prediction regarding the remaining battery life;

presenting, by the one or more computing devices and via a display device associated with the vehicle, the prediction regarding the remaining battery life; and

refining, by the one or more computing devices, the machine learning model based on the internal resistances of the battery of the vehicle, the operating condition corresponding to the vehicle, and the driving habits of the driver of the vehicle, wherein the refined machine learning model is subsequently used in a prediction of remaining battery life of a battery of another vehicle.

2. The method of claim 1, wherein the other operating condition includes at least one of:

a humidity measurement,

a temperature measurement,

a range of humidity levels over a period of time,

a range of temperatures over a period of time,

voltage readings with the vehicle off versus on,

a coolant temperature minimum,

a coolant temperature maximum,

a coolant temperature average,

a barometric pressure surrounding the battery.

3. The method of claim 1, wherein the one or more computing devices include a telematics device installed in the vehicle.

4. The method of claim 1, wherein the internal resistances of the battery are derived from an ohmic testing device electrically coupled to the battery.

5. The method of claim 1, wherein evaluating the prediction regarding the remaining battery life comprises:

accessing historical operating conditions of the battery; and

predicting the remaining battery life of the battery based on the internal resistances of the battery, the at least one other operating condition, the driving habits of the driver, and the historical operating conditions of the battery.

6. The method of claim 1, further comprising:

receiving feedback regarding the accuracy of the prediction;

further refining the machine learning model based on the feedback.

7. The method of claim 1, further comprising:

determining, based on another model, at least one other prediction regarding a future performance of the battery;

providing, to a server device, feedback regarding the accuracy of the at least one other prediction; and

receiving an updated version of the other model in response to providing the feedback to the server device.

8. One or more computing devices comprising:

a non-transitory memory device storing a plurality of processor-executable instructions; and

a processor configured to execute the processor-executable instructions, wherein executing the processor-executable instructions causes the processor to;

receive information corresponding to internal resistances of a battery of a vehicle;

receive information corresponding to at least one other operating condition, in addition to the internal resistances, corresponding to the vehicle;

receive information corresponding to an identity of a driver of the vehicle, the information originating from a mobile user device associated with the driver;

determine driving habits that are based on historic driving data associated with the driver;

receive a machine learning model that was trained, over time, on internal resistances of a plurality of vehicles, other operating conditions of the plurality of vehicles, and driving habits of a plurality of drivers associated with the plurality of vehicles;

evaluate the model based on the internal resistances of the battery of the vehicle and the at least one other operating condition, and the driving habits of the driver to produce a prediction regarding the remaining battery life;

communicate the prediction, regarding the remaining battery life, to a component of the vehicle; and

refine the machine learning model based on the internal resistances of the battery of the vehicle, the operating condition corresponding to the vehicle, and the driving habits of the driver of the vehicle, wherein the refined machine learning model is subsequently used in a prediction of remaining battery life of a battery of another vehicle.

9. The one or more devices of claim 8, wherein the other operating condition includes at least one of:

measurements of the internal resistance measurements that are made when the engine of the vehicle is off;

measurements of the internal resistance measurements that are made when the engine of the vehicle is idle, and

measurements of the internal resistance measurements that are made when the engine of the vehicle is moving.

10. The one or more devices of claim 8, wherein the one or more computing devices include a telematics device installed in the vehicle.

11. The one or more devices of claim 8, wherein the internal resistances of the battery are derived from an ohmic testing device that is built into the battery.

12. The one or more devices of claim 8, wherein, to evaluate the prediction regarding the remaining battery life, the circuitry is to:

access historical operating conditions of the battery; and

predict the remaining battery life of the battery based on the internal resistances of the battery, the at least one other operating condition, and the historical operating conditions of the battery.

13. The one or more devices of claim 8, wherein the circuitry is further to:

receive feedback regarding the accuracy of the prediction;

further refine the machine learning model based on the feedback.

14. The one or more devices of claim 8, wherein the circuitry is further to:

determine, based on another model, at least one other prediction regarding a future performance of the battery;

provide, to a server device, feedback regarding the accuracy of the at least one other prediction; and

receive an updated version of the other model in response to providing the feedback to the server device.

15. One or more computing devices, comprising:

a non-transitory memory device storing a plurality of processor-executable instructions; and

a processor configured to execute the processor-executable instructions, wherein executing the processor-executable instructions causes the processor to;

receive measurements of internal resistances of batteries installed at a plurality of vehicles;

receive measurements of other operating conditions, in addition to the internal resistances, relating to the plurality of vehicles;

receive information corresponding to identities of a plurality of drivers for the plurality of vehicles, vehicle the information originating from mobile user devices of the drivers;

determining driving habits based on historic driving data associated with the drivers;

train models over time, using machine learning techniques and based on the measurements of the internal resistances of batteries installed at the plurality of vehicles, the measurements of the other operating conditions, and the driving habits of the plurality of drivers, to predict battery failure in the plurality of vehicles,

wherein training the models over time includes modifying the models over time based on;

the measurements of internal resistances of batteries installed at a plurality of vehicle,

the other operating conditions relating to the plurality of vehicles, and

the driving habits of the plurality of drivers; and

transmit at least one trained model, of the trained models, to the plurality of vehicles, for prediction of battery failure at the plurality of vehicles.

16. The one or more computing device of claim 15, wherein the information defining one or more of the other operating conditions includes at least one of:

a make and a model of the battery,

a battery type,

cold cranking amps (CCAs) corresponding to the battery,

conductance measurements paired with other battery or automotive data,

a total number of trips associated with the battery,

a humidity measurement,

a temperature measurement,

a range of humidity levels over a period of time,

a range of temperatures over a period of time,

voltage readings with the vehicle off versus on,

a total number of vehicle starts corresponding to the battery,

needed amperage for the make and the model of the battery,

cold resets corresponding to the battery,

a minimum trip mileage,

a maximum trip mileage,

an average trip mileage,

a float voltage minimum,

a float voltage maximum,

a float voltage average,

a coolant temperature minimum,

a coolant temperature maximum,

a coolant temperature average,

a ride time corresponding to one or more trips,

a geographical location of the vehicle,

an engine load of the vehicle,

revolutions per minute corresponding to the vehicle,

a speed of the vehicle,

a temperature of the vehicle at a start of the trip,

variation of voltage over time,

a driving style associated with the vehicle or the driver of the vehicle,

differences between periodic voltage readings,

differences between periodic conductance readings or statistical derivations of measurement corresponding to a sensor of device of the vehicle,

a barometric pressure surrounding the battery,

an acceleration of the vehicle,

a duration between an installation date of the battery and a current date,

a manufacture date of the battery,

measurements of the internal resistance measurements that are made when the engine of the vehicle is off,

measurements of the internal resistance measurements that are made when the engine of the vehicle is idle,

measurements of the internal resistance measurements that are made when the engine of the vehicle is moving,

records of service corresponding to the battery, or

records of services corresponding to the vehicle.

17. The one or more computing device of claim 15, wherein:

the one or more computing devices comprises at least one server device, and

the information corresponding to the internal resistances of the batteries and the one or more other operating conditions are received, by the at least one server device and via a wireless telecommunications network, from the plurality of vehicles.

18. The one or more computing device of claim 15, wherein the internal resistances of the batteries are derived from ohmic testing devices electrically coupled to the batteries.

19. The one or more computing device of claim 18, wherein:

the information corresponding to the internal resistances of the batteries and the one or more other operating conditions are received, via a wireless telecommunications network, from telematics device installed in the plurality of vehicles.

20. The one or more computing device of claim 15, wherein executing the processor-executable instructions causes the processor to:

receive feedback regarding a particular prediction of battery failure of a particular vehicle;

determine a level of accuracy regarding the particular prediction based on the feedback;

further update the trained model used to predict the battery failure based on the level of accuracy regarding the prediction; and

transmit the updated trained model, to the plurality of vehicles, for prediction of battery failures at the plurality of vehicles.