Enhanced vehicle bad fuel sensor with crowdsourcing analytics

• US 9,996,990 B2
• Filed: 10/24/2016
• Issued: 06/12/2018
• Est. Priority Date: 10/24/2016
• Status: Active Grant

• Current Assignee: Allstate Insurance Company (Allstate Corporation)
• Original Assignee: Allstate Insurance Company (Allstate Corporation)
• Inventors: Slusar, Mark
• Primary Examiner(s): Sweeney, Brian P
• Application Number:
  US15/332,675
• Publication Number:
  US 20180114378A1
• Time in Patent Office: 596 Days
• Field of Search: 701 315
• CPC Class Codes: G01N 33/22 Fuels, explosives liquid hydrocarbons G01N33/28
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction
• CPC Class Codes: G07C 5/0841 Registering performance data recording measured values G01D; information storage G11B

Abstract

A fuel analysis system is described configured to assist vehicle drivers/users in preventing damage to their vehicles caused by bad fuel. Bad fuel can leave a driver and passengers stranded on the road in need of emergency road side service, and in many instances, results in permanent damage to the vehicle. The disclosed fuel analysis system describes an enhanced bad fuel sensor system that measures a delta in vehicle operation data to identify and in many instances, pre-emptively alert, a user of a vehicle of bad fuel. The fuel analysis system may use crowdsourcing through aggregation of refueling event profile records from a plurality of vehicles'"'"' telematics devices to increase the accuracy with which bad fuel is detected.

Claims

1. An enhanced sensor system to detect bad fuel in a user vehicle, the system comprising:

the user vehicle equipped with sensors configured to repeatedly measure a plurality of vehicle operation data indicative of bad fuel, wherein the sensors comprise an odometer, a clock, and a fuel level gauge, and wherein the repeated measuring occurs at least at a pre-refueling time that is before a refueling event and at a post-refueling time that is after the refueling event;

a telematics device coupled to the user vehicle, the telematics device comprising an electronic interface to the sensors of the user vehicle, a wireless communication circuitry, a user interface configured to communicate an alert to a user of the user vehicle, a processor configured to calculate a probability of having received bad fuel at the refueling event, and a computer memory; and

a server machine in wireless, remote communication with the wireless communication circuitry of the telematics device, the server machine comprising;

a vehicle operation database configured to store the plurality of vehicle operation data measured by the sensors, and

a fuel analysis module, which is communicatively coupled to the vehicle operation database, configured to improve an accuracy of the probability of bad fuel calculated by the processor of the telematics device;

wherein the telematics device detects the refueling event upon receiving a substantial increase in a measurement of the fuel level gauge of the user vehicle;

wherein the telematics device receives, through the electronic interface of the telematics device, the vehicle operation data measured by the sensors of the user vehicle at the pre-refueling time and at the post-refueling time;

wherein the computer memory of the telematics device comprises a non-volatile memory configured to store a refueling event profile record after detecting the refueling event, wherein the refueling event profile record comprises;

a last set of the plurality of vehicle operation data repeatedly measured by the sensors of the user vehicle before the refueling event;

the measurement of the fuel level gauge upon completion of the refueling event;

a distance measurement, by the odometer, at the refueling event;

a time measurement, by the clock, at the refueling event; and

a location measurement, by a global positioning satellite (GPS) unit, at the time of the refueling event;

wherein the processor of the telematics device is configured to;

compare the vehicle operation data of the refueling event profile with vehicle operation data at the post-refueling time;

determine that the two sets of vehicle operation data are different such that the probability of having received bad fuel at the refueling event is greater than zero;

calculate a first confidence score for the probability of bad fuel based on a delta in the distance measurements and a delta in the time measurements during the comparing step; and

send, through the wireless communication circuitry, the first confidence score to the server machine;

wherein the fuel analysis module of the server machine is configured to;

receive the first confidence score;

update the first confidence score into a second confidence score based on those confidence scores provided by other vehicles associated with refueling event profile records that store a similar location measurement and similar time measurement as the refueling event profile record of the user vehicle; and

send the second confidence score to the telematics device; and

wherein, upon receipt of the second confidence score at the telematics device, the user interface of the telematics device is configured to communicate the alert to the user of the user vehicle, wherein the alert indicates that the user vehicle was filled with bad fuel at the refueling event.

2. The system of claim 1, wherein the calculating the first confidence score for the probability of bad fuel includes:

decreasing the first confidence score when the last set of vehicle operation data stored in the refueling event profile record indicate negative values;

increasing the first confidence score when the delta in the time measurement is below a threshold time value;

decreasing the first confidence score when the delta in time measurement is above a maximum value and the delta in the distance measurement is below the minimum threshold distance value;

increasing the first confidence score when the delta in the distance measurement is above a minimum threshold distance value;

increasing the first confidence score when the last set of vehicle operation data stored in the refueling event profile record indicates that the fuel level gauge was below a threshold fuel level value and the measurement of the fuel level gauge upon completion of the refueling event indicates at least a twenty five percent increase in fuel level gauge; and

increasing the first confidence score when a delta in particular vehicle operation data indicative of bad fuel negatively increase with repeated measurements by the sensors.

3. The system of claim 1, wherein the second confidence score is higher than the first confidence score when a second vehicle, which refueled at the similar location and at the similar time as the user vehicle, calculated with a high confidence score that the second vehicle received bad fuel at its refueling event.

4. The system of claim 3, wherein the fuel analysis module comprises a plurality of database tables;

wherein a first table of the plurality of database tables comprises all refueling event profile records with the similar location measurement, and a second table of the plurality of tables comprises all refueling event profile records with a location measurement similar to a second location; and

wherein the plurality of database tables are organized such that the fuel analysis module executes the step of updating the first confidence score to the second confidence score with a single search query.

5. The system of claim 1, wherein the plurality of vehicle operation data indicative of bad fuel comprises at least one of measurements from:

an engine revolutions per minute (RPM) sensor, a rate of fuel consumption sensor, an oxygen sensor, and an engine stalling sensor.

6. The system of claim 1, wherein the electronic interface to the sensors of the user vehicle is an on-board diagnostics (OBD) port.

7. The system of claim 1, wherein the user vehicle comprises the GPS unit.

8. The system of claim 7, wherein the telematics device comprises the GPS unit.

9. The system of claim 7, wherein the user vehicle is an electric vehicle comprising an engine at least partially powered by an electric battery, wherein the fuel level gauge is configured to measure electric charge remaining in the electric battery, and wherein the substantial increase in the fuel level gauge amounts to more than a predetermined threshold increase in the electric battery'"'"'s charge.

10. The system of claim 1, further comprising:

a roadside server provider vehicle equipped with electronic circuitry to receive the alert from the server machine identifying the user vehicle as a victim of bad fuel,

wherein the alert comprises information about the vehicle operation data of the user vehicle.

11. The system of claim 1, further comprising:

an insurance server, in remote communication with the server machine, configured to receive the alert indicating bad fuel in the user vehicle,

wherein the insurance server pre-emptively initiates first notice of loss (FNOL) insurance claim processing for a possible claim submitted for the user vehicle with bad fuel.

12. A bad fuel detection system comprising:

a telematics device coupled to a user vehicle, the telematics device comprising an electronic interface to sensors of the user vehicle, a wireless communication circuitry, a user interface configured to communicate an alert to a user of the user vehicle, a processor configured to calculate a probability of having received bad fuel at a refueling event, and a computer memory; and

a server machine in wireless, remote communication with the wireless communication circuitry of the telematics device, the server machine comprising;

a vehicle operation database configured to store a plurality of vehicle operation data indicative of bad fuel measured by the sensors, and

a fuel analysis module, which is communicatively coupled to the vehicle operation database, configured to improve an accuracy of the probability of bad fuel calculated by the processor of the telematics device;

wherein the processor of the telematics device is programmed to perform steps comprising;

detecting a refueling event upon receiving a substantial increase in a measurement of a fuel level gauge sensor of the user vehicle;

receiving, through the electronic interface of the telematics device, the vehicle operation data measured by the sensors of the user vehicle at a pre-refueling time that is before the refueling event and at a post-refueling time that is after the refueling event;

after detecting the refueling event, storing, in the computer memory of the telematics device, a refueling event profile record comprising;

a last set of the vehicle operation data measured by the sensors before the refueling event;

a measurement of the fuel level gauge upon completion of the refueling event;

a distance measurement, by an odometer sensor of the user vehicle, at the refueling event;

a time measurement, by a clock of the user vehicle, at the refueling event; and

a location measurement, by a global positioning satellite (GPS) unit, at the time of the refueling event;

comparing the vehicle operation data of the refueling event profile with vehicle operation data measured at the post-refueling time;

determining that the two sets of vehicle operation data are different such that the probability of having received bad fuel at the refueling event is greater than zero;

calculating a first confidence score for the probability of bad fuel based on a delta in the distance measurements and a delta in the time measurements during the comparing step;

sending, through the wireless communication circuitry, the first confidence score to the server machine; and

upon receipt of an updated first confidence score at the telematics device, causing the user interface of the telematics device to communicate an alert to the user of the user vehicle, wherein the alert indicates that the user vehicle was filled with bad fuel at the refueling event.

13. The system of claim 12, wherein the fuel analysis module is programmed to perform steps comprising:

receiving the first confidence score;

updating the first confidence score based on those confidence scores provided by other vehicles associated with refueling event profile records that store a similar location measurement and similar time measurement as the refueling event profile record of the user vehicle; and

sending the updated first confidence score to the telematics device.

14. The system of claim 12, wherein the calculating the first confidence score for the probability of bad fuel includes at least one of:

increasing the first confidence score when the delta in the time measurement is below a threshold time value;

decreasing the first confidence score when the delta in time measurement is above a maximum value and the delta in the distance measurement is below the minimum threshold distance value; and

increasing the first confidence score when the delta in the distance measurement is above a minimum threshold distance value.

15. The system of claim 12, wherein the calculating the first confidence score for the probability of bad fuel includes at least one of:

decreasing the first confidence score when the last set of vehicle operation data stored in the refueling event profile record indicate negative values;

increasing the first confidence score when the last set of vehicle operation data stored in the refueling event profile record indicates that the fuel level gauge was below a threshold fuel level value and the measurement of the fuel level gauge upon completion of the refueling event indicates at least a twenty five percent increase in fuel level gauge; and

increasing the first confidence score when a delta in particular vehicle operation data indicative of bad fuel negatively increase with repeated measurements by the sensors.

16. The system of claim 12, wherein the plurality of vehicle operation data indicative of bad fuel comprises at least one of measurements from:

an engine revolutions per minute (RPM) sensor, a rate of fuel consumption sensor, an oxygen sensor, and an engine stalling sensor, and wherein the telematics device comprises the GPS unit.

17. A method comprising:

detecting, by a processor of a telematics device coupled to a user vehicle, a refueling event upon receiving a substantial increase in a measurement of a fuel level gauge sensor of the user vehicle;

receiving, through an electronic interface of the telematics device, vehicle operation data measured by sensors of the user vehicle at a pre-refueling time that is before the refueling event and at a post-refueling time that is after the refueling event;

after detecting the refueling event, storing, in a computer memory of the telematics device, a refueling event profile record comprising;

a last set of the vehicle operation data measured by the sensors before the refueling event;

a measurement of the fuel level gauge sensor upon completion of the refueling event;

a distance measurement, by an odometer sensor of the user vehicle, at the refueling event;

a time measurement, by a clock of the user vehicle, at the refueling event; and

a location measurement, by a global positioning satellite (GPS) unit, at the time of the refueling event;

comparing, by the processor, the vehicle operation data of the refueling event profile record with vehicle operation data measured at the post-refueling time;

determining, by the processor, that the two sets of vehicle operation data are different such that a probability of having received bad fuel at the refueling event is greater than zero;

calculating a confidence score for the probability of bad fuel based on a delta in the distance measurements and a delta in the time measurements during the comparing step;

sending, through a wireless communication circuitry of the telematics device, the confidence score to a server machine remotely located to the user vehicle; and

upon receipt of an updated confidence score at the telematics device, causing a user interface of the telematics device to communicate an alert to a user of the user vehicle, wherein the alert indicates that the user vehicle was filled with bad fuel at the refueling event.

18. The method of claim 17, wherein the calculating the confidence score for the probability of bad fuel includes at least one of:

decreasing the confidence score when the last set of vehicle operation data stored in the refueling event profile record indicate negative values;

increasing the confidence score when the delta in the time measurement is below a threshold time value;

decreasing the confidence score when the delta in time measurement is above a maximum value and the delta in the distance measurement is below the minimum threshold distance value;

increasing the confidence score when the delta in the distance measurement is above a minimum threshold distance value;

increasing the confidence score when the last set of vehicle operation data stored in the refueling event profile record indicates that the fuel level gauge was below a threshold fuel level value and the measurement of the fuel level gauge upon completion of the refueling event indicates at least above a minimum threshold increase in fuel level gauge; and

increasing the confidence score when a delta in particular vehicle operation data indicative of bad fuel negatively increase with repeated measurements by the sensors.

19. The method of claim 17, wherein the server machine comprises a fuel analysis module that is programmed to perform steps comprising:

receiving the confidence score;

updating the confidence score based on those confidence scores provided by other vehicles associated with refueling event profile records that store a similar location measurement and similar time measurement as the refueling event profile record of the user vehicle; and

sending the updated confidence score to the telematics device.

20. The method of claim 17, wherein the vehicle operation data indicative of bad fuel comprises at least one of measurements from:

an engine revolutions per minute (RPM) sensor, a rate of fuel consumption sensor, an oxygen sensor, and an engine stalling sensor.