On board vehicle diagnostic module using pattern recognition

• US 5,809,437 A
• Filed: 06/07/1995
• Issued: 09/15/1998
• Est. Priority Date: 06/07/1995
• Status: Expired due to Fees

• Current Assignee: Automotive Technologies International Incorporated
• Original Assignee: Automotive Technologies International Incorporated
• Inventors: Breed, David S.
• Primary Examiner(s): NGUYEN, TAN QUANG
• Application Number:
  US08/476,077
• Time in Patent Office: 1,196 Days
• Field of Search: 364/424.03, 364/424.04, 364/424.05, 364/431.11, 364/551.01, 364/508, 340/439, 340/459, 340/521, 395/20, 395/21, 395/23, 395/913, 395/905, 73/116, 73/117.3, 701/29, 701/35, 701/40, 701/44, 701/45, 701/34, 701/39, 701/43
• US Class Current: 701/29
• CPC Class Codes: B60N 2/02246 Electric motors therefor
• CPC Class Codes: B60N 2/0276 reaction to emergency situations, e.g. crash
• CPC Class Codes: B60N 2/2863 backward facing
• 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

Abstract

A component diagnostic system for a motor vehicle having at least one component which emits a signal having a pattern containing information as to whether that component is operating normally or abnormally. The system includes at least one sensor which senses the signal and outputs an electrical signal representative thereof and corresponding to the pattern, a processor coupled to the sensor(s) for processing the electrical signal and determining if the pattern is characteristic of abnormal state of operation of the component, and an output device coupled to the processor for affecting a another system within the vehicle if the component is operating abnormally. The processor preferably is a pattern recognition system.

Claims

1. In a motor vehicle having at least one component, said at least one component emitting a signal having a pattern containing information as to whether said at least one component is operating normally or abnormally, a component diagnostic system for diagnosing said at least one component comprising:

a) sensor means for sensing said signal having said pattern containing information as to whether said at least one component is operating normally or abnormally and outputting and electrical signal corresponding to said pattern containing information as to whether said at least one component is operating normally or abnormally;

b) processor means coupled to said sensor means for processing said electrical signal and determining if said pattern is characteristic of abnormal state of operation of said at least one component, said processor means comprising pattern recognition means; and

,

c) output means coupled to said processor means for affecting another system within said vehicle if said at least one component is operating abnormally, said another system comprising a display for indicating the abnormality of said at least one component, said display being arranged in a position in the vehicle to enable a driver of the vehicle to view said display and thus the indicated abnormality of said at least one component.

2. The system in accordance with claim 1, wherein said sensor means comprises a plurality of sensors, each of said sensors being selected from the group consisting of an accelerometer, a temperature transducer, a pressure transducer, a liquid level sensor, a flow meter, a voltage meter, a current meter, a humidity sensor, an engine knock sensor, a fluid turbidity sensor, a torque sensor, a position sensor, a wheel speed sensor, a velocity sensor, an RPM sensor, a chemical sensor, a clock, an odometer and an angle sensor.

3. The system in accordance with claim 2, wherein said sensor is an accelerometer, said accelerometer constituting a part of the vehicle crash sensor system.

4. The system in accordance with claim 1, wherein said sensor means comprises a microphone connected to said vehicle and not directly associated with said at least one component.

5. The system in accordance with claim 1, wherein said pattern recognition means is a neural network.

6. The system in accordance with claim 5, wherein said neural network is an algorithm determined by a neural network computer program.

7. The system in accordance with claim 1, wherein said vehicle further comprises at least one source of additional information and input means coupled to said vehicle for inputting said additional information into said processor means.

8. The system in accordance with claim 7, wherein said additional information is at least one of the current time and date.

9. The system in accordance with claim 1, wherein said another system further comprises transmission means for transmitting information related to the abnormality of said at least one component to a site remote from said vehicle.

10. The system in accordance with claim 9, wherein said remote site is a vehicle repair facility.

11. The system in accordance with claim 1, wherein said sensor means comprise a plurality of sensors, at least one of said sensors being a sensor not directly associated with said at least one component.

12. The system in accordance with claim 1, wherein said sensor means comprises a plurality of sensors coupled to a vehicle data bus, said processor means being coupled to said vehicle data bus.

13. In a motor vehicle having at least one component providing a time varying signal having a temporal pattern, said pattern containing information as to the state of operation of said at least one component, a component diagnostic system for diagnosing said at least one component comprising:

a) sensor means for sensing said time varying signal having the temporal pattern containing information as to the state operation of said least one component and converting said time varying signal having the temporal pattern containing information as to the state of operation of said at least one component into a time varying electrical signal;

b) processor means coupled to said sensor means for processing said time varying electrical signal and for determining if said temporal pattern of said time varying signal is characteristic of normal operation of said at least one component, said processor means comprising pattern recognition means; and

,

c) output means coupled to said processor means for affecting another system within said vehicle if said temporal pattern is not characteristic of normal operation of said at least one component, said another system comprising a display for indicating the abnormal operation of said at least one component, said display being arranged in a position in the vehicle to enable a driver of the vehicle to view said display and thus the indicated abnormal operation of said at least one component.

14. The system in accordance with claim 13 wherein said processor means comprise a pattern recognition algorithm derived from training.

15. The system in accordance with claim 13 wherein said electrical signal is a digital electrical signal;

said processor means processing said digital electrical signal to produce a time series of discrete data values comprising said pattern and determining if said pattern is characteristic of normal operation of said at least one component, said processor means comprising an algorithm which combines said time series data with other information to produce a result indicative of the state of operation of said at least one component.

16. A method for predicting that a component of a vehicle will fail, comprising the steps of:

(a) sensing a signal emitted from said component;

(b) converting said signal into a digital time series;

(c) entering the digital time series data into a pattern recognition algorithm;

(d) executing said pattern recognition algorithm to determine if there exists within said digital time series data a pattern characteristic of abnormal operation of said component; and

(e) notifying a driver of the vehicle if said abnormal pattern is recognized by displaying an indicia of the abnormal operation of said component on a display arranged on the vehicle and viewable to the driver.

17. In a motor vehicle having at least one component, a component diagnostic system for diagnosing said at least one component comprising:

a) sensor means coupled to said vehicle and comprising at least one sensor not directly associated with said at least one component each of said at least one sensor sensing a signal having a pattern containing information as to whether said at least one component is operating abnormally and outputting an electrical signal containing said pattern containing information as to whether said at least one component is operating abnormally;

b) processor means coupled to said at least one sensor for processing said respective signal and for determining if said pattern is characteristic of abnormal state of operation of said at least one component, said processor means comprising a pattern recognition algorithm; and

,

c) output means coupled to said processor means for affecting another system within said vehicle if said at least one component is operating abnormally, said another system comprising a display for indicating the abnormal state of operation of said at least one component, said display being arranged in a position in the vehicle to enable a driver of the vehicle to view said display and thus the indicated abnormal operation of said at least one component.

18. The system of claim 17, wherein said at least one sensor not directly associated with said at least one component comprises at least two different sensors, each of said at least two sensors sensing said signal and outputting an electrical signal corresponding to said pattern, said processor means receiving and processing said electrical signals output by said at least two sensors and based on said electrical signals output by said at least two sensors, determining if said pattern is characteristic of abnormal state of operation of said component.

19. The system of claim 17, wherein said at least one component comprises two unrelated components, each of said components emitting a signal having a pattern containing information as to whether said component is operating abnormally, said at least one sensor comprising a single sensor for sensing both of said signals and outputting electrical signals corresponding to said patterns, said processor means processing both of said electrical signals and determining if said patterns are characteristic of abnormal state of operation of a respective one of said components.

20. The system in accordance with claim 17, wherein said at least one sensor comprises a plurality of sensors not directly associated with said at least one component, all of said sensors being coupled to a vehicle data bus, said processor means being coupled to said vehicle data bus.