APPARATUS AND METHOD FOR MONITORING ABNORMAL STATE OF VEHICLE USING CLUSTERING TECHNIQUE

• US 20130297141A1
• Filed: 04/30/2013
• Published: 11/07/2013
• Est. Priority Date: 05/04/2012
• Status: Active Grant

• Current Assignee: Chungbuk National University Industry Academic Cooperation Foundation (Chungbuk National University), Electronics and Telecommunications Research Institute
• Original Assignee: Chungbuk National University Industry Academic Cooperation Foundation (Chungbuk National University), Electronics and Telecommunications Research Institute
• Inventors: LEE, Shin-Kyung, LEE, Jeong-Woo, YUN, Un-Il, KWON, Oh-Cheon, PYUN, Gwang-Bum, RYANG, Heung-Mo, LEE, Gang-In
• Granted Patent: US 9,075,701 B2
• Time in Patent Office: Days
• US Class Current: 701/29.1
• CPC Class Codes: B60W 50/0205 Diagnosing or detecting failures; Failure detection models
• CPC Class Codes: G06F 17/00 Digital computing or data processing equipment or methods, specially adapted for specific functions information retrieval, database structures or file system structures therefor G06F16/00
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 18/23213 with fixed number of clusters, e.g. K-means clustering
• CPC Class Codes: G06F 18/24137 Distances to cluster centroïds

Abstract

The present invention relates to an apparatus and method for monitoring abnormal state of a vehicle. In the method, CAN data collected from an ECU mounted on the vehicle is transformed into coordinates. The coordinates are applied to a distribution map in a specific space, a number of clusters is calculated based on results of the application, and an initial center point corresponding to the number of clusters is selected. Clustering is performed based on the initial center point, and then clusters are generated. At least one piece of data is extracted from each of the clusters, and a state feature of a corresponding cluster is decided on using a difference between maximum and minimum values of attributes constituting the at least one piece of data. A current state of the vehicle is monitored based on current CAN data of the vehicle and state features of the clusters.

Claims

1. A method for monitoring an abnormal state of a vehicle using a clustering technique, comprising:

transforming Control Area Network (CAN) data collected from an Electronic Control Unit (ECU) mounted on the vehicle into coordinates in correspondence with a range of clustering coordinates;

applying the coordinates to a distribution map in a specific space, calculating a number of clusters based on results of the application, and selecting an initial center point corresponding to the number of clusters;

performing clustering based on the initial center point, and then generating a plurality of clusters;

extracting at least one piece of data from each of the plurality of clusters, and deciding on a state feature of a corresponding cluster using a difference between maximum and minimum values of attributes constituting the at least one piece of data; and

monitoring a current state of the vehicle based on current CAN data of the vehicle and respective state features of the plurality of clusters.

2. The method of claim 1, wherein the CAN data of the vehicle is data corresponding to a battery voltage, a sensed value of a coolant temperature sensor, a sensed value of an air flow sensor, a throttle position voltage, a voltage of an accelerator pedal sensor, an air conditioner pressure, a sensed value of an oxygen sensor, air fuel ratio learning control, a sensed value of a barometric pressure sensor, and fuel pressure of the vehicle.

3. The method of claim 1, wherein generating the plurality of clusters comprises:

generating an initial cluster by grouping pieces of CAN data located within a preset radius around the initial center point;

calculating a new center point based on pieces of CAN data constituting the initial cluster;

generating clusters by grouping pieces of CAN data located within a preset radius around the new center point; and

calculating a center point of each generated cluster until the center point of the generated cluster is identical to the new center point.

4. The method of claim 3, wherein calculating the center point of each generated cluster until the center point of the generated cluster is identical to the new center point comprises:

if the center point of the generated cluster is identical to the new center point, analyzing distances from the center point of the generated cluster to pieces of CAN data constituting the cluster; and

removing noise data using results of the analysis of the distances, and then converting noise data-removed results into partial clusters.

5. The method of claim 1, wherein deciding on the state feature comprises:

deciding on a representative attribute of the corresponding cluster by determining whether the difference between the maximum and minimum values of the attributes constituting the at least one piece of data falls within a preset threshold range; and

deciding on the state feature of the cluster using the representative attribute of the cluster and information about an abnormal state of the vehicle.

6. The method of claim 1, wherein monitoring the current state of the vehicle comprises:

searching for a cluster having a state feature identical to that of coordinates corresponding to the current CAN data of the vehicle;

determining whether a state feature of a found cluster corresponds to a normal state;

if it is determined that the state feature of the found cluster corresponds to the normal state, terminating a monitoring operation; and

if it is determined that the state feature of the found cluster corresponds to an abnormal state, notifying a vehicle driver of a danger.

7. The method of claim 6, further comprising, if there is no cluster having the state feature identical to that of the coordinates corresponding to the current CAN data of the vehicle at the searching for the cluster having the identical state feature:

searching a specific space, in which the coordinates corresponding to the current CAN data of the vehicle are located, for a normal state cluster and an abnormal state cluster located within a preset radius;

analyzing a state of the vehicle based on a distance from a center point of the normal state cluster to a center point of the abnormal state cluster; and

providing results of the analysis of the vehicle state to the vehicle driver.

8. An apparatus for monitoring an abnormal state of a vehicle using a clustering technique, comprising:

a coordinate transformation unit for transforming Control Area Network (CAN) data collected from an Electronic Control Unit (ECU) mounted on the vehicle into coordinates in correspondence with a range of clustering coordinates;

a clustering unit for applying the coordinates to a distribution map in a specific space, calculating a number of clusters based on results of the application, and generating a plurality of clusters by performing clustering based on an initial center point corresponding to the number of clusters;

a feature decision unit for extracting at least one piece of data from each of the plurality of clusters, and deciding on a state feature of a corresponding cluster using a difference between maximum and minimum values of attributes constituting the at least one piece of data; and

a monitoring unit for monitoring a current state of the vehicle based on current CAN data of the vehicle and respective state features of the plurality of clusters.

9. The apparatus of claim 8, wherein the clustering unit is configured to generate an initial cluster by grouping pieces of CAN data located within a preset radius around the initial center point, calculate a new center point based on pieces of CAN data constituting the initial cluster, and generate clusters by grouping pieces of CAN data located within a preset radius around the new center point.

10. The apparatus of claim 9, wherein the clustering unit calculates a center point of each generated cluster until the center point of the generated cluster is identical to the new center point.

11. The apparatus of claim 8, further comprising an attribute decision unit for extracting at least one piece of data from each of the plurality of clusters, calculating a difference between maximum and minimum values of attributes constituting the at least one piece of data, checking whether the calculated difference falls within a preset threshold range, and deciding on a representative attribute of the cluster based on results of the checking.

12. The apparatus of claim 11, wherein the feature decision unit decides on a state feature of the corresponding cluster using the representative attribute and information about an abnormal state of the vehicle.

13. The apparatus of claim 8, wherein the monitoring unit is configured to search for a cluster having a state feature identical to that of coordinates corresponding to the current CAN data of the vehicle, and determine whether a state feature of a found cluster corresponds to a normal state.

14. The apparatus of claim 13, wherein if it is determined that the state feature of the found cluster corresponds to the normal state, a monitoring operation is terminated, whereas if it is determined that the state feature of the found cluster corresponds to an abnormal state, a vehicle driver is notified of a danger.

15. The apparatus of claim 13, wherein if there is no cluster having the state feature identical to that of the coordinates corresponding to the current CAN data of the vehicle, a specific space in which the coordinates corresponding to the current CAN data of the vehicle are located is searched for a normal state cluster and an abnormal state cluster located within a preset radius, a state of the vehicle is analyzed based on a distance from a center point of the normal state cluster to a center point of the abnormal state cluster, and results of the analysis of the vehicle state are provided to the vehicle driver.