Terrain classification and system health monitoring

Patent metadata

Field	Value
Publication number	US-12505705-B2
Application number	US-202217730486-A
Country	US
Kind code	B2
Filing date	Apr 27, 2022
Priority date	Apr 27, 2021
Publication date	Dec 23, 2025
Grant date	Dec 23, 2025

Abstract

The present disclosure provides a system for terrain classification and vehicle suspension sub-system health status indication. The system includes run-time terrain classification circuitry to determine a first terrain classification, for a vehicle travelling on a terrain segment, based on comparing a trained model to suspension sub-system sensor data and vehicle speed data; model accuracy determination circuitry to determine a second terrain classification, for the vehicle travelling on the terrain segment, based on the suspension sub-system sensor data and vehicle speed data and independent of the trained model; and sub-system health determination circuitry to determine a health indication of the suspension sub-system by comparing a difference between the first and second terrain classifications to at least one health threshold.

First claim

What is claimed is:

1 . A system for terrain classification and vehicle suspension sub-system health status indication, comprising:
run-time terrain classification circuitry to determine a first terrain classification, for a vehicle travelling on a terrain segment, based on comparing a trained model to suspension sub-system sensor data and vehicle speed data; model accuracy determination circuitry to determine a second terrain classification, for the vehicle travelling on the terrain segment, based on the suspension sub-system sensor data and vehicle speed data; wherein the run-time terrain classification circuitry being independent of the model accuracy determination circuitry; and wherein the second terrain classification being independent of the first terrain classification; comparator circuitry to determine an error value based on comparing the first terrain classification to the second terrain classification; wherein the error value represents an accuracy of the first terrain classification; sub-system health determination circuitry to determine a health indication of the suspension sub-system by comparing the error value a first health threshold which indicates the start of critical wear of the suspension sub-system and a second health threshold which indicates impending failure of the suspension sub-system; the sub-system health determination circuitry further configured to determine if the run-time terrain classification circuitry is no longer generating an accurate first terrain classification when the error value is greater than the first health threshold or second health threshold; and maximum velocity determination circuitry to determine a maximum velocity value based on the error value and the two health thresholds.

2 . The system of claim 1 , further comprising terrain classification training circuitry to generate the trained model by mapping the suspension sub-system sensor data and vehicle speed data to labelled training data that includes a plurality of terrain classifications of known terrains and corresponding ranges of suspension sub-system sensor data and vehicle speed data for each terrain classification of known terrains.

3 . The system of claim 1 , wherein the trained model comprises a plurality of terrain classifications mapped to ranges of suspension sub-system sensor data and vehicle speed data.

4 . The system of claim 1 , wherein the suspension sub-system sensor data comprises x, y and z-direction acceleration and x, y and z-direction gyroscopic data of the vehicle.

5 . The system of claim 1 , wherein the run-time terrain classification circuitry comprising multi-nodal neural network circuitry, and wherein a model data set used to generate the trained model, suspension sub-system sensor data and vehicle speed data each being assigned to at least one node of the multi-nodal neural network circuitry.

6 . The system of claim 2 , wherein the terrain classification training circuitry comprising multi-nodal neural network circuitry, and wherein the labelled training data, suspension sub-system sensor data and vehicle speed data each being assigned to at least one node of the multi-nodal neural network circuitry.

7 . A non-transitory storage device that includes machine-readable instructions that, when executed by one or more processors, cause the one or more processors to perform operations, comprising:
determine a first terrain classification, for a vehicle travelling on a terrain segment, based on comparing a trained model to suspension sub-system sensor data and vehicle speed data; determine a second terrain classification, for the vehicle travelling on the terrain segment, based on the suspension sub-system sensor data and vehicle speed data; wherein the second terrain classification being independent of the first terrain classification; determine an error value based on comparing the first terrain classification to the second terrain classification; wherein the error value represents an accuracy of the first terrain classification; determine a health indication of the suspension sub-system by comparing the error value to a first health threshold which indicates the start of critical wear of the suspension sub-system and a second health threshold which indicates impending failure of the suspension sub-system; determine if the run-time terrain classification circuitry is no longer generating an accurate first terrain classification when the error value is greater than the first health threshold or second health threshold; and determine a maximum velocity value based on the error value and the two health thresholds.

8 . The non-transitory storage device of claim 7 , wherein the machine-readable instructions that, when executed by one or more processors, cause the one or more processors to perform operations, further comprising:
generate the trained model by mapping the suspension sub-system sensor data and vehicle speed data to labelled training data that includes a plurality of terrain classifications of known terrains and corresponding ranges of suspension sub-system sensor data and vehicle speed data for each terrain classification of known terrains.

9 . The non-transitory storage device of claim 8 , wherein the trained model comprises a plurality of terrain classifications mapped to ranges of suspension sub-system sensor data and vehicle speed data.

10 . The non-transitory storage device of claim 7 , wherein the suspension sub-system sensor data comprises x, y and z-direction acceleration and x, y and z-direction gyroscopic data of the vehicle.

11 . A method for terrain classification and vehicle suspension sub-system health status indication, comprising:
determining a first terrain classification, for a vehicle travelling on a terrain segment, based on comparing a trained model to suspension sub-system sensor data and vehicle speed data; determining a second terrain classification, for the vehicle travelling on the terrain segment, based on the suspension sub-system sensor data and vehicle speed data; wherein the second terrain classification being independent of the first terrain classification; determining an error value based on comparing the first terrain classification to the second terrain classification; wherein the error value represents an accuracy of the first terrain classification; determining a health indication of the suspension sub-system by comparing the error value a first health threshold which indicates the start of critical wear of the suspension sub-system and a second health threshold which indicates impending failure of the suspension sub-system; determining if the run-time terrain classification circuitry is no longer generating an accurate first terrain classification when the error value is greater than the first health threshold or second health threshold; and determining a maximum velocity value based on the error value and the at least two health thresholds.

12 . The method of claim 11 , further comprising:
generating the trained model by mapping the suspension sub-system sensor data and vehicle speed data to labelled training data that includes a plurality of terrain classifications of known terrains and corresponding ranges of suspension sub-system sensor data and vehicle speed data for each terrain classification of known terrains.

13 . The method of claim 12 , wherein the trained model comprises a plurality of terrain classifications mapped to ranges of suspension sub-system sensor data and vehicle speed data.

14 . The method of claim 11 , wherein the suspension sub-system sensor data comprises x, y and z-direction acceleration data of th

Assignees

• Battelle Memorial Institute

Inventors

• Kresge Keith F
• Ward Robert D
• Coyle Jonathan

Classifications

• G05D1/86

  Monitoring the performance of the system, e.g. alarm or diagnosis modules · CPC title

• B60Y2306/15

  Failure diagnostics · CPC title

• B60G2400/82

  Ground surface · CPC title

• G07C5/008

  communicating information to a remotely located station (transmission systems for measured values G08C) · CPC title

• B60W50/04

  Monitoring the functioning of the control system · CPC title