Ground-Engaging Tool Wear Detection Using Adaptive LiDAR Scanning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing wear detection systems for ground engaging tools (GET) in work machines suffer from low resolution and non-adaptive scanning, leading to inaccurate measurement of wear and potential damage to downstream equipment due to undetected wear or loss of GET.

Innovation Solution

A system utilizing adaptive scanning LiDAR sensors and stereoscopic cameras to capture high-resolution imaging data, allowing for precise detection of GET wear by identifying regions of interest and generating three-dimensional point clouds for accurate wear analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If LiDAR sensor maintains a fixed field of view for scanning, then the system structure is simple, but the measurement precision of GET wear is insufficient

Engineering Contradiction:
ImproveGET wear measurement precisionVSAvoidLiDAR scanning system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements adaptive scanning technology that dynamically adjusts the LiDAR sensor's field of view and resolution based on detected regions of interest. The system transitions from static fixed-field scanning to dynamic adaptive scanning, where the field of view and resolution are adjusted in real-time to focus on GET components, thereby achieving millimeter-level measurement precision without requiring a completely complex reconfiguration of the entire scanning system.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system applies different scanning resolutions to different regions: high-resolution scanning is concentrated on identified GET regions while lower resolution is used for surrounding areas. This local quality approach allows the system to achieve high measurement precision for wear detection where needed, while maintaining overall system efficiency and avoiding uniform high-resolution scanning across the entire field of view.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If LiDAR sensor uses high resolution scanning, then the measurement precision improves, but the scanning time increases

Engineering Contradiction:
ImproveGET wear measurement precisionVSAvoidScanning time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the scanning process into two distinct phases: a preliminary low-resolution scan to identify regions of interest containing GET, followed by a targeted high-resolution scan only of those specific regions. This segmentation allows the system to achieve high measurement precision for wear detection while minimizing the total scanning time by avoiding unnecessary high-resolution scanning of entire areas.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs partial high-resolution scanning only on identified GET regions rather than the entire field of view. This partial action approach applies high-resolution scanning exactly where needed for wear measurement, achieving the required measurement precision while significantly reducing the time loss compared to comprehensive high-resolution scanning of all areas.

Inventive Principle:
Principle #16Partial or excessive action

3Measurement precision

If LiDAR sensor uses adaptive scanning with variable field of view, then the measurement precision improves, but the device complexity increases

Engineering Contradiction:
ImproveGET wear measurement precisionVSAvoidAdaptive scanning control complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces image processing algorithms and region-of-interest detection mechanisms as intermediaries between the LiDAR sensor and the adaptive scanning control. These intermediaries analyze preliminary scan data to identify GET locations, then guide the adaptive scanning process. This intermediary layer manages the complexity of variable field-of-view control by providing automated region detection and scanning parameter adjustment, reducing the need for complex manual control systems.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements feedback loops where preliminary scan results inform subsequent high-resolution scanning parameters. The region-of-interest detection provides feedback about GET locations, which then adjusts the LiDAR field of view and resolution for the next scanning phase. This feedback mechanism manages adaptive scanning complexity by using data-driven parameter adjustment rather than requiring complex pre-programmed control logic.

Inventive Principle:
Principle #23Feedback

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables precise measurement of GET wear at a millimeter level, providing timely alerts for replacement, thereby preventing damage to downstream processing equipment and optimizing machine operation.

Implementation Method 1

controlling an adaptive scanning LiDAR sensor to capture a second set of imaging data of the region of interest

Methodology Applied
Scientific EffectLiDAR: LIDAR

Data Source

PatentEP4347956B1Ground engaging tool wear and loss detection system and method
Publication Date: 2025.07.16 CATERPILLAR INC
  • EP4347956B1 patent drawingFigure 1
  • EP4347956B1 patent drawingFigure 2
  • EP4347956B1 patent drawingFigure 3

AI summary

An example wear detection system (110) receives first imaging data from one or more sensors (126, 128) associated with a work machine (100). The first imaging data comprises data related to at least one ground engaging tool (GET) (125) of the work machine. The example system identifies a region of interest including data of the at least one GET within the first imaging data. Based on the identified region of interest, the example system controls a LiDAR sensor (126) to capture second imaging data capturing the at least one GET that is of higher resolution than the first imaging data. The example system generates a three-dimensional point cloud of the at least one GET based on the second imaging data and determines a wear level or loss for the at least one GET based on the three-dimensional point cloud.