Bucket GET Wear Detection Using Video Pixel Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wear detection systems for ground engaging tools (GET) in work machines are computationally expensive and prone to false positives due to reliance on neural networks and machine learning, leading to ineffective detection of tool wear and loss.
Innovation Solution
A system and method using computer vision techniques to analyze video streams from a camera mounted on a work machine, identifying ground engaging tools through pixel counting and mapping over time, reducing false positives and computational requirements by determining wear levels based on pixel count changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of moving object
If ground engaging tools are allowed to wear down to a minimum size before replacement, then tool life and productivity are improved, but the risk of tool loss increases and can cause harmful effects to the harvesting mechanism
Solution Approach 1:
The system performs preliminary detection of tool wear and loss conditions before critical failures occur. Sensors continuously monitor tool parameters and predict when tools will reach minimum acceptable size or become detached, allowing proactive replacement before actual tool loss or mechanism damage happens.
Solution Approach 2:
The system implements continuous feedback through sensors that monitor tool wear indicators, vibration patterns, and operational parameters. This feedback loop provides real-time information about tool condition, enabling dynamic adjustment of harvesting operations and timely tool replacement to prevent both premature replacement and tool loss.
2Reliability
If tools are monitored continuously for wear and loss, then reliability and safety are improved, but device complexity increases
Solution Approach 1:
The monitoring system is designed to perform multiple functions using integrated sensor arrays that detect tool wear, tool loss, vibration patterns, and operational parameters simultaneously. This multi-functional approach consolidates what could be multiple separate systems into a unified monitoring platform, reducing overall complexity.
Solution Approach 2:
The system employs self-diagnostic capabilities where sensors and processors automatically detect anomalies, diagnose tool conditions, and trigger alerts without requiring external intervention. The harvesting mechanism itself generates the data needed for monitoring through its operational sensors, reducing the need for separate dedicated monitoring hardware.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A wear detection system (110) can be configured to receive a video stream including a plurality of images (520) of a bucket (120) of the work machine (100) from a camera (128) associated with the work machine. The bucket has one or more ground engaging tools (GET) (125). The wear detection system can also be configured to identify a plurality of tool images (620) from the video stream over a period of time. The plurality of tool images depict the GET at a plurality of instances over a period of time. The wear detection system can also be configured to determine a plurality of tool pixel counts (635) from the plurality of tool image and determine a wear level for the GET based on the plurality of tool pixel counts.