Blade Wear Monitoring Using Plant-Cut Image Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Harvesters face challenges in monitoring the wear of cutter blades, leading to decreased cutting performance and the need for frequent maintenance, which disrupts operations.
Innovation Solution
A computer-readable medium and device using a trained machine learning model to analyze images of plant cuts and determine the wear level of blades, generating alerts when the wear exceeds a threshold, allowing for continuous monitoring without halting operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional manual inspection methods are used to monitor blade wear, then operators can detect wear levels, but the harvester must halt operations for inspection and maintenance
Solution Approach 1:
The patent replaces manual mechanical inspection with an automated vision-based monitoring system using cameras and machine learning algorithms. The system captures images of cut plant material and automatically analyzes blade wear characteristics, eliminating the need for operators to halt the harvester for manual inspection while maintaining accurate wear detection
Solution Approach 2:
The system enables the harvester to self-monitor its blade condition through automated image capture and analysis. The machine learning model continuously processes visual data from the cutting area, allowing the system to autonomously detect wear levels and generate maintenance alerts without human intervention, thus maintaining continuous operation
2Manufacturing precision
If frequent manual inspection is performed to ensure cutting quality, then blade wear can be detected early, but operational downtime increases
Solution Approach 1:
The vision-based monitoring system operates continuously throughout harvester operation, capturing and analyzing images of cut plant material in real-time. This continuous monitoring enables early detection of blade wear trends without interrupting the cutting process, allowing maintenance to be scheduled at optimal intervals rather than through frequent halts for inspection
3Loss of information
If operators manually monitor blade wear, then wear levels can be assessed, but the complexity of the monitoring system increases due to human involvement
Solution Approach 1:
The system creates visual copies (images) of the cutting process and cut plant material, which are then analyzed by machine learning algorithms to determine blade wear levels. This digital copying and analysis approach replaces complex human judgment processes with automated image processing, simplifying the overall monitoring system while maintaining comprehensive wear information capture
Data Source
AI summary
Provided is a non-transitory computer readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to obtain a first signal based on an input image using a trained machine learning model, the input image being an image of a plant cut by a blade, and the first signal indicating a wear level of the blade, determine whether a level of the first signal is greater than or equal to a threshold, generate a second signal in response to determining the level of the first signal is greater than or equal to the threshold, and output the second signal.