Harvester Imaging System for Kernel Loss Detection and Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Harvesting processes face challenges in minimizing kernel loss due to impact with harvester components, leading to reduced yield and inefficiencies.
Innovation Solution
An imaging system with machine learning capabilities is integrated into the harvester to analyze images of harvested crop material, detecting kernel loss and adjusting harvester components such as deck plate gaps and stalk roller speeds to minimize product loss.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If harvester components (deck plates, stalk rollers) operate at high speed to increase productivity, then harvesting efficiency improves, but kernel loss increases due to impact with crop material
Solution Approach 1:
The system uses imaging devices to continuously monitor kernel loss and feeds this information back to the control system, which automatically adjusts deck plate gaps and stalk roller speeds in real-time to minimize further kernel loss while maintaining harvesting efficiency
Solution Approach 2:
The system dynamically adjusts harvester component parameters (deck plate gaps, stalk roller speeds) based on real-time imaging data, transitioning from static fixed settings to adaptive dynamic control that responds to actual kernel loss conditions
2Productivity
If manual monitoring of kernel loss is used, then system complexity remains low, but productivity decreases due to time-consuming manual inspection and adjustment
Solution Approach 1:
The system replaces manual visual inspection and mechanical adjustment processes with an automated imaging system that uses cameras, processors, and control algorithms to detect and respond to kernel loss conditions
Solution Approach 2:
The harvester system performs self-diagnosis and self-adjustment by automatically analyzing its own performance through imaging devices and modifying its operation without external manual intervention, enabling continuous autonomous optimization
3Adaptability or versatility
If fixed harvester settings are used throughout the field, then device complexity is minimized, but adaptability to varying crop conditions deteriorates
Solution Approach 1:
The system transitions from static fixed settings to dynamic adaptive control that continuously adjusts deck plate gaps and stalk roller speeds based on real-time imaging data reflecting actual crop conditions and kernel loss rates
Solution Approach 2:
The system automatically modifies operational parameters (gap dimensions, roller speeds) based on detected kernel loss patterns, enabling the harvester to adapt to varying crop types, densities, and conditions without manual reconfiguration
Data Source
AI summary
A detection and control system for an agricultural harvester includes a controller with at least one memory and at least one processor. The controller is configured to receive a sensor signal indicative of an image of harvested crop material within a feederhouse of the agricultural harvester; analyze the image to detect at least one ear of corn with kernel loss; analyze the image to identify one or more parameters of the at least one ear of corn with kernel loss; and determine an appropriate adjustment to one or more components of row units based on the one or more parameters of the at least one ear of corn with kernel loss.