Predictive Crop State Map for Dynamic Harvester Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Agricultural harvesters face performance degradation when operating in areas with varying crop states, such as downed crops, due to the need for adjusted machine settings to prevent grain loss and optimize harvesting efficiency.
Innovation Solution
The generation of a functional predictive crop state map using in-situ sensor data and prior maps like vegetative index, seeding characteristic, predictive yield, or predictive biomass maps, which allows for real-time adjustment of machine settings and harvesting paths to optimize crop engagement and reduce grain loss.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the agricultural harvester operates in areas with downed crops using standard settings, then the harvesting process continues without interruption, but grain loss increases and harvesting efficiency decreases
Solution Approach 1:
The system performs preliminary action by generating a predictive crop state map before harvesting operations begin. This map predicts crop state (standing, downed, partially downed) across the field using satellite imagery and machine learning models, allowing the harvester to proactively adjust settings and paths to areas with downed crops before encountering them, thereby preventing grain loss and maintaining harvesting efficiency
Solution Approach 2:
The system applies dynamics by enabling real-time adjustment of harvester settings and harvesting paths based on the predictive crop state map. The harvester dynamically modifies operational parameters (header height, reel speed, cutter engagement) and navigational path to adapt to varying crop states across different field locations, optimizing performance for both standing and downed crops
2Loss of substance
If the agricultural harvester adjusts machine settings to optimize harvesting in areas with downed crops, then grain loss is reduced, but the complexity of machine control increases
Solution Approach 1:
The system implements feedback by continuously monitoring the actual crop state during harvesting operations and comparing it with the predictive crop state map. The control system uses this feedback to automatically adjust machine settings and path planning in real-time, reducing the need for manual intervention and simplifying operator tasks while maintaining optimized harvesting performance
Solution Approach 2:
The system applies self-service by enabling the harvester to automatically adjust its own settings and navigate through the field based on the predictive crop state map. The automated control system performs setting adjustments and path modifications without requiring constant operator input, allowing the machine to serve itself in adapting to varying crop conditions
3Ease of operation
If the agricultural harvester follows a fixed harvesting path, then the harvesting operation is simple to execute, but grain loss increases in areas with downed crops
Solution Approach 1:
The system transforms the fixed harvesting path into a dynamic, adaptive path by using the predictive crop state map to generate optimized navigation routes. The harvester automatically adjusts its path to account for areas with downed crops, ensuring optimal engagement while maintaining automated control that simplifies operation
Solution Approach 2:
The system performs preliminary path planning by generating an optimized harvesting path before operations begin, based on the predictive crop state map. This pre-planned path accounts for areas with downed crops, allowing the harvester to follow an optimized route that minimizes grain loss while maintaining automated, simple operation
Data Source
AI summary
One or more information maps are obtained by an agricultural work machine. The one or more information maps map one or more agricultural characteristic values at different geographic locations of a field. An in-situ sensor on the agricultural work machine senses an agricultural characteristic as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural characteristic at different locations in the field based on a relationship between the values in the one or more information maps and the agricultural characteristic sensed by the in-situ sensor. The predictive map can be output and used in automated machine control.