Predictive Harvest Logistics for Crop Mixing and Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current agricultural harvesting systems struggle with efficiently managing crop material based on varying crop characteristics, leading to increased costs and reduced efficiency due to improper mixing or separation of crop materials that do not meet quality or moisture thresholds.
Innovation Solution
Agricultural harvesting systems utilize predictive models generated from in-situ data and prior or predicted data maps to control mobile machines, such as harvesters and receiving vehicles, optimizing path planning, material transfer, and delivery locations based on crop characteristics like moisture, quality, and constituents.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If crop material is mixed based on predictive models and maps, then production efficiency is improved and costs are reduced, but the system complexity increases due to predictive models and logistics modules
Solution Approach 1:
The system performs preliminary actions by generating predictive models and crop characteristic maps before the actual harvesting and mixing operations. The predictive models forecast crop characteristics (moisture, quality, constituents) at different field locations, and the harvesting logistics module pre-plans the mixing strategy based on these predictions, allowing efficient material handling without real-time complexity
Solution Approach 2:
The system uses predictive maps that are essentially copies or representations of the actual field conditions. Instead of directly measuring and analyzing every crop material in real-time, the system works with predictive copies (maps and models) that capture the essential characteristics, reducing the complexity of real-time decision-making while maintaining effective control
2Manufacturing precision
If crop material is separated and handled according to specific characteristics, then material quality is improved, but time consumption increases due to additional sorting and handling operations
Solution Approach 1:
The system applies local quality by treating different portions of crop material differently based on their specific characteristics. The predictive models identify regions with different moisture, quality, or constituent levels, and the harvesting logistics module directs specific handling actions (mixing, separating, drying) to specific material streams, ensuring each portion receives the appropriate treatment without unnecessary processing of all material
Solution Approach 2:
The system changes parameters (moisture content, quality thresholds, constituent levels) as control criteria for material handling. By using these parameter thresholds from predictive models, the system automatically determines when separation or mixing is needed, optimizing the balance between material quality and processing time without manual intervention
Data Source
AI summary
An agricultural harvesting system includes a harvesting logistics module that is configured to receive a map that maps values of a crop characteristic to different geographic locations in a field. The harvesting logistics module further configured to identify a crop characteristic threshold and to identify a mixture of crop material based on the map and based on the crop characteristic threshold. The harvesting logistics module configured to generate a route for a mobile machine, such as a receiving machine or a harvester, based on the identified mixture.