Predictive Crop Constituent Mapping for Harvester Cut Height Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current forage harvesters lack precision in controlling the cutting height of crops to achieve desired constituent concentrations and tonnage, leading to potential nutritional inadequacies and increased operational costs due to the need for supplemental nutrition.
Innovation Solution
A system that utilizes sensors to detect crop constituents and tonnage values, generates predictive maps of crop constituent distributions, and adjusts the harvester's header position based on these values to optimize cutting height and yield.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If the header cutting height is not precisely controlled, then the harvesting process is simple and fast, but the constituent concentrations and tonnage cannot be optimized, leading to nutritional inadequacies
Solution Approach 1:
The system generates predictive maps of crop constituent distributions and tonnage values before harvesting, allowing the header cutting height to be optimized in advance based on predicted crop characteristics at different locations. This preliminary mapping enables precise cutting height control without adding complex real-time adjustment mechanisms during harvesting.
Solution Approach 2:
The patent replaces mechanical methods of determining cutting height with sensor-based detection and predictive modeling. Sensors detect crop constituents and tonnage, and a predictive model algorithmically determines optimal cutting heights, substituting mechanical trial-and-error with intelligent computational control.
2Reliability
If the header cutting height is precisely controlled to optimize constituent concentrations, then nutritional quality improves, but the harvesting process becomes more complex and time-consuming
Solution Approach 1:
Predictive maps are generated before harvesting to pre-determine optimal cutting heights for different field locations. This allows the harvester to maintain precise cutting heights without real-time adjustments, ensuring consistent nutritional quality while maintaining harvesting speed.
Solution Approach 2:
The system uses onboard sensors to detect crop constituents and tonnage, and the predictive model automatically determines optimal cutting heights without requiring external intervention or complex manual adjustments. The system serves itself by using its own sensor data to control the harvesting process.
3Manufacturing precision
If sensors and predictive mapping are used to optimize cutting height, then constituent concentrations and tonnage are precisely controlled, but the system complexity and cost increase
Solution Approach 1:
The predictive mapping system serves multiple functions: it maps crop constituent distributions, predicts tonnage values, determines optimal cutting heights, and guides the harvesting process. This multi-functionality reduces the need for separate systems for each task, thereby limiting the increase in overall system complexity.
Solution Approach 2:
The predictive model acts as an intermediary between sensor data and harvesting control. Sensors detect crop characteristics, the predictive model processes this data to determine optimal cutting heights, and the header position is adjusted accordingly. This intermediary layer simplifies the control architecture by centralizing the decision-making process.
4Productivity
If traditional harvesting without predictive mapping is used, then the system is simpler and faster, but supplemental nutrition is required increasing operational costs
Solution Approach 1:
The system performs preliminary predictive mapping to identify areas with sufficient constituent concentrations and tonnage. This allows the harvester to focus on optimizing cutting heights in areas that meet nutritional targets, maintaining harvesting efficiency while preventing nutritional deficiencies through targeted precision control.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A map is obtained by an agricultural system. The map includes values of one or more characteristics at different geographic locations in a worksite. In-situ sensor data indicative of values of one or more crop constituents at cut heights is obtained as the mobile machine operates at the worksite. A predictive model generator generates a predictive model that models a relationship between values of the one or more crop constituents at cut heights and the values of the one or more characteristics in the map. A predictive map generator generates a predictive map that predicts values of the one or more crop constituents at two or more cut heights at different geographic locations in the worksite based on the predictive model. The predictive map can be output and used in automated machine control.