Predictive Crop State Maps for Downed Crop Harvest 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 use of a historical crop state model combined with seasonal data to generate a functional predictive crop state map, which is used to control agricultural work machines like harvesters. This map predicts the orientation and magnitude of crop bending, allowing for optimized machine settings and path planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the agricultural harvester operates at standard speed and settings, then productivity is maintained, but grain loss increases and harvesting performance degrades in areas with downed crops
Solution Approach 1:
The system generates a predictive crop state map before harvesting to identify areas with downed crops. This advance information allows the harvester to pre-adjust speed, path direction, and machine settings before entering problematic areas, preventing grain loss while maintaining productivity in unaffected areas
Solution Approach 2:
The system dynamically adjusts harvester operating parameters (speed, path direction, machine settings) based on real-time location and predictive crop state data. This dynamic adaptation allows the harvester to optimize performance for each specific area, maintaining high productivity in good areas while preventing grain loss in areas with downed crops
2Loss of substance
If the agricultural harvester adjusts machine settings and path planning for downed crops, then grain loss is reduced, but productivity decreases due to slower operation
Solution Approach 1:
The system applies different operating strategies to different areas of the field based on the predictive crop state map. Areas with downed crops receive specialized attention with adjusted settings, while areas with standing crops are harvested at standard speed and settings, maintaining overall productivity while preventing grain loss where needed
Solution Approach 2:
By generating the predictive crop state map in advance, the system allows for optimal path planning that minimizes the total distance and time spent in areas requiring reduced speed. The pre identification of problematic areas enables efficient routing that limits productivity impact while still protecting against grain loss
3Reliability
If the agricultural harvester uses a historical crop state model with seasonal data to generate predictive maps, then harvesting performance is optimized, but system complexity increases
Solution Approach 1:
The system uses a multi-functional predictive model that processes multiple data types (historical crop state data, seasonal data, weather data, soil data) through a single integrated framework. This universal approach consolidates what could be multiple separate systems into one cohesive solution, managing complexity while delivering reliable harvesting performance optimization
Solution Approach 2:
The system automatically generates and updates the predictive crop state map using available data without requiring manual intervention. The model self-adjusts based on new seasonal data and historical patterns, reducing the operational complexity for users while maintaining high reliability through continuous optimization
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
Historical and seasonal data is obtained by an agricultural work machine. The historical data provides historical values of agricultural characteristics, which may or may not be geolocated, and the seasonal data provides seasonal values of agricultural characteristics corresponding to a current season. A predictive map generator generates a predictive map that predicts an agricultural characteristic, such as crop state, at different locations in the field based on a relationship between the historical values of agricultural characteristics in the historical data and based on the seasonal values of agricultural characteristics in the seasonal data at those different locations. The predictive map can be output and used in automated machine control.