Predictive Yield Map for Harvester Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Agricultural harvesters face performance degradation when transitioning between areas of varying yields without appropriate adjustments in operating settings, leading to inefficiencies and reduced performance.
Innovation Solution
The development of a system that generates a predictive yield map by combining historical yield data with real-time sensor inputs, using models to anticipate crop yields and adjust harvester settings accordingly, enabling optimal operation across different yield areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the harvester operates with fixed settings across the field, then the device complexity is reduced and ease of operation is improved, but the productivity decreases when transitioning between areas of varying yield
Solution Approach 1:
The system performs preliminary actions by generating a predictive yield map before harvesting begins. This map combines historical yield data with current vegetative index data to predict where high and low yield areas will be located. The operator can review this map beforehand and pre-adjust harvester settings or plan transitions between control zones, avoiding reactive adjustments during harvesting and maintaining high productivity without requiring complex real-time control systems.
Solution Approach 2:
The field is segmented into different control zones based on the predictive yield map, dividing it into areas of expected high yield, medium yield, and low yield. Each zone can be assigned specific harvester settings and speed parameters. This segmentation allows the operator to manage complexity by working with discrete zones rather than continuous adjustments, improving productivity through systematic zone-by-zone harvesting while keeping the control system manageable.
2Productivity
If the operator manually adjusts settings during harvesting transitions, then the productivity is maintained, but the loss of time occurs during adjustment periods
Solution Approach 1:
The predictive yield map is generated in advance before harvesting operations begin, allowing the operator to identify all transition points between yield zones beforehand. The operator can pre-configure appropriate settings for each zone and plan the harvesting sequence, eliminating the need for time-consuming manual adjustments during actual harvesting transitions and maintaining continuous productivity.
Solution Approach 2:
The system enables dynamic control by allowing the operator to pre-set multiple control zones with different parameters in the predictive yield map. During harvesting, the operator can quickly switch between pre-configured zones using simple zone selection rather than manually adjusting multiple individual settings, significantly reducing adjustment time while maintaining optimal productivity across varying yield conditions.
3Measurement precision
If real-time yield sensing is used to control harvesting, then the manufacturing precision of yield measurement is improved, but the device complexity increases
Solution Approach 1:
The system uses an intermediary approach by combining simple, low-cost vegetative index sensors (such as optical sensors measuring plant density and health) with historical yield data from previous harvesting operations. This combination creates a predictive model that achieves high measurement precision for yield prediction without requiring complex real-time yield sensing hardware. The vegetative index serves as an intermediary indicator that correlates with expected yield, providing accurate predictions through simple, inexpensive sensors.
Data Source
Figure 1
Figure 2
Figure 3A
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.