Geo-Spatial Harvester Control for Predicted Grain Tank Fill Points

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current combine harvesters face inefficiencies due to difficulty in predicting when the clean grain tank will be full and where, leading to idle time waiting for haulage units, especially when haulage units are not deployed optimally.

Innovation Solution

An agricultural harvesting machine system that uses georeferenced yield estimation with error mapping to generate a probability distribution of fill capacity along the harvester's path, allowing for controlled subsystems to optimize path and speed to rendezvous with haulage units efficiently.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If the harvester operates without predictive capacity modeling, then the system is simpler to operate, but idle time increases due to unpredictable unloading needs

Engineering Contradiction:
Improveidle timeVSAvoidsystem complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The system performs preliminary calculations of the georeferenced probability distribution to predict where the harvester will reach capacity before actually reaching that point. This allows proactive planning of unloading operations, reducing idle time by ensuring haulage units are positioned appropriately in advance.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The field is divided into multiple georeferenced segments along the harvester path, with capacity probability calculated for each segment. This segmentation allows the system to provide detailed, location-specific predictions rather than a single aggregate prediction, improving the precision of unloading planning.

Inventive Principle:
Principle #1Segmentation

2Productivity

If haulage units are deployed without predictive information, then deployment is simpler, but harvesting efficiency decreases due to mismatched arrivals

Engineering Contradiction:
Improveharvesting efficiencyVSAvoidcapacity timing information
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The system incorporates feedback from actual yield measurements and harvester operating data to continuously update and refine the probability distribution predictions. This feedback loop improves the accuracy of capacity predictions over time, enabling better coordination of haulage unit arrivals with actual unloading needs.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system provides preliminary information about expected capacity points to haulage unit operators before the harvester reaches those points. This advance notice allows haulage units to position themselves optimally, reducing waiting time and improving harvesting efficiency through better-synchronized operations.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If the system uses detailed georeferenced probability distributions, then unloading timing is more accurate, but the system becomes more complex to operate

Engineering Contradiction:
Improvecapacity prediction accuracyVSAvoidoperational simplicity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system automatically calculates and updates the georeferenced probability distribution without requiring manual intervention from operators. The automated nature of the calculations and the intuitive presentation of results maintain operational simplicity while providing high-precision predictions.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3643160B1Controlling a harvesting machine based on a geo-spatial representation indicating where the harvesting machine is likely to reach capacity
Publication Date: 2021.10.20 DEERE & CO
  • EP3643160B1 patent drawingFigure 1
  • EP3643160B1 patent drawingFigure 2
  • EP3643160B1 patent drawingFigure 3A

AI summary

A georeferenced probability distribution is generated indicating a probability that a harvester will reach its full capacity at different locations in a field. A control signal is generated to control the harvester based upon the georeferenced probability distribution. The control signal is used to control one of a plurality of different controllable subsystems, such as the propulsion system (to control harvester speed), a steering subsystem (to control the harvester's path), or other controllable subsystems.