Work Machine Control Using Real-Time Predictive Field Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for controlling work machines, such as combine harvesters, rely on a priori data that does not account for actual, ground truth data, leading to predictive models that are not accurate during operations, and thus fail to provide real-time control improvements.
Innovation Solution
A control system that generates a predictive model using both a priori geo-referenced vegetative index data and in situ field data collected during operations, dynamically evaluates the model's quality, and adjusts control strategies based on actual yield data to ensure accurate and efficient harvesting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a priori data is used to generate predictive models, then model generation is simplified, but model accuracy during operations deteriorates
Solution Approach 1:
The system performs preliminary actions by collecting and processing field data during operational phases to update predictive models in real-time. Sensors mounted on the work machine continuously gather actual operational data, which is then used to refine the predictive model before critical decisions are made, ensuring both ease of model generation and high accuracy during operations.
Solution Approach 2:
The system implements feedback mechanisms where actual field data collected during operations is fed back into the predictive model to continuously update and refine it. This closed-loop approach allows the model to learn from real-world performance, maintaining simplicity in model generation while progressively improving accuracy through iterative refinement based on actual operational outcomes.
2Device complexity
If a priori data only is used for control, then system complexity is reduced, but adaptability to actual field conditions deteriorates
Solution Approach 1:
The control system transitions from static a priori models to dynamic adaptive modeling. The system continuously updates predictive models during operations based on real-time sensor data, allowing the control parameters to adapt dynamically to changing field conditions while maintaining manageable system complexity through modular architecture and automated data processing.
Solution Approach 2:
The system implements self-service capabilities where the work machine autonomously collects its own operational data through mounted sensors and automatically uses this data to update its predictive models. This self-updating mechanism enhances adaptability to field conditions without requiring external intervention or increasing operational complexity, as the system serves itself by leveraging its own operational experience.
3Measurement precision
If real-time field data collection is implemented, then model accuracy is improved, but data processing time increases
Solution Approach 1:
The system applies partial action by selectively processing only the most critical and relevant field data for model updates, rather than analyzing every data point in detail. This approach maintains high model accuracy by focusing on key predictive variables while reducing overall data processing time through prioritized processing of essential operational parameters.
Solution Approach 2:
The system implements continuous data collection and processing during operational phases, eliminating idle time between data gathering and model updates. By maintaining continuous useful action through real-time parallel processing of sensor data and model refinement, the system improves model accuracy without significant time loss, as data processing occurs concurrently with operational activities rather than as a separate sequential step.
Data Source
AI summary
A priori geo-referenced vegetative index data is obtained for a worksite, along with field data that is collected by a sensor on a work machine that is performing an operation at the worksite. A predictive model is generated, while the machine is performing the operation, based on the geo-referenced vegetative index data and the field data. A model quality metric is generated for the predictive model and is used to determine whether the predictive model is a qualified predicative model. If so, a control system controls a subsystem of the work machine, using the qualified predictive model, and a position of the work machine, to perform the operation.