Camera-Guided Harvester Control for Yield Loss and Impurity Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing plant harvester machines introduce impurities and fail to maximize yield due to issues like chaffing, breakage, and sub-optimal threshing processes, leading to additional post-harvest costs and loss of usable plants.
Innovation Solution
The implementation of machine learning techniques for real-time impurity detection and yield optimization using cameras and controllers to adjust harvester settings, such as cutter height and speed, to minimize impurities and improve harvest efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the cutter moves quickly to increase harvesting speed, then productivity increases, but plant breakage and impurities increase
Solution Approach 1:
The system dynamically adjusts the cutter speed based on real-time detection of plant conditions and impurity levels. The controller modulates the cutter motor speed to optimize the balance between harvesting productivity and minimizing plant breakage, transitioning from static fixed-speed operation to dynamic adaptive speed control.
Solution Approach 2:
The system uses cameras and sensors to detect impurities and plant breakage in real-time, feeding this information back to the controller which then adjusts cutter speed accordingly. This closed-loop feedback mechanism enables the system to respond to actual harvesting conditions and optimize the trade-off between speed and quality.
2Productivity
If the thresher moves quickly to increase processing speed, then productivity increases, but de-stemming effectiveness decreases and impurities increase
Solution Approach 1:
The thresher speed is dynamically adjusted based on real-time detection of de-stemming effectiveness. The controller monitors the quality of threshed material and modulates thresher speed to maintain optimal de-stemming performance while maximizing productivity, replacing static speed control with adaptive dynamic control.
Solution Approach 2:
The system implements feedback control by detecting impurity levels and de-stemming effectiveness during threshing, then using this information to adjust thresher speed. This closed-loop system ensures that threshing quality requirements are met while optimizing processing speed and productivity.
3Manufacturing precision
If manual detection and removal of impurities is performed after harvesting, then impurity removal is achieved, but post-harvest costs increase and usable plant loss occurs
Solution Approach 1:
The system performs impurity detection during the harvesting process itself rather than after harvesting is complete. By detecting and flagging impurities in real-time during harvesting, the system enables preliminary action that prevents the need for expensive post-harvest manual detection and removal processes.
Solution Approach 2:
The system replaces manual mechanical detection and removal of impurities with automated optical detection using cameras and sensors. This substitution of mechanical/manual processes with automated sensing and control systems reduces post-harvest processing costs and eliminates the need for labor-intensive impurity removal.
4Productivity
If traditional harvesting processes are used without real-time detection, then device complexity is minimized, but yield optimization and loss prevention are insufficient
Solution Approach 1:
The system uses multi-functional cameras and sensors that serve multiple purposes: detecting impurities, monitoring plant conditions, tracking harvest yield, and guiding harvesting operations. By making the detection system universal and multi-functional, the system achieves yield optimization without proportionally increasing device complexity.
Solution Approach 2:
The harvesting system performs self-monitoring and self-adjustment using integrated sensors and controllers that automatically detect conditions and optimize harvesting parameters without external intervention. This self-service capability enables yield optimization while minimizing the complexity of external control systems.
Data Source
AI summary
Systems and methods are disclosed herein for optimizing harvester yield. In an embodiment, a controller receives a pre-harvest image from a front-facing camera of a harvester. The controller inputs the pre-harvest image into a model, and receives as output from the model a predicted harvest yield. The controller receives, from an interior camera of the harvester, a post-harvest image including the plants as harvested. The controller inputs the post-harvest image into a second model and receives, as output, an actual harvest yield of the plants as-harvested. The controller determines that the predicted harvest yield does not match the actual harvest yield, and outputs a control signal.