Grain Tailings Elevator Camera for Quality Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Agricultural combine harvesters face challenges in monitoring and improving grain quality due to limitations in reliable sampling and imaging techniques, which affect the classification of clean and broken grains, and material other than grain (MOG).
Innovation Solution
A grain quality control system that includes a camera with an image sensor mounted on a grain tailings elevator, enabling real-time imaging and analysis of grain constituents within the elevator, utilizing deep-learning capabilities for enhanced image processing and classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sampling and imaging techniques are used for grain quality monitoring, then the system structure remains simple, but the classification accuracy and reliability of grain quality assessment deteriorates
Solution Approach 1:
The imaging system is divided into multiple specialized components: illumination subsystem with adjustable LED arrays, imaging subsystem with interchangeable lenses, and processing subsystem with GPU acceleration. This segmentation allows each component to be optimized independently for its specific function while maintaining overall system accuracy.
Solution Approach 2:
A complex image processing pipeline acts as an intermediary between the simple imaging capture and the final grain quality classification. The pipeline includes noise reduction, feature extraction, and deep learning-based classification algorithms that transform raw images into accurate quality assessments.
2Reliability
If real-time imaging of grain tailings is implemented, then grain quality monitoring capability is improved, but the device complexity and manufacturing cost increases
Solution Approach 1:
The imaging and monitoring system is extracted as a separate, modular subsystem from the main elevator structure. This allows the monitoring functionality to be added without fundamentally redesigning the elevator, maintaining manufacturing simplicity while enabling advanced monitoring capabilities.
Solution Approach 2:
The imaging system is designed to serve multiple functions: quality classification, contamination detection, and process optimization. This multi-functionality justifies the added complexity by providing comprehensive monitoring from a single integrated system.
3Measurement precision
If deep-learning capabilities are added for image processing, then classification accuracy is improved, but the computational requirements and system complexity increases
Solution Approach 1:
Image preprocessing operations such as normalization, noise filtering, and feature extraction are performed before deep learning classification. This preliminary action reduces the complexity of the main classification task and improves computational efficiency.
Solution Approach 2:
Traditional mechanical or rule-based classification methods are replaced with deep learning algorithms. The system uses neural networks to automatically learn classification boundaries from training data, substituting complex manual feature engineering with automated computational learning.
Data Source
AI summary
A grain tailings elevator for a combine harvester includes a an elevator housing having an interior containing a conveyor arrangement configured to transport grain tailings through the elevator housing to a discharge outlet. The elevator housing has a side wall with a window to the interior of the elevator housing. A camera having a camera housing containing an image sensor is mounted to the side wall of the elevator housing over the window with the image sensor in registration with the window. The image sensor is trained on the conveyor arrangement and configured to image the grain tailings transported by the conveyor arrangement through the elevator housing.