AI Conveyor Sorting With Timed Pusher Diversion for Recyclables
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional recycling center sorting systems are inflexible, large, and inefficient, struggling to handle various recyclable items and require manual operation, lacking the ability to adapt to new materials.
Innovation Solution
A system comprising imaging sensors, a controller with a processor and memory, and pusher devices that use machine learning to identify and divert recyclable items on a conveyor belt, dynamically reconfiguring to recognize new materials and handle multiple objects, employing pneumatic, mechanical, or air jet mechanisms for efficient sorting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional sorting systems are used, then sorting can be performed, but the systems are large in size and lack flexibility
Solution Approach 1:
The system uses a single imager and controller that can identify and sort multiple types of recyclable materials (plastic bottles, aluminum cans, cardboard cartons, and other recyclable items). The controller is programmable to handle various sorting scenarios, making one system perform multiple sorting functions rather than requiring separate dedicated systems for each material type.
Solution Approach 2:
The patent replaces large conventional mechanical sorting systems with a more compact automated system using an imager, processor, and controlled pusher devices. The sorting function is achieved through optical detection and automated mechanical intervention rather than large-scale mechanical conveyance and manual sorting infrastructure.
2Adaptability or versatility
If conventional sorting systems are used, then sorting can be performed, but they lack the ability to be readily updated to handle new or different materials
Solution Approach 1:
The controller is designed to be programmable and reconfigurable, allowing the sorting criteria and parameters to be dynamically changed through software updates. The system can adapt to new material types by updating the identification algorithms and sorting rules in the controller without requiring hardware changes, enabling flexible response to changing recycling requirements.
Solution Approach 2:
The system changes operational parameters (such as identification thresholds, sorting categories, and pusher activation criteria) through software configuration rather than physical reconfiguration. This allows the same hardware system to handle different material types by adjusting the parameters in the controller's processing logic.
3Productivity
If manual sorting is used, then various types of items can be handled, but the process is time-consuming and less efficient
Solution Approach 1:
The system performs automatic identification and sorting of materials without requiring manual inspection. The imager automatically captures images of moving materials, the controller processes the images to identify material types, and the pusher devices automatically divert items to appropriate bins, creating a self-service automated sorting process that eliminates manual labor while maintaining high sorting speeds.
4Ease of manufacture
If conventional sorting systems are used, then sorting can be performed, but they are not cost-effective
Solution Approach 1:
By using a single multi-functional system that can sort multiple material types with one imager and controller, the patent reduces the total number of sorting systems needed in a recycling facility. This consolidation lowers equipment costs, maintenance expenses, and operational complexity while maintaining or improving overall sorting capacity and efficiency.
Data Source
AI summary
Systems and methods for sorting recyclable items and other materials are provided. In one embodiment, a system for sorting objects comprises: at least one imaging sensor; a controller comprising a processor and memory storage, wherein the controller receives image data captured by the image sensor; and at least one pusher device coupled to the controller, wherein the at least one pusher device is configured to receive an actuation signal from the controller. The processor is configured to detect objects travelling on a conveyor device and recognize at least one target item traveling on a conveyor device by processing the image data and to determine an expected time when the at least one target item will be located within a diversion path of the pusher device. The controller selectively generates the actuation signal based on whether a sensed object detected in the image data comprise the at least one target item.