Smart Resin Collection Units for Accurate Plastic Waste Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The inefficient disposal and procurement of recyclable resin due to lack of segregation, data on recycling centers, and uncertainty in resin identification codes poses significant challenges in managing single-use plastic waste, leading to environmental pollution.
Innovation Solution
A system utilizing a convolutional neural network (CNN) model with image and non-image data processing, including Histogram of Oriented Gradients, to identify and classify recyclable resin types based on image, weight, and location, integrated with IoT-based collection units and a server for dynamic procurement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual sorting and identification of plastic waste is used, then operational simplicity is maintained, but sorting accuracy and resin identification reliability deteriorate
Solution Approach 1:
The patent replaces manual mechanical sorting with an automated system using image sensors, CNN models, and machine learning algorithms to identify resin types. The system captures images of plastic waste, processes them through convolutional neural networks, and automatically classifies resin types, eliminating the need for manual visual inspection and significantly improving identification accuracy.
Solution Approach 2:
The patent introduces an intermediary processing layer between waste collection and recycling facilities. This intermediary system includes image sensors, processing units with CNN models, and communication modules that bridge the gap between waste generators and recycling centers, enabling automated identification and optimal routing without requiring direct manual intervention at each stage.
2Productivity
If comprehensive data collection and analysis systems are implemented, then procurement efficiency is improved, but data processing time and computational resources increase
Solution Approach 1:
The patent implements preliminary action by pre-training CNN models with extensive plastic waste image datasets before deployment. The system pre-establishes resin identification algorithms and procurement matching logic, so that when actual waste is collected, the already-trained models can rapidly classify resin types and match them with appropriate recycling facilities without requiring complex real-time analysis.
Solution Approach 2:
The patent uses copying by creating digital replicas of physical plastic waste through image sensors. Instead of physically analyzing each waste item, the system creates image copies that are processed through virtual CNN models, enabling rapid classification and procurement matching without the time-consuming process of physical inspection and transportation of sample items.
3Adaptability or versatility
If centralized recycling management is implemented, then resource utilization is optimized, but collection and transportation costs increase
Solution Approach 1:
The patent segments the centralized recycling network into multiple regional collection centers, each equipped with identification and sorting capabilities. Instead of transporting all waste to a single centralized facility, the system divides the network into manageable segments that can independently process and redirect waste streams, reducing transportation distances and energy consumption while maintaining overall network coordination.
Solution Approach 2:
The patent implements dynamic routing that adapts to real-time conditions. The system continuously monitors waste accumulation at various locations, resin type distributions, and facility capacities, then dynamically adjusts collection routes and facility assignments. This dynamic approach optimizes transportation paths and load distribution, reducing unnecessary energy consumption while maintaining flexible adaptability to changing conditions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This disclosure relates method and system for systematic disposal and dynamic procurement of recyclable waste resin. Typical systems for disposal and procurement of recyclable resin pose challenges such as lack of segregation and collection of different types of plastics, data on recycling centers in proximity, uncertainty over resin identification codes, and so on. The disclosed system provides a framework having multiple smart collection units that may be communicatively coupled with a server. The smart bins are capable of collecting plastic items and taking multiple images thereof. The system determines information on type, weight, and location of the plastic resin in the plastic item by means of a trained CNN model, and stores in a repository. The system further includes a route optimization model that is enables selection of a set of collection units for procurement of the resin (of a specific type and a specific quantity).