Reducing Waste in 3D Printing Using a Neural Network Based on an Own Elbow Exoskeleton

Area of Science:

• Biomedical Engineering
• Rehabilitation Technology
• Artificial Intelligence in Manufacturing

Background:

• Traditional rehabilitation systems are advancing with robotic support for improved physical therapy.
• Early rehabilitation after stroke and neurological disorders requires reliable assessment and robotic assistance for upper limb joints.
• Rising plastic costs and consumption necessitate optimization in manufacturing processes like 3D printing.

Purpose of the Study:

• To introduce an AI-based optimization strategy for 3D printing procedures in rehabilitation device manufacturing.
• To reduce material waste, filament usage, and environmental impact in the production of rehabilitation tools.
• To demonstrate cost and time savings in producing high-quality, thinly designed mass products for rehabilitation.

Main Methods:

• Utilizing artificial intelligence-based (AI-based) design and injection simulation for 3D printing optimization.
• Implementing AI algorithms to minimize material consumption and reduce waste during the printing process.
• Focusing on the development of an elbow exoskeleton for upper limb rehabilitation.

Main Results:

• AI-based optimization significantly reduces filament usage and material waste.
• The optimized 3D printing method leads to substantial time and cost savings.
• Achieved material savings equivalent to one free print for every 6.67 prints, minimizing environmental impact.

Conclusions:

• AI-based optimization of 3D printing is a viable strategy for cost-effective and sustainable manufacturing of rehabilitation devices.
• The developed elbow exoskeleton supports daily living activities and proactive physiotherapy for functional recovery.
• This approach offers a competitive advantage in mass production while enhancing the quality and accessibility of rehabilitation technology.