Advanced Additive develops AI-driven slicer software for Fused Layer Modeling (FLM) that optimizes path generation to enhance precision, speed, and reproducibility in 3D printing. The software integrates seamlessly with existing slicers, reducing production waste and costs while improving component quality and manufacturing efficiency.
Funding
Funding not disclosed
Founders
Product
Problem
Fused Layer Modeling (FLM) 3D printing faces challenges in achieving optimal precision, speed, and reproducibility due to inefficient path generation during the slicing process. This can lead to production waste, increased costs, and compromised component quality.
Solution
Advanced Additive offers an AI-driven software solution, Project Path AI, designed to optimize path planning for FLM 3D printing, enhancing precision, speed, and reproducibility. The software seamlessly integrates with existing slicers as a plug-in or post-processor, leveraging a proprietary process simulation (digital twin) and reinforcement learning AI models. This approach enables simulation-driven AI training, eliminating the need for extensive data collection and creating a universally applicable model, independent of machine manufacturer and component size. By optimizing path generation, the software reduces production waste, lowers costs, simplifies production planning, and increases production volume while ensuring consistent results and unlocking new levels of precision and productivity.
Target Audience
The primary target audience includes manufacturers in the aerospace, automotive, medical, dental, and industrial sectors who utilize FLM 3D printing and seek to improve the efficiency, precision, and reliability of their additive manufacturing processes.
Features
- AI-driven path planning for optimized precision, speed, and reproducibility in FLM 3D printing
- Seamless integration with existing slicers as a plug-in or through G-code post-processing
- In-house developed process simulation (digital twin) for replicating and optimizing production environments
- Reinforcement learning AI models trained via simulation, eliminating the need for extensive data collection
- Universal compatibility across all machines, manufacturing methods, and materials (metal, plastic, composite)
- Customized slicing algorithms tailored to achieve desired component properties
- Precise design of internal component structure for specific outcomes
- Reduction of production waste and optimized material and energy usage for enhanced sustainability