Search for: All records

Additive manufacturing enables the fabrication of complex designs while minimizing waste, but faces challenges related to defects and process anomalies. This study presents a novel multimodal Retrieval-Augmented Generation-based framework that automates anomaly detection across various Additive Manufacturing processes leveraging retrieved information from literature, including images and descriptive text, rather than training datasets. This framework integrates text and image retrieval from scientific literature and multimodal generation models to perform zero-shot anomaly identification, classification, and explanation generation in a Laser Powder Bed Fusion setting. The proposed framework is evaluated on four L-PBF manufacturing datasets from Oak Ridge National Laboratory, featuring various printer makes, models, and materials. This evaluation demonstrates the framework's adaptability and generalizability across diverse images without requiring additional training. Comparative analysis using Qwen2-VL-2B and GPT-4o-mini as MLLM within the proposed framework highlights that GPT-4o-mini outperforms Qwen2-VL-2B and proportional random baseline in manufacturing anomalies classification. Additionally, the evaluation of the RAG system confirms that incorporating retrieval mechanisms improves average accuracy by 12% by reducing the risk of hallucination and providing additional information. The proposed framework can be continuously updated by integrating emerging research, allowing seamless adaptation to the evolving landscape of AM technologies. This scalable, automated, and zero-shot-capable framework streamlines AM anomaly analysis, enhancing efficiency and accuracy. 

A novel, scalable process to deposit nanostructures with multiscale 3D geometric shapes and its application in fabricating p–n heterojunctions with n‐type ZnO and p‐type CuO is demonstrated. The process combines a microreactor‐assisted solution deposition with soft lithography to control and generate a chemical reactive flux that is transported by a patterned microfluidic channel for film printing. The precursor solutions are mixed and heated in a microreactor to generate reactive species controllably. Patterned polydimethylsiloxane (PDMS) channels guides the reacting solution to the substrate surface to form ZnO nanostructures with multiscale 3D geometric shapes. The channel geometry, flow rate, and substrate temperature are found to control the pattern geometry. A thin‐film diode composed of two different layers of a thin film with CuO at the bottom and ZnO at the top is fabricated to demonstrate fabrication of complicated functional nanostructures using low‐cost and facile solution‐based methods on desired substrate regions. The growth of the thin film can be controlled and accelerated compared to the traditional chemical bath deposition process, thanks to the continuous formation of the precursor solution with constant concentrations. 

This study explores the microreactor-assisted soft lithography (MASL) method for direct, one-step synthesis and patterning of additive-free antimony sulfide (Sb₂S₃) nanostructured thin films.