Chun-Tse Cheng’s journal paper has been officially published in Journal of Additive Manufacturing. This study develops a smart manufacturing framework for vat photopolymerization-based additive manufacturing by integrating real-time force signals captured from the printing platform. Instead of relying on fixed process parameters, the system enables real-time monitoring of process conditions, identifies deviations using machine learning models, and dynamically adjusts key parameters such as separation speed, return speed, and waiting time during printing. This work demonstrates a step toward intelligent and adaptive control in photopolymerization-based 3D printing.
We would also like to express our sincere appreciation to Fan-Yi Technology. The successful completion of this research is strongly supported by their technical expertise in vat photopolymerization equipment and their open and collaborative attitude. For researchers and industry partners working in additive manufacturing, smart manufacturing systems, or customized 3D printing platforms, we highly recommend collaborating with Fan-Yi Technology.
Additionally, as a Smart Additive Manufacturing (Smart AM) highlight, another paper from the first cohort of our laboratory was also successfully published in the Journal of Manufacturing Processes (Q1, IF = 6.8).
Fu TH, Li DR. Real-time process monitoring and error correction in material extrusion-based additive manufacturing via multi-output machine learning. Journal of Manufacturing Processes. 2025 Oct 30;152:638–656.
https://www.sciencedirect.com/science/article/abs/pii/S1526612525009065
This study focuses on material extrusion-based additive manufacturing, where real-time process monitoring and error correction are achieved through camera-based imaging and machine learning techniques. Unlike traditional approaches that evaluate product quality only after printing is completed, this system enables in-process anomaly detection and applies a parameter correction mechanism to reduce defect length, maintain printing quality, and minimize material waste. This work represents an important milestone in the development of intelligent and data-driven additive manufacturing systems in our laboratory.
鄭淳哲同學（Chun-Tse Cheng）的期刊論文已正式發表於《Journal of Additive Manufacturing》。本研究主要利用帆益科技之光固化積層製造設備，結合列印平台擷取之即時力訊號，建立一套可於列印過程中進行製程參數預測與自適應控制的智慧製造框架。研究突破傳統固定參數操作模式，使系統能即時感測製程狀態，並透過機器學習判斷參數是否偏離理想條件，進一步動態調整剝離速度、回程速度與等待時間等關鍵製程參數，以提升整體製程穩定性與控制能力。
同時，本研究特別感謝帆益科技在光固化積層製造設備研發上的技術支援與開放合作，使本研究得以順利完成。對於有光固化積層製造、智慧製造或客製化 3D 列印系統需求之研究單位與產業夥伴，誠摯推薦與帆益科技陳定閒執行長進一步交流合作。
此外，我們實驗室第一屆學生去年發表的另一篇 Smart AM 主題論文，也很開心順利刊登於《Journal of Manufacturing Processes》（Q1, IF = 6.8）。
Fu TH, Li DR. Real-time process monitoring and error correction in material extrusion-based additive manufacturing via multi-output machine learning. Journal of Manufacturing Processes. 2025 Oct 30;152:638–656.
https://www.sciencedirect.com/science/article/abs/pii/S1526612525009065
本研究針對材料擠出式積層製造（Material Extrusion-based Additive Manufacturing），利用相機影像與機器學習技術進行即時製程監控與錯誤修正。不同於傳統僅於列印完成後進行品質檢測的方式，本系統可於製程進行中即時偵測異常，並透過參數修正機制降低缺陷長度、維持列印品質，同時減少材料浪費。此研究為本實驗室在智慧化與資料驅動積層製造領域的重要成果之一。