隨著製造業面臨高變異、多品項與即時交付等市場挑戰，異常事件的頻繁發生已成為企業營運效能的重要瓶頸。特別是中小型製造企業，普遍面臨人力有限、資訊斷鏈與流程缺乏標準化的問題，導致異常處理倚賴個人經驗，回應速度與解決品質難以掌控。在數位轉型浪潮下，如何以低門檻方式導入智慧技術，建構可落地的異常管理流程，成為企業提升競爭力的關鍵課題。
本研究旨在建構一套具系統性與彈性調整特性的智慧轉型方法，專為中小型製造企業於異常處理與管理流程中之應用所設計。研究透過文獻回顧、現況分析與系統性規劃，提出以流程整合、資料管理與智慧互動為核心的數位模組設計，並實際導入於A公司異常處理作業中，進行驗證與效益評估。
研究成果顯示，導入本研究所建構之智慧流程架構，能有效提升異常資訊通報效率、決策支援透明度、執行紀錄完整性與經驗知識累積，進而促進跨部門協作與作業標準化。本研究亦開發具代表性的智慧會議輔助模組，驗證生成式人工智慧於知識整理應用之可行性。理論上，本研究補足中小企業智慧化轉型方法論的研究缺口；實務上，提供企業導入智慧流程之參考依據與模組設計架構，具備一定的推廣性與應用價值。

As the manufacturing industry faces increasing challenges such as high variability, diversified product lines, and demands for real-time delivery, frequent abnormal events have become critical bottlenecks that hinder operational efficiency. Small and medium-sized enterprises (SMEs), in particular, often encounter limitations in manpower, fragmented information, and the absence of standardized processes. Consequently, their abnormal handling tends to rely on individual experience, leading to inconsistent response times and quality. Under the wave of digital transformation, developing a low-threshold, intelligent process framework has become essential to enhancing competitiveness.

This study aims to construct a systematic and adaptable smart transformation methodology tailored to the abnormal handling and management processes of SMEs in the manufacturing sector. Through literature review, current-state analysis, and structured planning, the study proposes a digital module framework centered on process integration, data management, and intelligent interaction. The proposed methodology is implemented and validated through a real-world case in Company A’s abnormal handling procedures.

The results demonstrate that the smart process framework significantly improves information reporting efficiency, decision-making transparency, execution traceability, and knowledge accumulation. It also fosters cross-department collaboration and promotes operational standardization. Moreover, this study develops an intelligent meeting assistance module and verifies the feasibility of applying generative AI to knowledge summarization. Theoretically, this research addresses a methodological gap in SME digital transformation; practically, it provides a reference architecture and application framework for enterprises seeking intelligent process enhancement.

工研院產業經濟與趨勢研究中心（IEK） (2023). 台灣製造業動態與展望。
戴志強、陳鴻祥（2022），〈製造業智慧異常偵測與自動調適研究〉，《工業工程與管理期刊》，29(3)，1-18。
Achouch, M., Brahmi, Z., Benmoussa, R., & Lefebvre, E. (2022). On predictive maintenance in Industry 4.0: Overview, models, and challenges. Applied Sciences, 12(16), 8081.
Aras, A., & Büyüközkan, G. (2023). Digital transformation journey guidance: A holistic digital maturity model based on a systematic literature review. Systems, 11(4), 213.
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S.,& Liang, P. (2021). On the opportunities and risks of foundation models. Stanford Center for Research on Foundation Models.
Cai, C. C., Jiang, Z. Y., Wu, H., Wang, J., Liu, J., & Song, L. (2024). Research on knowledge graph driven equipment fault diagnosis method for intelligent manufacturing. The International Journal of Advanced Manufacturing Technology, 130, 4649–4662.
García Reyes, J. F., & García, A. J. (2020). Improving a manufacturing process using the 8Ds method. Applied Sciences, 10(7), 2433.
Huang, S. H., Dismukes, J. P., Shi, J., Su, Q., & Razzak, M. A. (2003). Manufacturing productivity improvement using effectiveness metrics and simulation analysis. International Journal of Production Research, 41(3), 513-527.
Kusiak, A. (2018). Smart manufacturing. International Journal of Production Research, 56(1-2), 508-517.
Kreps, S., McCain, R., & Brundage, M. (2020). All the news that's fit to fabricate: AI-generated text as a tool of media misinformation.
Lee, J., Bagheri, B., & Kao, H. A. (2018). A cyber-physical systems architecture for Industry 4.0-based manufacturing systems. Manufacturing Letters, 3, 18–23.
Lee, J., Davari, H., Singh, J., & Pandhare, V. (2020). Industrial artificial intelligence for Industry 4.0-based manufacturing systems. Manufacturing Letters, 18, 20–23.
Marrella, A., & Mecella, M. (2018). Cognitive business process management for adaptive cyber-physical processes. arXiv preprint, arXiv:1802.02986.
McKinsey & Company (2020). How manufacturers can accelerate digital transformation in Industry 4.0.
Malburg, L., Grüger, J., & Bergmann, R. (2022). An IoT-enriched event log for process mining in smart factories. arXiv preprint,
Mohammadi, M., & Alizadeh, M. (2022). Identifying tools and methods for risk identification and control in manufacturing industry. International Journal of Industrial Engineering, 29(3), 45–60.
Peças, P., Pinto Ferreira, L., Alves, A. C., Leitão, P., & Rodrigues, R. (2021). DCA 4.0: A new conceptual approach for continuous improvement in the Industry 4.0 paradigm. Applied Sciences, 11(3), 1072.
Senna, P. P., Barros, A. C., Bonnin Roca, J., & Azevedo, A. (2023). Development of a digital maturity model for Industry 4.0 based on the technology–organization–environment framework. Computers & Industrial Engineering, 185, 109645.
Tao, F., Qi, Q., Liu, A., & Kusiak, A. (2018). Data-driven smart manufacturing. Journal of Manufacturing Systems, 48, 157-169.
Tao, F., Zhang, M., Liu, Y., & Nee, A. Y. C. (2018). Digital twin in industry: State-of-the-art. IEEE Transactions on Industrial Informatics, 15(4), 2405–2415
Tao, F., Qi, Q., Liu, A., & Kusiak, A. (2019). Data-driven smart manufacturing. Journal of Manufacturing Systems, 48, 157–169.
Tayeh, T., & Shami, A. (2021). Anomaly detection in smart manufacturing with an application focus on robotic finishing systems: A review. arXiv preprint, arXiv:2107.05053.
World Bank. (2023). Manufacturing, value added (% of GDP). [22] Xu, X. (2017). Machine learning for quality monitoring in manufacturing. Procedia CIRP, 63, 167-172.
Zonta, T., da Costa, C. A., da Rosa Righi, R., de Lima, M. J., da Trindade, E. S., & Li, G. P. (2020). Predictive maintenance in the Industry 4.0: A systematic literature review. Computers in Industry, 123, 103298.
Zipfel, J., Boehm, M., Koerber, J., & Weber, C. (2023). Anomaly detection for industrial quality assurance: A comparative evaluation of unsupervised deep learning models. Computers & Industrial Engineering, 177, 109045.