Aboshosha Ashraf, Haggag Ayman, George Neseem, Hamad Hisham A
Rad. Eng. Dept., NCRRT, Egyptian Atomic Energy Authority (EAEA), Cairo, Egypt.
Electronics Technology Department, Faculty of Technology and Education, Helwan University, Cairo, Egypt.
Sci Rep. 2023 Jul 27;13(1):12186. doi: 10.1038/s41598-023-38887-z.
Industry 4.0 technologies need to plan reactive and Preventive Maintenance (PM) strategies for their production lines. This applied research study aims to employ the Predictive Maintenance (PdM) technology with advanced automation technologies to counter all expected maintenance problems. Moreover, the deep learning based AI is employed to interpret the alarming patterns into real faults by which the system minimizes the human based fault recognition errors. The Sensors Information Modeling (SIM) and the Internet of Things (IoT) have the potential to improve the efficiency of industrial production machines maintenance management. This research work provides a better maintenance strategy by utilizing a data-driven predictive maintenance planning framework based on our proposed SIM and IoT technologies. To verify the feasibility of our approach, the proposed framework is applied practically on a corrugated cardboard production factory in real industrial environment. The Fuzzy Logic System (FLS) is utilized to achieve the AI based PM while the Deep Learning (DL) is applied for the alarming and fault diagnosis in case the fault already occured.
工业4.0技术需要为其生产线制定反应性和预防性维护（PM）策略。本应用研究旨在采用预测性维护（PdM）技术与先进的自动化技术，以应对所有预期的维护问题。此外，基于深度学习的人工智能被用于将警报模式解释为实际故障，从而使系统将基于人工的故障识别错误降至最低。传感器信息建模（SIM）和物联网（IoT）有潜力提高工业生产机器维护管理的效率。本研究工作通过利用基于我们提出的SIM和物联网技术的数据驱动预测性维护规划框架，提供了一种更好的维护策略。为了验证我们方法的可行性，所提出的框架在实际工业环境中的一家瓦楞纸板生产厂进行了实际应用。模糊逻辑系统（FLS）用于实现基于人工智能的预防性维护，而深度学习（DL）则用于在故障已经发生时进行警报和故障诊断。
