Development of a cloud-based digital twin simulation platform for flexible manufacturing systems with IoT technology

数字孪生(DT)技术在加拿大制造业得到了广泛关注。这项技术创建了相应物理对象的数字副本，例如人、设备、系统或流程，在充分了解其历史性能的情况下反映了实际流程。它的优势是能够实现敏捷性和理解的趋同，以支持更有效的决策和资源分配优化。然而，现有的DT仿真平台要么是单片的、面向功能的，要么是专用的俘虏软件套件。此外，大多数数字双胞胎平台都是独立的，只支持离线模拟。由于DT不是包罗万象的解决方案，对员工进行有关新技术的教育，以了解它是否有价值，对中小型企业(SME)来说是一个巨大的风险。由于严格的检疫规则和人类活动的减少，新冠肺炎疫情给目前的制造工厂运营增加了巨大的挑战和中断。迫切需要一个在线DT平台来监控所有进程、捕获实时性能并提供远程控制。该项目包括圭尔夫大学的数字制造团队(杨博士和德菲莎博士)和Aleo Canada Inc.(魁北克省蒙特利尔)之间的合作伙伴关系。这项合作研究的主要目标是开发一个基于云的DT平台，利用物联网(IoT)传感器数据可靠地捕获柔性制造系统(即，用于制造各种部件的计算机化和可重构生产单元)的实时性能。该项目的预期影响和成果包括：1)发展对柔性制造系统进行实时监测和控制的能力，以支持经济复苏；2)利用物联网技术开发基于云的DT仿真的管道和基础设施；3)为AI算法和闭环控制提供新的试验台；以及4)提供HQP在数字转型、物联网、人工智能(AI)和云服务方面的培训。拟议项目的预期成果将为加拿大的数字经济和大流行后的恢复做出积极贡献。

Digital twin (DT) technology has received widespread attention in Canada's manufacturing sector. This technology creates a digital replica of a corresponding physical object, such as a human, device, system, or process that mirrors the actual process with full knowledge of its historical performance. It has the advantage of enabling agility and convergence of understanding to support more effective decision-making and resource allocation optimization. However, existing DT simulation platforms are either monolithic and function-oriented or dedicated in a captive software suite. Moreover, most digital twin platforms are standalone and only support offline simulation. Since DT is not a catch-all solution, educating a workforce on the new technology to see if it might be of value bears a significant risk for small-to-medium enterprises (SMEs). The COVID-19 pandemic has added an enormous challenge and disruption in current manufacturing plant operations due to strict quarantine rules and reduced human activities. There is an urgent demand for an online DT platform to monitor all the processes, capture real-time performance, and provide remote control. This project includes a partnership between the digital manufacturing team (Drs. Yang and Defersha) at the University of Guelph and Aleo Canada Inc. (Montreal, Quebec). The primary goal of this collaborative research is to develop a cloud-based DT platform that reliably captures the real-time performance of a flexible manufacturing system (i.e., a computerized and reconfigurable production unit to manufacture a variety of parts) with Internet of Things (IoT) sensor data. The expected impacts and outcomes of this project include: 1) develop the ability to conduct real-time monitoring and control of a flexible manufacturing system to support economic recovery; 2) develop the pipeline and infrastructures for cloud-based DT simulation with IoT technology; 3) provide a new testbed for AI algorithms and closed-loop control; and 4) provide training of HQP in digital transformation, IoT, Artificial Intelligence (AI), and cloud services. The expected outcomes of the proposed project will positively contribute to Canada's digital economy and post-pandemic recovery.