Smart Campus Integrated Platform Development

瑞尔森大学的研究人员和FuseForward Solutions Group正在合作为瑞尔森大学校园开发云托管的数字孪生（DT）。这个数字孪生将作为所有校园数据的模拟和可视化环境，将校园建筑，支持物理基础设施和移动系统结合到一个通用界面中。这将允许园区管理人员和其他最终用户a）观察园区的当前和历史行为，B）识别不规则行为或潜在问题，以及c）执行可行性和“假设”分析以测试新的园区策略，例如应急响应、能源管理等。 开发这一DT需要若干新技术： 1)全面的数据结构，集成了来自四个领域的广泛数据：智能建筑，智能基础设施，智能交通和遥感，为智能城市创建可扩展的方法 2)采用新技术来确定传感器的最佳位置，以便收集数据，并将来自相邻传感器的数据拼接在一起，以创建园区的无缝“视图” 3)利用无人机（drone）、车载设备和车载设备的新型遥感技术，收集校园物理信息（室内和室外），并将其用于创建3D模型。传感器网络创建 4)机器学习算法，使用传感器和其他校园系统数据近实时地分类和预测事件。 5)开发大型多学科DT开发方法，使用瑞尔森校园进行演示，可以作为在城市或社区规模开发DT的中间步骤。 该项目产生的知识将共同开发一套应用程序，这些应用程序可以集成到一个通用的解决方案中，以优化能源效率，为行人保持安全的环境，识别和标记潜在的危险或安全威胁，识别设备故障或建筑结构退化，以及其他类似的应用程序，以降低建筑运营成本，同时保护公共安全和环境。

Ryerson University researchers and FuseForward Solutions Group are collaborating to develop an cloud-hosted Digital Twin (DT) for the Ryerson University campus. This Digital Twin will serve as a simulation and visualization environment for all campus data, combining the campus buildings, supporting physical infrastructure, and mobility systems into a common interface. This will allow campus managers and other end-users to a) observe the current and historical behavior of the campus, b) identify irregular behavior or potential issues, and c) perform feasiblity and "what-if" analyses to test new campus strategies, such as emergency response, energy management, etc. Several new technologies will be required to develop this DT: 1) A comprehensive data structure that integrates a breadth of data from four domains: Smart Buildings, Smart Infrastructure, Smart Transportation, and Remote Sensing to create a scalable approach for Smart Cities 2) New technologies to identify the optimal locations of sensors for data gathering and to stitch together data from adjacent sensors to create a seamless 'view' of the campus 3) New remote sensing technologies using unmanned aerial vehicles (drones), person-mounted equipment, and vehicle-mounted equipment to gather campus physical information (both indoor and outdoor) and use it to create 3D models. sensor networks to create 4) Machine learning algorithms to classify and predict events, using sensor and other campus system data in near-real-time. 5) Development of an approach to large, multidisciplinary DT development, demonstrated using the Ryerson Campus, that can serve as an intermediate step to developing DTs at the city or neighbourhood scale. Together, the knowledge generated from this project will develop a suite of applications that can be integrated into a common solution to optimize energy efficiency, maintain a safe environment for pedestrians, identify and flag potential hazards or security threats, identify equipment malfunction or building structural degradation, and other similar applications to reduce building operational costs while protecting public safety and the environment.