SBIR Phase I: Big Data Analytics for Facility Operations and Management

小型企业创新研究(SBIR)第一阶段项目的更广泛影响/商业潜力是帮助商业和机构建筑的所有者和运营商通过分析已建基础设施的数据来改善资源配置，以便在详细、可衡量的实时知识的支持下做出更明智的决策。通过自动集成使用各种软件应用程序和格式存储的建筑信息，这一创新使业主和设施管理人员能够高效地搜索信息，响应紧急情况和故障，并主动规划操作和维护任务。这项创新还应用人工智能自动进行大数据分析，识别机会，以提高资产和室内环境的能效和运营业绩。组织不仅可以通过减少设备故障和能源浪费来节省运营预算，还可以提高居住者的生活质量和生产力。该小型企业创新研究(SBIR)第一阶段项目旨在开发中间件技术，以自动集成和分析设施设计和运营中的结构化和非结构化数据。设施维护和运营是建筑物生命周期中时间最长的阶段，占总拥有成本的60%以上。业主和设施经理面临着有效管理老化和拥挤的建筑基础设施以延长资产寿命和控制成本的挑战。然而，建筑信息零散和分析不足，导致大多数维修工作都是被动地进行，以解决已经造成重大损失或浪费的问题。这项创新的愿景是开发一个完全商业化的软件包，使设施管理人员能够更主动地提高建筑物居住者的舒适度，将有限的资源集中在他们最重要的地方，并通过优化的机械控制减少能源浪费。该项目旨在展示使用大数据分析和机器学习来彻底改变设施运营和维护决策的概念可行性。这项应用研究的结果将包括将结构化数据与实地收集的非结构化数据相结合，形成适合改进决策的定性和定量输出的算法和方法。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to help owners and operators of commercial and institutional buildings to improve resource allocation by analyzing data from built infrastructure to enable smarter decision-making supported by detailed, measureable, real-time knowledge. By automatically integrating building information that is stored using various software applications and formats, this innovation enables owners and facilities managers to efficiently search for information and respond to emergency and failures, and proactively plan for operation and maintenance tasks. This innovation also applies artificial intelligence to automatically conduct big data analysis and identify opportunities to improve energy efficiency and operating performance of assets and indoor environment. Organizations can not only save operating budget by reducing equipment failures and energy waste, but also improve the quality of life and productivity for occupants. This Small Business Innovation Research (SBIR) Phase I project is aimed at developing middleware technology to automatically integrate and analyze both structured and unstructured data from facilities design and operations. Facilities maintenance and operating is the longest phase in the life-cycle of buildings, accounting for more than 60% of the total cost of ownership. Owners and facilities managers are faced with the challenges of efficiently managing aging and crowded building infrastructure to extend the life of assets and control costs. However, fragmented and under-analyzed building information results in most maintenance work being conducted reactively to address problems that have already caused significant loss or waste. The vision of this innovation is to develop a fully commercialized software package to enable facilities managers to be more proactive in improving building occupant comfort, aligning limited resources where they have the most significant impact, and reducing wasted energy through optimized mechanical controls. This project aims to demonstrate the conceptual feasibility of using big data analytics and machine learning to revolutionize facilities operating and maintenance decisions. The results from this applied research will include algorithms and methods to combine structured data with field collected unstructured data into qualitative and quantitative output appropriate for improved decision making.