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

这个小企业创新研究（SBIR）二期项目的更广泛的影响/商业潜力来自于提高机构和商业建筑的设施管理（FM）效率，通过使用大数据分析的力量实现高效、主动运营的简化过渡。这提供了一个机会，每年仅在美国商业设施市场，就可以减少约785亿至1273亿美元的无功维护浪费。数据驱动的主动方法为设施管理人员提供了一个独特的机会，使他们能够评估资产的现状，避免非增值活动，并计划维护任务，以避免故障和停机。这将有助于将传统行业转变为先进的数据驱动行业。它还将大大减少因设施故障而对居住者造成的干扰。鉴于美国人85% -90%的时间都在室内度过，任何由设施造成的干扰都会直接影响他们的生活质量，减少设施故障的更广泛的社会影响是显著的。这个小型企业创新研究（SBIR）二期项目旨在研究、开发和展示使用大数据分析和机器学习来改变设施运营和维护决策的可行性。在美国，超过500万的商业和机构建筑的业主和经营者面临着管理老化和拥挤的建筑基础设施的挑战。它们以一种效率低下的被动模式运行，浪费了30%到40%的资源。该项目的目标是开发计算机制，自动分析综合建筑信息，以识别模式，从而产生可操作的见解，帮助减少非增值活动，并提高FM日常操作和计划中的资源利用率。通过将先进的机器学习技术与现有的建筑信息模型（BIM）资源相结合，该公司提议开发高影响力、统计和可视化的方法，以优化设施管理人员的决策能力，并以此优化关键设施基础设施和维护人员的绩效。这项研究的结果将包括规范化异构建筑数据的算法和方法，检测模式和异常，从中可以从领域知识中获得可操作的见解，并产生适合于改进商业设施管理决策的定性和定量输出。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project results from improving the efficiency in facilities management (FM) of institutional and commercial buildings by enabling a streamlined transition to efficient, proactive operations using the power of big data analytics. This provides an opportunity to reduce estimated $78.5 Billion - $127.3 Billion in waste due to reactive maintenance per year in the US commercial facilities market alone. A data driven, proactive approach provides a unique opportunity that enable facilities managers to assess as-is conditions of assets, avoid non value-add activities and plan maintenance tasks to avoid failures and shutdown. This will contribute towards transforming a traditional industry to an advanced data-driven one. It will also enable significant reduction in the disruptions caused to occupants due to failures in facilities. Given that Americans spend 85-90% of their time indoors and any disruptions caused by facilities directly impact their qualities of lives, the broader societal impact of reducing failures in facilities is significant. This Small Business Innovation Research (SBIR) Phase II project intends to research, develop and demonstrate the feasibility of using big data analytics and machine learning to transform facilities operations and maintenance decisions. Owners and operators of the over five million commercial and institutional buildings in the United States are faced with the challenges of managing aging and crowded building infrastructure. They waste between 30% and 40% of resources by operating in a predominantly inefficient, reactive mode. This project targets development of computational mechanisms that automatically analyze integrated building information to identify patterns that lead to actionable insights that help reduce non value-add activities and improve resource utilization in FM daily operation and planning. By combining advanced machine learning technologies with existing building information modeling (BIM) resources, the company is proposing to develop high-impact, statistical and visual methods for optimizing the decision-making abilities of facility managers and with that, the performance of critical facilities infrastructure and maintenance crews. The results of this research will include algorithms and methods to normalize heterogeneous building data, detect patterns and anomalies, from which actionable insights can be derived with domain knowledge, and generate qualitative and quantitative output appropriate for improved decision making in managing commercial facilities.