Proactive Water Quality Management of Water Networks in Buildings

这笔赠款将解决商业和机构建筑物的水质问题和水量管理，这些建筑物往往有复杂的管网，为居住者和建筑功能提供用水。商业和机构建筑可以占市政用水量的近50%，水质管理必须平衡细菌生长和材料杂质的健康风险与水的有效和可持续利用。最终目标是为水网设计和水质管理提供指导方针，这项研究将使用与计算资源网络连接的增强数据收集方法，开发数据驱动模型，以积极确保安全的水质，同时以最小的浪费提供水。相关的教育活动涵盖了STEM的全部领域，包括水科学、技术、计算机科学和应用数学，以及人类与技术的互动。在大学内，将有研究和环境工程，运筹学和计算机科学的课程整合的积极影响，因此新的机会，以增加专业劳动力的多样性。该项目还将成为激发K-12学生和广大公众对使用网络连接技术进行更好水质管理的兴趣的工具。基本贡献包括综合利用建筑物水网络中的化学和微生物学过程科学以及物理水流动力学，以开发新的数据驱动的水包时空轨迹模型，因为水流过建筑物管网，最终被居住者使用。该研究将使用统计机器学习方法来开发新的宏观功能模型，以捕捉状态动态的显著特征，从而使用各种测量和监测技术来估计水质状态。此外，该研究将开发用于主动水质管理系统的预测模型，其中在建筑物的供水网络中的给定点处提供控制，例如注入化学品和部分冲洗水，该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的学术价值和更广泛的影响评审标准。

This grant will address water quality issues and water quantity management in commercial and institutional buildings, which often have complex pipe networks that provide water for human occupants’ use and building functions. Commercial and institutional buildings can account for nearly 50 percent of municipal water use, and water quality management must balance health risks from bacteria growth and material impurities with efficient and sustainable use of water. With the ultimate goal of providing guidelines for water network design and water quality management, this research will use enhanced data-gathering approaches that are cyber-connected to computational resources, to develop data-driven models to proactively ensure safe water quality while delivering water with minimal wastage. The associated educational activities span the full breadth of STEM including water science, technology, computer science and applied mathematics, and human interactions with technology. Within the university, there will be the positive impacts of the integration of research and curricula of Environmental Engineering, Operations Research, and Computer Science, and hence new opportunities to increase the diversity of the professional workforce. The project will also be a vehicle to stimulate interests of K-12 students and the public at large on the use of cyber-connected technologies for better water quality management. The fundamental contributions include the integrative use of the sciences of chemistry and microbiology processes within buildings’ water networks, and the physical water-flow dynamics, to develop new data-driven models of the space-time trajectories of water parcels as water flows through the building pipe network to its eventual uses by occupants. The research will use statistical machine-learning approaches to develop new macro functional models to capture the salient features of state dynamics to estimate the state of water quality using various measurement and monitoring techniques. In addition, the research will develop predictive models for use in a proactive water quality management system, where available controls at given points in the building’s water network, such as injection of chemicals and partial flushing of water, can achieve a desired level of quality while optimizing a given performance objective.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.