STTR Phase I: Machine learning and video-based sensor for measuring sewer flows

这项小型企业技术转让（STTR）第一阶段项目的广泛影响将是为水回收设施提供准确可靠的数据，涵盖所有管道流量条件，以便制定基础设施和运营决策。这种决策能力非常重要，因为许多设施每年花费数百万美元用于改善下水道系统功能，但却受到缺乏下水道流量高质量数据的限制。改进的下水道流量数据可能有助于优化基础设施改进并减少纳税人的成本。此外，这项工作可以通过改善废水收集系统的运行，减少溢流和地下室备份，直接促进美国公众的健康和福利。这项技术具有更广泛的社会影响，因为低收入和少数民族社区受到洪水影响的程度不成比例。这项小型企业技术转让（STTR）第一阶段项目旨在推进一种新型非接触式传感器，该传感器可以收集卫生下水道系统中废水流量的视频，以测量流量并检测关键下水道事件。具体来说，该技术收集下水道流量的视频，并使用机器学习算法对其进行实时处理，以测量流量的速度和水位。该技术还可以评估下水道流量的图像，以识别进入系统的非法排放物。在拟议的项目中，将解决对这一创新成功商业化至关重要的几个关键技术障碍，包括在封闭管道环境中使用人工照明系统，制定考虑流量快速变化的策略，以及开发识别关键下水道事件的数据分析方法。考虑到这些技术障碍，该项目的目标将是开发一种基于视频的流量传感器，该传感器可以在预期的环境条件下准确捕获流速和水位，并分析拟议传感器的数据，以准确识别关键的下水道事件，如堵塞和非法排放。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact of this Small Business Technology Transfer (STTR) Phase I project will be to provide water reclamation facilities with accurate and reliable data across all pipe flow conditions in order to make infrastructure and operational decisions. This decision-making capability is important as many facilities spend millions of dollars each year on improving sewer system function, yet are constrained by lack of quality data on sewer flows. Improved sewer flow data may help to optimize infrastructure improvements and reduce costs to taxpayers. In addition, this work may directly advance the health and welfare of the American public through improved wastewater collection systems operations and reduced overflows and basement backups. This technology has broader social implications as low-income and minority communities are disproportionately affected by flood impacts.This Small Business Technology Transfer (STTR) Phase I project seeks to advance a novel, non-contact sensor that collects video of wastewater flow in sanitary sewer systems to measure flow rate and detect critical sewer events. Specifically, the technology collects video of sanitary sewer flows and processes it in real time using a machine learning algorithm to measure the velocity and water level of the flow. This technology also evaluates images of sewer flows to identify illicit discharges into the system. Several key technical hurdles crucial to successful commercialization of this innovation will be addressed in the proposed project, including the use of artificial illumination systems in closed pipe environments, the development of strategies to account for rapid variations in flow rates, and the development of data analytic methods to identify critical sewer events. Given these technical hurdles, the objectives of this project will be to develop a video-based flow sensor that can accurately capture velocity and water level under expected environmental conditions and to analyze data from the proposed sensor to accurately identify critical sewer events such as blockages and illicit discharges.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.