SBIR Phase I: Advanced fouling detection for district cooling facilities treated with a novel nano-engineered surface treatment

这个小型企业创新研究（SBIR）项目的更广泛的影响/商业潜力将通过最先进的系统运行监测和分析来减少区域冷却（DC）工厂的能源需求。与传统的建筑空调机组相比，区域供冷系统是一种更有效、更具成本效益的跨校园生产冷冻水的方式。直流系统中的污垢积累是环境、水源和操作条件的不可避免的副产品;它导致效率低下，从而导致电力成本增加。该项目的目的是使用机器学习，基于算法的系统性能指标（SPI）以及减少污垢积累和改善传热的纳米材料来提高对污垢的理解和分析。SPI将为DC运营商提供价值，使他们能够主动而不是被动地执行维护协议，这将提高其冷却系统的效率并降低其运营成本。总之，这一创新技术包将优化直流操作，并有助于减少能源需求和排放。SBIR第一阶段项目旨在通过以下活动提高区域冷却（DC）系统的系统分析能力，从而提高DC系统的效率：1）将机器学习技术集成到DC系统数据分析中，以生成系统性能指标（SPI）。SPI将预测结垢开始，以发出需要用纳米材料再处理的信号，并进行其他维护，而不是发出结垢已经发生的信号。 2)通过集成用于系统性能诊断的附加传感器来优化系统。该项目将对一个系统进行验证和确认，该系统可以在没有完整传感器套件的情况下改造单个诊断传感器。该奖项反映了NSF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/commercial potential of this Small Business Innovation Research (SBIR) project will reduce the energy demands of district cooling (DC) plants via state-of-the-art monitoring and analysis of system operations. District cooling systems are a more efficient, cost-effective way to produce chilled water across campuses compared to traditional building air conditioning units. Fouling accumulation in DC systems is an inevitable byproduct of environment, water source, and operating conditions; it contributes to inefficiencies that lead to increased power costs. This project’s aim is to improve the understanding and analysis of fouling using a machine learning, algorithm-based system performance indicator (SPI) in conjunction with a nanomaterial that reduces fouling accumulation and improves heat transfer. The SPI will provide value to DC operators by enabling them to be proactive instead of reactive in their maintenance protocols, which will improve the efficiency of their cooling systems and reduce their operating costs. Together, this innovative technology package will optimize DC operations and contribute to reduced energy demand and emissions. An average size DC plant can realize an estimated savings of $300,000 annually.This SBIR Phase I project proposes to improve the efficiency of district cooling (DC) systems by increasing their system analysis capabilities through the following activities: 1) Integrate machine learning techniques into DC system data analysis to generate a system performance indicator (SPI). Instead of signaling that fouling has already occurred, the SPI will predict fouling onset to signal the need for retreatment with the nanomaterial and conduct other maintenance. 2) Optimize a system by integrating additional sensors for system performance diagnostics. The proposed project will conduct verification and validation for a system that could retrofit a single diagnostic sensor in the absence of a full sensor suite.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.