SBIR Phase II: Real-Time Decision Making Software for Wastewater Treatment Operators

这项小型企业创新研究（SBIR）项目的更广泛影响/商业潜力是为废水设施开发实时软件，以降低成本提高营养物的去除和回收。通过该SBIR项目开发的技术将提供一个主动监测过程，使废水运营商能够观察和诊断未来的过程故障，主动缓解潜在的根本原因，并防止污染物释放，而无需使用昂贵且对环境有害的化学品。提高处理效率和降低运营和维护成本将限制人类活动对环境的影响，提高废水处理基础设施的可持续性，确保公众健康，并减少与废水处理有关的财政负担。在部署之后，每个大型设施每年可以节省140万美元以上的商业成本，因为废水处理服务的合规性得到了改善，化学品成本也得到了降低，在美国，这一市场机会估计高达4.2亿美元。该项目可提高35%的法规遵从性，降低35%的化学处理成本，并为缺乏经验的操作人员提供指导系统，该行业预计在未来5-10年内将有50%的操作人员退休。此外，该项目还将制定一项基于游戏的培训计划，培训新操作员掌握领导复杂设施操作的技能。SBIR第二阶段项目建议进一步开发一个软件平台，该平台使用可用的操作、生物和气象数据作为输入，向操作人员提供有关生物除磷的过程预测和见解。机器学习预测模型将成为基于归因的推理和决策系统的基础，用于诊断和减轻众所周知不稳定的生物除磷过程的干扰。在该项目中，一个全规模污水处理设施的数据系统将与软件平台同步，以提供实时结果，并将在12个月的中试测试中进行评估。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/commercial potential of this Small Business Innovation Research (SBIR) project is the development of a real-time software for wastewater facilities to improve nutrient removal and recovery at reduced costs. The technology developed through this SBIR project will provide a proactive monitoring process that allows wastewater operators to observe and diagnose future process upsets, proactively mitigate underlying root causes, and prevent pollutant release without the use of expensive and environmentally damaging chemicals. Improvements in treatment effectiveness and reduction of operating and maintenance costs will limit the environmental impact of human activities, improve sustainability of wastewater treatment infrastructure, ensure public health, and reduce financial burdens associated with wastewater treatment. Following deployment individual facilities may see annual commercial savings upwards of $1.4 M per large facility from improved compliance and reduction in chemical costs in a wastewater services, a market opportunity estimated at upwards of $420 M in the United States. This project could lead to 35% improvement in regulatory compliance, 35% reduction in chemical treatment costs, and a guidance system for inexperienced operators in an industry expecting 50% of its operator workforce to retire over the next 5-10 years. In addition, the project will develop a game-based training program to train new operators in the skill sets to lead operation of sophisticated facilities. This SBIR Phase II project proposes to further the development of a software platform that uses available operational, biological, and meteorological data as inputs to deliver process forecasts and insights regarding biological phosphorus removal to operators. Machine-learning forecast models will be the basis of an attribution-based inference and decision-making system used for diagnosis and mitigation of upsets to the notoriously unstable biological phosphorus removal process. In this project, data systems of a full-scale wastewater facility will be synced with the software platform to deliver real-time results that will be evaluated over 12 months of pilot testing.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.