PFI-TT: Acoustic Continuous Condition Monitoring of Manufacturing Machinery

这个PFI项目的更广泛的影响/商业潜力是为制造业提供先进的解决方案，通过持续的声学监测及早发现机器故障。机械故障对制造业有重大负面影响，包括：意外停机导致设备和工作人员利用不足；生产不合规格的产品导致成品和原材料浪费；以及维修费用高昂和维护计划效率低下。所有这些影响增加了制造成本，并可能导致收入损失，直接影响这些公司的利润率，从而影响竞争力。通过改进机器状态监控和广泛采用预测性维护，我们相信我们的解决方案可以促进美国制造业的增长，并带来所有重大的辅助好处。更好地预测机器故障还可能影响制造操作中的能效、环境影响和工作场所安全。拟议的项目将开发一种集成的工业物联网(IIoT)解决方案，以持续监测制造机械的状态。我们的解决方案以低成本、高质量的远程声音传感设备网络为中心，该设备具有嵌入式人工智能(AI)用于声音识别，可以自动检测和诊断机器故障的早期迹象。我们的新技术专注于声发射，包括声学和超声波范围，这意味着我们的传感器是非接触式的，因此易于安装，能够监控每个传感器的多个部件，并且能够比现有解决方案更早地发出警告。此外，我们使用人工智能进行声音识别，实现了快速且可扩展的实时分析，所需的专业知识最少。我们提供一个统一的网络基础设施，集成了边缘计算、云数据存储和易于使用的仪表板，以方便导航、检索和操作。这种结合有可能产生一种颠覆性和变革性的产品，在显著降低部署和运营成本的同时改善机器状态监控。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势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 PFI project is in providing the manufacturing sector with advanced solutions for the early detection of machine malfunctions via continuous acoustic monitoring. Machinery malfunctions have significant negative effects on the manufacturing industry, including: unscheduled downtime leading to the under-utilization of equipment and staff; the production of off-spec products leading to waste of finished product and raw materials; as well as costly-repairs and inefficient maintenance schedules. All these effects increase the cost of manufacturing and can result in loss of revenue, directly affecting the margin of profitability, and thus the competitiveness, for these companies. By improving machine condition monitoring and enabling the widespread adoption of predictive maintenance, we believe our solutions can contribute to the growth of the US manufacturing sector, with all the significant ancillary benefits that entails. Better prediction of machine failures could also potentially affect energy efficiency, environmental impact and workplace safety in manufacturing operations. The proposed project will develop an integrated, Industrial Internet-of-Things (IIoT) solution to continuous condition monitoring of manufacturing machinery. Our solution is centered around a network of low-cost, high quality, remote acoustic sensing devices with embedded artificial intelligence (AI) for sound recognition, that can automatically detect and diagnose the early signs of machine failure. Our novel focus on acoustic emissions, both in the audible and ultrasonic range, means that our sensors are non-contact and thus easy to install, capable of monitoring multiple parts per sensor, and able to produce earlier warnings than those possible with existing solutions. Furthermore, our use of AI for sound recognition results in fast and scalable analytics in real-time with minimal expertise required. We provide a unified cyber-infrastructure integrating edge computing, cloud data storage and an easy-to-use dashboard to facilitate navigation, retrieval and operation. This combination has the potential to result in a disruptive and transformative product that improves machine condition monitoring while significantly lowering the cost of deployment and operation.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.