STTR Phase I: Edge-Based Oil Condition Monitoring System for Heavy Equipment

这个小型企业技术转让(STTR)第一阶段项目将开发一种智能现场油液状态监测系统，以快速分析高速旋转和往复机械的健康状况。石油状况监测是一个新的高增长市场，2017年收入为5.05亿美元，预计到2023年将增长至8.5亿美元。在同一时间范围内，现场石油监测市场预计将从1.93亿美元增加到3.32亿美元。该项目为运输和重型设备行业开发了台式油液监测最低可行系统。该系统不仅提供机器的当前健康状态，而且还提供对磨损趋势和生命周期的预测。该系统为每台机器提供规范和优化的维护策略，延长其寿命和可靠性，并防止灾难性的机器故障。它将带来显著的成本、能源和时间节约，并带来可持续效益。该项目的智力优势是开发了基于磨粒传感阵列和基于人工智能的油性传感技术的破坏性现场石油状况系统。主要创新包括：1)独特的感应脉冲传感阵列，可以检测细微磨损颗粒；2)微流控信号多路复用技术，检测细微磨损颗粒；3)独特的大数据分析和信号多路复用，允许快速数据处理，以获得实时健康状态；4)新的人工智能技术，即通用回归神经网络(GRNN)方法，允许利用传感器的交叉灵敏度快速获取稳健、可靠的许多特性测量，同时显著减少网络的训练时间。因此，该传感系统可提供有关机油状况和机器健康状态的全面、实时信息。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。

This Small Business Technology Transfer (STTR) Phase I project will develop an intelligent onsite oil condition monitoring system to quickly analyze the health of high-speed rotating and reciprocating machinery. Oil condition monitoring is a new and high-growth market with revenues of $505 million in 2017 and expected growth to $850 million by 2023. The market for onsite oil monitoring is expected to increase from $193 million to $332 million during the same time frame. This project develops a benchtop oil monitoring minimum viable system for the transportation and heavy equipment industry. The system offers not only the current health status of a machine but also prognosis of wear trends and life cycle. The system informs a prescriptive and optimized maintenance strategy for each piece of machinery, extending its life and reliability and preventing catastrophic machine failures. It will lead to significant cost, energy, and time savings with sustainability benefits. The intellectual merit of this project develops a disruptive onsite oil condition system based on wear debris sensing arrays and artificial intelligence-based oil property sensing technology. The major innovations include: 1) a unique inductive pulse sensing array that can detect fine wear debris, 2) microfluidic signal multiplexing technologies to detect fine wear debris, 3) unique big data analysis and signal multiplexing that allow fast data processing to obtain real time health status, and 4) a novel artificial intelligence technique, namely a General Regression Neural Network (GRNN) approach that allows acquiring robust, reliable measurements of many properties rapidly with sensors’ cross sensitivities, but significantly reduces the network’s training time. As a result, the sensing system provides comprehensive, real-time information about oil conditions and the machine health status.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.