SBIR Phase II: Proposal for Research into Low-Cost Distributed Wireless Sensing of Operational Condition in Industrial Electric Motors

这个小型企业创新研究（SBIR）的第二阶段项目将产生一个商业上可行的低成本无线传感器网络，可以在电机故障发生之前预测故障。美国的工业和制造商严重依赖电动机为他们的设备和工艺提供动力。为了最大限度地减少电机停机成本，许多人使用劳动密集型预防性维护程序，按固定时间表手动检查电机。这些检查平均每台汽车每年花费500美元，其中80%的费用被浪费了。这种浪费可以通过使用全天候实时监控电机性能的传感器来消除。不幸的是，目前的系统平均每个电机花费数千美元。这对于大多数1-150马力的电机应用来说太贵了，这些应用占电机市场的98%。本研究将通过受控的实验室测试和现场测试，量化和改进低成本传感器节点网络的性能，以及节点用于预测电机故障的算法。它还将把振动能量收集技术集成到节点中。结果将是一个传感器原型网络，该网络被证明符合关键性能和价格指标，并且在商业上可行，可用于1-150马力的电机。该项目的更广泛的影响/商业潜力是，一个原型低成本传感器系统将促进美国工业和制造设施中电动机的预测性维护，其成本仅为当前替代方案的一小部分。因此，美国数以万计的工厂将能够负担得起对其电机系统实施预测性维护的初始投资，最大限度地延长正常运行时间，并最大限度地降低电机维护成本。这将提高这些美国工业和制造业公司的竞争力，并最终帮助创造和保护美国的就业机会。此外，研究结果产生的原型系统将为低成本、低功耗无线传感器节点提供重要的概念验证，这将有助于刺激该领域的未来发展和投资，进而有助于“智能电网”、“智能城市”和其他智能基础设施的发展。

This Small Business Innovation Research (SBIR) Phase II project will result in a commercially viable network of low cost wireless sensors that predict electric motor failure before failure occurs. American industries and manufacturers rely heavily on electric motors to power their equipment and processes. To minimize motor downtime costs, many use labor intensive preventative maintenance programs, manually inspecting motors on a fixed schedule. These inspections cost an average of $500 per motor per year, with 80% of that cost wasted. This waste can be eliminated through the use of sensors that monitor motor performance in real time, 24x7. Unfortunately, current systems cost thousands of dollars per motor on average. This is too expensive for most 1-150 HP motor applications, which comprise 98% of the motor market. This research will quantify and refine the performance of a low cost network of sensor nodes, and algorithms used by the nodes to predict motor failures, through controlled laboratory testing and field testing. It will also integrate vibration energy harvesting technology into the nodes. The result will be a network of sensor prototypes that are demonstrated to meet key performance and price metrics, and are commercially viable for use with 1-150 HP motors.The broader impact/commercial potential of this project is that a prototype low cost sensor system will facilitate predictive maintenance of electric motors in US industrial and manufacturing facilities at a fraction of the cost of the current alternatives. As a result, tens of thousands of facilities around the US will be able to afford the initial investment to implement predictive maintenance on their motor systems, maximize up-time, and minimize motor maintenance costs. This will increase the competitiveness of these US industrial and manufacturing firms and ultimately help create and preserve American jobs. Additionally, the prototype system produced as a result of the research will provide an important proof-of-concept for low-cost, low-power wireless sensor nodes that should help spur future development and investment in this field, which is in turn instrumental for the development of "smart grids", "smart cities", and other intelligent infrastructure.