AI-MEMS Sensors for Preemptive Maintenance (Phase I)

用于预防性维护的 AI-MEMS 传感器（第一阶段）

• 批准号: 555555-2020
• 负责人: Sylvestre, Julien
• 金额: $ 9.11万
• 依托单位: Université de Sherbrooke
• 依托单位国家: 加拿大
• 项目类别: Idea to Innovation
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=705352
• 关键词: AI; MEMS; Sensors; Preemptive; Maintenance

We have developed a new class of MEMS devices that add artificial intelligence (AI) capabilities to sensors. This unique technology has been validated thoroughly in the laboratory, and is now entering a phase of prototype demonstrations in real world applications. These prototypes demand improved robustness, packaging, integration with the MEMS drive electronics and training software. The objective of the proposed I2I Phase I project is to deliver these improvements by creating an AI-MEMS sensor platform to detect faulty machinery automatically to trigger preemptive maintenance actions in an industrial setting. The proposed AI-MEMS sensors will be small, fully autonomous, and robustly packaged for an industrial environment. They will be trained to separate abnormal conditions from normal operation, and to report wirelessly the detected abnormalities.

我们开发了一种新型 MEMS 设备，为传感器添加了人工智能 (AI) 功能。这项独特的技术已在实验室得到彻底验证，目前正进入现实应用中的原型演示阶段。这些原型需要改进的稳健性、封装、与 MEMS 驱动电子设备和培训软件的集成。拟议的目标 I2I 第一阶段项目旨在通过创建 AI-MEMS 传感器平台来自动检测故障机械，从而在工业环境中触发先发制人的维护操作，从而实现这些改进。拟议的 AI-MEMS 传感器体积小、完全自主且封装坚固，适合工业环境。他们将接受培训，将异常情况与正常操作分开，并以无线方式报告检测到的异常情况。