AI-based early failure detection in 3D printing for better print quality, less material waste, and shorter trial and error process

3D 打印中基于人工智能的早期故障检测可提高打印质量、减少材料浪费并缩短试错过程

• 批准号: 557164-2020
• 负责人: Lin, Xianke
• 金额: $ 2.18万
• 依托单位: University of Ontario Institute of Technology
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 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=706671
• 关键词: AI; based; early; failure; detection

3D printing technologies are rapidly evolving. Fused Deposition Modeling (FDM) is one of the most popular types of 3D printers. However, there are still many challenges related to product quality, robustness, and reliability, which hinders the business expansion of 3D printing in the manufacturing industry. Research on the failure detection for the typical FDM machines and the corresponding automatic monitoring methods are required to address these challenges. This research program proposes an AI-based early failure detection system for 3D printing. This research program aims to achieve the following 4 objectives: (1) investigate the failure mechanisms in the 3D printing process to reproduce failures for data collection. (2) design experiment, collect the failure data, carry out correlation analysis, and extract the best features for failure detection. (3) based on the selected features, design the AI-based algorithms to detect failures. (4) implement the early failure detection system in the cloud-based 3D printing management system at Mech Solutions. This proposed project will combine the AI-based early fault detection system developed in Dr. Lin's lab and the commercialization capability of the industrial partner. The NSERC Alliance Grant program provides an opportunity for us to develop the advanced failure detection methods in the university lab. The industrial partner, Mech Solutions, can benefit from the developed algorithms from Dr. Lin's lab to improve the 3D printing service. The results will significantly benefit the relevant products and services in a wide range of important applications in Canada through direct transfer of knowledge and technology to industry.

3D打印技术正在迅速发展。熔融沉积成型（FDM）是最受欢迎的3D打印机类型之一。然而，在产品质量、坚固性和可靠性方面仍然存在许多挑战，这阻碍了3D打印在制造业的业务扩展。研究典型FDM设备的故障检测和相应的自动监测方法是解决这些挑战的必要条件。该研究计划提出了一种基于AI的3D打印早期故障检测系统。本研究计划旨在达到以下4个目的：（1）研究3D打印过程中的故障机制，以重现故障数据收集。(2)设计实验，收集故障数据，进行相关性分析，提取用于故障检测的最佳特征。(3)根据选定的特征，设计基于人工智能的算法来检测故障。(4)在Mech Solutions基于云的3D打印管理系统中实施早期故障检测系统。该拟议项目将联合收割机结合林博士实验室开发的基于人工智能的早期故障检测系统和工业合作伙伴的商业化能力。 NSERC联盟资助计划为我们在大学实验室开发先进的故障检测方法提供了机会。工业合作伙伴Mech Solutions可以从Lin博士实验室开发的算法中受益，以改善3D打印服务。通过直接向工业界转让知识和技术，其结果将大大有利于加拿大广泛重要应用中的相关产品和服务。