EAGER: Exploration of Data-Driven Methods for Cyber Manufacturing

EAGER：探索数据驱动的网络制造方法

• 批准号: 2113672
• 负责人: Shreyes Melkote
• 金额: $ 30万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-03-01 至 2024-02-29
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2113672&HistoricalAwards=false
• 关键词: EAGER; Exploration; Data; Driven; Methods

This EArly-concept Grant for Exploratory Research (EAGER) project will investigate the knowledge and data-driven and cyber-enabled tools needed to link design and manufacturing, thereby enabling a cyber manufacturing marketplace that identifies the on-demand manufacturing capabilities necessary for rapid realization of product designs. Such a marketplace can democratize access to “know-how” and means of production on a massive scale, by seamlessly connecting designers with manufacturers in a broad platform of regional and global supply chains and democratizing access to manufacturing capabilities without compromising manufacturers’ “know-how” and trade secrets.To realize this impact, it is necessary to (1) create data-driven methods to harvest knowledge of manufacturing capabilities that can transform a computer-aided design (CAD) into the desired physical product, and (2) create methods to efficiently search for this knowledge through the cyber infrastructure. The project hypothesizes that: (i) computing machines can learn the manufacturing capabilities required to transform a CAD model into the desired physical part from available design and manufacturing data, and (ii) efficient cyber-enabled search of the required manufacturing capabilities for a part design can be realized through statistical similarity-based search methods. The hypothesis will be tested through innovative and convergent data-driven approaches that utilize expertise in computer-aided design, manufacturing science and technology, and machine learning.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.

这一早期概念探索性研究资助(AGIRE)项目将调查将设计和制造联系起来所需的知识和数据驱动和网络使能工具，从而建立一个网络制造市场，识别快速实现产品设计所需的按需制造能力。这样的市场可以通过在区域和全球供应链的广泛平台上无缝地将设计师与制造商联系起来，并在不损害制造商的“技术诀窍”和贸易秘密的情况下使对制造能力的访问民主化，从而可以大规模地使获得“专有技术”和生产手段的途径大众化。为了实现这种影响，有必要(1)创建数据驱动的方法来获取制造能力的知识，该方法可以将计算机辅助设计(CAD)转化为所需的物理产品，以及(2)创建方法来通过网络基础设施高效地搜索这些知识。该项目假设：(I)计算机可以从现有的设计和制造数据中学习将CAD模型转换为所需物理部件所需的制造能力，以及(Ii)可以通过基于统计相似性的搜索方法实现对部件设计所需制造能力的高效网络搜索。这一假设将通过创新和融合的数据驱动方法进行验证，这些方法利用计算机辅助设计、制造科学和技术以及机器学习方面的专业知识。这一奖项反映了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。

项目成果

Manufacturing process classification based on heat kernel signature and convolutional neural networks

• DOI: 10.1007/s10845-022-02009-9
• 发表时间: 2022-08
• 期刊: Journal of Intelligent Manufacturing
• 影响因子: 8.3
• 作者: Zhichao Wang;David Rosen

Manufacturing Process Classification Based on Distance Rotationally Invariant Convolutions

基于距离旋转不变卷积的制造过程分类

• DOI: 10.1115/1.4056806
• 发表时间: 2023
• 期刊: Journal of Computing and Information Science in Engineering
• 影响因子: 3.1
• 作者: Wang, Zhichao;Rosen, David
• 通讯作者: Rosen, David

Manufacturing process selection based on similarity search: incorporating non-shape information in shape descriptor comparison

基于相似性搜索的制造工艺选择：在形状描述符比较中纳入非形状信息

• DOI: 10.1007/s10845-024-02368-5
• 发表时间: 2024
• 期刊: Journal of Intelligent Manufacturing
• 影响因子: 8.3
• 作者: Wang, Zhichao;Yan, Xiaoliang;Bjorni, Jacob;Dinar, Mahmoud;Melkote, Shreyes;Rosen, David
• 通讯作者: Rosen, David

Automated manufacturability analysis and machining process selection using deep generative model and Siamese neural networks

• DOI: 10.1016/j.jmsy.2023.01.006
• 发表时间: 2023-04
• 期刊: Journal of Manufacturing Systems
• 影响因子: 12.1
• 作者: Xiaoliang Yan;S. Melkote

Generative Modeling of the Shape Transformation Capability of Machining Processes

加工过程形状变换能力的生成建模

• DOI: 10.1016/j.mfglet.2022.07.098
• 发表时间: 2022
• 期刊: Manufacturing Letters
• 影响因子: 3.9
• 作者: Yan, Xiaoliang;Melkote, Shreyes
• 通讯作者: Melkote, Shreyes