Tailorable & Adaptive Connected Digital Additive Manufacturing (TACDAM)

可量身定制

• 批准号: EP/P030262/1
• 负责人: George Panoutsos
• 金额: $ 28.24万
• 依托单位: University of Sheffield
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2017
• 资助国家: 英国
• 起止时间: 2017 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FP030262%2F1
• 关键词: Tailorable; Adaptive; Connected; Digital; Additive

The TACDAM project will remove the the final hurdles for the adoption of additive manufacturing in automotive applications in a staged low-mid-high volume approach. The essential requisite for this, besides having the right portfolio of products, is meeting automotive expectation of low cost and high quality, the delivery of which is the primary objective of the project. Although the biggest single contributor to product cost across the value chain has been Additive Manufacturing (AM) build time it is expected that by the end of 2017 substantial further increases will have been made. A result of this is that costs associated to pre- and post-processing are becoming relatively much more significant. Key enabling technologies, that will be developed by The University of Sheffield, include the creation of model-based approaches, that are used to optimise the part life-cycle in the manufacturing environment. This includes the identification of key factors in the value-chain, and data-driven methodologies that will 'learn' from data towards the better fundamental understanding of the process.

TACDAM项目将以分阶段的低-中-高批量方法消除在汽车应用中采用增材制造的最后障碍。除了拥有合适的产品组合外，这一点的基本要求是满足汽车对低成本和高质量的期望，交付是该项目的主要目标。虽然整个价值链中产品成本的最大单一贡献者是增材制造（AM）的构建时间，但预计到2017年底将进一步大幅增加。其结果是，与预处理和后处理相关的成本变得相对重要得多。关键使能技术将由谢菲尔德大学开发，包括创建基于模型的方法，用于优化制造环境中的零件生命周期。这包括确定价值链中的关键因素，以及从数据中“学习”以更好地理解流程的数据驱动方法。

项目成果

General Type-2 Radial Basis Function Neural Network: A Data-Driven Fuzzy Model

• DOI: 10.1109/tfuzz.2018.2858740
• 发表时间: 2019-02-01
• 期刊: IEEE TRANSACTIONS ON FUZZY SYSTEMS
• 影响因子: 11.9
• 作者: Rubio-Solis, Adrian;Melin, Patricia;Panoutsos, George
• 通讯作者: Panoutsos, George

A data-driven approach for predicting printability in metal additive manufacturing processes

用于预测金属增材制造工艺中可印刷性的数据驱动方法

• DOI: 10.1007/s10845-020-01541-w
• 发表时间: 2020
• 期刊: Journal of Intelligent Manufacturing
• 影响因子: 8.3
• 作者: Mycroft W

Evolutionary Extreme Learning Machine for the Interval Type-2 Radial Basis Function Neural Network: A Fuzzy Modelling Approach

• DOI: 10.1109/fuzz-ieee.2018.8491583
• 发表时间: 2018-07
• 期刊: 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
• 作者: Adrian Rubio Solis;Uriel Martinez-Hernandez;G. Panoutsos