权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

EAGER: Cybermanufacturing: Predictive Analytics Models and Techniques for Intelligent Cybermanufacturing

EAGER：网络制造：智能网络制造的预测分析模型和技术

基本信息

批准号：
1547102
负责人：
Yan Wang
金额：
$ 10万
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：
2015
资助国家：
美国
起止时间：
2015-09-01 至 2017-08-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1547102&HistoricalAwards=false
关键词：
EAGER Cybermanufacturing Predictive Analytics Models

项目摘要

Enabling information infrastructure is the major element of the emerging service-oriented cybermanufacturing paradigm. Quality and cost are the major issues that 3D printing service providers (i.e. manufacturers) are facing as they are the critical measures for keeping their services competitive and affordable. The bidding price from a manufacturer or 3D printing service provider for a submitted job is crucial in market competition. This EArly-concept Grant for Exploratory Research (EAGER) project is the development of three data analytics approaches in a pilot prototype system to provide accurate cost estimation of 3D printing jobs. They are shape mining, user-product usage based analytics, and a hybrid approach combining shape mining with statistical mining of user-oriented data for enhanced cost prediction. The data analytics models and service-oriented framework will provide a generic and systematic approach to improve the efficiency of next-generation cybermanufacturing infrastructure, enabling manufacturers to make timely and sound decisions based on evidence and insight derived from deep learning from big data. This data science-based approach will enable better understanding of the power and the potential of cybermanufacturing in manufacturing efficiency enhancement and decision making.

促进信息基础设施是新兴的以服务为导向的网络制造模式的主要要素。质量和成本是3D打印服务提供商(即制造商)面临的主要问题，因为它们是保持其服务竞争力和负担得起的关键措施。制造商或3D打印服务提供商对提交的工作的投标价格在市场竞争中至关重要。这个早期概念探索性研究补助金(AGER)项目是在一个试点原型系统中开发三种数据分析方法，以提供3D打印作业的准确成本估计。它们是形状挖掘、基于用户产品使用情况的分析，以及将形状挖掘与面向用户的数据的统计挖掘相结合的混合方法，以增强成本预测。数据分析模型和面向服务的框架将提供通用和系统的方法，以提高下一代网络制造基础设施的效率，使制造商能够根据从大数据中深入学习得到的证据和洞察力做出及时和合理的决策。这种以数据科学为基础的方法将使人们更好地了解网络制造在提高制造效率和决策方面的力量和潜力。