期刊文献+

一种基于数字赋能视角下的微系统先进封装研发模式探索

A research model for advanced packaging of microsystem from the perspective of digital empowerment
下载PDF
导出
摘要 数字赋能是利用数学化知识和数字化技术改变传统模式的新型生产研发手段,在先进封装领域具有重要意义.部分国际先进企业的研究进展和现有研究成果多以生产管理控制精密化为主,虽然运用了传感、人工智能、神经网络算法、物联网等多种智能手段,但关于研发阶段数据分析的相关研究尚无系统性的方法.其原因在于先进封装研发体系是一个开放的复杂巨系统,不能只简单依据设计-仿真-迭代实验的模式进行研发.在此基础上,依据钱学森先生的定性-定量法思想提出了一种全周期智能优化自演进工程方法论:既通过建立面向微系统先进封装技术的各环节封装子系统,分别对研发及生产过程的数据进行针对性的收集,结合先进算法,构建数学模型及经验公式,又通过专家系统的分析综合迭代,形成具有足够科学根据的结论.该方法论可用于微系统先进封装研发,并对基于该成果在封装设计、封装制造等研发过程中的应用情况进行展示,总结归纳出下一步的工作方向思路. Digital empowerment is a new type of production and research and development means that changes the traditional mode by using mathematical knowledge and digital means.It is of great significance in the field of advanced packaging.In this field,the research progress and existing research results of some international advanced enterprises are mainly focused on the refinement of production management and control.Although a variety of intelligent means such as sensors,artificial intelligence,neural network algorithms,and the Internet of Things(IoT)have been used,no systematic methods have been proposed for research on data analysis in the research stage.The fundamental reason for this is that the advanced packaging research and development system is an open and complex giant system,and it cannot be developed simply based on the design-simulation-iterative experiment mode.Based on this,a full-cycle intelligent optimization selfevolving engineering methodology is proposed based on Qian Xuesen's qualitative-quantitative method.It not only establishes packaging subsystems for each link of advanced packaging technology for microsystems,collects data for research and production processes in a targeted manner,combines advanced algorithms to build mathematical models and empirical formulas,and then analyzes and synthesizes the data through expert systems to form conclusions with sufficient scientific basis.This methodology can be used for advanced packaging research and development of microsystems,and it demonstrates the application of the results in the research process of packaging design,packaging manufacturing,etc.,and summarizes the work directions that need to be carried out next.
作者 明雪飞 李可 王刚 田爽 王波 张明新 宿磊 MING Xuefei;LI Ke;WANG Gang;TIAN Shuang;WANG Bo;ZHANG Mingxin;SU Lei(The 58th Research Institute of China Electronics Technology Group Corporation,Wuxi 214035,China;School of Mechanical Engineering,Jiangnan University,Wuxi 214122,China)
出处 《微电子学与计算机》 2023年第11期1-8,共8页 Microelectronics & Computer
关键词 数字赋能 先进封装 微系统 先进算法 数学模型 digital empowerment advanced packaging microsystems advanced algorithms mathematical models
  • 相关文献

参考文献4

二级参考文献30

  • 1管晓芳.正交试验灰关联度分析法[J].水利与建筑工程学报,2007,5(2):76-77. 被引量:7
  • 2VladimirNVapnik著 张学工译.统计学习理论的本质[M].北京:清华大学出版社,2000,9..
  • 3V N Vapnik.The Nature of Statistical Learning Theory[M].NewYork:Springer, 1995
  • 4V N Vapnik. Estimation of Dependencies Based on Empirical Data[M].Berlin : Springer-Verlag, 1982
  • 5C J C Burges.A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998; 2 ( 2 ):121~167
  • 6Kreβel U.Pairwise classification and support vector machines[M].In B Scholkopf,C J C Burges,A J Smola Eds.Advances in Kernel Methods-Support Vector Learning,Cambridge,MAT:Press,1999:255~268
  • 7Weston J,C Watkins. Multi-class support vector machines[R].Technicai Report CSD-TR-98-04 ,England :Department of Computer Science Egham surrey, 1998
  • 8Chih-Chung Chang,Chih-Jen Lin. LIBSVM :a library for support vector machines[EB/OL].http:∥www.csie.ntu.edu.tw/~cjlin/libsvm,2001-12-04
  • 9O Mangasarian. Arbitrary-norm separating plane[R].TR-97-07.University of Wisconsin, 1997
  • 10Tom M Mitchell著.曾华军译.机器学习[M].北京:机械工业出版社,2003

共引文献19

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部