Data Mining and Machine Learning Methods Applied to A Numerical Clinching Model

• 作者: Ferenc Leichsenring Marco G?tz Michael Kaliske Peter Müller Thomas Kropp Tobias Falk Welf-Guntram Drossel Wolfgang Graf
• 来源期刊: 工程与科学中的计算机建模(英文)
• 学科: 工学
• 关键词: DESIGN data mining computational INTELLIGENCE META-MODELLING permissible DESIGN space sensitivity analysis SELF-ORGANIZING MAPS inverse problem early stage of DESIGN clinching.
• 年，卷（期）: 2018,（12）
• 页码范围: 387-423
• 页数: 37页
• 分类号: TP3

摘要

Numerical mechanical models used for design of structures and processes are very complex and high-dimensionally parametrised.The understanding of the model characteristics is of interest for engineering tasks and subsequently for an efficient design.Multiple analysis methods are known and available to gain insight into existing models.In this contribution,selected methods from various fields are applied to a real world mechanical engineering example of a currently developed clinching process.The selection of introduced methods comprises techniques of machine learning and data mining,in which the utilization is aiming at a decreased numerical effort.The methods of choice are basically discussed and references are given as well as challenges in the context of meta-modelling and sensitivities are shown.An incremental knowledge gain is provided by a step-bystep application of the numerical methods,whereas resulting consequences for further applications are highlighted.Furthermore,a visualisation method aiming at an easy design guideline is proposed.These visual decision maps incorporate the uncertainty coming from the reduction of dimensionality and can be applied in early stage of design.