Data Mining and Machine Learning Methods Applied to A Numerical Clinching Model
Data Mining and Machine Learning Methods Applied to A Numerical Clinching Model
复制标题
DOI：
10.31614/cmes.2018.04112
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Marco Götz;F. Leichsenring;T. Kropp;P. Müller;T. Falk;W. Graf;M. Kaliske;W. Drossel
中科院分区：
文献类型：
--
作者：
Marco Götz;F. Leichsenring;T. Kropp;P. Müller;T. Falk;W. Graf;M. Kaliske;W. Drossel
用于结构和工艺设计的数值力学模型是非常复杂和高维参数化的。了解模型特征对于工程任务以及随后的高效设计都很有意义。多种分析方法是已知的，并且可用于深入了解现有模型。在这方面的贡献，从各个领域选择的方法适用于一个真实的世界机械工程的例子，目前开发的铆接过程。引入的方法的选择包括机器学习和数据挖掘技术，其中的利用旨在减少数值工作。基本上讨论了选择的方法，并给出了参考文献，以及元建模和敏感性方面的挑战。一个增量的知识增益提供了一步一步的应用程序的数值方法，而所产生的后果，进一步的应用突出显示。此外，一个可视化的方法，旨在一个简单的设计准则提出。这些视觉决策图包含了降维带来的不确定性，可以应用于设计的早期阶段。
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-by-step 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.