Enhanced prediction of thermomechanical systems using machine learning, PCA, and finite element simulation

被引:0
|
作者
Schneider, Thomas [1 ]
Bedrikow, Alexandre Beiderwellen [1 ]
Stahl, Karsten [1 ]
机构
[1] Tech Univ Munich, Munich, Germany
关键词
BEHAVIOR; TEMPERATURE;
D O I
10.1186/s40323-024-00268-0
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
This research paper presents a comprehensive methodology for analyzing wet clutches, focusing on their intricate thermomechanical behavior. The study combines advanced encoding techniques, such as Principal Component Analysis (PCA), with metamodeling, to efficiently predict pressure and temperature distributions on friction surfaces. By parametrically varying input parameters and utilizing Finite Element Method (FEM) simulations, we generate a dataset comprising 200 simulations, divided into training and testing sets. Our findings indicate that PCA encoding effectively reduces data dimensionality while preserving essential information. Notably, the study reveals that only a few PCA components are required for accurate encoding: two components for temperature distribution and pressure, and three components for heat flux density. We compare various metamodeling techniques, including Linear Regression, Decision Trees, Random Forest, Support Vector Regression, Gaussian Processes, and Neural Networks. The results underscore the varying performance of these techniques, with Random Forest excelling in mechanical metamodeling and Neural Networks demonstrating superiority in thermal metamodeling.
引用
收藏
页数:27
相关论文
共 50 条
  • [1] Towards Hip Fracture Prediction using Finite Element analysis and Machine Learning
    Missoum, Samy
    Jiang, Peng
    Hu, Chengcheng
    Hsieh, Pei-Shan
    Chen, Zhao
    JOURNAL OF BONE AND MINERAL RESEARCH, 2013, 28
  • [2] Comparing Activation Functions in Machine Learning for Finite Element Simulations in Thermomechanical Forming
    Pantale, Olivier
    ALGORITHMS, 2023, 16 (12)
  • [3] Finite Element Simulation of Thermomechanical Spinning Process
    Marghmaleki, Iman Soleimani
    Beni, Y. Tadi
    Noghrehabadi, Amin Reza
    Kazemi, Asieh Sadat
    Abadyan, Mohamadreza
    11TH INTERNATIONAL CONFERENCE ON THE MECHANICAL BEHAVIOR OF MATERIALS (ICM11), 2011, 10 : 3769 - 3774
  • [4] Prediction of Cutting Forces in Milling Using Machine Learning Algorithms and Finite Element Analysis
    Charalampous, Paschalis
    JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE, 2021, 30 (03) : 2002 - 2013
  • [5] Prediction of Cutting Forces in Milling Using Machine Learning Algorithms and Finite Element Analysis
    Paschalis Charalampous
    Journal of Materials Engineering and Performance, 2021, 30 : 2002 - 2013
  • [6] Finite element network analysis: A machine learning based computational framework for the simulation of physical systems
    Jokar, Mehdi
    Semperlotti, Fabio
    COMPUTERS & STRUCTURES, 2021, 247
  • [7] Prediction of microelectronic substrate warpage using homogenized thermomechanical finite element models
    Hutapea, Parsaoran
    Grenestedt, Joachim L.
    Modi, Mitul
    Mello, Michael
    Frutschy, Kristopher
    Advances in Electronic Packaging 2005, Pts A-C, 2005, : 1141 - 1145
  • [8] Performance prediction from simulation systems to physical systems using machine learning with transfer learning and scaling
    Mankodi, Amit
    Bhatt, Amit
    Chaudhury, Bhaskar
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2023, 35 (18):
  • [9] FINITE ELEMENT THERMOMECHANICAL SIMULATION OF STEEL CONTINUOUS CASTING
    Forestier, R.
    Costes, Frederic
    Jaouen, Olivier
    Bellet, Michel
    MODELING OF CASTING, WELDING, AND ADVANCED SOLIDIFICATION PROCESSES - XII, 2009, : 295 - +
  • [10] Viscoelastic Effects on Drop Deformation Using a Machine Learning-Enhanced, Finite Element method
    Luis Prieto, Juan
    POLYMERS, 2020, 12 (08)