查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A new study on artificial intelligence is now available. According to news reporting from the University of Tokyo by N ewsRx journalists, research stated, “In the initial stages of railway vehicle de sign, finite element analyses are often repeated while adjusting design variable s such as plate thickness, window dimensions, and under-floor equipment installa tion positions to achieve the desired performance. However, this repetitive proc ess of finite element analysis, which involves the detailed modeling of large an d complex vehicle structures, is highly computationally demanding.” The news correspondents obtained a quote from the research from University of To kyo: “Therefore, it is necessary to improve the efficiency and speed of analysis . In this paper, we propose a machinelearning- based surrogate model to replace finite element analysis in railway vehicle design. To address the complexity res ulting from the vast number of nodal values, this model utilizes dimensionality reduction through principal component analysis (PCA) and a multilayer perceptron architecture. It enables the prediction of critical parameters for railway vehi cle designs including maximum deflection, deformation, stress distribution, eige nfrequencies, and eigenmodes, directly from design parameters such as plate thic kness, window dimensions, and under-floor equipment loading positions. The model demonstrates high accuracy, with predicted maximum deflection and eigenfrequenc ies within 0.2% and 1% deviation, respectively, acro ss all input variables. Additionally, nodal displacements, stress distributions, and eigenmodes are also predicted with accuracies of 4.2%, 13% , and 2.5%, respectively. Slightly lower accuracy is observed parti cularly when inputting loading positions of point loads.”
NETL
NSTL