中文
相关论文

相关论文: Can Neural Networks Learn Nanoscale Friction?

200 篇论文

This paper addresses the trajectory-tracking problem under uncertain road-surface conditions for autonomous vehicles. We propose a stochastic nonlinear model predictive controller (SNMPC) that learns a tire--road friction model online using…

系统与控制 · 电气工程与系统科学 2023-05-09 Sean Vaskov , Rien Quirynen , Marcel Menner , Karl Berntorp

Large Language Models (LLMs) are unable to reliably reason about specific physical systems. Attempts to imbue LLMs with knowledge of the necessary physics concepts have shown great promise, but explainability and validation remain open…

人工智能 · 计算机科学 2026-05-22 Sean Memery , Kartic Subr

Machine-learning (ML) techniques have revolutionized a host of research fields of chemical and materials science with accelerated, high-efficiency discoveries in design, synthesis, manufacturing, characterization and application of novel…

材料科学 · 物理学 2021-08-31 Zhexu Xi

Carbon nanotubes (CNTs) are well known for their exceptional thermal, mechanical and electrical properties. For many CNT applications it is of the foremost importance to know their frictional properties. However, very little is known about…

材料科学 · 物理学 2015-07-20 Marcel Lucas , Xiaohua Zhang , Ismael Palaci , Christian Klinke , Erio Tosatti , Elisa Riedo

Recent advances unveiled physical neural networks as promising machine learning platforms, offering faster and more energy-efficient information processing. Compared with extensively-studied optical neural networks, the development of…

机器学习 · 计算机科学 2024-04-25 Shuaifeng Li , Xiaoming Mao

Machine-learned coarse-grained (MLCG) molecular dynamics is a promising option for modeling biomolecules. However, MLCG models currently require large amounts of data from reference atomistic molecular dynamics or substantial computation…

生物物理 · 物理学 2024-07-02 Aleksander E. P. Durumeric , Yaoyi Chen , Frank Noé , Cecilia Clementi

Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying…

The potential of mean force (PMF) between two nano crystals (NCs) represents an effective interaction potential that can be used to study the assembly of NCs to various superstructures. For a given temperature, the effective interaction is…

介观与纳米尺度物理 · 物理学 2015-12-31 Alexander Lange , Fabian Danecker , Gernot Bauer , Nadezda Gribova , Joachim Gross

Accurately predicting friction in sliding interfaces that contain third body wear particles is critical for engineering applications such as sliding movement in pistons, bearings, or metal forming. We present a hierarchical multiscale…

The influence of microscopic force fields on the motion of Brownian particles plays a fundamental role in a broad range of fields, including soft matter, biophysics, and active matter. Often, the experimental calibration of these force…

计算物理 · 物理学 2020-06-17 Aykut Argun , Tobias Thalheim , Stefano Bo , Frank Cichos , Giovanni Volpe

The physics of sliding friction is gaining impulse from nanoscale and mesoscale experiments, simulations, and theoretical modeling. This Colloquium reviews some recent developments in modeling and in atomistic simulation of friction,…

介观与纳米尺度物理 · 物理学 2013-04-04 Andrea Vanossi , Nicola Manini , Michael Urbakh , Stefano Zapperi , Erio Tosatti

Neutrino experiments study the least understood of the Standard Model particles by observing their direct interactions with matter or searching for ultra-rare signals. The study of neutrinos typically requires overcoming large backgrounds,…

计算物理 · 物理学 2020-12-30 Fernanda Psihas , Micah Groh , Christopher Tunnell , Karl Warburton

Computational experiments are exploited in finding a well-designed processing path to optimize material structures for desired properties. This requires understanding the interplay between the processing-(micro)structure-property linkages…

计算工程、金融与科学 · 计算机科学 2023-05-04 Junrong Lin , Mahmudul Hasan , Pinar Acar , Jose Blanchet , Vahid Tarokh

Molecular dynamics (MD) simulations have become indispensable for exploring tribological deformation patterns at the atomic scale. However, transforming the resulting high-dimensional data into interpretable deformation pattern maps remains…

材料科学 · 物理学 2025-12-08 Hendrik J. Ehrich , Marvin C. May , Stefan J. Eder

Machine Learning (ML) is making a strong resurgence in tune with the massive generation of unstructured data which in turn requires massive computational resources. Due to the inherently compute- and power-intensive structure of Neural…

机器学习 · 计算机科学 2018-06-27 Behzad Salami , Osman Unsal , Adrian Cristal

Recently, machine learning has emerged as an alternative, powerful approach for predicting quantum-mechanical properties of molecules and solids. Here, using kernel ridge regression and atomic fingerprints representing local environments of…

材料科学 · 物理学 2018-03-08 Teppei Suzuki , Ryo Tamura , Tsuyoshi Miyazaki

Contact-rich manipulation tasks with stiff frictional elements like connector insertion are difficult to model with rigid-body simulators. In this work, we propose a new approach for modeling these environments by learning a quasi-static…

机器人学 · 计算机科学 2023-12-15 Kevin Tracy , Zachary Manchester , Ajinkya Jain , Keegan Go , Stefan Schaal , Tom Erez , Yuval Tassa

The development of reliable and extensible molecular mechanics (MM) force fields -- fast, empirical models characterizing the potential energy surface of molecular systems -- is indispensable for biomolecular simulation and computer-aided…

A machine-learning method for extracting the short-range part of the probe-surface interaction from force spectroscopy curves is presented. Our machine-learning algorithm consists of two stages: the first stage determines a boundary that…

介观与纳米尺度物理 · 物理学 2020-08-26 Zhuo Diao , Daiki Katsube , Hayato Yamashita , Yoshiaki Sugimoto , Oscar Custance , Masayuki Abe

Machine learning (ML) enables the development of interatomic potentials that promise the accuracy of first principles methods while retaining the low cost and parallel efficiency of empirical potentials. While ML potentials traditionally…