Combined Use of Modal Analysis and Machine Learning for Materials Classification.

Materials (Basel)

Department of Material Engineering, Faculty of Textile Engineering, Technical University of Liberec, 461 17 Liberec, Czech Republic.

Published: July 2021

The present study deals with modal work that is a type of framework for structural dynamic testing of linear structures. Modal analysis is a powerful tool that works on the modal parameters to ensure the safety of materials and eliminate the failure possibilities. The concept of classification through this study is validated for isotropic and orthotropic materials, reaching up to a 100% accuracy when deploying the machine learning approach between the mode number and the associated frequency of the interrelated variables that were extracted from modal analysis performed by ANSYS. This study shows a new classification method dependent only on the knowledge of resonance frequency of a specific material and opens new directions for future developments to create a single device that can identify and classify different engineering materials.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8348414PMC
http://dx.doi.org/10.3390/ma14154270DOI Listing

Publication Analysis

Top Keywords

modal analysis
12
machine learning
8
classification study
8
combined modal
4
analysis machine
4
materials
4
learning materials
4
materials classification
4
study deals
4
modal
4

Similar Publications

Introduction: Colorectal cancer (CRC) is the third most common and second most deadly cancer worldwide, with significant morbidity and mortality risks. Despite advancements in surgical care, postoperative complications and recovery challenges persist. The severity of these issues is linked to preoperative functional capacity and emotional distress.

View Article and Find Full Text PDF

Atypical face processing is commonly reported in autism. Its neural correlates have been explored extensively across single neuroimaging modalities within key regions of the face processing network, such as the fusiform gyrus (FFG). Nonetheless, it is poorly understood how variation in brain anatomy and function jointly impacts face processing and social functioning.

View Article and Find Full Text PDF

An integrated approach to uncertainty and global sensitivity analysis in penstock structural modeling.

Heliyon

January 2025

Department of Mechanical Engineering, Mohammadia School of Engineering, Avenue Ibn Sina B.P 765, Agdal, Rabat, 10090, Morocco.

Enhanced penstock structural models significantly advance hydropower engineering, yet their increasing complexity introduces challenges. As model interactions intensify, predictability and comprehensibility decrease, complicating the evaluation of model accuracy and alignment with operational performance metrics and safety standards. This issue is particularly pronounced in dynamic modeling, where knowledge gaps hinder straightforward validation via observational data.

View Article and Find Full Text PDF

Permeable, Stretchable, and Recyclable Cellulose Aerogel On-Skin Electronics for Dual-Modal Sensing and Personal Healthcare.

ACS Nano

January 2025

CAS Key Laboratory of Mechanical Behavior and Design of Materials, Department of Modern Mechanics, University of Science and Technology of China, Hefei, Anhui 230027, PR China.

Flexible on-skin electronics present tremendous popularity in intelligent electronic skins (e-skins), healthcare monitoring, and human-machine interfaces. However, the reported e-skins can hardly provide high permeability, good stretchability, and large sensitivity and are limited in long-term stability and efficient recyclability when worn on the human body. Herein, inspired from the human skin, a permeable, stretchable, and recyclable cellulose aerogel-based electronic system is developed by sandwiching a screen-printed silver sensing layer between a biocompatible CNF/HPC/PVA (cellulose nanofiber/hydroxypropyl cellulose/poly(vinyl alcohol)) aerogel hypodermis layer and a permeable polyurethane layer as the epidermis layer.

View Article and Find Full Text PDF

Summary: With the increased reliance on multi-omics data for bulk and single cell analyses, the availability of robust approaches to perform unsupervised learning for clustering, visualization, and feature selection is imperative. We introduce nipalsMCIA, an implementation of multiple co-inertia analysis (MCIA) for joint dimensionality reduction that solves the objective function using an extension to Non-linear Iterative Partial Least Squares (NIPALS). We applied nipalsMCIA to both bulk and single cell datasets and observed significant speed-up over other implementations for data with a large sample size and/or feature dimension.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!