A hybrid-attention-ConvLSTM-based deep learning architecture to extract modal frequencies from limited data using transfer learning

判别式 情态动词 学习迁移 人工智能 滤波器(信号处理) 计算机科学 深度学习 帧(网络) 循环神经网络 模式识别(心理学) 过程(计算) 光学(聚焦) 噪音(视频) 加速度计 人工神经网络 计算机视觉 机器学习 图像(数学) 光学 物理 操作系统 电信 化学 高分子化学
作者
Mehrdad Shafiei Dizaji,Zhu Mao,Mulugeta Haile
出处
期刊:Mechanical Systems and Signal Processing [Elsevier BV]
卷期号:187: 109949-109949 被引量:9
标识
DOI:10.1016/j.ymssp.2022.109949
摘要

This paper leverages each pixel of a picture acquired from a video camera, in which structural dynamic information is contained, in order to decompose spatiotemporal information from such a non-contact virtual sensor array in the same way as traditional accelerometers to extract structural modal frequencies. Attention-based deep neural network architecture is proposed in this work to better visualize the dynamic properties of structures in the existence of noise with a high resolution. The work combines CNNs and Recurrent Neural Networks (RNNs) to predict modal frequencies of structures from a series of consecutive images. High discriminative features of video frames are firstly extracted using the CNN, and then Conv-Long Short-Term Memory (ConvLSTM) is applied to further process the extracted features to capture the temporal dynamics in videos. The attention mechanisms are embedded in the network to ensure the model learns to focus selectively on those frames containing system dynamics. In particular, the proposed computer vision-based deep learning model takes the video of a vibrating structure as the input and successfully estimates the modal frequencies. Transfer learning is applied to cohere the knowledge learned from publicly available datasets to a much more sophisticated structure and estimate the resonant frequencies. The proposed algorithm optimizes the filter design for video processing in a fully automated way without any human intervention and can generalize and transfer that learned information to more complex structures. The model is trained using publicly available generic baseline data (Dataset A) consisting of several simple beam structures with different material properties and sizes and transferred the learned knowledge to unseen data (Dataset B) consisting of an independent turbine blade. It is concluded that the newly proposed method is more autonomous, accurate, and capable of generalizing the model to a new independent dataset using a transfer learning strategy, and the most advantage of the proposed approach is that the trained deep learning architecture has the capability of estimating the resonant frequencies for independent structures and extending the resonant frequency estimations to higher modes.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
要吃虾饺完成签到,获得积分10
1秒前
LinHan完成签到,获得积分10
2秒前
3秒前
Jiangnj完成签到,获得积分20
3秒前
可靠觅珍应助HIT_C采纳,获得30
5秒前
5秒前
Diego完成签到,获得积分10
6秒前
9秒前
11秒前
12秒前
13秒前
CipherSage应助chai采纳,获得10
13秒前
三百一十四完成签到 ,获得积分10
14秒前
wahhhlt完成签到,获得积分10
15秒前
小学僧完成签到,获得积分10
16秒前
16秒前
小二郎应助孙成成采纳,获得10
18秒前
咸鱼完成签到,获得积分20
19秒前
20秒前
20秒前
科目三应助清爽胡萝卜采纳,获得10
20秒前
苟小兵完成签到,获得积分10
21秒前
量子星尘发布了新的文献求助10
22秒前
22秒前
23秒前
orixero应助淡淡向日葵采纳,获得10
24秒前
25秒前
XZY发布了新的文献求助10
25秒前
触摸涨停板完成签到,获得积分0
26秒前
留无影发布了新的文献求助10
26秒前
27秒前
美好斓发布了新的文献求助30
30秒前
30秒前
俏皮芷蕊发布了新的文献求助10
31秒前
科研通AI5应助火星上听寒采纳,获得10
32秒前
DENANANA发布了新的文献求助30
33秒前
hzs发布了新的文献求助10
33秒前
隐形曼青应助淡淡的沅采纳,获得10
33秒前
彭于晏应助江夏清采纳,获得10
33秒前
香蕉觅云应助小月月采纳,获得10
34秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3975610
求助须知:如何正确求助?哪些是违规求助? 3519986
关于积分的说明 11200337
捐赠科研通 3256337
什么是DOI,文献DOI怎么找? 1798246
邀请新用户注册赠送积分活动 877446
科研通“疑难数据库(出版商)”最低求助积分说明 806357