Bidirectional dynamic neural networks with physical analyzability

物理系统 计算机科学 人工神经网络 弹道 系统动力学 系统标识 鉴定(生物学) 人工智能 深度学习 机器人 惯性 算法 控制理论(社会学) 控制(管理) 物理 数据建模 经典力学 生物 数据库 量子力学 植物 天文
作者
Changjun Li,Fei Zhao,Xuguang Lan,Zhiqiang Tian,Tao Tao,Xuesong Mei
出处
期刊:Nonlinear Dynamics [Springer Science+Business Media]
卷期号:111 (17): 16309-16324
标识
DOI:10.1007/s11071-023-08672-8
摘要

The rapid growth in research exploiting deep learning to predict mechanical systems has revealed a new route for system identification; however, the analytic model as a white box has not been replaced in applications because of its open physical information. In contrast, the models generated by end-to-end learning usually lack the ability of physical analysis, which makes them inapplicable in many situations. Consequently, high-accuracy modeling with physical analyzability becomes a necessity. In this paper, we introduce bidirectional dynamic neural networks, a deep learning framework that can infer the dynamics of physical systems from control signals and observed state trajectories. Based on forward dynamics, we train the neural ordinary differential equations in a trajectory backtracking algorithm. With the trained model, the inverse dynamics can be calculated and based on $$\textit{Lagrangian}$$ $$\textit{Mechanics}$$ , the physical parameters of the mechanical system can be estimated, including inertia, Coriolis and centrifugal forces, and gravity. As a result, the model can seamlessly incorporate prior knowledge, learn unknown dynamics without human intervention, and provide information as transparent as analytic models. We demonstrate our method on simulated 2-axis and 6-axis robots to evaluate model accuracy, including physical parameters and verified its applicability on real 7-axis robots. The experimental results show that this method is superior to the existing methods. This framework provides a new idea for system identification by providing interpretable, physically consistent models for physical systems.
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
李泽雄发布了新的文献求助10
1秒前
呵呵哒给呵呵哒的求助进行了留言
2秒前
3秒前
JggHoo发布了新的文献求助10
7秒前
风轻青柠完成签到,获得积分10
7秒前
8秒前
10秒前
10秒前
量子星尘发布了新的文献求助10
10秒前
11秒前
R2L23发布了新的文献求助10
13秒前
13秒前
诚心的扬发布了新的文献求助10
14秒前
15秒前
liupc2019完成签到,获得积分10
16秒前
顾矜应助momo采纳,获得10
17秒前
周em12_发布了新的文献求助10
17秒前
18秒前
19秒前
19秒前
FashionBoy应助ZZZ采纳,获得10
20秒前
22秒前
清爽傲云发布了新的文献求助10
24秒前
24秒前
26秒前
28秒前
嗨嗨害发布了新的文献求助10
28秒前
Eileen发布了新的文献求助10
29秒前
呵呵哒发布了新的文献求助10
32秒前
清爽傲云完成签到,获得积分10
34秒前
34秒前
35秒前
momo发布了新的文献求助10
39秒前
诚心的扬关注了科研通微信公众号
40秒前
42秒前
嗨嗨害完成签到,获得积分10
43秒前
吧啦吧啦完成签到,获得积分10
43秒前
44秒前
45秒前
zero完成签到,获得积分10
46秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3989297
求助须知:如何正确求助?哪些是违规求助? 3531418
关于积分的说明 11253893
捐赠科研通 3270097
什么是DOI,文献DOI怎么找? 1804884
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809158