权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

EAGER: Real-Time: Ultrasonic Reconstruction and Localization with Deep Helmholtz Networks

EAGER：实时：利用深亥姆霍兹网络进行超声重建和定位

基本信息

批准号：
1839704
负责人：
Joel Harley
金额：
$ 27.31万
依托单位：
University of Florida
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2018
资助国家：
美国
起止时间：
2018-10-01 至 2022-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1839704&HistoricalAwards=false
关键词：
EAGER Real Time Ultrasonic Reconstruction

项目摘要

Ultrasonic Reconstruction and Localization with Deep Helmholtz NetworksThis project studies physics-informed neural networks to characterize and monitor materials and engineered systems with ultrasound. Ultrasound is studied because it is a wireless, high resolution, medically safe, and inherently secure technology that is driving innovations in wearables, medical implants, secure / encrypted communication systems, and imaging. The project's neural network algorithms can characterize materials and engineered systems from the micro-level (e.g., micro-electrical-mechanical systems) to the macro-level (e.g., pipelines, airplanes, or rail lines). The neural networks characterize the materials by learning the general behavior of ultrasound from simulated data, physical constraints, and measured data. That learned behavior is then compared with the true measured behavior. To achieve our goal, three significant challenges of applying neural networks (and machine learning generally) to many engineered systems are studied: (1) experimental training data is often scarce or unavailable, (2) data diversity and variability is typically high, and (3) purely data-driven approaches offer few engineering assurances. Data scarcity is addressed by training neural networks with simulations rather than experimental data. Data diversity and variability is addressed by using transfer learning theory to transfer generalized knowledge from the simulation data into the analysis of the experimental data. Engineering assurances are improved by incorporating physics-based constraints into the neural networks. The resulting neural networks are referred to as Helmholtz networks, named for the time-independent wave equation.The objective of the project is to establish the foundation for Helmholtz networks, which are deep, generative, physics-informed neural networks that reconstruct ultrasonic wave propagation and locate ultrasonic sources. The Helmholtz networks are based on the fact that each frequency of a wave can be represented as the sum of a sparse number of spatial modes. The modes are constrained by the Helmholtz equation and this physical constraint ensures that the machine learning algorithm is trustworthy for system-critical engineered systems (e.g., health monitoring of an aircraft). Such physics-informed machine learning is an important (albeit not widely studied) topic for integrating advanced computation tools into real-time engineered systems. The research thrusts of this proposal are to initiate and explore the foundations for three new types of neural networks: (1) generative Helmholtz networks to learn modal representations of waves and reconstruct wavefields, (2) localization networks to locate ultrasonic sources under uncertainties, and (3) localization Helmholtz networks to locate sources from learned modal representations. Thrust 1 explores the creation of generative models (i.e., generative Helmholtz networks) that learn the spatial modal characteristics of a medium from simulations. These generative models then reconstruct wavefields from undersampled test data. Thrust 2 studies localization networks to locate ultrasonic sources under simulated uncertainties, such as velocity, delay, and/or amplitude uncertainty. Thrust 3 investigates the use of transfer learning to combine Thrust 1 and Thrust 2 and use the learned modes to locate sources in geometrically complex media.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

利用深度亥姆霍兹网络的超声重建和定位该项目研究物理信息神经网络，以表征和监测材料和工程系统的超声波。之所以研究超声波，是因为它是一种无线、高分辨率、医疗安全和固有的安全技术，正在推动可穿戴设备、医疗植入物、安全/加密通信系统和成像方面的创新。该项目的神经网络算法可以从微观层面(例如，微型机电系统)到宏观层面(例如，管道、飞机或铁路线)描述材料和工程系统的特征。神经网络通过从模拟数据、物理约束和测量数据学习超声波的一般行为来表征材料。然后，将习得的行为与真正测量的行为进行比较。为了实现我们的目标，研究了将神经网络(通常还有机器学习)应用于许多工程系统的三个重要挑战：(1)实验训练数据往往稀缺或不可用，(2)数据多样性和可变性通常很高，(3)纯粹的数据驱动方法提供的工程保证很少。数据稀缺是通过用模拟而不是实验数据来训练神经网络来解决的。利用迁移学习理论将广义知识从模拟数据转化到实验数据分析中，解决了数据的多样性和可变性问题。通过将基于物理的约束融入到神经网络中来改善工程保证。由此产生的神经网络被称为Helmholtz网络，以与时间无关的波动方程命名。该项目的目标是为Helmholtz网络奠定基础，Helmholtz网络是一种深度、生成性、物理信息的神经网络，可以重建超声波传播并定位超声源。亥姆霍兹网络是基于这样一个事实，即波的每个频率都可以表示为稀疏数量的空间模式的总和。这些模式受Helmholtz方程的约束，这种物理约束确保机器学习算法对于系统关键型工程系统(例如，飞机的健康监测)是可靠的。对于将先进的计算工具集成到实时工程系统中，这种基于物理知识的机器学习是一个重要的(尽管没有广泛研究的)主题。这一建议的研究重点是启动和探索三种新型神经网络的基础：(1)生成式Helmholtz网络，用于学习波的模式表示并重建波场；(2)定位网络，用于在不确定情况下定位超声源；(3)本地化Helmholtz网络，用于从学习的模式表示中定位源。推力1探索了生成模型(即生成性亥姆霍兹网络)的创建，这些模型从模拟中学习介质的空间模式特征。然后，这些生成模型从欠采样测试数据中重建波场。推力2号研究了定位网络，以在模拟的不确定性下定位超声源，例如速度、延迟和/或幅度的不确定性。推力3研究了使用转移学习来组合推力1和推力2，并使用学习的模式在几何复杂的介质中定位信号源。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

期刊论文数量（11）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Closing the Sim-to-Real Gap in Guided Wave Damage Detection with Adversarial Training of Variational Auto-Encoders

通过变分自动编码器的对抗训练来缩小导波损伤检测中的模拟与真实差距

DOI：
10.1109/icassp43922.2022.9746196
发表时间：
2022
期刊：
Speech and Signal Processing (ICASSP
影响因子：
0
作者：
Khurjekar, Ishan D.;Harley, Joel B.
通讯作者：
Harley, Joel B.

A physics-informed machine learning based dispersion curve estimation for non-homogeneous media

基于物理信息的机器学习的非均匀介质色散曲线估计

DOI：
10.1121/10.0016136
发表时间：
2022
期刊：
The Journal of the Acoustical Society of America
影响因子：
0
作者：
Tetali, Harsha Vardhan;Harley, Joel
通讯作者：
Harley, Joel

Estimating Guided Wave Velocity Variation With Neural Networks

使用神经网络估计导波速度变化

DOI：
10.1115/qnde2021-75080
发表时间：
2021
期刊：
Proc. of the Annual Review of Progress in Quantitative Nondestructive Evaluation
影响因子：
0
作者：
Leibovici, Ori;Yang, Kang;Harley, Joel B.
通讯作者：
Harley, Joel B.

Deep Neural Network-Based Guided Wave Damage Localization

基于深度神经网络的导波损伤定位