Progress Towards Data-Driven High-Rate Structural State Estimation on Edge Computing Devices
Progress Towards Data-Driven High-Rate Structural State Estimation on Edge Computing Devices
复制标题
边缘计算设备上数据驱动的高速结构状态估计的进展
DOI：
10.1115/detc2022-90118
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Comert, Gurcan
中科院分区：
文献类型：
--
作者：
Satme, Joud;Coble, Daniel;Priddy, Braden;Downey, Austin R.;Bakos, Jason D.;Comert, Gurcan
在高速动态环境中运行的结构，如高超声速飞行器、轨道空间基础设施和爆炸减缓系统，需要微秒级（μs）的决策。实时传感、边缘计算和高带宽计算机存储器的进步使高速结构健康监测（HR-SHM）等新兴技术变得更加可行。由于此类系统运行的时间限制，从事件检测到决策的目标设置为1毫秒，以启用HR-SHM。考虑到最小化延迟，在这项初步工作中，研究了一种数据驱动的方法，该方法依赖于实时处理的时间序列测量来推断结构的状态。提出了一种利用下采样时间序列振动数据部署基于lstm的结构状态估计器的方法。将所提出的估计器部署到嵌入式实时设备中，并讨论了所达到的精度以及系统时序。所提出的方法已经显示出高速率状态估计的潜力，因为它为所考虑的结构提供了足够的精度，同时实现了2.5 ms的时间步长。这项工作的贡献有两个方面：1)一个用于实时部署LSTM模型以进行高速率状态估计的框架，2)在实时计算系统上运行LSTM的实验验证。
Structures operating in high-rate dynamic environments, such as hypersonic vehicles, orbital space infrastructure, and blast mitigation systems, require microsecond (μs) decision-making. Advances in real-time sensing, edge-computing, and high-bandwidth computer memory are enabling emerging technologies such as High-rate structural health monitoring (HR-SHM) to become more feasible. Due to the time restrictions such systems operate under, a target of 1 millisecond (ms) from event detection to decision-making is set at the goal to enable HR-SHM. With minimizing latency in mind, a data-driven method that relies on time-series measurements processed in real-time to infer the state of the structure is investigated in this preliminary work. A methodology for deploying LSTM-based state estimators for structures using subsampled time-series vibration data is presented. The proposed estimator is deployed to an embedded real-time device and the achieved accuracy along with system timing are discussed. The proposed approach has shown potential for high-rate state estimation as it provides sufficient accuracy for the considered structure while a time-step of 2.5 ms is achieved. The Contributions of this work are twofold: 1) a framework for deploying LSTM models in real-time for high-rate state estimation, 2) an experimental validation of LSTMs running on a real-time computing system.
DOI：
--
发表时间：
2000
期刊：
影响因子：
--
作者：
C. Stein;R. Roybal;P. Tlomak;W. Wilson
通讯作者：
W. Wilson
DOI：
--
发表时间：
2021
期刊：
Data Science in Engineering, Volume 9
影响因子：
--
作者：
J. Dodson;Austin Downey;S. Laflamme;M. Todd;A. Moura;Yang Wang;Zhu Mao;P. Avitabile;Erik Blasch
通讯作者：
Erik Blasch
影响因子：
8.4
作者：
Downey, Austin;Hong, Jonathan;Scheppegrell, James
通讯作者：
Scheppegrell, James