Phy-Taylor: Partially Physics-Knowledge-Enhanced Deep Neural Networks via NN Editing
Phy-Taylor: Partially Physics-Knowledge-Enhanced Deep Neural Networks via NN Editing
复制标题
Phy-Taylor：通过 NN 编辑部分物理知识增强的深度神经网络
DOI：
10.1109/tnnls.2023.3325432
复制
发表时间：
2024
影响因子：
10.4
通讯作者：
Abdelzaher, Tarek
中科院分区：
文献类型：
--
作者：
Mao, Yanbing;Gu, Yuliang;Sha, Lui;Shao, Huajie;Wang, Qixin;Abdelzaher, Tarek
应用于物理工程系统的纯数据驱动的深度神经网络(DNN)可以推断出违反物理定律的关系，从而导致意想不到的结果。为了应对这一挑战，我们提出了一种物理知识增强型DNN框架，称为Phy-Taylor，加快了物理知识的学习顺应性表示。Phy-Taylor框架有两个关键贡献：它引入了一种新的建筑物理兼容神经网络(PHN)，并具有一种新的遵从机制，我们称之为物理制导神经网络(NN)编辑。PHN的目标是直接捕获非线性物理量，如动能、电能和空气动力阻力。为此，PHN在NN层中增加了两个关键组件：1)用于捕获物理量的泰勒级数的单项式；2)用于减轻噪声影响的抑制器。NN编辑机制进一步修改与物理知识一致的网络链接和激活函数。作为扩展，我们还提出了一个用于自治系统安全关键控制的自校正Phy-Taylor框架，它引入了两个额外的功能：1)安全关系学习和2)当发生安全违规时自动输出校正。实验结果表明，Phy-Taylor算法具有参数少、训练速度快等特点，同时提高了模型的稳健性和准确性。
Purely data-driven deep neural networks (DNNs) applied to physical engineering systems can infer relations that violate physics laws, thus leading to unexpected consequences. To address this challenge, we propose a physics-knowledge-enhanced DNN framework called Phy-Taylor, accelerating learning-compliant representations with physics knowledge. The Phy-Taylor framework makes two key contributions; it introduces a new architectural physics-compatible neural network (PhN) and features a novel compliance mechanism, which we call physics-guided neural network (NN) editing. The PhN aims to directly capture nonlinear physical quantities, such as kinetic energy, electrical power, and aerodynamic drag force. To do so, the PhN augments NN layers with two key components: 1) monomials of the Taylor series for capturing physical quantities and 2) a suppressor for mitigating the influence of noise. The NN editing mechanism further modifies network links and activation functions consistently with physics knowledge. As an extension, we also propose a self-correcting Phy-Taylor framework for safety-critical control of autonomous systems, which introduces two additional capabilities: 1) safety relationship learning and 2) automatic output correction when safety violations occur. Through experiments, we show that Phy-Taylor features considerably fewer parameters and a remarkably accelerated training process while offering enhanced model robustness and accuracy.