Designing Hybrid Neural Network Using Physical Neurons—A Case Study of Drill Bit-Rock Interaction Modeling
Designing Hybrid Neural Network Using Physical Neurons—A Case Study of Drill Bit-Rock Interaction Modeling
复制标题
使用物理神经元设计混合神经网络——钻头-岩石相互作用建模案例研究
DOI：
10.1115/1.4062631
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Song, Xingyong
中科院分区：
文献类型：
--
作者：
Zhang, Zihang;Song, Xingyong
神经网络在系统动力学建模中得到了广泛的应用。一种特殊类型的网络，混合神经网络，将神经网络模型与物理模型相结合，这可以提高训练中的收敛速度。然而，大多数现有的混合神经网络方法需要一个显式的物理模型，这有时可能是不可行的，在实践中，或可能会削弱捕捉复杂的和隐藏的物理现象的能力。在本文中，我们提出了一种新的方法来构建一个混合神经网络。该方法将物理信息融入到网络结构中，但不需要建立明确的物理模型。最后将该方法应用于井下钻井系统中钻头-岩石相互作用的建模，验证了该方法在复杂过程建模中的有效性和训练收敛的效率。
Neural networks have been widely applied in system dynamics modeling. One particular type of networks, hybrid neural networks, combines a neural network model with a physical model, which can increase rate of convergence in training. However, most existing hybrid neural network methods require an explicit physical model constructed, which sometimes might not be feasible in practice or could weaken the capability of capturing complex and hidden physical phenomena. In this paper, we propose a novel approach to construct a hybrid neural network. The new method incorporates the physical information to the structure of network construction, but does not need an explicit physical model constructed. The method is then applied to modeling of bit-rock interaction in the down-hole drilling system as a case study, to demonstrate its effectiveness in modeling complex process and efficiency of convergence in training.