Shuai Yan

Shuai Yan

Auto-generated profile, based on publicly available information

Shuai Yan

Institute of Electrical Engineering, State Key Laboratory of High Density Electromagnetic Power and Systems, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 October 2015 in Environmental Science & Technology
Verified
Journal Article
Closed access
FDFan Dong
Fan Dong
Zaiwang ZhaoZaiwang Zhao
Zaiwang Zhao
Yanjuan SunYanjuan Sun
Yanjuan Sun
Yuxin ZhangYuxin Zhang
Yuxin Zhang
SYShuai Yan
Shuai Yan
ZWZhongbiao Wu
Zhongbiao Wu

1 February 2022 in Algorithms
Verified
Journal Article
Open access
PDF file
Yaoyao MaYaoyao Ma
Yaoyao Ma
XXXiaoyu Xu
Xiaoyu Xu
SYShuai Yan
Shuai Yan
ZRZhuoxiang Ren
Zhuoxiang Ren
The problem of electro-thermal coupling is widely present in the integrated circuit (IC). The accuracy and efficiency of traditional solution methods, such as the finite element method (FEM), are tightly related to the quality and density of mesh construction. Recently, PINN (physics-informed neural network) was proposed as a method for solving differential equations. This method is mesh free and generalizes the process of solving PDEs regardless of the equations’ structure. Therefore, an experiment is conducted to explore the feasibility of PINN in solving electro-thermal coupling problems, which include the electrokinetic field and steady-state thermal field. We utilize two neural networks in the form of sequential training to approximate the electric field and the thermal field, respectively. The experimental results show that PINN provides good accuracy in solving electro-thermal coupling problems.

1 July 2022 in IEEE Transactions on Magnetics
Verified
Journal Article
Closed access
ZGZe Guo
Ze Guo
SYShuai Yan
Shuai Yan
XXXiaoyu Xu
Xiaoyu Xu
ZCZhifu Chen
Zhifu Chen
ZRZhuoxiang Ren
Zhuoxiang Ren
With the advent of the digital age, real-time monitoring, diagnosis, and control become essential demands in the life-cycle management of electrical equipment. The methods for behavior modeling that allows accurate and real-time physical simulation gain increasing attention in recent years. Construction of the behavior model in a parametric space needs a large amount of simulation data based on the physics model which is very time-consuming. This work proposes a methodology by using the model order reduction (MOR) technique based on the proper orthogonal decomposition (POD) to build compact behavior model of rotating electric motors. With the help of the reduced-order model, the computation time to generate simulation data in a parametric space is largely reduced. The association of the behavior models with the mechanical rotation equation leads to twin models of the motors that can reflect accurately their physical state in real time. Results show that the twin models can provide an accurate time-domain response of the motor (including the speed, the torque, as well as the power angle) when compared to the finite-element method (FEM) simulation while the simulation time is negligible.

17 March 2023 in Electronics
Verified
Journal Article
Open access
PDF file
Yaoyao MaYaoyao Ma
Yaoyao Ma
XXXiaoyu Xu
Xiaoyu Xu
SYShuai Yan
Shuai Yan
YZYaxing Zhou
Yaxing Zhou
TZTianyu Zheng
Tianyu Zheng
LCLan Chen
Lan Chen
Interconnect parasitic capacitance extraction is crucial in analyzing VLSI circuits’ delay and crosstalk. This paper uses the deep neural network (DNN) to predict the parasitic capacitance matrix of a two-dimensional pattern. To save the DNN training time, the neural network’s output includes only coupling capacitances in the matrix, and total capacitances are obtained by summing corresponding predicted coupling capacitances. In this way, we can obtain coupling and total capacitances simultaneously using a single neural network. Moreover, we introduce a mirror flip method to augment the datasets computed by the finite element method (FEM), which doubles the dataset size and reduces data preparation efforts. Then, we compare the prediction accuracy of DNN with another neural network ResNet. The result shows that DNN performs better in this case. Moreover, to verify our method’s efficiency, the total capacitances calculated from the trained DNN are compared with the network (named DNN-2) that takes the total capacitance as an extra output. The results show that the prediction accuracy of the two methods is very close, indicating that our method is reliable and can save the training workload for the total capacitance. Finally, a solving efficiency comparison shows that the average computation time of the trained DNN for one case is not more than 2% of that of FEM.

13 January 2020 in IEEE Transactions on Magnetics
Verified
Journal Article
Closed access
SYShuai Yan
Shuai Yan
XXXiaoyu Xu
Xiaoyu Xu
PLPengfei Lyu
Pengfei Lyu
ZRZhuoxiang Ren
Zhuoxiang Ren
Full wave solutions of Maxwell’s equations defined on a wide-range parametric space can be necessary for modelling and design of high frequency electronic systems. Model order reduction (MOR) techniques can be used to develop efficient solvers for accelerating the parameter sweeping process. In this work, we implement two MOR methods for solving parametric full wave problems. One is the well-known proper orthogonal decomposition (POD) method and the other is a more recent and novel method, which is proper generalized decomposition (PGD). The two methods are both applied on a wave propagation problem in frequency domain and frequency-permittivity domain. Results show that both POD and PGD can model the field changes in the parametric space accurately. The efficiency and behaviour of the reduction modes of both methods are compared and discussed.

18 December 2019 in IEEE Transactions on Magnetics
Verified
Journal Article
Closed access
SYShuai Yan
Shuai Yan
ZTZuqi Tang
Zuqi Tang
THThomas Henneron
Thomas Henneron
ZRZhuoxiang Ren
Zhuoxiang Ren
In this article, the proper orthogonal decomposition (POD) is applied for parametric analysis in the gauged potential formulation of the Darwin model, considering both capacitive and inductive effects. Due to the large contrast in material parameters, the resulting system matrix is ill-conditioned. In addition, the condition number of the corresponding snapshot complex matrices is very huge. To improve the stability of the POD method, a structured-preserving strategy is considered and implemented for different unknown potentials, namely, the magnetic vector potential (MVP) $\mathbf {A}$ , the electric scalar potential (ESP) $\varphi $ , and the Lagrange multiplier $p$ . In addition, a greedy algorithm is proposed to select the snapshots adaptively. Two numerical examples, including a parallel plate capacitor and a modified $RLC$ device structure, are provided to illustrate the capability of the proposed POD in model-order reduction in the frequency-domain solvers.