Zhikun Cai

Zhikun Cai

Auto-generated profile, based on publicly available information

Zhikun Cai

Department of Electrical Engineering, State Key Laboratory of Power Transmission Equipment and System Security and New Technology, Chongqing University, Chongqing 400044 China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
23 December 2020 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
RLRuiheng Li
Ruiheng Li
NYNian Yu
Nian Yu
Xuben WangXuben Wang
Xuben Wang
YLYang Liu
Yang Liu
ZCZhikun Cai
Zhikun Cai
EWEnci Wang
Enci Wang
Neural networks (NNs) are efficient tools for rapidly obtaining geoelectric models to solve magnetotelluric (MT) inversion problems. Training an NN with strong predictive power requires numerous training samples to prevent underfitting. To reduce the computational burden of generating a large number of training samples, this work analyzes the influence of the sample features and distribution on the training effect for an NN and proposes an efficient method of sample generation. This innovative method consists of three steps: 1) geoelectrically simplifying the features; 2) removing unnecessary features on the basis of realistic geological characteristics; and 3) mapping the samples to a higher-dimensional space. Numerical examples based on simple stratified models show that the number of samples can be reduced to below one-millionth of the original number while improving the predictive effect of the NN. The performance and effectiveness for processing more complex structures are verified by the inversion results obtained for a public data set, COPROD2. We conclude that this advanced method can generate high-quality training samples at a greatly reduced computational cost. The analysis of the sample features and distribution not only advances the state of research on the use of machine learning in geophysical inversion but also is a forward-looking study on the mechanisms of underfitting, tracing the source of these phenomena back to the training samples used.

17 March 2021 in IEEE Transactions on Electromagnetic Compatibility
Verified
Journal Article
Closed access
NYNian Yu
Nian Yu
ZCZhikun Cai
Zhikun Cai
RLRuiheng Li
Ruiheng Li
QZQiang Zhang
Qiang Zhang
LGLei Gao
Lei Gao
ZSZhibo Sun
Zhibo Sun
In ground return mode of high-voltage direct current (HVDC) transmission, direct current is injected into the soil through a ground electrode, causing ground potential rise in different areas and direct current at the neutral point of transformers. Earth surface potential (ESP) and neutral current are closely related to the 3-D structure of soil, but few studies treat the soil three dimensionally when calculating these two parameters. In this article, a 3-D resistor network (RN) is developed to construct the soil model, and a soil–grid unified circuit model is proposed to simplify the calculation of neutral current. The RN method is verified by calculating ESP of a horizontal multilayer soil model and contrasting the result with that of CDEGS software. The feasibility and accuracy of the soil–grid unified circuit model is demonstrated through comparing neutral currents of two substations with the results calculated by finite-element method (FEM). The influence of resistivity changes in a water-bearing fault on ESP and neutral current is specifically analyzed using RN method and FEM to prove the necessity of considering the 3-D complex soil structure. The results of this article contribute to the simulation of DC distribution of wide-area HVDC transmission in complex soil structures.