Probabilistic Distribution Modeling of Crosstalk in Multi-Conductor Transmission Lines via Maximum Entropy Method

被引：6

作者：

Gao, Le ^{[1
]}

Yu, Quanyi ^{[1
]}

Wu, Dingchao ^{[2
]}

Wang, Tianhao ^{[1
]}

Yu, Xianli ^{[3
]}

Chi, Yaodan ^{[4
]}

Zhang, Tong ^{[5
]}

机构：

[1] Jilin Univ, Coll Instrumentat & Elect Engn, Changchun 130021, Jilin, Peoples R China

[2] FAW Volkswagen Automot Co Ltd, EMC Ctr, Changchun 130013, Jilin, Peoples R China

[3] Jilin Univ, Coll Geoexplorat Sci & Technol, Changchun 130021, Jilin, Peoples R China

[4] Jilin Jianzhu Univ, Jilin Prov Key Lab Architectural Elect & Comprehe, Changchun 130118, Jilin, Peoples R China

[5] China Mobile Commun Corp Jilin Co Ltd, Changchun Branch, Network Dept, Changchun 130000, Jilin, Peoples R China

来源：

IEEE ACCESS | 2019年 / 7卷

基金：

中国国家自然科学基金; 中国博士后科学基金;

关键词：

Crosstalk; probabilistic modeling; multi-conductor transmission lines (MTL); maximum entropy (MaxEnt) method; full factorial numerical integration (FFNI); sparse grid numerical integration (SGNI); EFFICIENT; DESIGN;

D O I：

10.1109/ACCESS.2019.2929203

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A novel statistical method, referred to as the maximum entropy (MaxEnt) method is proposed in this paper for effective probabilistic modeling of crosstalk in multi-conductor transmission lines (MTLs). The principle of the MaxEnt method states that for the given information constraints, the probability distribution that has the MaxEnt is considered to be the most unbiased and reasonable one. As for low- and high-dimensional spaces composed of the input random variables in MTL, the statistical moments of crosstalk required by the MaxEnt method as its information constraints are obtained through full-factorial numerical integration and sparse grid numerical integration, respectively. Then, a probability distribution model of crosstalk in MTL is established based on the MaxEnt method. Compared with the conventional Monte Carlo method, the proposed method can not only accurately predict the probability distribution and statistics of crosstalk in MTL but also considerably increases the computational efficiency. Therefore, the MaxEnt method is effective in modeling the probability distribution of crosstalk in MTL.

引用

页码：103650 / 103661

页数：12

共 35 条

[1] Entropy methods for joint distributions in decision analysis
Abbas, AE
[J]. IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT, 2006, 53 (01) : 146 - 159
[2] [Anonymous], 1964, Handbook of mathematical functions
[3] [Anonymous], P 11 INT WORKSH MAX
[4] [Anonymous], 1963, Sov. Math. Dokl
[5] High dimensional polynomial interpolation on sparse grids
Barthelmann, V
Novak, E
Ritter, K
[J]. ADVANCES IN COMPUTATIONAL MATHEMATICS, 2000, 12 (04) : 273 - 288
[6] Characterisation of crosstalk in terms of mean value and standard deviation
Bellan, D
Pignari, SA
Spadacini, G
[J]. IEE PROCEEDINGS-SCIENCE MEASUREMENT AND TECHNOLOGY, 2003, 150 (06) : 289 - 295
[7] Efficient Estimation of Crosstalk Statistics in Random Wire Bundles With Lacing Cords
Bellan, Diego
Pignari, Sergio A.
[J]. IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY, 2011, 53 (01) : 209 - 218
[8] CICCOLELLA A, 1995, EMC - A GLOBAL CONCERN : IEEE 1995 INTERNATIONAL SYMPOSIUM ON ELECTROMAGNETIC COMPATIBILITY, SYMPOSIUM RECORD, P51, DOI 10.1109/ISEMC.1995.523517
[9] Uncertainty Quantification of Crosstalk Using Stochastic Reduced Order Models
Fei, Zhouxiang
Huang, Yi
Zhou, Jiafeng
Xu, Qian
[J]. IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY, 2017, 59 (01) : 228 - 239
[10] Maximum Crosstalk Estimation in Lossless and Homogeneous Transmission Lines
Halligan, Matthew S.
Beetner, Daryl G.
[J]. IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2014, 62 (09) : 1953 - 1961

← 1 2 3 4 →