Adaptive Real-Time Hybrid Neural Network-Based Device-Level Modeling for DC Traction HIL Application

被引：3

作者：

Liang, Tian ^{[1
]}

Huang, Zhen ^{[1
]}

Dinavahi, Venkata ^{[1
]}

机构：

[1] Univ Alberta, Dept Elect & Comp Engn, Edmonton, AB T6G 2V4, Canada

来源：

IEEE ACCESS | 2020年 / 8卷

基金：

加拿大自然科学与工程研究理事会;

关键词：

Behavioral model; device-level transients; field programmable gate array (FPGA); hardware-in-the-loop (HIL); insulated-gate bipolar transistor (IGBT); k -nearest neighbors (k NN); recurrent neural network (RNN); real-time systems; POWER ELECTRONICS; IMPLEMENTATION;

D O I：

10.1109/ACCESS.2020.2986298

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

DC traction drive systems require high-frequency switching in the power converter whose device-level switching transients have a significant impact on the accuracy of hardware-in-the-loop emulation. Real-time device-level emulation has high computation demand for calculating the switch on and off transients. This paper introduces a new method to estimate the switching transients by utilizing artificial intelligence in the hardware design. In the hybrid neural network, the k -nearest neighbors (k NN) concept and the recurrent neural network (RNN) have been employed to emulate the transient waveforms in the DC traction drive. The k NN module classifies the switching states while the RNN module predicts the transient current for a specific condition. This work also proves that the classification of the input switching states with the help of k NN can play an essential role. The hardware implementation of the study case can be executed at a time-step of 100 ns with device-level transients. The results have been validated by PSCAD/EMTDCr at system-level and SaberRDr at device-level.

引用

页码：69543 / 69556

页数：14

共 31 条

[1]

[Anonymous], TECHN INF INF IGBT M

[2]

[Anonymous], 2009, Neural networks and learning machines

[3]

Atkinson K. E., 1989, An Introduction to Numerical Analysis, V2nd ed., DOI DOI 10.1002/0471667196.ESS1837

[4] A 3-D-Lumped Thermal Network Model for Long-Term Load Profiles Analysis in High-Power IGBT Modules [J].

Bahman, Amir Sajjad ;

Ma, Ke ;

Ghimire, Pramod ;

Iannuzzo, Francesco ;

Blaabjerg, Frede .

IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS, 2016, 4 (03) :1050-1063

[5] Neural network applications in power electronics and motor drives- An introduction and perspective [J].

Bose, Bimal K. .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2007, 54 (01) :14-33

[6] Managing the Italian high-speed railway network: Provisions for reducing interference between electric traction systems [J].

Caracciolo F. ;

Fumi A. ;

Cinieri E. .

IEEE Electrification Magazine, 2016, 4 (03) :42-47

[7] Finite-Element Modeling and Optimization-Based Parameter Extraction Algorithm for NPT-IGBTs [J].

Chibante, Rui ;

Araujo, Armando ;

Carvalho, Adriano .

IEEE TRANSACTIONS ON POWER ELECTRONICS, 2009, 24 (5-6) :1417-1427

[8] Recurrent-neural-network-based implementation of a programmable cascaded low-pass filter used in stator flux synthesis of vector-controlled induction motor drive [J].

da Silva, LEB ;

Bose, BK ;

Pinto, JOP .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 1999, 46 (03) :662-665

[9] Direct Neural-Network Hardware-Implementation Algorithm [J].

Dinu, Andrei ;

Cirstea, Marcian N. ;

Cirstea, Silvia E. .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2010, 57 (05) :1845-1848

[10] Reconfigurable Real-Time Hardware-in-the-Loop Environment for Automotive Electronic Control Unit Testing and Verification [J].

Enisz, Krisztian ;

Fodor, Denes ;

Szalay, Istvan ;

Kovacs, Laszlo .

IEEE INSTRUMENTATION & MEASUREMENT MAGAZINE, 2014, 17 (04) :31-36

← 1 2 3 4 →