Real-Time Deep Learning at the Edge for Scalable Reliability Modeling of Si-MOSFET Power Electronics Converters

被引:49
作者
Baharani, Mohammadreza [1 ]
Biglarbegian, Mehrdad [1 ]
Parkhideh, Babak [1 ]
Tabkhi, Hamed [1 ]
机构
[1] Univ N Carolina, Elect & Comp Engn Dept, Energy Prod & Infrastruct Ctr, Charlotte, NC 28223 USA
关键词
Deep learning; high-frequency power converter; long short-term memory (LSTM); MOSFET; reliability modeling; DESIGN;
D O I
10.1109/JIOT.2019.2896174
中图分类号
TP [自动化技术、计算机技术];
学科分类号
080201 [机械制造及其自动化];
摘要
With the significant growth of advanced high-frequency power converters, online monitoring and active reliability assessment of power electronic devices are extremely crucial. This paper presents a transformative approach, named deep learning reliability awareness of converters at the edge (Deep RACE), for real-time reliability modeling and prediction of high-frequency MOSFET power electronic converters. Deep RACE offers a holistic solution which comprises algorithm advances, and full system integration (from the cloud down to the edge node) to create a near real-time reliability awareness. On the algorithm side, this paper proposes a deep learning algorithmic solution based on stacked long short-term memory for collective reliability training and inference across collective MOSFET converters based on device resistance changes. Deep RACE also proposes an integrative edge-to-cloud solution to offer a scalable decentralized devices-specific reliability monitoring, awareness, and modeling. The MOSFET convertors are Internet-of-Things (IoT) devices which have been empowered with edge real-time deep learning processing capabilities. The proposed Deep RACE solution has been prototyped and implemented through learning from MOSFET data set provided by NASA. Our experimental results show an average miss prediction of 8.9% over five different devices which is a much higher accuracy compared to well-known classical approaches (Kalman filter and particle filter). Deep RACE only requires 26-ms processing time and 1.87-W computing power on edge IoT device.
引用
收藏
页码:7375 / 7385
页数:11
相关论文
共 35 条
[1]
Computationally Efficient, Real-Time, and Embeddable Prognostic Techniques for Power Electronics [J].
Alghassi, Alireza ;
Perinpanayagam, Suresh ;
Samie, Mohammad ;
Sreenuch, Tarapong .
IEEE TRANSACTIONS ON POWER ELECTRONICS, 2015, 30 (05) :2623-2634
[2]
Anderson JM, 2011, IEEE ENER CONV, P3920, DOI 10.1109/ECCE.2011.6064302
[3]
[Anonymous], 2005, ORNL/TM-2005/230, DOI DOI 10.2172/885985
[4]
[Anonymous], 2018, POWER ELECT HDB
[5]
[Anonymous], 2014, P ANN C PROGN HLTH M
[6]
[Anonymous], STRESS TEST QUAL AUT
[7]
High-level design space exploration of locally linear neuro-fuzzy models for embedded systems [J].
Baharani, Mohammadreza ;
Noori, Hamid ;
Aliasgari, Mohammad ;
Navabi, Zain .
FUZZY SETS AND SYSTEMS, 2014, 253 :44-63
[8]
Review of Internet of Things (IoT) in Electric Power and Energy Systems [J].
Bedi, Guneet ;
Venayagamoorthy, Ganesh Kumar ;
Singh, Rajendra ;
Brooks, Richard R. ;
Wang, Kuang-Ching .
IEEE INTERNET OF THINGS JOURNAL, 2018, 5 (02) :847-870
[9]
Celaya J.R., 2011, Proc. Annu. Conf. Progn. Heal. Manag. Soc, V2, P1
[10]
Celaya J. R., 2012, PROC ANN C PHM SOC, P1