Temperature Estimation of a PMSM using a Feed-Forward Neural Network

被引:5
作者
Schueller, Stephan [1 ]
Azeem, Mohammad [1 ]
Von Hoegen, Anne [1 ]
De Doncker, Rik W. [1 ]
机构
[1] Rhein Westfal TH Aachen, Inst Power Elect & Elect Drives ISEA, Campus Blvd 89, D-52074 Aachen, Germany
来源
2022 25TH INTERNATIONAL CONFERENCE ON ELECTRICAL MACHINES AND SYSTEMS (ICEMS 2022) | 2022年
关键词
machine learning; temperature estimation; permanent magnet synchronous motor; neural networks;
D O I
10.1109/ICEMS56177.2022.9983072
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Temperature monitoring of electrical machines is crucial to exploit the full potential of the machine while protecting it against thermal overload. Accordingly, the development of suitable monitoring methods has been an important research focus in recent decades. Especially in the automotive industry, precise methods for temperature monitoring without additional hardware are important since high thermal utilization is necessary to reach highest power densities. Artificial intelligence techniques such as neural networks have shown promise in recent years for estimating temperatures in electrical machines. In this work, a feed-forward neural network is implemented to estimate the temperature of a permanent magnet synchronous machine based on the operating point and past temperature values. The performance of the thermal monitoring method using feed-forward neural networks is evaluated by comparison with measurements.
引用
收藏
页数:6
相关论文
共 15 条
[1]  
Brochu E., 2010, arXiv
[2]   MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].
HORNIK, K ;
STINCHCOMBE, M ;
WHITE, H .
NEURAL NETWORKS, 1989, 2 (05) :359-366
[3]  
Keras, NAD
[4]   Data-Driven Permanent Magnet Temperature Estimation in Synchronous Motors With Supervised Machine Learning: A Benchmark [J].
Kirchgaessner, Wilhelm ;
Wallscheid, Oliver ;
Boecker, Joachim .
IEEE TRANSACTIONS ON ENERGY CONVERSION, 2021, 36 (03) :2059-2067
[5]  
Kirchgassner W., 2021, ELECT MOTOR TEMPERAT
[6]  
Klein A., 2016, arXiv:1605.07079
[7]  
Qi F., 2014, 2014 17 INT C ELECT
[8]  
Qi F., 2016, PROC 20 INT C ELECT, P1
[9]  
Qi F., 2014, 7 IET INT C POWER EL
[10]  
Qi F., 2015, 2015 IEEE INT ELECT