http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Kumar, Sunil,Zhao, Wenliang,Du, Zhentao S.,Lipo, Thomas,Kwon, Byung-Il IEEE 2015 IEEE transactions on magnetics Vol.51 No.11
<P>This paper focuses on the design and the analysis of an ultrahigh speed axial-flux permanent magnet (AFPM) machine for an aerospace flywheel energy storage system. The superiority of the proposed AFPM machine is the material-efficient PM shape, which contributes to obtain a sinusoidal back electromotive force (back EMF) and, hence, reduces the torque pulsations of the machine such as torque ripple. The harmonics present in back EMF have a large influence on iron loss and torque pulsations, which are always unacceptable in the applications involving the speed as high as 1 000 000 r/min. Analytical modeling is first performed to determine the PM shape for the proposed models. Then, the advantages of the proposed models are verified by comparing with the basic model with the conventional ring-shaped PMs using the 3-D finite-element method. The results show that the proposed models have a nearly ideal sinusoidal back-EMF waveform that significantly reduces the torque ripples compared with the basic model.</P>
Rapid warning of wind turbine blade icing based on MIV-tSNE-RNN
Zhiqiang Zhang,Bin Fan,Yong Liu,Peng Zhang,Jianguo Wang,Wenliang Du 대한기계학회 2021 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.35 No.12
A fast early warning algorithm for wind turbine blade icing based on a RNN model is proposed. Through wind turbine blade history data and labels as model input, the evaluation of raw m-dimension data through mean impact value (MIV) indices eliminates data with an MIV index of less than one; the remaining n-dimension data is reduced to x-dimension by the tSNE method; dimensional data is inputted into the RNN, and the model output is the icing state of the wind turbine blade in a certain future period. Based on the SCADA data from a wind field, the model was verified by an example. Using a certain example case, if the model training data is 10 4 orders of magnitude, using the MIV-tSNE-RNN algorithm, the prediction accuracy can reach approximately 72 %; compared with the RNN model, the prediction accuracy is improved by approximately 150 % while reducing the algorithm running time by approximately 45 %. If the amount of data exceeds 10 4 orders of magnitude, using the MIVtSNE-RNN algorithm, the prediction accuracy is improved by approximately 100 %. This algorithm can provide accurate and rapid prediction results for wind turbine blade icing according to actual needs.