http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Predicting wind-induced structural response with LSTM in transmission tower-line system
Jiayue Xue,Ge Ou 국제구조공학회 2021 Smart Structures and Systems, An International Jou Vol.28 No.3
Wind-induced dynamic response of the nonlinear structure is critical for the structural safety and reliability. The traditional approaches for this response including observation or simulation focus on the structural health monitoring, the experiment, or finite element model development. However, all these approaches require high cost or computational investment. This paper proposes to predict the wind-induced dynamic response of the nonlinear structure with a novel deep learning approach, LSTM, and applies this in a structural lifeline system, the transmission tower-line system. By constructing the optimized LSTM architectures, the proposed method applies to both the linear structure, the single transmission tower and the nonlinear structure, the transmission tower-line system, with promising results for the dynamic and extreme response prediction. It can conclude that the layers and the hidden units have a strong impact on the LSTM prediction performance, and with proper training data set, the computational time can significantly decrease. A comparison surrogate model developed by CNN is also utilized to demonstrate the robustness of the LSTM-based surrogate model with limited data scale.
Fatigue life prediction of rear axle using time series model
Yimin SHAO,Jieping FANG,Liang Ge,Jiafu OU,Hao JU,Ying MA 제어로봇시스템학회 2008 제어로봇시스템학회 국제학술대회 논문집 Vol.2008 No.10
The rear axle is one of the key parts of the automobile, lots failure of rear axle resulted from fatigue failure of the spiral bevel gears. A new method is proposed to solve the problem of accurately predicting the fatigue life of spiral bevel gears in rear axle. The method uses the recurrence tracing and difference method to improve the Autoregressive Moving Average (ARMA) model prediction accuracy, which uses variables determined from on-line measurements to characterize the state of the deterioration rear axle. The experimental results show the proposed method has relatively high prediction accuracy.
K-doping effect of the superconductivity in K2xFeTe1-xSx (0.07 ≤ x ≤ 0.3)
Cheng Cheng,Zhenjie Feng,Qing Li,Tao Li,Qiang Hou,Fei Chen,Zhongmin Ou,Jun-Yi Ge,Shixun Cao,Jincang Zhang 한국물리학회 2019 Current Applied Physics Vol.19 No.4
Bulk samples of K doping K2xFeTe1-xSx with x=0.07, 0.1, 0.2, 0.3 are successfully prepared by using easy-to-use stable compound K2S as the reactant. The lattice constant calculated from X-ray diffraction patterns indicate that K ions enter the Fe-Te-S layers. K doping is beneficial enhance the superconductivity transition temperature from the R-T curves. The apparent diamagnetic signal is observed in M-T curves when the content of K is smaller than 0.1. However, differential curves (dM/dT) in K-rich samples appear sharp slope mutations, which means that the Meissner effect signal is covered by the increased excess ferromagnetic ions. The number of excess Fe magnetic ions is proportional to K content, which may play an important role in determining the superconductivity.