排序方式: 共有14条查询结果,搜索用时 15 毫秒
11.
Liu Jixue Tang Dengbin YangYingzhao 《中国航空学报》2007,20(4):313-319
The process of evolution, especially that of nonlinear evolution, of C-type instability of laminar-turbulent flow transition in nonparallel boundary layers are studied by means of a newly developed method called parabolic stability equations (PSE). Initial conditions, which are very important for the nonlinear problem, are investigated by computing initial solution of the harmonic waves, modifying the mean-flow-distortion, and giving initial value of TS wave and its subharmonic waves at initial station by solving linear PSE. A numerical method with high-order accuracy are developed in the text, the key normalization conditions in the PSE are satisfied, and nonlinear PSE are solved efficiently and implemented stably by the spatial marching. It has been shown that the computed process of nonlinear evolution of C-type instability in Blasius boundary layer is in good agreement with the experimental results. 相似文献
12.
Fault diagnosis of bearings based on deep separable convolutional neural network and spatial dropout
Bearing pitting, one of the common faults in mechanical systems, is a research hotspot in both academia and industry. Traditional fault diagnosis methods for bearings are based on manual experience with low diagnostic efficiency. This study proposes a novel bearing fault diagnosis method based on deep separable convolution and spatial dropout regularization. Deep separable convolution extracts features from the raw bearing vibration signals, during which a 3 × 1 convolutional kernel with a one-s... 相似文献
13.
适用于全包线的航空发动机BP网络模型的动态辨识 总被引:3,自引:2,他引:3
为克服传统的发动机动态模糊辨识中存在的辨识精度低,辨识模型应用范围窄等不足,把对非线性系统具有高度逼近能力的神经网络应用于航空发动机动态特性的辨识,从而为发动机动态辨识开辟更为广阔的道路,采用均方差归一法的处理方法和BP算法的改进算法-输出端动量BP地,以某型发动机在飞行包线内某一飞行条件下的数据作为学习样本,辨识了发同的神经网络模型,在全包线范围内对该模型进行检验,结果表明,所得的发动机动态模型在全包线内都有很高的逼近精度,而且对噪声有很强的抑制能力。 相似文献
14.