Recently, wavelet neural networks have become a popular tool for non-linear functional approximation. Wavelet neural networks, which basis functions are orthonormal scalling functions, are more suitable in approximati...Recently, wavelet neural networks have become a popular tool for non-linear functional approximation. Wavelet neural networks, which basis functions are orthonormal scalling functions, are more suitable in approximating to function. Based on it, approximating to NLAR(p) with wavelet neural networks is studied.展开更多
To improve the prediction accuracy of micro-electromechanical systems(MEMS)gyroscope random drift series,a multi-scale prediction model based on empirical mode decomposition(EMD)and support vector regression(SVR)is pr...To improve the prediction accuracy of micro-electromechanical systems(MEMS)gyroscope random drift series,a multi-scale prediction model based on empirical mode decomposition(EMD)and support vector regression(SVR)is proposed.Firstly,EMD is employed to decompose the raw drift series into a finite number of intrinsic mode functions(IMFs)with the frequency descending successively.Secondly,according to the time-frequency characteristic of each IMF,the corresponding SVR prediction model is established based on phase space reconstruction.Finally,the prediction results are obtained by adding up the prediction results of all IMFs with equal weight.The experimental results demonstrate the validity of the proposed model in random drift prediction of MEMS gyroscope.Compared with a single SVR model,the proposed model has higher prediction precision,which can provide the basis for drift error compensation of MEMS gyroscope.展开更多
In this study, seven pinned double-rectangular tube assembled buckling-restrained brace （DRT-ABRB） specimens were experimentally charaeterised by means of an axial cyclic test. The core member of the specimens was a...In this study, seven pinned double-rectangular tube assembled buckling-restrained brace （DRT-ABRB） specimens were experimentally charaeterised by means of an axial cyclic test. The core member of the specimens was a single flat-plate. Two rectangular tubes were assembled using high strength bolts to form an external restraining member. Each rectangular tube was composed of an external steel channel and a cover plate. A gap or thin rubber filler was set between the core and the external restraining member to form an unbonded layer. The influence of several design parameters on the failure mode and energy dissipation capacity of the ABRB was investigated, including the height of the core wing plate, thickness of the external cover plate, and height of the external channel flange. This experimental study demonstrated that a local pressure-bearing failure at the end of the external member arises when the external cover plate is too thin or if the end construction detail is unreasonable. When the end rotations of the DRT-ABRB were restricted, the hysteretic performance was shown to be superior to that of a pure pinned DRT-ABRB. Finally, all the tested DRT-ABRBs exhibited excellent energy dissipation performance which amply satisfied existing regulation requirements.展开更多
文摘Recently, wavelet neural networks have become a popular tool for non-linear functional approximation. Wavelet neural networks, which basis functions are orthonormal scalling functions, are more suitable in approximating to function. Based on it, approximating to NLAR(p) with wavelet neural networks is studied.
基金National Natural Science Foundation of China(No.61427810)。
文摘To improve the prediction accuracy of micro-electromechanical systems(MEMS)gyroscope random drift series,a multi-scale prediction model based on empirical mode decomposition(EMD)and support vector regression(SVR)is proposed.Firstly,EMD is employed to decompose the raw drift series into a finite number of intrinsic mode functions(IMFs)with the frequency descending successively.Secondly,according to the time-frequency characteristic of each IMF,the corresponding SVR prediction model is established based on phase space reconstruction.Finally,the prediction results are obtained by adding up the prediction results of all IMFs with equal weight.The experimental results demonstrate the validity of the proposed model in random drift prediction of MEMS gyroscope.Compared with a single SVR model,the proposed model has higher prediction precision,which can provide the basis for drift error compensation of MEMS gyroscope.
基金Project supported by the National Natural Science Foundation of China （Nos. 51178243 and 51608014）, the China Postdoctoral Science Foundation （No. 2015M580030）, and the Natural Science Foundation of Beijing, China （No. 8131002）
文摘In this study, seven pinned double-rectangular tube assembled buckling-restrained brace （DRT-ABRB） specimens were experimentally charaeterised by means of an axial cyclic test. The core member of the specimens was a single flat-plate. Two rectangular tubes were assembled using high strength bolts to form an external restraining member. Each rectangular tube was composed of an external steel channel and a cover plate. A gap or thin rubber filler was set between the core and the external restraining member to form an unbonded layer. The influence of several design parameters on the failure mode and energy dissipation capacity of the ABRB was investigated, including the height of the core wing plate, thickness of the external cover plate, and height of the external channel flange. This experimental study demonstrated that a local pressure-bearing failure at the end of the external member arises when the external cover plate is too thin or if the end construction detail is unreasonable. When the end rotations of the DRT-ABRB were restricted, the hysteretic performance was shown to be superior to that of a pure pinned DRT-ABRB. Finally, all the tested DRT-ABRBs exhibited excellent energy dissipation performance which amply satisfied existing regulation requirements.
