Axis orbit is an important characteristic to be used in the condition monitoring and diagnosis system of rotating machine. The wavelet moment has the invariant to the translation, scaling and rotation. A method, which...Axis orbit is an important characteristic to be used in the condition monitoring and diagnosis system of rotating machine. The wavelet moment has the invariant to the translation, scaling and rotation. A method, which uses a neural network based on Radial Basis Function (RBF) and wavelet moment invariants to identify the orbit of shaft centerline of rotating machine is discussed in this paper. The principle and its application procedure of the method are introduced in detail. It gives simulation results of automatic identification for three typical axis orbits. It is proved that the method is effective and practicable.展开更多
A new method is presented in this paper for fitting Voltage-to-Frequency Converter (VFC's) output functions by using Functionally Connected High-order Neural Networks (FCHNN). The nonlinear estimation is implement...A new method is presented in this paper for fitting Voltage-to-Frequency Converter (VFC's) output functions by using Functionally Connected High-order Neural Networks (FCHNN). The nonlinear estimation is implemented when the VFC110 is used at a full-scale output frequency of 4 MHz. Two kinds of on-line dynamic calibrating circuits are designed to improve the sampling precision. This method can also be applied to different industrial areas.展开更多
基金the Programming of the National Ministry of Education(20002175)
文摘Axis orbit is an important characteristic to be used in the condition monitoring and diagnosis system of rotating machine. The wavelet moment has the invariant to the translation, scaling and rotation. A method, which uses a neural network based on Radial Basis Function (RBF) and wavelet moment invariants to identify the orbit of shaft centerline of rotating machine is discussed in this paper. The principle and its application procedure of the method are introduced in detail. It gives simulation results of automatic identification for three typical axis orbits. It is proved that the method is effective and practicable.
文摘A new method is presented in this paper for fitting Voltage-to-Frequency Converter (VFC's) output functions by using Functionally Connected High-order Neural Networks (FCHNN). The nonlinear estimation is implemented when the VFC110 is used at a full-scale output frequency of 4 MHz. Two kinds of on-line dynamic calibrating circuits are designed to improve the sampling precision. This method can also be applied to different industrial areas.
