Complete decoupling rebalance loop design of a micromachined electrostatically suspended gyroscope

A micromachined electrostatically suspended gyroscope(MESG)based on UV-LIGA microfabrication process was introduced.By close-loop control,the suspended rotor is kept in null position and through the torque rebalance loop,in which the output control voltages reflects the input angular velocity,a dual-axis input angular velocity can be measured simultaneously.First,the system model of MESG was established by dynamic analysis based on the torque analysis.Then,the rebalance loop under ideal condition is designed using modern control technique.The performance of the designed decoupling rebalance loop was compared with that of conventional proportional integral differential(PID)rebalance loop combined with the compensation loop.In order to realize the decoupling of the output voltages,a compensated decoupling matrix and its difference equation were presented and realized by a digital decoupling method employing digital signal processor(DSP).It was confirmed that the controller could realize the complete decoupling and improve the performance of the gyroscope,which includes merits of fast response speed,low overshoot and good dynamic performance,as the simulation results shown.At last,the circuit and digital realization scheme were given.

Automatic Product Image Classification with Multiple Support Vector Machine Classifiers

For the task of visual-based automatic product image classification for e-commerce,this paper constructs a set of support vector machine(SVM) classifiers with different model representations.Each base SVM classifier is trained with either different types of features or different spatial levels.The probability outputs of these SVM classifiers are concatenated into feature vectors for training another SVM classifier with a Gaussian radial basis function(RBF) kernel.This scheme achieves state-of-the-art average accuracy of 86.9%for product image classification on the public product dataset PI 100.