Papers by Author: Jing Kang

Abstract: A SVM(Support Vector Machine)-like framework provides a novel way to learn linear principal component analysis (PCA), which is easy to be solved and can obtain the unique global solution. SVM is good at classification and PCA features is introduced into SVM. So, a new recognition method based on hybrid PCA and SVM is proposed and used for a series of experiments on chatter gestation. The results of chatter gestation recognition and chatter prediction experiments are presented and show that the method proposed is effective.

Abstract: This paper proposes a gear fault diagnosis method based on cyclostationary degree and Hidden Markov Model (HMM) theory. By using the demodulation characteristic of cyclostationary degree for AM and FM signals, we extract the characteristic information of the gear working status. This information can be converted into sets of fault feature vector, which is used as the training sample or observed sample of HMM model for gear fault identification. Experimental results show that the gear fault diagnosis method has good recognition result for the four kinds of status of normal, broken teeth, pitting and wear gear.

Abstract: RETRACTED PAPER: A method of tool wear intelligence measure based on Discrete Hidden Markov Models (DHMM) is proposed to monitor tool wear and to predict tool failure. FFT features are first extracted from the vibration signal and cutting force in cutting process, and then FFT vectors are presorted and converted into integers by SOM. Finally, these codes are introduced to DHMM for machine learning and 3 models for different tool wear stage are built up. Pattern of HMM is recognised by calculating probability. The results of tool wear intelligence measure and pattern recognition of tool wear experiments show that the method is effective.

Abstract: Rotor Complex Fault Vibration signals are very hard to analysis since there are many frequencies lies in them. It needs new signal processing methods to deal with these problems. Empirical Mode Decomposition (EMD) is a non-stationary signal processing method developed recently. The frequency heterodyne EMD method can improve the frequency resolution of EMD by shifting the original frequencies to enlarge the frequencies ratio between components. It proves that the method can enhance the performance of EMD easily and effectively. The paper discusses the principle and steps of this method in detail and uses it to analyse rotor complex fault signals. The result shows that frequency heterodyne EMD method can separate different faults and detect the weaker faults in complex fault more effectively than that of normal EMD method.

Abstract: In order to improve form cutter accuracy in grinding process, a closed-loop control system was designed to accomplish adaptive control of constant force in grinding process. Since it is a complicated dynamic process with severe nonlinear and much stochastic disturbance, fuzzy adaptive controller was used which can adjust parameters online. By measuring grinding force, characteristic information of grinding process was acquired. Regulation factor of feed rate is determined by grinding force ratio, and force deviation and its change rate are used as evaluation indexes. Thus, adaptive control of constant force in grinding process is accomplished. Simulation and tool grinding test indicate that the system has high precision and stability, and reduces cutter error efficiently.

Abstract: In profile envelope process of form cutter for involute gear, the grinding depth is variable which causes grinding force to change on a large scale and the profile error of envelope to increase. To improve form cutter accuracy, a closed-loop control system was designed to accomplish control of envelope process. For complicated dynamic process, fuzzy controller is used to adjust parameters online. By measuring grinding force, characteristic information of grinding process is acquired. Regulation factor of feed rate is determined by grinding force ratio, force deviation and its change rate used as evaluation indexes. Thus, fuzzy control of constant force grinding process is accomplished. Simulation and cutter grinding test indicates that the system has high precision and stability, and reduces cutter error effectively.