Wei Xiuye

Research on Fault Diagnosis of Gearbox Based on Particle Swarm Optimization Algorithm

In this paper, base on studying learning rate of PSO, in order to adjust the social part and the cognition part proportions, learning rate change linearly with velocity-formula evolving is made; the BP neural network PSO training heavily increases the congruence speed of the networks to avoid involving local extremum. According to actual data of two levels gearbox in vibration lab, signals are analyzed and their feature values are abstracted. By applying trained BP neural networks to diagnosing gearbox faults got sound effect

Fault feature extraction based on KPCA optimized by PSO algorithm

For blindness of the parameter settings in kernel principal component analysis (KPCA), kernel function parameter optimized by particle swarm optimization algorithm (PSO) is proposed, and KPCA is applied to feature extraction. The mathematical model of kernel function parameter optimized is constructed firstly, then the particle swarm optimization algorithm with adaptive accelerate (CPSO) is used to optimize it. The optimized KPCA is applied to feature extraction of gearbox typical faults. The results indicate that KPCA after parameter optimized can effectively reduce the dimensions of feature vector of gearbox, and it has a better fault classification performance than linear principal component analysis (PCA). This method has an advantage in nonlinear feature extraction of mechanical failure signal.

Analysis of fluid-structure interaction vibration response for vibration system excited by wave exciter

The hydraulic vibration system excited by wave exciter is established. After analysis on Poisson coupling and Junction coupling in excited vibration system 4-eqation dynamics model on liquid flowing, pressure fluctuation and pipe vibration is adopted, and numerical analysis of fluid–solid coupled vibration system excited by wave exciter is carried out by using method of characteristics. The results of numerical analysis show that pressure wave velocity is descending, and vibration periodicity prolongs because of Poisson coupling; at the same time, stress wave velocity of pipe is increasing, and vibration periodicity is shortened. The results of numerical analysis agree with those of experiment.

Research of optimal placement of gearbox sensor based on particle swarm optimization

This paper discusses the optimization layout of the acceleration sensor and application of particle swarm optimization (PSO) algorithm to solve the fitness problems of such optimization. Based on the gearbox finite element modeling and the result of modal analysis, use the particle swarm optimization with adaptive velocity (VPSO) algorithm, and take the two kinds of fitness function as evaluation goal, has realized the optimization and positioning of gearbox sensor layout, analyzed optimization result.

Study of gearbox fault diagnosis based on a modified PSO algorithm

Particle swarm optimization algorithm with adaptive velocity (VPSO) has been proposed, based on the moving maximum limited velocity set in original particle swarm optimization (PSO) algorithm, in this paper. The testing results by neural network show that this algorithm is better than original PSO in convergent speed and accuracy, and its parameters selection is flexible and is easily realized. The modified algorithm has been applied to fault diagnosis system of neural network for an experimental gearbox, and compared to the PSO and back propagation neural network (BP) algorithm. The conclusion is that VPSO applying to fault diagnosis system not only has higher discrimination for gearbox faults, but also greatly improves the accuracy and efficiency of fault diagnosis.

Particle swarm optimization algorithm with adaptive velocity and its application to fault diagnosis

This paper introduces a particle swarm optimization algorithm with adaptive velocity (VPSO), in which a moving maximum limited velocity is set in original particle swarm optimization (PSO) algorithm to improve the performance of the PSO. The test results by neural network show that this algorithm is better than original PSO in convergent speed and accuracy, and its parameters selection is flexible and is easily realized. The modified algorithm has been applied to fault diagnosis system of neural network for an experimental gearbox, and compared with the PSO and BP algorithm. The conclusion is that VPSO applying to fault diagnosis system not only has higher discrimination for gearbox faults, but also greatly improves the accuracy and efficiency of fault diagnosis.

Study of fault feature extraction based on KPCA optimized by PSO algorithm

For blindness of the parameter settings in kernel principal component analysis (KPCA), kernel function parameter optimized by particle swarm optimization (PSO) algorithm is proposed, and KPCA is applied to feature extraction in fault diagnosis. The mathematical model of kernel function parameter optimized is constructed firstly, then the PSO algorithm with adaptive accelerate (CPSO) is used to optimize it. The optimized KPCA is applied to feature extraction of gearbox typical faults. The results indicate that KPCA after parameter optimized can effectively reduce the dimensions of feature vector of gearbox, and it has a better fault classification performance than linear principal component analysis (PCA). This method has an advantage in nonlinear feature extraction of mechanical failure signal.

Analysis of fluctuation mechanics for excited vibration system by pressing transient flow

In this paper, the fluctuation mechanics produced by pressing transient flow in a pipeline system and its propagation character have been analyzed firstly, and then excited vibration system by pressing transient flow has been calculated by classical hydraulic fluctuation equation, in which the controlled principle of pressure and fluid velocity are researched. After establishing excited vibration test system by pressing transient flow, the parameters such as pressure, acceleration and amplitude of vibration at different measuring point in various working condition are measured and analyzed by advanced signal processing technology. The results from theory and test prove that amplitude of pressure, vibration frequency and displacement, velocity of excited vibration system by pressing transient flow are fully controlled and regulated by setting frequency of wave exciter and system pressure.

Notice of Retraction Study on fault diagnosis of adaptive collaborative inertia weighted velocity particle swarm optimization

JZQ250 gear box is studied in order to make real-time monitoring and fault diagnostics for the gearbox in engineering. With dynamic maximum speed limit set in particle swarm optimization (PSO), a method of diagnosing the gearboxs fault, i.e., the adaptive collaborative weighted velocity PSO (WVPSO) is suggested to train BP neural network. The fault diagnosis is made with the monitoring characteristic values as the gearboxs condition monitoring values obtained by analyzing the time-domain parameters, and with fault feature vectors as the input vectors of neural network, the results of which are compared with those of the BP algorithm. The results show that the WVPSO algorithm has a faster convergence speed, and is quicker to converge to the optimal solution in the learning training of the neural network. Thus, this algorithm has higher recognition accuracy for gearbox faults, the neural network model established for fault diagnosis is somewhat universal, and the accuracy and efficiency for fault diagnosis are comparatively high.