Huang Jin-ying

Fuzzy Controller Design of Autonomy Overtaking System

Based on the fuzzy control theory and taking vehicles overtaking process as the research objective, the fuzzy controller is designed and simulated. For the control strategy of intelligent vehicles, most research institutions construct the model according to the given moving trajectory, which has the disadvantages of low anti-jamming capability, great costs and lower response speed. The fuzzy control strategy for intelligent vehicles in this paper is a new dynamical fuzzy controller with three-input and three-output, and its control rule base is composed of 135 pieces of fuzzy reasoning rule. The simulation result proves that the control system of this dynamical fuzzy controller is obviously superior to the traditional system of non-fuzzy controller.

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.

Fault diagnosis of circuit board based on fault tree

PCB fault detection and positioning is always a complex and difficult work. This thesis designed a fault diagnosis system for PCB circuit, which uses voltage signals as incentive signals and the voltage or current response signals as the output. Fault tree is established and fault searching and positioning method introduced fault dictionary analysis according to the fault tree. Through simulation analysis, it is indicated that fault diagnosis of circuit board based fault tree analysis is feasible.PCB fault detection and positioning is always a complex and difficult work. This thesis designed a fault diagnosis system for PCB circuit, which uses voltage signals as incentive signals and the voltage or current response signals as the output. Fault tree is established and fault searching and positioning method introduced fault dictionary analysis according to the fault tree. Through simulation analysis, it is indicated that fault diagnosis of circuit board based fault tree analysis is feasible.

Fault Characteristic Extracting Based on PSO

The fault symptoms of the gearbox can be indicated by different characteristic parameters. In the working process of gearbox, because the responding signal is very complex, it is difficult to extract its sensitive fault attributive information. The sensitivity of the fault degree, fault position and fault type is very different, so the characteristic parameter set constructed by the traditional characteristic extraction and analysis method is voluminous. Therefore, how to define the reliable and effective fault characteristic parameter set and how to optimize the parameter set by the sensitivity are problems should be solved to realize real time and online fault diagnosis. In this paper, the characteristic extractive method base on PSO is presented for fault characteristic selection of gearbox. Then the technology is applied to analyze and process the vibration responding signal of gearbox, extract and optimize the fault characteristic parameter set. Finally the parameter set osculating related to the gearboxs fault is constructed and it is used to the fault diagnosis. It proves the diagnosis result that PSO algorithm has good effectiveness, higher diagnosis precision and fast optimal speed than the traditional genetic algorithm.

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.

Research of fault-characteristic extractive technology based on particle swarm optimization

In the work process of gearbox, because the responding signal is very complex, it is difficult to extract its sensitive fault attributive information. The sensitivity of the fault degree, fault position and fault type is very different, so the characteristic parameter set constructed by the traditional characteristic extraction and analysis method is voluminous. Therefore, how to define the reliable and effective fault characteristic parameter set and how to optimize the parameter set by the sensitive degree are the await solved problems to realize real time and online fault diagnosis. In this paper, the characteristic extractive method base on particle swarm optimization (PSO) is presented for the problem of gearbox failure characteristic selection. Then the technology is applied to analyze and process the vibration responding signal of gearbox, extract and optimize the fault characteristic parameter set. Finally the parameter set nearly related to the gearboxs fault is constructed and it is used to the fault diagnosis. It proves validity of the diagnosis result that PSO algorithm has good effectiveness, higher diagnosis precision and fast optimal speed than the traditional genetic algorithm, The experimental result indicates that the wavelet neural network training method based on the PSO algorithm is an effective training algorithm, and meanwhile it is also an available approach to solve fault diagnosis problems.

A study of intelligent vehicle motion control system based on multi-sensor information fusion

Aiming at the randomness of intelligent vehicle data collection and the huge difference between the data collected which may easily result in information conflict, missing of effective data and large decreasing of effective data, method of distribution chart is used to eliminate negligent errors on the basis of multi-sensor data collecting and data is processed by adaptive weighted information fusion algorithm in the mean time to obtain more reliable distance information. Experiment shows this method improves the accuracy of the distance measuring system and eliminates effectively errors caused by sensor failure.

The application of CPSO on measurement point optimization

In order to solve the problem of sensors placement in gearbox faults detection, a method of measurement point optimization based on particle swarm optimization (PSO) is discribed. The fitness of PSO is set up based on analysis on the modal assurance criterion(MAC) for measurement point optimization. After setting up finite element model and proceeding modal analysis of gearbox, particle swarm optimization with dynamic accelerating constants (CPSO) is applied to optimize and dertermin the numbers and locations of sensors for gearbox. In optimal process the fitness function is taken as evaluation object. The method discribed in this paper is proved to be feasible by an example of gearbox fault diagnosis. The fault identified accuracy after measurement point optimization is improved.

Gearbox feature extraction and fault diagnosis based on blind source separation

In this paper, SOBI blind source separation algorithm is applying to extract the fault feature of gearbox vibration signal. It is Tested and verified by BP neural network for fault diagnosis. The result shows that the fault feature extraction method based on blind source separation for gearbox fault diagnosis is very effective.