With the development of manufacturing engineer,the aeroengine structure and operating condition have become more complex and the circumstance is generally under mal-condition with high temperature and pressure,so keep...
详细信息
With the development of manufacturing engineer,the aeroengine structure and operating condition have become more complex and the circumstance is generally under mal-condition with high temperature and pressure,so keeping its reliability and safety of airplane is *** effective method for aeroengine fault diagnosis using wavelet neural networks is *** wavelet transform can accurately detect and localize the characteristics of transient signal in time-frequency *** advantage of wavelet transform is in achieving flexible frequency resolution logarithmic time frequency bands,thus making it able to extract both high-frequency and low-frequency components from the vibration *** characteristic information obtained are input nodes of neural network for fault pattern *** mathematics model for aeroengine fault diagnosis is established and the improved optimization technique for neural network training algorithm is used to accomplish the network parameter *** means of enough experiment samples to train the neural network,the fault mode can be obtained from the network output ***,the robustness of wavelet network for fault diagnosis is *** results obtained from the application of the method on monitored data collected from a facility validate the utility of this approach.
The power system load equipment is more sensitive to power quality disturbances than equipment applied in the ***,the electric supply quality has become a major concern of electric utilities and end-users.A novel appr...
详细信息
The power system load equipment is more sensitive to power quality disturbances than equipment applied in the ***,the electric supply quality has become a major concern of electric utilities and end-users.A novel approach to detect and locate power quality disturbance in distributed power system combining wavelet transform with neural network is *** performing decomposition of transient waveform,the original signal is divided into two parts:the low-frequency and the high-frequency, corresponding to approximation part and details part *** paper aims at complex wavelet analysis, and then explores feature extraction of disturbance signal to obtain dynamic parameters,superior to real wavelet analysis *** characteristic vector obtained from wavelet decomposition coefficients are input data of neural network for power quality disturbance pattern *** improved training algorithm is used to complete the network parameter *** means of simulation and experimental data,the disturbance pattern can be obtained from the neural network *** simulation results show that the proposed method is effective for transient signal analysis,taking advantage of complex wavelet transform and neural network.
Radial Basis Function(RBF) networks are widely applied in function approximation,system identification,chaotic time series forecasting,*** use a RBF network,a training algorithm is absolutely necessary for determining...
详细信息
Radial Basis Function(RBF) networks are widely applied in function approximation,system identification,chaotic time series forecasting,*** use a RBF network,a training algorithm is absolutely necessary for determining the network *** this paper,we use Particle Swarm Optimization(PSO),a evolutionary search technique,to train RBF neural network and therefore apply PSO-trained RBF network in chaotic time series *** proposed method was test on Mackey-Glass model,and the results show that it can predict the time series quickly and precisely.
The growing concern for power quality issues from both utilities and power users is generated by proliferation of power electronic devices and nonlinear loads in power system ***,the techniques for power quality monit...
详细信息
The growing concern for power quality issues from both utilities and power users is generated by proliferation of power electronic devices and nonlinear loads in power system ***,the techniques for power quality monitoring and power disturbance mitigation are capturing increasing attention. A novel approach for the power quality disturbances recognition using wavelet transform and neural network is *** wavelet transform is used to complete feature extraction and can accurately localizes the characteristics of transient signal both in time and frequency *** feature vectors are input variables for neural network training and the neural network structure is designed for disturbance pattern recognition. Therefore,the wavelet network combines advantages of wavelet transformation for purposes of feature extraction and selection with the characteristic decision capabilities of neural network *** the training process,the wavelet network learns adequate decision functions and arbitrarily complex decision regions defined by the weight *** simulation results demonstrate the proposed method gives a new way for signal analysis and pattern recognition of power quality disturbances.
This paper proposes a new Sequential Minimal Optimization (SMO) algorithm for fast training the regression support vector machine (SVM), firstly gives brief introduction of regression support vector m
This paper proposes a new Sequential Minimal Optimization (SMO) algorithm for fast training the regression support vector machine (SVM), firstly gives brief introduction of regression support vector m
Weak classifiers selection plays an important role in face detection based on Ada Boost algorithmMore discriminative weak classifiers can not only reduce training time but also enhance classification accuracyIn this p...
详细信息
Weak classifiers selection plays an important role in face detection based on Ada Boost algorithmMore discriminative weak classifiers can not only reduce training time but also enhance classification accuracyIn this paper, a new weak classifiers selecting algorithm based on PSO is proposed to make improvement in weak classifier selectionFirst, we eliminate some less discriminative features in the feature formation stage to select weak classifiers, rather than select weak classifiers using all the featuresSecond, the weak classifiers are constructed by using PSO to select the best features and the best thresholds, and then combine these key weak classifiers into a more effective strong classifierExperimental results indicate that the method can effectively solve the problem of too much training time and gain higher training efficiency.
Artificial Neural Networks(ANNs)and Genetic algorithm(CA)are two techniques for mod- elling,optimisation and learning,each with own strengths and *** researchers have attempted to combine the two approaches and conclu...
详细信息
Artificial Neural Networks(ANNs)and Genetic algorithm(CA)are two techniques for mod- elling,optimisation and learning,each with own strengths and *** researchers have attempted to combine the two approaches and concluded that the GA-based ANNs learning algo- rithm is superior compared to the traditional training methods such as Levenberg-mardquardt and
Recognition of handwritten Chinese characters belongs to the pattern recognition problems in large scale. This paper firstly presents a geometrical representation of sphere neighborhood model, by which the training pr...
详细信息
Recognition of handwritten Chinese characters belongs to the pattern recognition problems in large scale. This paper firstly presents a geometrical representation of sphere neighborhood model, by which the training problem of neural network may be transformed into the geometrical covering problem of a point set. After the neural network separate boundary faces are analyzed, an improved training approach to feedforward neural network is introduced and neural network ensemble is also applied. The performance of the approach is tested with the handwritten Chinese characters recognition problem. Laboratorial results not only are satisfactory but also show that the proposed approach is effective in the pattern recognition problems in large scale.
作者：
H. TourajizadehS. ManteghiS. R. NekooAssistant professor
Department of Mechanical Engineering Faculty of Engineering Kharazmi University Tehran Iran M. Sc.
College of Computer and Mechatronics Engineering Islamic Azad University Branch of Science and Research Tehran Iran PhD Student
School of Mechanical Engineering Iran University of Science and Technology (IUST) Tehran Iran
In this paper, parametric and numerical model of the motors of a robot are extracted. A method is proposed here to control the torque and velocity of the motor simultaneously using the extracted dynamics of the motor ...
详细信息
ISBN:
(纸本)9781467372350
In this paper, parametric and numerical model of the motors of a robot are extracted. A method is proposed here to control the torque and velocity of the motor simultaneously using the extracted dynamics of the motor and consequently control the robot motion more accurately. Parametric model of the motors are derived by conducting standard tests like locked rotor test and step and sine wave input test. In order to derive the neural network and numerical models, a set of sinusoidal, triangular, and random steps signal, are applied as the input to the motor and its speed is recorded as the output. Neural network model of the motors is extracted by using these dataset and considering the MLP neural network structure with Levenberg _Marquardt training method. Results of the numerical model and parametric models are compared and validated by experimental tests.
暂无评论