Dae-Jong Lee

C-ANFIS based fault diagnosis for voltage-fed PWM motor drive systems

Since most of the induction motors are operated by the inverter, an unexpected fault of the inverter can cause serious troubles such as downtime of equipment, heavy loss, and etc. Therefore, the studies on the robust drive system for induction motors to protect the system under the fault modes are gaining more interests. This paper investigates the fault diagnosis for open-switch damages in a voltage-fed PWM motor drive system. For diagnosing the conditions of a inverter, we transform the current signal to the d-q axis. And then, we obtain the features consisting of the trajectories of d-q phase currents for each fault mode. In the ideal cases, a set of fault modes can be classified by using the shape of these trajectories. There are, however, many variational elements such as load torque and the electrical/mechanical variable parameters. So, we propose a robust diagnosis method based on the neuro-fuzzy algorithm. For this, we adopted the Clustering Adaptive Neuro Fuzzy Inference System(C-ANFIS) to recognize the various and vague fault patterns. Finally, we implement the method for the diagnosis module of the inverter with MATLAB and show its usefulness.

Parameter Optimization of Extreme Learning Machine Using Bacterial Foraging Algorithm

Recently, Extreme learning machine(ELM), a novel learning algorithm having much faster than the traditional gradient-based learning algorithm, was proposed for single-hid den-layer feedforward neural networks (SLFNs). Usually, the initial input weights and hidden biases of ELM are randomly chosen, and then the output weights are analytically determined by using Moore-Penrose (MP) generalized inverse. However, ELM may need higher number of hidden neurons due to the random determination of the input weights and hidden biases. In this paper, an optimization method based on the bacterial foraging (BF) algorithm is proposed to adjust the input weights and hidden biases. Experimental result shows that this method can achieve better performance for problems having higher dimension than others.

Fault Diagnosis of Power Transformer Using SVM and FCM

In this study, we are concerned with fault diagnosis of power transformer. The objective is to explore the use of some advanced techniques such as SVM and FCM and quantify their effectiveness when dealing with dissolved gases extracted from power transformers. The proposed fault diagnosis system consists of data acquisition, fault/normal diagnosis, identification of fault and analysis of aging degree parts. In data acquisition part, concentrated gases are extracted from transformer for data gas analysis. In fault/normal diagnosis part, SVM is performed to separate normal state from fault types. The determination of fault type is executed by multi-class SVM in identification part. Although the inputted data is normal state, the analysis of aging degree is performed by considering the distance measure calculated by comparing with reference model constructed by FCM and input data. Our approach makes it possible to measure the possibility and degree of aging in normal transformer as well as the identification of faults in abnormal transformer. As the simulation results to verify the effectiveness, the proposed method showed more improved classification results than conventional methods.

Fault Diagnosis of Induction Motors by DFT and Wavelet

A method for diagnosing fault of an induction motor is provided to finally diagnose fault of induction motor using fusion algorithm. A characteristic vector is calculated using fourier transform, linear discriminant analysis and wavelet transform from current signal value. Similarity value is calculated through distance comparison between standard model and characteristic vector calculated. Similarity value is calculated according to each fault classification. The diagnosis is performed by selecting a model having high similarity with conventional model.

Speech recognition using integra-normalizer and neuro-fuzzy method

This paper represents a new method of recognizing speech using the metric defined by the integra-normalizer (IN) and the neuro-fuzzy method. A codebook contains a set of feature vectors that is extracted from raw speech data. The degree of similarity between speech is measured as the distance between the speech feature vectors. The method of measuring distance between feature vectors is obtained by using the new metric presented in this paper using the IN that possesses some advantage to conventional metrics such as the metric defined to measure the least square error. With the approach used in this paper, information on the shape of the speech patterns is mapped to the feature vectors and the metric measures the difference between speech patterns considering the shape of the patterns also. The results of the computer simulation are shown for the validity of this proposed method.

Face Recognition Using Wavelet Coefficients and Hidden Markov Model

In this paper, we proposes a method for face recognition using HMM(hidden Markov model) and wavelet coefficients First, input images are compressed by using the multi-resolution analysis based on the discrete wavelet transform. And then, the wavelet coefficients obtained from each subband are used as feature vectors to construct the HMMs. In the recognition stage, we obtained higher recognition rate by summing of each recognition rate of wavelet subband. The usefulness of the proposed method was shown by comparing with conventional VQ and DCT-HMM ones. The experimental results show that the proposed method is more satisfactory than previous ones.

Robust Speech Recognition with Car Noise based on the Wavelet Filter Banks

This paper proposes a robust speech recognition algorithm based on the wavelet filter banks. Since the proposed algorithm adopts a multiple band decision-making scheme, it performs robustness for noise as the presence of noisy severely degrades the performance of speech recognition system. For evaluating the performance of the proposed scheme, we compared it with the conventional speech recognizer based on the VQ for the 10-isolated korean digits with car noise. Here, the proposed method showed more 9~27% improvement of the recognition rate than the conventional VQ algorithm for the various car noisy environments.

An Ultrasonic Multi-Beam Concentration Meter with a Neuro-Fuzzy Algorithm for Water Treatment Plants

Ultrasonic concentration meters have widely been used at water purification, sewage treatment and waste water treatment plants to sort and transfer high concentration sludges and to control the amount of chemical dosage. When an unusual substance is contained in the sludge, however, the attenuation of ultrasonic waves could be increased or not be transmitted to the receiver. In this case, the value measured by a concentration meter is higher than the actual density value or vibration. As well, it is difficult to automate the residuals treatment process according to the various problems such as sludge attachment or sensor failure. An ultrasonic multi-beam concentration sensor was considered to solve these problems, but an abnormal concentration value of a specific ultrasonic beam degrades the accuracy of the entire measurement in case of using a conventional arithmetic mean for all measurement values, so this paper proposes a method to improve the accuracy of the sludge concentration determination by choosing reliable sensor values and applying a neuro-fuzzy learning algorithm. The newly developed meter is proven to render useful results from a variety of experiments on a real water treatment plant.

Boundary Depth Estimation Using Hough Transform and Focus Measure

Depth estimation is often required for robot vision, 3D modeling, and motion control. Previous method is based on the focus measures which are calculated for a series of image by a single camera at different distance between and object. This method, however, has disadvantage of taking a long time for calculating the focus measure since the mask operation is performed for every pixel in the image. In this paper, we estimates the depth by using the focus measure of the boundary pixels located between the objects in order to minimize the depth estimate time. To detect the boundary of an object consisting of a straight line and a circle, we use the Hough transform and estimate the depth by using the focus measure. We performed various experiments for PCB images and obtained more effective depth estimation results than previous ones. Key Word : Depth estimation, Focus measures, Hough transform, Digital Image processing

Real Fuzzy Vault for Protecting Face Template

Face recognition techniques have been widely used for various areas including criminal identification due to their capability of easy implementing and user friendly interface. However, they have some drawbacks related to individual`s privacy in case that his or her face information is divulged to illegal users. So, this paper proposed a novel method for protecting face template based on the real fuzzy vault. This proposed method has some advantages of regenerating a new face template when a registered face template is disclosed. Through implementing and testing the proposed method, we showed its validity and usefulness.