Sami Ekici

An adaptive neuro-fuzzy inference system (ANFIS) model for wire-EDM

A wire electrical discharge machined (WEDM) surface is characterized by its roughness and metallographic properties. Surface roughness and white layer thickness (WLT) are the main indicators of quality of a component for WEDM. In this paper an adaptive neuro-fuzzy inference system (ANFIS) model has been developed for the prediction of the white layer thickness (WLT) and the average surface roughness achieved as a function of the process parameters. Pulse duration, open circuit voltage, dielectric flushing pressure and wire feed rate were taken as models input features. The model combined modeling function of fuzzy inference with the learning ability of artificial neural network; and a set of rules has been generated directly from the experimental data. The models predictions were compared with experimental results for verifying the approach.

Energy and entropy-based feature extraction for locating fault on transmission lines by using neural network and wavelet packet decomposition

The aim of this paper is to estimate the fault location on transmission lines quickly and accurately. The faulty current and voltage signals obtained from a simulation are decomposed by wavelet packet transform (WPT). The extracted features are applied to artificial neural network (ANN) for estimating fault location. As data sets increase in size, their analysis become more complicated and time consuming. The energy and entropy criterion are applied to wavelet packet coefficients to decrease the size of feature vectors. The test results of ANN demonstrate that the applying of energy criterion to current signals after WPT is a very powerful and reliable method for reducing data sets in size and hence estimating fault locations on transmission lines quickly and accurately.

Support vector machines models for surface roughness prediction in CNC turning of AISI 304 austenitic stainless steel

In the present investigation, three different type of support vector machines (SVMs) tools such as least square SVM (LS-SVM), Spider SVM and SVM-KM and an artificial neural network (ANN) model were developed to estimate the surface roughness values of AISI 304 austenitic stainless steel in CNC turning operation. In the development of predictive models, turning parameters of cutting speed, feed rate and depth of cut were considered as model variables. For this purpose, a three-level full factorial design of experiments (DOE) method was used to collect surface roughness values. A feedforward neural network based on backpropagation algorithm was a multilayered architecture made up of 15 hidden neurons placed between input and output layers. The prediction results showed that the all used SVMs results were better than ANN with high correlations between the prediction and experimentally measured values.

Support Vector Machines for classification and locating faults on transmission lines

This paper presents a new approach to classify fault types and predict the fault location in the high-voltage power transmission lines, by using Support Vector Machines (SVM) and Wavelet Transform (WT) of the measured one-terminal voltage and current transient signals. Wavelet entropy criterion is applied to wavelet detail coefficients to reduce the size of feature vector before classification and prediction stages. The experiments performed for different kinds of faults occurred on the transmission line have proved very good accuracy of the proposed fault location algorithm. The fault classification error is below 1% for all tested fault conditions. The average error of fault location in a 380kV-360-km transmission line is below 0.26% and the maximum error did not exceed 0.95km.

Classification of power system disturbances using support vector machines

This paper presents an effective method based on support vector machines (SVM) for identification of power system disturbances. Because of its advantages in signal processing applications, the wavelet transform (WT) is used to extract the distinctive features of the voltage signals. After the wavelet decomposition, the characteristic features of each disturbance waveforms are obtained. The wavelet energy criterion is also applied to wavelet detail coefficients to reduce the sizes of data set. After feature extraction stage SVM is used to classify the power system disturbance waveforms and the performance of SVM is compared with the artificial neural networks (ANN).

A transmission line fault locator based on Elman recurrent networks

In this paper, a transmission line fault location model which is based on an Elman recurrent network (ERN) has been presented for balanced and unbalanced short circuit faults. All fault situations with different inception times are implemented on a 380-kV prototype power system. Wavelet transform (WT) is used for selecting distinctive features about the faulty signals. The system has the advantages of utilizing single-end measurements, using both voltage and current signals. ERN is able to determine the fault location occurred on transmission line rapidly and correctly as an important alternative to standard feedforward back propagation networks (FFNs) and radial basis functions (RBFs) neural networks.

A fault location technique for HVDC transmission lines using extreme learning machines

In this study, a new approach is proposed for fault estimation in high voltage direct current transmission lines using discrete wavelet transform and extreme learning machine. Recently, signal processing and intelligent systems have gained importance to ease very different tasks such as fault location and estimation, load estimations, reactive power compensation, the risk of blackouts. Therefore, a fast, accurate and reliable protection algorithms have a major interest in the extended usage of high voltage direct current systems for many areas. In this study, single phase-ground faults on DC lines examined and a new machine learning approach also discussed. The virtual faults obtained from Matlab simulation is utilized in the course of feature extraction of the wavelet transform. Furthermore, for identifying steady state and faulted condition, Shannon entropy and signal’s energy values have been calculated by using coefficients of the wavelet transform. After that, the coefficients normalized between [-1,1]. Finally, the extreme learning machine used to fault estimation and location process.

Computer-aided power system fault analysis

Most of power systems courses contain mathematical analysis, animations, simulations, and technical tours to power stations. However, experimental studies particularly in fault analysis are very difficult due to high voltages and currents passed through short circuits. Although there are experimental equipments and prototype systems for the students, they are very expensive. This paper presents a new computer‐aided approach for power system analysis course at The University of Firat. The new course covers the previous course which contains only a short experiment by using a prototype power system. The sequence of new updated course for high‐voltage fault analysis is following: experimental implementations, simulation, signal processing and fault classification. A questionnaire containing 11 questions has been applied to students to determine the effectiveness of the new course. According to questionnaire; the updated course has been found more useful to analyze and understand the transmission line faults than the previous course.

Deep learning based face liveness detection in videos

The human face is an important biometric quantity which can be used to access a user-based system. As human face images can easily be obtained via mobile cameras and social networks, user-based access systems should be robust against spoof face attacks. In other words, a reliable face-based access system can determine both the identity and the liveness of the input face. To this end, various feature-based spoof face detection methods have been proposed. These methods generally apply a series of processes against the input image(s) in order to detect the liveness of the face. In this paper, a deep-learning-based spoof face detection is proposed. Two different deep learning models are used to achieve this, namely local receptive fields (LRF)-ELM and CNN. LRF-ELM is a recently developed model which contains a convolution and a pooling layer before a fully connected layer that makes the model fast. CNN, however, contains a series of convolution and pooling layers. In addition, the CNN model may have more fully connected layers. A series of experiments were conducted on two popular spoof face detection databases, namely NUAA and CASIA. The obtained results were then compared, and the LRF-ELM method yielded better results against both databases.

Gender recognition from face images with deep learning

Gender is one of the main factors in the interaction between individuals. Recently, with the development of social media environments and smartphones, gender recognition applications have both begun to grow and become important. In many fields such as face recognition, facial expression analysis, tracking and surveillance, human-computer interaction, biometry, gender recognition applications can be seen. In this study, gender recognition was carried out from face images with deep learning. The Local Receptive Field-Extreme Learning Machine (LRF-ELM) and Convolutional Neural Networks (CNN) were used as the deep learning methods. Experiments were performed on a face data set generated for age and gender recognition. LRF-ELM and CNN achieved performance rate of 80% and 87.13%, respectively.