Mehmet Karakose

Design and simulation of self-tuning PID-type fuzzy adaptive control for an expert HVAC system

The modelling, numerical simulation and intelligent control of an expert HVAC (heating, ventilating and air-conditioning) system having two different zones with variable flow-rate were performed by considering the ambient temperature in this study. The sub-models of the system were obtained by deriving heat transfer equations of heat loss of two zones by conduction and convection, cooling unit and fan. All models of the variable flow-rate HVAC system were generated by using MATLAB/SIMULINK, and proportional-integral-derivative (PID) parameters were obtained by using Fuzzy sets. For comfortable of people the temperatures of the two different zones were decreased to 5^oC from the ambient temperature. The successful results were obtained by applying self-tuning proportional-integral-derivative (PID)-type fuzzy adaptive controller if comparing with the fuzzy PD-type and the classical PID controller. The obtained results were presented in a graphical form.

A multi-objective artificial immune algorithm for parameter optimization in support vector machine

Support vector machine (SVM) is a classification method based on the structured risk minimization principle. Penalize, C; and kernel, @s parameters of SVM must be carefully selected in establishing an efficient SVM model. These parameters are selected by trial and error or mans experience. Artificial immune system (AIS) can be defined as a soft computing method inspired by theoretical immune system in order to solve science and engineering problems. A multi-objective artificial immune algorithm has been used to optimize the kernel and penalize parameters of SVM in this paper. In training stage of SVM, multiple solutions are found by using multi-objective artificial immune algorithm and then these parameters are evaluated in test stage. The proposed algorithm is applied to fault diagnosis of induction motors and anomaly detection problems and successful results are obtained.

An approach for automated fault diagnosis based on a fuzzy decision tree and boundary analysis of a reconstructed phase space.

Although reconstructed phase space is one of the most powerful methods for analyzing a time series, it can fail in fault diagnosis of an induction motor when the appropriate pre-processing is not performed. Therefore, boundary analysis based a new feature extraction method in phase space is proposed for diagnosis of induction motor faults. The proposed approach requires the measurement of one phase current signal to construct the phase space representation. Each phase space is converted into an image, and the boundary of each image is extracted by a boundary detection algorithm. A fuzzy decision tree has been designed to detect broken rotor bars and broken connector faults. The results indicate that the proposed approach has a higher recognition rate than other methods on the same dataset.

Artificial immune based support vector machine algorithm for fault diagnosis of induction motors

The use of induction motors is widespread in industry. Many researchers have studied the condition monitoring and detecting the faults of induction motors at an early stage. Early detection of motor faults results in fast unscheduled maintenance. In this study, a new artificial immune based support vector machine algorithm is proposed for fault diagnosis of induction motors. Support vector machines (SVMs) have become one of the most popular classification methods in soft computing, recently. However, classification accuracy depends on kernel and penalty parameters. Artificial immune system has abilities of learning, memory and self adaptive control. The kernel and penalizes parameters of support vector machine are tuned using artificial immune system. The training data of support vector machine are extracted from three phase motor current. The new feature vector is constructed based on parks vector approach. The phase space of this feature vector is constructed using nonlinear time series analysis. Broken rotor bar and stator short circuit faults are classified in combined phase space using support vector machines. The experimental data are taken from a three phase induction motor. One, two and three broken rotor bar faults and 10% short circuit of stator faults are detected successfully.

Artificial immune classifier with swarm learning

Artificial immune systems are computational systems inspired by the principles and processes of the natural immune system. The various applications of artificial immune systems have been used for pattern recognition and classification problems; however, these artificial immune systems have three major problems, which are growing of the memory cell population, eliminating of the useful memory cells in next the steps, and randomly using cloning and mutation operators. In this study, a new artificial immune classifier with swarm learning is proposed to solve these three problems. The proposed algorithm uses the swarm learning to evolve the antibody population. In each step, the antibodies that belong to the same class move to the same way according to their affinities. The size of the memory cell population does not grow during the training stage of the algorithm. Therefore, the method is faster than other artificial immune classifiers. The classifier was tested on two case studies. In the first case study, the algorithm was used to diagnose the faults of induction motors. In the second case study, five benchmark data sets were used to evaluate the performance of the algorithm. The results of second case studies show that the proposed method gives better results than two well-known artificial immune systems for real word data sets. The results were compared to other classification techniques, and the method is competitive to other classifiers.

A Robust Anomaly Detection in Pantograph-Catenary System Based on Mean-Shift Tracking and Foreground Detection

This study presents a robust condition monitoring and anomaly detection for pantograph-catenary system. The pantograph overhead system is monitored by using a digital camera. A general framework for anomaly detection for pantograph-catenary system consists of two key components. The first component is based on mean-shift tracking of contact wire. Therefore, the contact point between pantograph and catenary can be continuously monitored and anomaly contact to some points will be detected. The second component uses Gaussian mixture model (GMM) for foreground detection. When the foreground of the current frame has been detected, the mean-shift tracking and GMM combines trajectory-based and region-based information for detection any anomaly in pantograph-catenary interaction. The experimental results show that proposed method is useful to detect burst of arcing, and irregular positioning of contact line.

Combined intelligent methods based on wireless sensor networks for condition monitoring and fault diagnosis

This study presents new combined methods based on multiple wireless sensor system for real-time condition monitoring of electric machines. The established experimental setup measures multiple signals such as current and vibration on a common wireless node. The proposed methods are low-cost, intelligent, and non-intrusive. The proposed wireless network based framework is useful for analyzing and monitoring of signals from multiple induction motors. Motor current and vibration signals are simultaneously read from multiple motors through wireless nodes and the faults are estimated using two combined methods. Phase space analysis of vibration data and amplitudes of three phase current signals are used as features in combined intelligent classifiers. Stator related faults are diagnosed by analyzing the magnitudes of read current signals with fuzz logic. The vibration signal taken from the two-axis acceleration meter is normalized and phase space of this signal is constructed. The change in phase spaces are analyzed with machine learning techniques based on Gaussian Mixture Models and Bayesian classification to detect bearing faults. The phase space of vibration signals is constructed by using non-linear time series analysis and Gaussian mixtures are obtained for healthy and each faulty conditions. The constructed mixture models are classified according to their distribution on phase space by using Bayesian classification method. Four motor operating conditions- stator open phase fault, one and two bearing imbalance faults, and healthy condition are considered and related signals are obtained to evaluate the proposed system. The accuracy of the proposed system is confirmed by experimental data.

The intelligent fault diagnosis frameworks based on fuzzy integral

Fuzzy integral is an information aggregation and combination process in a multi-criteria environment using fuzzy measures. This paper presents a new data fusion method using fuzzy integral for fault diagnosis. The method consists of two frameworks. The first framework was employed to identify the relations between features and a specified fault. The second framework was implemented to integrate different diagnosis algorithms to improve the accuracy rates of them. The choquet fuzzy integral was utilized for two frameworks. The proposed approach was experimentally implemented on a 0.37 kW induction motor. Broken rotor bar and stator faults were evaluated to validate the models. The results showed that the proposed method performs very well for broken rotor bar and stator faults.

Anomaly detection using a modified kernel-based tracking in the pantograph-catenary system

A new contactless condition monitoring method is proposed for anomaly detection in the pantograph-catenary system.Kernel-based tracking is modified for a robust tracking of catenary wire.The foreground detection and object tracking are combined for simultaneously arcing detection.The detailed analysis of the trajectory of the contact wire gives useful information to evaluate the pantograph condition. Condition monitoring is very important in railway systems to reduce maintenance costs and to increase the safety. A high power is needed for the movement of the electric train and collection of the current is critical. Faults occurred in the current collection system cause serious damage in the line and disrupt the railway traffic. When a wear occurs on the contact strip, the asymmetries and distortion are generated in supply voltage and current waveforms because of pantograph arcing. Therefore, the monitoring of pantograph-catenary system has been a hot topic in recent years. This paper deals with a method based on kernel-based object tracking for identifying the interaction between pantograph-catenary systems that gives useful information about the problems of catenary-pantograph systems. The method consists of two key components. The first component is based on the kernel based tracking of the contact wire. The contact point between pantograph and catenary is tracked and the obtained positions are saved as a signal. In the other hand, the foreground of each frame is found by using Gaussian mixture models (GMMs). The occurred arcs are detected by combining tracking and foreground detection methods. The second component employs S-transform for analyzing the pantograph problems, which are used to detect the faults occurred on pantograph strip. The experimental results imply that the proposed method is useful to detect burst of arcing, and irregular positioning of the contact wire.

Artificial immune inspired fault detection algorithm based on fuzzy clustering and genetic algorithm methods

Early detection and diagnosis of incipient faults are desired for online condition monitoring and improved operational efficiency of induction motors. In this study, an artificial immune inspired fault detection algorithm based on fuzzy clustering and genetic algorithm is developed to detect broken rotor bar and broken connector faults in induction motors. The proposed algorithm uses only one phase stator current as input without the need for any other signals. The new feature signal called envelop is obtained by using Hilbert transform. This signal is examined in a phase space that is constructed by nonlinear time series analysis method. The artificial immune algorithm called negative selection is used to detect faults. The cluster centers of healthy motor phase space are obtained by fuzzy clustering method and they are taken as self patterns. The detectors of negative selection are generated by genetic algorithm. Self patterns generated by fuzzy clustering speed up the training stage of our algorithm and only small numbers of detectors are sufficient to detect any faults of induction motor. Results have demonstrated that the proposed system is able to detect faults in a three phase induction motor, successfully.