Erdal Kilic

Comparison of the results of response surface methodology and artificial neural network for the biosorption of lead using black cumin.

In this study, Response Surface Methodology (RSM) and Artificial Neural Network (ANN) were employed to develop an approach for the evaluation of heavy metal biosorption process. A batch sorption process was performed using Nigella sativa seeds (black cumin), a novel and natural biosorbent, to remove lead ions from aqueous solutions. The effects of process variables which are pH, biosorbent mass, and temperature, on the sorbed amount of lead were investigated through two-levels, three-factors central composite design (CCD). Same design was also utilized to obtain a training set for ANN. The results of two methodologies were compared for their predictive capabilities in terms of the coefficient of determination-R(2) and root mean square error-RMSE based on the validation data set. The results showed that the ANN model is much more accurate in prediction as compared to CCD.

Diagnosability of fuzzy discrete event systems

In this paper, discrete event systems (DESs) are reformulated as fuzzy discrete event systems (FDESs) and fuzzy discrete event dynamical systems (FDEDSs). These frameworks include fuzzy states, events and IF-THEN rules. In these frameworks, all events occur at the same time with different membership degrees. Fuzzy states and events have been introduced to describe uncertainties that occur often in practical problems, such as fault diagnosis applications. To measure a diagnosers fault discrimination ability, a fuzzy diagnosability degree is proposed. If the diagnosability of the degree of the system yields one a diagnoser can be implemented to identify all possible fault types related to a system. For any degree less than one, researchers should not devote their time to distinguish all possible fault types correctly. Thus, two different diagnosability definitions FDEDS and FDES are introduced. Due to the specialized fuzzy rule-base embedded in the FDEDS, it is capable of representing a class of non-linear dynamic system. Computationally speaking, the framework of diagnosability of the FDEDS is structurally similar to the framework of diagnosability of a non-linear system. The crisp DES diagnosability has been turned into the term fuzzy diagnosability for the FDES. The newly proposed diagnosability definition allows us to define a degree of diagnosability in a class of non-linear systems. In addition, a simple fuzzy diagnosability checking method is introduced and some numerical examples are provided to illustrate this theoretical development. Finally, the potential applications of the proposed method are discussed.

Modeling and real-time fault identification in transformers

Abstract In this paper, a different internal fault modeling and an identification algorithm are presented. There has been an increasing concern about turn-to-turn faults in transformers because of the high costs of unexpected outages. It is not always possible to analyze the transformer behavior under such faults at rated conditions, since the tests are highly destructive. To develop transformer internal fault detection technique, a transformer model to simulate internal faults is required. This paper describes a novel technique and methodology for modeling and identifying transformer internal faults by using transmission line method (TLM) and fuzzy reasoning technique based on dynamic principal component analysis (PCA), respectively. The transformer has been modeled considering non-linearities as hysteresis and saturation. Transformer internal fault currents are successfully discriminated from the rated currents. The degree and priority of transformer internal faults are obtained by the proposed method. It is suited for implementation on computers because of no computation complexity. Hence, the proposed algorithm can be used effectively in real-time fault identification problems.

A New Method for Fault Detection and Identification of Incipient Faults in Power Transformers

Abstract This article presents a new scheme for incipient fault detection and its identification in transformers. The new approach is actually based on adaptive modeling of transformers using the transmission line method (TLM) obtained from the hysteresis model. The adaptive TLM observer representing no-load, quarter-load, half-load, and rated-load conditions is used for faults detection. The continuous wavelet transform (CWT) is performed on residuals that are obtained by comparing real system currents and calculated TLM observer currents in order to extract the features for fault identification. An adaptive fuzzy reasoning technique is used to identify incipient faults in the transformer. The sum of CWT coefficients of residuals is applied to the adaptive fuzzy rule-based decision-making unit to indicate the type of faults. The main advantage of the suggested scheme is that different types of incipient faults in the transformer can be correctly identified. The test results verify the effectiveness of the suggested method.

Fault diagnosis with dynamic fuzzy discrete event system approach

Determining faults is a challenging task in complex systems. A discrete event system (DES) or a fuzzy discrete event system (FDES) approach with a fuzzy rule-base may resolve the ambiguity in a fault diagnosis problem especially in the case of multiple faults. In this study, an FDES approach with a fuzzy rule-base is used as a means of indicating the degree and priority of faults, especially in the case of multiple faults. The fuzzy rule-base is constructed using event-fault relations. Fuzzy events occurring any time with different membership degrees are obtained using k-means clustering algorithm. The fuzzy sub-event sequences are used to construct super events. The study is concluded by giving some examples about the distinguishability of fault types (parameter, actuator) in an unmanned small helicopter.

From classic observability to a simple fuzzy observability for fuzzy discrete-event systems

In order to determine uncertainties from restricted available information, fuzzy discrete-event systems (FDESs), or fuzzy discrete-event dynamic systems (FDEDSs), were recently proposed. These frameworks include fuzzy states and events occurring simultaneously with different membership degrees. Fuzzy states and events have been used to describe uncertainties that occur often in practical problems, such as treatment planning for HIV/AIDS patients, sensory information processing for robotic control, and fault diagnosis problems. In order to measure information associated with FDESs or FDEDSs, the classical discrete event system (DES) observability has been turned into fuzzy observability for FDESs or FDEDSs. The newly proposed method allows ease of defining degrees of observability so that uncertainties in FDESs or FDEDSs can be dealt with effectively. This gives an opportunity to design better decision-making systems. To calculate the observability degree, a simple fuzzy observability checking method is introduced, and two examples are elaborated upon to illustrate the presented method. Finally, the newly proposed method is tested on a heating, ventilating, and air-conditioning (HVAC) system.

Identification of Transformer Internal Faults by Using an RBF Network Based on Dynamical Principle Component Analysis

In this paper; a method is proposed to detect and identify parameter faults in nonlinear dynamical systems. The approach is based on the principal component analysis (PCA) and artificial neural networks (ANNs) based on radial basis functions (RBFs). A nonlinear systems input and output data is manipulated without taking consideration any model in the approach. The method is applied to a three phase custom built transformer in order to detect and identify internal short circuit faults. It is obsered theughgh various application examples that the proposed method leads to satisfactory results in terms of detecting parameter faults in non-linear dynamical systems.

Development of Experimental Results by Artificial Neural Network Model for Adsorption of Cu2+ Using Single Wall Carbon Nanotubes

Removal of copper ions from aqueous solution using single wall carbon nanotubes (SWCNTs) as a function on pH was studied using batch technique. The results indicate that adsorption is strongly dependent on pH. The adsorption of Cu2+ on SWCNTs increases slowly with increasing pH value at pH < 7.0 and then the adsorption increases rapidly with increasing pH at pH > 7.0. The equilibrium adsorption data were analyzed by the Langmuir, Freundlich, and Temkin adsorption isotherm models. The Freundlich adsorption model agrees well with experimental data. The pseudo-second order kinetic was the best fit kinetic model for the experimental data. The experimental results were also constructed an artificial neural network (ANN) to predict removal of copper ions. A four-layer ANN, an input layer with four neurons, two hidden layers with 13 neurons, and an output layer with one neuron (4-8-5-1) is constructed. Different training algorithms are tested on the model proposed to obtain the best weights and bias values for ANN. Our results suggest that SWCNTs have a good potential application in environmental protection. This novel modeling tool is newly grown and has been used yet to model the above-mentioned experiments for SWCNTs.

Fault detection in induction motors with independent component analysis (ICA)

In this study, the aim is to detect an induction motors winding faults by using independent component analysis (ICA). Many laboratory experiments have been done on an induction motor to check the performance of the proposed method. The phase currents of the induction motor are used in the fault detection algorithm. The algorithm is implemente d by using MATLAB. The proposed method is compared to FFT solution to see its ability to distinguish fault currents. It has been observed that the proposed method based on ICA can efficiently be used to detect induction motors winding faults.

Fault Identification in Induction Motors with RBF Neural Network Based on Dynamical PCA

Early detection and diagnosis of incipient faults is desirable for on-line condition assessment, product quality assurance and improved efficiency of induction motors running off power supply mains. In the applications of three-phase induction motors in industry, the inner faults may occur in their rotor and stator windings. These kinds of faults will make serious health problems on the motor. This paper presents a new protection scheme for internal short circuit faults occurring with a degree (single or multiple) in three-phase induction motors. The results are compared with traditional outcomes existed from fast Fourier transformation (FFT) of the motor currents. The proposed algorithm is simpler and only uses stator currents. There is no need any other sensor knowledge.