Almas Shintemirov | Nazarbayev University (original) (raw)

Papers by Almas Shintemirov

IEEE Transactions on Power Delivery, 2009

2013 IEEE International Conference on Mechatronics and Automation, 2013

ABSTRACT This paper presents the preliminary prototype design and implementation of the Nazarbaye... more ABSTRACT This paper presents the preliminary prototype design and implementation of the Nazarbayev University (NU) Hand, a new semi-anthropomorphic multigrasp robotic hand. The hand is designed to be an end effector for industrial and service robots. The main objective is to develop a low-cost, low-weight and easily manufacturable robotic hand with a sensor module allowing acquisition of data for autonomous intelligent object manipulation. 3D printing technologies were extensively used in the implementation of the hand. Specifically, the structure of the hand is printed using a 3D printer as a complete assembly voiding the need of using fasteners and bearings for the assembly of the hand and decreasing the total weight. The hand also incorporates a sensor module containing a LIDAR, digital camera and non-contact infrared temperature sensor for intelligent automation. As an alternative to teach pendants for the industrial manipulators, a teaching glove was developed, which acts as the primary human machine interface between the user and the NU Hand. The paper presents an extensive performance characterization of the robotic hand including finger forces, weight, audible noise level during operation and sensor data acquisition.

Abstract: This paper presents an improved model of uniform transformer winding for frequency resp... more Abstract: This paper presents an improved model of uniform transformer winding for frequency response analysis (FRA), based on traveling wave theory. The accurate representation of the losses and detailed consideration of measurement chains are the main features of the model. The transfer function expression of the transformer winding and equivalent distributed-parameter circuit for FRA have been derived and upon which numerical simulation has been performed.

Abstract We present a novel model-based approach for parameter identification of a laminated core... more Abstract We present a novel model-based approach for parameter identification of a laminated core, such as magnetic permeability and electrical conductivity, of power transformers on the basis of frequency response analysis (FRA) measurements. The method establishes a transformer core model using the duality principle between magnetic and electrical circuits for parameter identification with genetic algorithms.

This paper discusses the possibility of utilizing power transformer modelling for interpretation ... more This paper discusses the possibility of utilizing power transformer modelling for interpretation of frequency response analysis (FRA) measurements. FRA is a reliable technique for power transformer winding distortion and deformation assessment and monitoring. A lumped parameter model of a three phase power transformer is briefly presented and applied to simulate frequency responses at various winding fault conditions such as short-circuited turns, axial displacements and radial deformations. Simulations and discussions are presented to explore the potentials of the model to transformer fault detection based on FRA measurements.

This paper presents a novel model-based identification approach to determining laminated core par... more This paper presents a novel model-based identification approach to determining laminated core parameters of power transformers on the basis of frequency response analysis (FRA) measurements. A genetic algorithm is employed for parameter identification of a transformer core model, established using the duality principle between magnetic and electrical circuits. A well-known lumped parameter model of a 3-phase transformer is used to simulate reference input impedance frequency responses for analyzing the identification accuracy of the proposed approach. It is suggested that the approach can be applied for transformer core modeling and FRA result interpretation at low frequencies.

This paper presents a simplified distributed parameter model for minor winding deformation fault ... more This paper presents a simplified distributed parameter model for minor winding deformation fault analysis of power transformers on the basis of frequency response analysis (FRA). The FRA data of an experimental transformer is employed as a reference trace, which are compared with the simulations of the simplified distributed parameter model concerning minor winding deformation faults. In order to perform quantitative analysis when a deformation fault occurs, three statistical indicators are used to analyze the FRA simulation data. It is suggested in the results that minor winding deformation faults can be detected at the frequency range above 1 MHz.

This paper discusses a feature extraction technique with genetic programming (GP) and bootstrap t... more This paper discusses a feature extraction technique with genetic programming (GP) and bootstrap to improve interpretation accuracy of dissolved gas analysis (DGA) fault classification in power transformers, dealing with highly versatile or noise corrupted data. Initial DGA data are preprocessed with bootstrap to equalize the sample numbers for different fault classes, thus improving subsequent extraction of classification features with GP for each fault class. The features extracted with GP are then used as the inputs to artificial neural network (ANN), support vector machine (SVM) and K-nearest neighbor (KNN) classifiers for fault classification. The test results indicate that the proposed preprocessing approach can significantly improve the accuracy of power transformer fault classification based on DGA data.

Electric Power Systems Research, 2010

The paper discusses an improved modelling of transformer windings based on bacterial swarming alg... more The paper discusses an improved modelling of transformer windings based on bacterial swarming algorithm (BSA) and frequency response analysis (FRA). With the purpose to accurately identify transformer windings parameters a model-based identification approach is introduced using a well-known lumped parameter model. It includes search space estimation using analytical calculations, which is used for the subsequent model parameters identification with a novel BSA. The newly introduced BSA, being developed upon a bacterial foraging behavior, is described in detail. Simulations and discussions are presented to explore the potential of the proposed approach using simulated and experimentally measured FRA responses taken from two transformers. The BSA identification results are compared with those using genetic algorithm. It is shown that the proposed BSA delivers satisfactory parameter identification and improved modelling can be used for FRA results interpretation.

Iet Electric Power Applications, 2010

The study presents an evidential reasoning (ER) approach to transformer winding assessment based ... more The study presents an evidential reasoning (ER) approach to transformer winding assessment based on frequency response analysis (FRA). A conventional FRA assessment process is firstly discussed, where frequency response comparison methods and interpretation features are briefly introduced. Then an FRA assessment process is transferred into a multiple-attribute decision-making (MADM) problem under an ER framework and an introduction to the ER algorithm is given. Subsequently, several examples of transformer winding condition assessment problems are considered using two ER evaluation analysis models, where the potential of the ER approach in combining evidence and dealing with uncertainties is demonstrated. In the case when more than one expert is involved in an FRA assessment process, the developed ER framework can be used to aggregate experts' subjective judgements and produce an overall evaluation of the condition of a transformer winding in a formalised form.

IEEE Transactions on Systems, Man, and Cybernetics, 2009

This paper presents an intelligent fault classification approach to power transformer dissolved g... more This paper presents an intelligent fault classification approach to power transformer dissolved gas analysis (DGA), dealing with highly versatile or noise-corrupted data. Bootstrap and genetic programming (GP) are implemented to improve the interpretation accuracy for DGA of power transformers. Bootstrap preprocessing is utilized to approximately equalize the sample numbers for different fault classes to improve subsequent fault classification with GP feature extraction. GP is applied to establish classification features for each class based on the collected gas data. The features extracted with GP are then used as the inputs to artificial neural network (ANN), support vector machine (SVM) and K-nearest neighbor (KNN) classifiers for fault classification. The classification accuracies of the combined GP-ANN, GP-SVM, and GP-KNN classifiers are compared with the ones derived from ANN, SVM, and KNN classifiers, respectively. The test results indicate that the developed preprocessing approach can significantly improve the diagnosis accuracies for power transformer fault classification. Index Terms-Bootstrap, dissolved gas analysis (DGA), fault classification, feature extraction, genetic programming, K-nearest neighbor (KNN), neural networks, power transformer, support vector machine (SVM).

IEEE Transactions on Systems, Man, and Cybernetics, 2009

This paper presents a novel association rule mining (ARM)-based dissolved gas analysis (DGA) appr... more This paper presents a novel association rule mining (ARM)-based dissolved gas analysis (DGA) approach to fault diagnosis (FD) of power transformers. In the development of the ARM-based DGA approach, an attribute selection method and a continuous datum attribute discretization method are used for choosing user-interested ARM attributes from a DGA data set, i.e. the items that are employed to extract association rules. The given DGA data set is composed of two parts, i.e. training and test DGA data sets. An ARM algorithm namely Apriori-Total From Partial is proposed for generating an association rule set (ARS) from the training DGA data set. Afterwards, an ARS simplification method and a rule fitness evaluation method are utilized to select useful rules from the ARS and assign a fitness value to each of the useful rules, respectively. Based upon the useful association rules, a transformer FD classifier is developed, in which an optimal rule selection method is employed for selecting the most accurate rule from the classifier for diagnosing a test DGA record. For comparison purposes, five widely used FD methods are also tested with the same training and test data sets in experiments. Results show that the proposed ARM-based DGA approach is capable of generating a number of meaningful association rules, which can also cover the empirical rules defined in industry standards. Moreover, a higher FD accuracy can be achieved with the association rule-based FD classifier, compared with that derived by the other methods.

IEEE Transactions on Power Delivery, 2009

The paper presents a hybrid model of disc-type power transformer winding for frequency response a... more The paper presents a hybrid model of disc-type power transformer winding for frequency response analysis (FRA) based on traveling wave and multiconductor transmission line (MTL) theories. Each disc of a winding is described by traveling wave equations, which are connected to each other in a form of MTL matrix model. This significantly reduces the order of the model with respect to previously established MTL models of transformer winding. The model is applied to frequency response simulation of two single-phase transformers. The simulations are compared with the experimental data and calculated results using lumped parameter and MTL models reported in other publications. It is shown that the model can be used for FRA result interpretation in an extended range of frequencies up to several mega Hertz and resonance analysis under very fast transient overvoltages (VFTOs).

Lecture Notes in …, Jan 1, 2007

The paper presents a simplified mathematical model of disc-type transformer winding for frequency... more The paper presents a simplified mathematical model of disc-type transformer winding for frequency response analysis (FRA) based on traveling wave and multiconductor transmission line theories. The simplified model is applied to the FRA simulation of a transformer winding. In order to identify the distributed parameters of the model, an intelligent learning technique, rooted from particle swarm optimiser with passive congregation (PSOPC) is utilised. Simulations and discussions are presented to explore ...

Applications of Evolutionary …, Jan 1, 2007

The paper presents a simplified mathematical model of disc-type transformer winding for frequency... more The paper presents a simplified mathematical model of disc-type transformer winding for frequency response analysis (FRA) based on traveling wave and multiconductor transmission line theories. The simplified model is applied to the FRA simulation of a transformer winding. In order to identify the distributed parameters of the model, an intelligent learning technique, rooted from particle swarm optimiser with passive congregation (PSOPC) is utilised. Simulations and discussions are presented to explore ...

Control Conference, 2007. CCC …, Jan 1, 2007

Abstract This paper presents a least square support vector machine (LS-SVM) approach to dissolved... more Abstract This paper presents a least square support vector machine (LS-SVM) approach to dissolved gas analysis (DGA) problems for power transformers. Two methods are employed to improve the diagnosis accuracy for DGA analysis. First, bootstrap preprocessing is utilised to equalise the sample numbers for different fault types. Then, the preprocessed samples are inputted to a classier for fault classification. For comparison purposes, four classifiers are utilised, ie artificial neural network (ANN), k-nearest neighbour (KNN), simple SVM and LS ...

IEEE Transactions on Power Delivery, 2009

2013 IEEE International Conference on Mechatronics and Automation, 2013

ABSTRACT This paper presents the preliminary prototype design and implementation of the Nazarbaye... more ABSTRACT This paper presents the preliminary prototype design and implementation of the Nazarbayev University (NU) Hand, a new semi-anthropomorphic multigrasp robotic hand. The hand is designed to be an end effector for industrial and service robots. The main objective is to develop a low-cost, low-weight and easily manufacturable robotic hand with a sensor module allowing acquisition of data for autonomous intelligent object manipulation. 3D printing technologies were extensively used in the implementation of the hand. Specifically, the structure of the hand is printed using a 3D printer as a complete assembly voiding the need of using fasteners and bearings for the assembly of the hand and decreasing the total weight. The hand also incorporates a sensor module containing a LIDAR, digital camera and non-contact infrared temperature sensor for intelligent automation. As an alternative to teach pendants for the industrial manipulators, a teaching glove was developed, which acts as the primary human machine interface between the user and the NU Hand. The paper presents an extensive performance characterization of the robotic hand including finger forces, weight, audible noise level during operation and sensor data acquisition.

Abstract: This paper presents an improved model of uniform transformer winding for frequency resp... more Abstract: This paper presents an improved model of uniform transformer winding for frequency response analysis (FRA), based on traveling wave theory. The accurate representation of the losses and detailed consideration of measurement chains are the main features of the model. The transfer function expression of the transformer winding and equivalent distributed-parameter circuit for FRA have been derived and upon which numerical simulation has been performed.

Abstract We present a novel model-based approach for parameter identification of a laminated core... more Abstract We present a novel model-based approach for parameter identification of a laminated core, such as magnetic permeability and electrical conductivity, of power transformers on the basis of frequency response analysis (FRA) measurements. The method establishes a transformer core model using the duality principle between magnetic and electrical circuits for parameter identification with genetic algorithms.

This paper discusses the possibility of utilizing power transformer modelling for interpretation ... more This paper discusses the possibility of utilizing power transformer modelling for interpretation of frequency response analysis (FRA) measurements. FRA is a reliable technique for power transformer winding distortion and deformation assessment and monitoring. A lumped parameter model of a three phase power transformer is briefly presented and applied to simulate frequency responses at various winding fault conditions such as short-circuited turns, axial displacements and radial deformations. Simulations and discussions are presented to explore the potentials of the model to transformer fault detection based on FRA measurements.

This paper presents a novel model-based identification approach to determining laminated core par... more This paper presents a novel model-based identification approach to determining laminated core parameters of power transformers on the basis of frequency response analysis (FRA) measurements. A genetic algorithm is employed for parameter identification of a transformer core model, established using the duality principle between magnetic and electrical circuits. A well-known lumped parameter model of a 3-phase transformer is used to simulate reference input impedance frequency responses for analyzing the identification accuracy of the proposed approach. It is suggested that the approach can be applied for transformer core modeling and FRA result interpretation at low frequencies.

This paper presents a simplified distributed parameter model for minor winding deformation fault ... more This paper presents a simplified distributed parameter model for minor winding deformation fault analysis of power transformers on the basis of frequency response analysis (FRA). The FRA data of an experimental transformer is employed as a reference trace, which are compared with the simulations of the simplified distributed parameter model concerning minor winding deformation faults. In order to perform quantitative analysis when a deformation fault occurs, three statistical indicators are used to analyze the FRA simulation data. It is suggested in the results that minor winding deformation faults can be detected at the frequency range above 1 MHz.

This paper discusses a feature extraction technique with genetic programming (GP) and bootstrap t... more This paper discusses a feature extraction technique with genetic programming (GP) and bootstrap to improve interpretation accuracy of dissolved gas analysis (DGA) fault classification in power transformers, dealing with highly versatile or noise corrupted data. Initial DGA data are preprocessed with bootstrap to equalize the sample numbers for different fault classes, thus improving subsequent extraction of classification features with GP for each fault class. The features extracted with GP are then used as the inputs to artificial neural network (ANN), support vector machine (SVM) and K-nearest neighbor (KNN) classifiers for fault classification. The test results indicate that the proposed preprocessing approach can significantly improve the accuracy of power transformer fault classification based on DGA data.

Electric Power Systems Research, 2010

The paper discusses an improved modelling of transformer windings based on bacterial swarming alg... more The paper discusses an improved modelling of transformer windings based on bacterial swarming algorithm (BSA) and frequency response analysis (FRA). With the purpose to accurately identify transformer windings parameters a model-based identification approach is introduced using a well-known lumped parameter model. It includes search space estimation using analytical calculations, which is used for the subsequent model parameters identification with a novel BSA. The newly introduced BSA, being developed upon a bacterial foraging behavior, is described in detail. Simulations and discussions are presented to explore the potential of the proposed approach using simulated and experimentally measured FRA responses taken from two transformers. The BSA identification results are compared with those using genetic algorithm. It is shown that the proposed BSA delivers satisfactory parameter identification and improved modelling can be used for FRA results interpretation.

Iet Electric Power Applications, 2010

The study presents an evidential reasoning (ER) approach to transformer winding assessment based ... more The study presents an evidential reasoning (ER) approach to transformer winding assessment based on frequency response analysis (FRA). A conventional FRA assessment process is firstly discussed, where frequency response comparison methods and interpretation features are briefly introduced. Then an FRA assessment process is transferred into a multiple-attribute decision-making (MADM) problem under an ER framework and an introduction to the ER algorithm is given. Subsequently, several examples of transformer winding condition assessment problems are considered using two ER evaluation analysis models, where the potential of the ER approach in combining evidence and dealing with uncertainties is demonstrated. In the case when more than one expert is involved in an FRA assessment process, the developed ER framework can be used to aggregate experts' subjective judgements and produce an overall evaluation of the condition of a transformer winding in a formalised form.

IEEE Transactions on Systems, Man, and Cybernetics, 2009

This paper presents an intelligent fault classification approach to power transformer dissolved g... more This paper presents an intelligent fault classification approach to power transformer dissolved gas analysis (DGA), dealing with highly versatile or noise-corrupted data. Bootstrap and genetic programming (GP) are implemented to improve the interpretation accuracy for DGA of power transformers. Bootstrap preprocessing is utilized to approximately equalize the sample numbers for different fault classes to improve subsequent fault classification with GP feature extraction. GP is applied to establish classification features for each class based on the collected gas data. The features extracted with GP are then used as the inputs to artificial neural network (ANN), support vector machine (SVM) and K-nearest neighbor (KNN) classifiers for fault classification. The classification accuracies of the combined GP-ANN, GP-SVM, and GP-KNN classifiers are compared with the ones derived from ANN, SVM, and KNN classifiers, respectively. The test results indicate that the developed preprocessing approach can significantly improve the diagnosis accuracies for power transformer fault classification. Index Terms-Bootstrap, dissolved gas analysis (DGA), fault classification, feature extraction, genetic programming, K-nearest neighbor (KNN), neural networks, power transformer, support vector machine (SVM).

IEEE Transactions on Systems, Man, and Cybernetics, 2009

This paper presents a novel association rule mining (ARM)-based dissolved gas analysis (DGA) appr... more This paper presents a novel association rule mining (ARM)-based dissolved gas analysis (DGA) approach to fault diagnosis (FD) of power transformers. In the development of the ARM-based DGA approach, an attribute selection method and a continuous datum attribute discretization method are used for choosing user-interested ARM attributes from a DGA data set, i.e. the items that are employed to extract association rules. The given DGA data set is composed of two parts, i.e. training and test DGA data sets. An ARM algorithm namely Apriori-Total From Partial is proposed for generating an association rule set (ARS) from the training DGA data set. Afterwards, an ARS simplification method and a rule fitness evaluation method are utilized to select useful rules from the ARS and assign a fitness value to each of the useful rules, respectively. Based upon the useful association rules, a transformer FD classifier is developed, in which an optimal rule selection method is employed for selecting the most accurate rule from the classifier for diagnosing a test DGA record. For comparison purposes, five widely used FD methods are also tested with the same training and test data sets in experiments. Results show that the proposed ARM-based DGA approach is capable of generating a number of meaningful association rules, which can also cover the empirical rules defined in industry standards. Moreover, a higher FD accuracy can be achieved with the association rule-based FD classifier, compared with that derived by the other methods.

IEEE Transactions on Power Delivery, 2009

The paper presents a hybrid model of disc-type power transformer winding for frequency response a... more The paper presents a hybrid model of disc-type power transformer winding for frequency response analysis (FRA) based on traveling wave and multiconductor transmission line (MTL) theories. Each disc of a winding is described by traveling wave equations, which are connected to each other in a form of MTL matrix model. This significantly reduces the order of the model with respect to previously established MTL models of transformer winding. The model is applied to frequency response simulation of two single-phase transformers. The simulations are compared with the experimental data and calculated results using lumped parameter and MTL models reported in other publications. It is shown that the model can be used for FRA result interpretation in an extended range of frequencies up to several mega Hertz and resonance analysis under very fast transient overvoltages (VFTOs).

Lecture Notes in …, Jan 1, 2007

The paper presents a simplified mathematical model of disc-type transformer winding for frequency... more The paper presents a simplified mathematical model of disc-type transformer winding for frequency response analysis (FRA) based on traveling wave and multiconductor transmission line theories. The simplified model is applied to the FRA simulation of a transformer winding. In order to identify the distributed parameters of the model, an intelligent learning technique, rooted from particle swarm optimiser with passive congregation (PSOPC) is utilised. Simulations and discussions are presented to explore ...

Applications of Evolutionary …, Jan 1, 2007

The paper presents a simplified mathematical model of disc-type transformer winding for frequency... more The paper presents a simplified mathematical model of disc-type transformer winding for frequency response analysis (FRA) based on traveling wave and multiconductor transmission line theories. The simplified model is applied to the FRA simulation of a transformer winding. In order to identify the distributed parameters of the model, an intelligent learning technique, rooted from particle swarm optimiser with passive congregation (PSOPC) is utilised. Simulations and discussions are presented to explore ...

Control Conference, 2007. CCC …, Jan 1, 2007

Abstract This paper presents a least square support vector machine (LS-SVM) approach to dissolved... more Abstract This paper presents a least square support vector machine (LS-SVM) approach to dissolved gas analysis (DGA) problems for power transformers. Two methods are employed to improve the diagnosis accuracy for DGA analysis. First, bootstrap preprocessing is utilised to equalise the sample numbers for different fault types. Then, the preprocessed samples are inputted to a classier for fault classification. For comparison purposes, four classifiers are utilised, ie artificial neural network (ANN), k-nearest neighbour (KNN), simple SVM and LS ...