chirag naik - Academia.edu (original) (raw)

Papers by chirag naik

TENCON 2017 - 2017 IEEE Region 10 Conference

This study investigates the performance of a filter based feature selection approach for PQ event... more This study investigates the performance of a filter based feature selection approach for PQ event identification. The filter based approach is independent of the nature of induction algorithms used for the classification purposes and therefore offers several advantages over other approaches such as wrappers. This property of filter approach has been exploited in this study to obtain a generic feature subset that can be used with any induction algorithm. For this purpose, fourteen distinct single and simultaneous PQ events were simulated following IEEE Std. 1159. The feature selection of these events is accomplished through a combination of meta-heuristic search method and correlation based feature evaluation. Two meta-heuristic search methods based on Genetic Algorithm (GA) and Binary Particle Swarm Optimization (BPSO) have been included for the comparison of search performance. The efficacy of reduced feature subsets is evaluated through induction algorithm based on Naive-Bayes. The results convincingly demonstrated that it is possible to obtain significant reduction in the features (approx. 50% with GA, 86% with BPSO) without any compromise in the classification performance.

TENCON 2017 - 2017 IEEE Region 10 Conference, 2017

The present study focuses on the selection of appropriate wavelet basis which would result in bet... more The present study focuses on the selection of appropriate wavelet basis which would result in better classification of Power Quality (PQ) events. The accuracy of the classification is often critically dependent on the nature of wavelet basis and the induction algorithm. This study, therefore, comprehensively investigates the performance of several wavelet families including Daubechies, Coiflets, Symlets, Fejer-Korovkin, Bi-orthogonal and Reverse Bi-orthogonal from the prospective of PQ event identification. The performance of these wavelets was evaluated through fourteen distinct single and simultaneous PQ events which were generated following IEEE Std. 1159. Further, to investigate the interaction between induction algorithm and wavelet basis, two induction algorithms were included: k-Nearest Neighbor (k-NN) and Naive Bayes (NB). The results of the investigation convincingly demonstrate that ‘db18’ from the Daubechies family provides the best overall performance among 110 wavelet bases included in this study.

2016 IEEE 2nd Annual Southern Power Electronics Conference (SPEC), 2016

A novel method of classifying Power quality (PQ) events using Wavelet Packet Transform (WPT) and ... more A novel method of classifying Power quality (PQ) events using Wavelet Packet Transform (WPT) and Extreme Learning Machines (ELM) has been proposed. In recent times, the power quality has been a major research concern due to changing regulations, liberalized distribution market and increased use of power electronic based equipment. The first step of any remedial action requires proper identification of PQ events. One of the major challenge of this event identification is to extract significant features from the limited measurements, which can subsequently be used for the classification. Therefore, in the present study Wavelet Packet Transform (WPT) has been used to obtain several mathematical features. These features can segregate both single and simultaneous PQ event occurrences. Further to improve the classification performance, the ELM based classifier has been used. This classifier significantly reduces the training time by many-fold. The performance of the proposed approach has been compared with ANN based classifier considering over 1000 PQ signals from various PQ events. The results of the simulation demonstrate that the proposed approach can achieve over 99% classification accuracy.

Modelling, Measurement and Control A, 2019

The changed power system regulations, liberalization in distribution market and enhanced use of p... more The changed power system regulations, liberalization in distribution market and enhanced use of power electronics based equipment has raised the concerns about power quality (PQ). Though, the responsibility of PQ deterioration is shared by both utility and its consumers; the most influencing factor to the poor PQ is the consumer's load. The estimation of individual consumers' responsibility is a herculean task for the utilities. In this paper, a technique based on S-transform is proposed for the identification of the load responsible for specific type of PQ disturbance and the estimation of its responsibility in causing PQ deterioration at the point of common coupling (PCC). The main objective of this work is to fill the void in the PQ study by including utility's perspective. This paper presents a simple approach to identify the share of consumer's load that causes the PQ deterioration at the PCC. The proposed method is validated by PCC signals acquired by both MATLAB simulations and by using laboratory experimental setup.

Applied Soft Computing, 2019

A novel two-dimensional (2D) learning framework has been proposed to address the feature selectio... more A novel two-dimensional (2D) learning framework has been proposed to address the feature selection problem in Power Quality (PQ) events. Unlike the existing feature selection approaches, the proposed 2D learning explicitly incorporates the information about the subset cardinality (i.e., the number of features) as an additional learning dimension to effectively guide the search process. The efficacy of this approach has been demonstrated considering fourteen distinct classes of PQ events which conform to the IEEE Standard 1159. The search performance of the 2D learning approach has been compared to the other six well-known feature selection wrappers by considering two induction algorithms: Naive Bayes (NB) and k-Nearest Neighbors (k-NN). Further, the robustness of the selected/reduced feature subsets has been investigated considering seven different levels of noise. The results of this investigation convincingly demonstrate that the proposed 2D learning can identify significantly better and robust feature subsets for PQ events.

Pattern Recognition, 2018

This paper proposes a new generalized two dimensional learning approach for particle swarm based ... more This paper proposes a new generalized two dimensional learning approach for particle swarm based feature selection. The core idea of the proposed approach is to include the information about the subset cardinality into the learning framework by extending the dimension of the velocity. The 2D-learning framework retains all the key features of the original PSO, despite the extra learning dimension. Most of the popular variants of PSO can easily be adapted into this 2D learning framework for feature selection problems. The efficacy of the proposed learning approach has been evaluated considering several benchmark data and two induction algorithms: Naive-Bayes and k-Nearest Neighbor. The results of the comparative investigation including the time-complexity analysis with GA, ACO and five other PSO variants illustrate that the proposed 2D learning approach gives feature subset with relatively smaller cardinality and better classification performance with shorter run times.

IET Science, Measurement & Technology, 2018

IFAC-PapersOnLine, 2015

The nature of today's power system has become highly dynamic due to the increased use of nonlinea... more The nature of today's power system has become highly dynamic due to the increased use of nonlinear loads, power electronics based equipment and changed power system regulations. Conventionally, the Fourier transform (FT) is used for the power quality (PQ) analysis with parameters such as; THD and TDD. These parameters are suitable for stationary disturbances only. The recent state of power system demands to analyze the PQ disturbances on the basis of magnitude, time and frequency. In this paper, a new parameter based on Wavelet Packet Transform (WPT) is defined and tested for the short duration PQ disturbances such as; voltage sag, voltage swell, momentary interruptions, oscillatory transients and harmonics, simulated as per their broad definitions provided by the IEEE 1159-2009 standards.

2014 IEEE 6th India International Conference on Power Electronics (IICPE), 2014

ABSTRACT

2013 Annual International Conference on Emerging Research Areas and 2013 International Conference on Microelectronics, Communications and Renewable Energy, 2013

ABSTRACT The increased use of non-linear loads, power electronic switches and changing regulation... more ABSTRACT The increased use of non-linear loads, power electronic switches and changing regulations in today's power distribution system has made power quality (PQ) an important concern. The various types of PQ disturbances are defined in IEEE standards 1159-2009 in terms of their frequency, magnitude and duration. The broadness of these definitions further makes it difficult to investigate these disturbances. Harmonics are among very common disturbances and are taken care of by Fourier transform based index; total harmonic disturbance (THD) very well. In this paper, discrete wavelet transform (DWT) based approach is presented to detect, localize and investigate the transient disturbances present in the PQ signals. The PQ signals carrying harmonics and transient disturbances simultaneously are specifically considered to verify the usefulness of proposed wavelet transform based method in compare to Fourier transform based index, THD.

International Journal of Electrical Power & Energy Systems, 2013

ABSTRACT Changing power system regulations and increased use of nonlinear devices have made power... more ABSTRACT Changing power system regulations and increased use of nonlinear devices have made power quality (PQ) a highly important issue. The short duration transient disturbances, along with the stationary harmonics have become very common due to the increased use of power electronic switches. These transients are defined in terms of their spectral content, duration and magnitude by IEEE 1159-2009 standards and are non-stationary in nature. The conventional PQ indices based on Fourier transform fails to indicate them, since Fourier transform gives amplitude frequency distribution and the time information gets void. In this paper, a PQ index, based on discrete wavelet transform (DWT) is proposed in order to determine the amount of deviation from the desired pure signal. The proposed PQ index is defined as the weighted sum of percentage energy deviation of the DWT details. The test system is simulated using ATP/EMTP software. Transients resulted from ten different switching instants covering a full cycle of the signal and having natural frequency ranging from 500 Hz to 47 kHz, are considered to validate the proposed index. The proposed index is also tested with the signals containing harmonics. Further, the proposed index is verified with the real signals acquired by the laboratory experimentation.

2013 Annual IEEE India Conference (INDICON), 2013

ABSTRACT The increased use of power electronics based equipment, nonlinear loads and the changing... more ABSTRACT The increased use of power electronics based equipment, nonlinear loads and the changing power system regulations has made power quality (PQ) an important issue. The changed load condition has increased the proliferation of non-stationary PQ disturbances such as; voltage sag, swell, momentary interruptions, transients, along with the stationary harmonics. The conventionally used Fourier transform is found unsuitable for the analysis of non-stationary PQ disturbances. In this paper, a new feature vector based on the time-frequency distribution technique; S-transform is proposed for the analysis of PQ disturbances. The new feature vector is based on the variance. Simulated signals of different short duration PQ disturbances with different possible variations are used to validate the proposed feature vector. Various simultaneously occurring disturbances are also considered for the validation. Further, the average, maximum and minimum values of this feature vector are calculated to show the effectiveness of the proposed feature for the identification of simulated PQ disturbances.

2012 IEEE International Conference on Power and Energy (PECon), 2012

ABSTRACT The changing power system regulations and increased use of power electronics based equip... more ABSTRACT The changing power system regulations and increased use of power electronics based equipment, has made power quality (PQ) a highly important issue. The conventional Fourier transform based PQ indices work well with stationary disturbances, but fail to indicate or quantify the PQ issues related to non-stationary disturbances. In order to consider the effects of PQ disturbances, that occur for a short duration and contain frequency components other than fundamental, a method based on time-frequency distribution, called S-transform, is used in this paper. S-transform is used to define two PQ indices, instantaneous form factor, IFF(τ) and instantaneous frequency variation index, IFI(τ), to indicate and quantify PQ. Simulated PQ signals for different short duration PQ disturbances like; voltage sag, voltage swell, momentary interruption, harmonics, impulsive transient and oscillatory transients with different possible variations are used to test proposed PQ indices. Averages and peak values of proposed indices are also computed to justify their indicating capabilities.

2011 International Conference on Power and Energy Systems, 2011

Digital signal processing techniques based power quality analysis has attracted the attention of ... more Digital signal processing techniques based power quality analysis has attracted the attention of number of researchers. There are different time frequency techniques like short time Fourier transform (STFT), Continuous Wavelet transform (CWT) and S-transform used for the analysis of power quality disturbances. S-transform is a modified version of CWT with a phase correction. It offers a distinct advantage over the

Australian Journal of Chemistry, 2007

Starting from the well known stable free radical 2,2-diphenyl-1-picrylhydrazyl (DPPH; 2a) and its... more Starting from the well known stable free radical 2,2-diphenyl-1-picrylhydrazyl (DPPH; 2a) and its congener 2,2-diphenyl-1-(4-cyano-2,6-dinitrophenyl)hydrazyl 2b, or from their reduced hydrazine counterparts 1a,b, it was possible to obtain the p-quinonoid compounds 4a,b by oxidation with ceric (Ce4+) sulfate, which by reduction gave the corresponding hydroxyl derivatives 2-phenyl-2-(4-hydroxyphenyl)-1-picrylhydrazine 5a or 2-phenyl-2-(4-hydroxyphenyl)-1-(4-cyano-2,6-dinitrophenyl)hydrazine 5b. These hydroxyl derivatives (5a,b) react with 4-carboxy-TEMPO or 2,2-diphenyl-1-(4-carboxy-2,6-dinitrophenyl)hydrazine to form the corresponding esters 6a,b or 8a,b. These esters (6a,b and 8a,b) lead to the hybrid hetero diradicals (nitroxide–hydrazyl type) 7a,b or homo biradicals (hydrazyl–hydrazyl type) 9a,b by oxidation with lead dioxide or potassium permanganate. The new compounds were characterized by UV-vis, NMR, EPR, and MS analysis, and their magnetic behaviour was investigated.

TENCON 2017 - 2017 IEEE Region 10 Conference

This study investigates the performance of a filter based feature selection approach for PQ event... more This study investigates the performance of a filter based feature selection approach for PQ event identification. The filter based approach is independent of the nature of induction algorithms used for the classification purposes and therefore offers several advantages over other approaches such as wrappers. This property of filter approach has been exploited in this study to obtain a generic feature subset that can be used with any induction algorithm. For this purpose, fourteen distinct single and simultaneous PQ events were simulated following IEEE Std. 1159. The feature selection of these events is accomplished through a combination of meta-heuristic search method and correlation based feature evaluation. Two meta-heuristic search methods based on Genetic Algorithm (GA) and Binary Particle Swarm Optimization (BPSO) have been included for the comparison of search performance. The efficacy of reduced feature subsets is evaluated through induction algorithm based on Naive-Bayes. The results convincingly demonstrated that it is possible to obtain significant reduction in the features (approx. 50% with GA, 86% with BPSO) without any compromise in the classification performance.

TENCON 2017 - 2017 IEEE Region 10 Conference, 2017

The present study focuses on the selection of appropriate wavelet basis which would result in bet... more The present study focuses on the selection of appropriate wavelet basis which would result in better classification of Power Quality (PQ) events. The accuracy of the classification is often critically dependent on the nature of wavelet basis and the induction algorithm. This study, therefore, comprehensively investigates the performance of several wavelet families including Daubechies, Coiflets, Symlets, Fejer-Korovkin, Bi-orthogonal and Reverse Bi-orthogonal from the prospective of PQ event identification. The performance of these wavelets was evaluated through fourteen distinct single and simultaneous PQ events which were generated following IEEE Std. 1159. Further, to investigate the interaction between induction algorithm and wavelet basis, two induction algorithms were included: k-Nearest Neighbor (k-NN) and Naive Bayes (NB). The results of the investigation convincingly demonstrate that ‘db18’ from the Daubechies family provides the best overall performance among 110 wavelet bases included in this study.

2016 IEEE 2nd Annual Southern Power Electronics Conference (SPEC), 2016

A novel method of classifying Power quality (PQ) events using Wavelet Packet Transform (WPT) and ... more A novel method of classifying Power quality (PQ) events using Wavelet Packet Transform (WPT) and Extreme Learning Machines (ELM) has been proposed. In recent times, the power quality has been a major research concern due to changing regulations, liberalized distribution market and increased use of power electronic based equipment. The first step of any remedial action requires proper identification of PQ events. One of the major challenge of this event identification is to extract significant features from the limited measurements, which can subsequently be used for the classification. Therefore, in the present study Wavelet Packet Transform (WPT) has been used to obtain several mathematical features. These features can segregate both single and simultaneous PQ event occurrences. Further to improve the classification performance, the ELM based classifier has been used. This classifier significantly reduces the training time by many-fold. The performance of the proposed approach has been compared with ANN based classifier considering over 1000 PQ signals from various PQ events. The results of the simulation demonstrate that the proposed approach can achieve over 99% classification accuracy.

Modelling, Measurement and Control A, 2019

The changed power system regulations, liberalization in distribution market and enhanced use of p... more The changed power system regulations, liberalization in distribution market and enhanced use of power electronics based equipment has raised the concerns about power quality (PQ). Though, the responsibility of PQ deterioration is shared by both utility and its consumers; the most influencing factor to the poor PQ is the consumer's load. The estimation of individual consumers' responsibility is a herculean task for the utilities. In this paper, a technique based on S-transform is proposed for the identification of the load responsible for specific type of PQ disturbance and the estimation of its responsibility in causing PQ deterioration at the point of common coupling (PCC). The main objective of this work is to fill the void in the PQ study by including utility's perspective. This paper presents a simple approach to identify the share of consumer's load that causes the PQ deterioration at the PCC. The proposed method is validated by PCC signals acquired by both MATLAB simulations and by using laboratory experimental setup.

Applied Soft Computing, 2019

A novel two-dimensional (2D) learning framework has been proposed to address the feature selectio... more A novel two-dimensional (2D) learning framework has been proposed to address the feature selection problem in Power Quality (PQ) events. Unlike the existing feature selection approaches, the proposed 2D learning explicitly incorporates the information about the subset cardinality (i.e., the number of features) as an additional learning dimension to effectively guide the search process. The efficacy of this approach has been demonstrated considering fourteen distinct classes of PQ events which conform to the IEEE Standard 1159. The search performance of the 2D learning approach has been compared to the other six well-known feature selection wrappers by considering two induction algorithms: Naive Bayes (NB) and k-Nearest Neighbors (k-NN). Further, the robustness of the selected/reduced feature subsets has been investigated considering seven different levels of noise. The results of this investigation convincingly demonstrate that the proposed 2D learning can identify significantly better and robust feature subsets for PQ events.

Pattern Recognition, 2018

This paper proposes a new generalized two dimensional learning approach for particle swarm based ... more This paper proposes a new generalized two dimensional learning approach for particle swarm based feature selection. The core idea of the proposed approach is to include the information about the subset cardinality into the learning framework by extending the dimension of the velocity. The 2D-learning framework retains all the key features of the original PSO, despite the extra learning dimension. Most of the popular variants of PSO can easily be adapted into this 2D learning framework for feature selection problems. The efficacy of the proposed learning approach has been evaluated considering several benchmark data and two induction algorithms: Naive-Bayes and k-Nearest Neighbor. The results of the comparative investigation including the time-complexity analysis with GA, ACO and five other PSO variants illustrate that the proposed 2D learning approach gives feature subset with relatively smaller cardinality and better classification performance with shorter run times.

IET Science, Measurement & Technology, 2018

IFAC-PapersOnLine, 2015

The nature of today's power system has become highly dynamic due to the increased use of nonlinea... more The nature of today's power system has become highly dynamic due to the increased use of nonlinear loads, power electronics based equipment and changed power system regulations. Conventionally, the Fourier transform (FT) is used for the power quality (PQ) analysis with parameters such as; THD and TDD. These parameters are suitable for stationary disturbances only. The recent state of power system demands to analyze the PQ disturbances on the basis of magnitude, time and frequency. In this paper, a new parameter based on Wavelet Packet Transform (WPT) is defined and tested for the short duration PQ disturbances such as; voltage sag, voltage swell, momentary interruptions, oscillatory transients and harmonics, simulated as per their broad definitions provided by the IEEE 1159-2009 standards.

2014 IEEE 6th India International Conference on Power Electronics (IICPE), 2014

ABSTRACT

2013 Annual International Conference on Emerging Research Areas and 2013 International Conference on Microelectronics, Communications and Renewable Energy, 2013

ABSTRACT The increased use of non-linear loads, power electronic switches and changing regulation... more ABSTRACT The increased use of non-linear loads, power electronic switches and changing regulations in today's power distribution system has made power quality (PQ) an important concern. The various types of PQ disturbances are defined in IEEE standards 1159-2009 in terms of their frequency, magnitude and duration. The broadness of these definitions further makes it difficult to investigate these disturbances. Harmonics are among very common disturbances and are taken care of by Fourier transform based index; total harmonic disturbance (THD) very well. In this paper, discrete wavelet transform (DWT) based approach is presented to detect, localize and investigate the transient disturbances present in the PQ signals. The PQ signals carrying harmonics and transient disturbances simultaneously are specifically considered to verify the usefulness of proposed wavelet transform based method in compare to Fourier transform based index, THD.

International Journal of Electrical Power & Energy Systems, 2013

ABSTRACT Changing power system regulations and increased use of nonlinear devices have made power... more ABSTRACT Changing power system regulations and increased use of nonlinear devices have made power quality (PQ) a highly important issue. The short duration transient disturbances, along with the stationary harmonics have become very common due to the increased use of power electronic switches. These transients are defined in terms of their spectral content, duration and magnitude by IEEE 1159-2009 standards and are non-stationary in nature. The conventional PQ indices based on Fourier transform fails to indicate them, since Fourier transform gives amplitude frequency distribution and the time information gets void. In this paper, a PQ index, based on discrete wavelet transform (DWT) is proposed in order to determine the amount of deviation from the desired pure signal. The proposed PQ index is defined as the weighted sum of percentage energy deviation of the DWT details. The test system is simulated using ATP/EMTP software. Transients resulted from ten different switching instants covering a full cycle of the signal and having natural frequency ranging from 500 Hz to 47 kHz, are considered to validate the proposed index. The proposed index is also tested with the signals containing harmonics. Further, the proposed index is verified with the real signals acquired by the laboratory experimentation.

2013 Annual IEEE India Conference (INDICON), 2013

ABSTRACT The increased use of power electronics based equipment, nonlinear loads and the changing... more ABSTRACT The increased use of power electronics based equipment, nonlinear loads and the changing power system regulations has made power quality (PQ) an important issue. The changed load condition has increased the proliferation of non-stationary PQ disturbances such as; voltage sag, swell, momentary interruptions, transients, along with the stationary harmonics. The conventionally used Fourier transform is found unsuitable for the analysis of non-stationary PQ disturbances. In this paper, a new feature vector based on the time-frequency distribution technique; S-transform is proposed for the analysis of PQ disturbances. The new feature vector is based on the variance. Simulated signals of different short duration PQ disturbances with different possible variations are used to validate the proposed feature vector. Various simultaneously occurring disturbances are also considered for the validation. Further, the average, maximum and minimum values of this feature vector are calculated to show the effectiveness of the proposed feature for the identification of simulated PQ disturbances.

2012 IEEE International Conference on Power and Energy (PECon), 2012

ABSTRACT The changing power system regulations and increased use of power electronics based equip... more ABSTRACT The changing power system regulations and increased use of power electronics based equipment, has made power quality (PQ) a highly important issue. The conventional Fourier transform based PQ indices work well with stationary disturbances, but fail to indicate or quantify the PQ issues related to non-stationary disturbances. In order to consider the effects of PQ disturbances, that occur for a short duration and contain frequency components other than fundamental, a method based on time-frequency distribution, called S-transform, is used in this paper. S-transform is used to define two PQ indices, instantaneous form factor, IFF(τ) and instantaneous frequency variation index, IFI(τ), to indicate and quantify PQ. Simulated PQ signals for different short duration PQ disturbances like; voltage sag, voltage swell, momentary interruption, harmonics, impulsive transient and oscillatory transients with different possible variations are used to test proposed PQ indices. Averages and peak values of proposed indices are also computed to justify their indicating capabilities.

2011 International Conference on Power and Energy Systems, 2011

Digital signal processing techniques based power quality analysis has attracted the attention of ... more Digital signal processing techniques based power quality analysis has attracted the attention of number of researchers. There are different time frequency techniques like short time Fourier transform (STFT), Continuous Wavelet transform (CWT) and S-transform used for the analysis of power quality disturbances. S-transform is a modified version of CWT with a phase correction. It offers a distinct advantage over the

Australian Journal of Chemistry, 2007

Starting from the well known stable free radical 2,2-diphenyl-1-picrylhydrazyl (DPPH; 2a) and its... more Starting from the well known stable free radical 2,2-diphenyl-1-picrylhydrazyl (DPPH; 2a) and its congener 2,2-diphenyl-1-(4-cyano-2,6-dinitrophenyl)hydrazyl 2b, or from their reduced hydrazine counterparts 1a,b, it was possible to obtain the p-quinonoid compounds 4a,b by oxidation with ceric (Ce4+) sulfate, which by reduction gave the corresponding hydroxyl derivatives 2-phenyl-2-(4-hydroxyphenyl)-1-picrylhydrazine 5a or 2-phenyl-2-(4-hydroxyphenyl)-1-(4-cyano-2,6-dinitrophenyl)hydrazine 5b. These hydroxyl derivatives (5a,b) react with 4-carboxy-TEMPO or 2,2-diphenyl-1-(4-carboxy-2,6-dinitrophenyl)hydrazine to form the corresponding esters 6a,b or 8a,b. These esters (6a,b and 8a,b) lead to the hybrid hetero diradicals (nitroxide–hydrazyl type) 7a,b or homo biradicals (hydrazyl–hydrazyl type) 9a,b by oxidation with lead dioxide or potassium permanganate. The new compounds were characterized by UV-vis, NMR, EPR, and MS analysis, and their magnetic behaviour was investigated.