Pub Date : 2018-10-01DOI: 10.1109/ICon-EEI.2018.8784326
Muhammad Ihsan Zul, F. Yulia, Dini Nurmalasari
Opinions are a major influence when making decisions for individuals or organizations. A collection of opinions can be extracted to gain useful knowledge. This knowledge is used as a source of information which can be used as a consideration in decision making. The extraction of knowledge from text has been known as text mining. Text mining has any kinds of algorithm to extract information from collected text, such as K-Means, K-Nearest Neighbors, Naïve Bayes, and the others. One of the sources of opinion is from social media, especially Facebook and Twitter. On Facebook and Twitter, many people have been writing their opinions about many things. This very much data are difficult to analyze thoroughly. In this paper, K-Means and Naïve Bayes algorithm are developed to analyze public opinions or sentiments. Outlier removal is also added to this analysis. Opinions are taken from Facebook and Twitter. The accuracy of the system is tested 10 times at k different points for each k value (k=6, 7, 8, 9 and 10). As the result, the combination of K-Means and Naïve Bayes has lower accuracy than the accuracy produced by Naïve Bayes without the combination of K-Means, but almost same accuracies. The accuracy of Naïve Bayes algorithm is from 80.526%–82.500%, while the combination of Naïve Bayes and K-Means has 80.323%–81.523% accuracy.
{"title":"Social Media Sentiment Analysis Using K-Means and Naïve Bayes Algorithm","authors":"Muhammad Ihsan Zul, F. Yulia, Dini Nurmalasari","doi":"10.1109/ICon-EEI.2018.8784326","DOIUrl":"https://doi.org/10.1109/ICon-EEI.2018.8784326","url":null,"abstract":"Opinions are a major influence when making decisions for individuals or organizations. A collection of opinions can be extracted to gain useful knowledge. This knowledge is used as a source of information which can be used as a consideration in decision making. The extraction of knowledge from text has been known as text mining. Text mining has any kinds of algorithm to extract information from collected text, such as K-Means, K-Nearest Neighbors, Naïve Bayes, and the others. One of the sources of opinion is from social media, especially Facebook and Twitter. On Facebook and Twitter, many people have been writing their opinions about many things. This very much data are difficult to analyze thoroughly. In this paper, K-Means and Naïve Bayes algorithm are developed to analyze public opinions or sentiments. Outlier removal is also added to this analysis. Opinions are taken from Facebook and Twitter. The accuracy of the system is tested 10 times at k different points for each k value (k=6, 7, 8, 9 and 10). As the result, the combination of K-Means and Naïve Bayes has lower accuracy than the accuracy produced by Naïve Bayes without the combination of K-Means, but almost same accuracies. The accuracy of Naïve Bayes algorithm is from 80.526%–82.500%, while the combination of Naïve Bayes and K-Means has 80.323%–81.523% accuracy.","PeriodicalId":114952,"journal":{"name":"2018 2nd International Conference on Electrical Engineering and Informatics (ICon EEI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129752485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICon-EEI.2018.8784312
T. Chandrawati, R. F. Sari
This paper reviews the firefly algorithm and its implementation on path planning problems, vehicle routing problem and traveling salesman problem. Swarm Intelligence is an intelligence based on collective behavior in decentralized systems. One of the algorithms based on swarm intelligent is the firefly algorithm. Firefly algorithm is widely used to solve optimization problems. Many researchers share developed the standard firefly algorithm to solve the problems encountered due to the different characteristics of the problem. This condition raises several terms for the new algorithm, namely Modified Firefly Algorithm, Adaptive Firefly Algorithm, Discrete Firefly Algorithm, and Hybrid Firefly Algorithm. We explored different firefly algorithm to solve their common characteristics the path planning, vehicle routing problem, and traveling salesman problem which are path, time and distance optimization.
{"title":"A Review of Firefly Algorithms for Path Planning, Vehicle Routing and Traveling Salesman Problems","authors":"T. Chandrawati, R. F. Sari","doi":"10.1109/ICon-EEI.2018.8784312","DOIUrl":"https://doi.org/10.1109/ICon-EEI.2018.8784312","url":null,"abstract":"This paper reviews the firefly algorithm and its implementation on path planning problems, vehicle routing problem and traveling salesman problem. Swarm Intelligence is an intelligence based on collective behavior in decentralized systems. One of the algorithms based on swarm intelligent is the firefly algorithm. Firefly algorithm is widely used to solve optimization problems. Many researchers share developed the standard firefly algorithm to solve the problems encountered due to the different characteristics of the problem. This condition raises several terms for the new algorithm, namely Modified Firefly Algorithm, Adaptive Firefly Algorithm, Discrete Firefly Algorithm, and Hybrid Firefly Algorithm. We explored different firefly algorithm to solve their common characteristics the path planning, vehicle routing problem, and traveling salesman problem which are path, time and distance optimization.","PeriodicalId":114952,"journal":{"name":"2018 2nd International Conference on Electrical Engineering and Informatics (ICon EEI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125478951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICon-EEI.2018.8784311
I. Rosma, Ichsan Maulana Putra, D. Y. Sukma, Ery Safrianti, Azriyenni Azhari Zakri, A. Abdulkarim
The utilization of Solar Photovoltaic (SPV) generation system is generally installed at some certain tilted angles, therefore it does not obtain the optimum solar radiation from the sun. In order to overcome this weakness, the SPV generation system that is equipped with a single axis sun tracker was designed and analyzed in this paper. The sun tracker system has two LDR sensors to estimate the position of the sun. Arduino Uno 3 was implemented as a controller system. The Arduino Uno 3 instructs a servo motor to drive SPV panel from the east to the west to track the movement of the sun in a similar direction. In order to understand the energy gain of single axis sun tracker, it has been compared with SPV generation system installed at the certain number of tilted angles. It can be noted from the results that the SPV generation system with single axis sun tracker has a significant increase in energy production than without tracker where its energy gain is up to 22%. Therefore, it can be concluded that there is a promising potential increase in energy when the SPV panel is equipped with the single axis sun tracker generally in tropical regions.
利用太阳能光伏(SPV)发电系统通常安装在一定的倾斜角度，因此不能获得最佳的太阳辐射。为了克服这一缺点，本文设计并分析了单轴太阳跟踪器的SPV发电系统。太阳跟踪系统有两个LDR传感器来估计太阳的位置。Arduino Uno 3作为控制器系统实现。Arduino Uno 3指示伺服电机驱动SPV面板从东向西跟踪太阳在类似方向的运动。为了了解单轴太阳跟踪器的能量增益，将其与安装在一定倾角下的SPV发电系统进行了比较。结果表明，采用单轴太阳跟踪器的SPV发电系统比不采用跟踪器的SPV发电系统发电量显著增加，其能量增益可达22%。因此，可以得出结论，在热带地区，SPV面板一般配备单轴太阳跟踪器时，有很好的增加能量的潜力。
{"title":"Analysis of Single Axis Sun Tracker System to Increase Solar Photovoltaic Energy Production in the Tropics","authors":"I. Rosma, Ichsan Maulana Putra, D. Y. Sukma, Ery Safrianti, Azriyenni Azhari Zakri, A. Abdulkarim","doi":"10.1109/ICon-EEI.2018.8784311","DOIUrl":"https://doi.org/10.1109/ICon-EEI.2018.8784311","url":null,"abstract":"The utilization of Solar Photovoltaic (SPV) generation system is generally installed at some certain tilted angles, therefore it does not obtain the optimum solar radiation from the sun. In order to overcome this weakness, the SPV generation system that is equipped with a single axis sun tracker was designed and analyzed in this paper. The sun tracker system has two LDR sensors to estimate the position of the sun. Arduino Uno 3 was implemented as a controller system. The Arduino Uno 3 instructs a servo motor to drive SPV panel from the east to the west to track the movement of the sun in a similar direction. In order to understand the energy gain of single axis sun tracker, it has been compared with SPV generation system installed at the certain number of tilted angles. It can be noted from the results that the SPV generation system with single axis sun tracker has a significant increase in energy production than without tracker where its energy gain is up to 22%. Therefore, it can be concluded that there is a promising potential increase in energy when the SPV panel is equipped with the single axis sun tracker generally in tropical regions.","PeriodicalId":114952,"journal":{"name":"2018 2nd International Conference on Electrical Engineering and Informatics (ICon EEI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130449411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICon-EEI.2018.8784323
Budhi Anto, Yangly Pamma Refli, F. Murdiya, E. Hamdani, Suwitno, A. Hamzah
The method of designing a single-stack variable-reluctance (VR) stepping motor for use as an actuator of the transition mechanism of the new type of automatic transfer switch is presented in this paper. The design procedure is explained and supported with several equations derived from electromechanical conversion theory. The golden ratio is introduced in design equation which relates the axial length of the stator core to the stator bore diameter. The flux density inside all parts of the machine is investigated using finite-element analysis based software package MagNet Infolytica in order to ensure the machine is operated at linear region of the core magnetization curve. The software also generates the torque profile which graphically figures the electromagnetic torque produced by the machine versus the rotor position. The material for stator and rotor cores uses high permeability magnetic material such as Carpenter silicon steel. The stepping motor will have 6 poles at the stator and 4 teeth at the rotor and will produce maximum torque of 0.3 Nm at 1 A excitation current. Based on the simulation results, the dimensions of the stator and rotor cores of VR stepping motor are as follows, motor axial length 80 mm, stator outer diameter 122 mm, stator bore diameter 72 mm, rotor outer diameter 71 mm and rotor shaft diameter 20 mm, and also the coil of each stator poles will have 800 turns.
{"title":"Design and Analysis of Variable-Reluctance Stepping Motor as Actuator Element of New Type Automatic Transfer Switch","authors":"Budhi Anto, Yangly Pamma Refli, F. Murdiya, E. Hamdani, Suwitno, A. Hamzah","doi":"10.1109/ICon-EEI.2018.8784323","DOIUrl":"https://doi.org/10.1109/ICon-EEI.2018.8784323","url":null,"abstract":"The method of designing a single-stack variable-reluctance (VR) stepping motor for use as an actuator of the transition mechanism of the new type of automatic transfer switch is presented in this paper. The design procedure is explained and supported with several equations derived from electromechanical conversion theory. The golden ratio is introduced in design equation which relates the axial length of the stator core to the stator bore diameter. The flux density inside all parts of the machine is investigated using finite-element analysis based software package MagNet Infolytica in order to ensure the machine is operated at linear region of the core magnetization curve. The software also generates the torque profile which graphically figures the electromagnetic torque produced by the machine versus the rotor position. The material for stator and rotor cores uses high permeability magnetic material such as Carpenter silicon steel. The stepping motor will have 6 poles at the stator and 4 teeth at the rotor and will produce maximum torque of 0.3 Nm at 1 A excitation current. Based on the simulation results, the dimensions of the stator and rotor cores of VR stepping motor are as follows, motor axial length 80 mm, stator outer diameter 122 mm, stator bore diameter 72 mm, rotor outer diameter 71 mm and rotor shaft diameter 20 mm, and also the coil of each stator poles will have 800 turns.","PeriodicalId":114952,"journal":{"name":"2018 2nd International Conference on Electrical Engineering and Informatics (ICon EEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128531763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICon-EEI.2018.8784338
F. Murdiya, N. Frimayanti, Marzieh Yaeghoobi
Air is a gas insulation in high voltage engineering. Generally, the air content consisted of several gas elements like N2, CO2, CO, H2, CO, and O2. Sunlight can cause the air ionization, the air ionization can resulted because of the high electric fields and also the interaction between electrons from gas molecules. The air which ionized in the high voltage, leads to the event of isolation failure or better known as the failure process of Streamer and Townsend. The main purpose of this research was to get a better insight of air ionization process. Tools such as molecular dynamic and SCF calculation can be used to achieve this goal. For the CO2 molecule, the best pose was selected at the time value of 1.000 s with the energy of 0.0502 kcal/mol, at temperature of 120.440 K and pressure of 1260386 barr. While the other gas, N2 molecule, is seems to be stable under ionization process. Thus, for this molecule, the best pose was found at the time value of 1.000 s, energy of 0.0526 kcal/mol, with temperature of 205.949 K and pressure of 78539.601 barr. Based on the molecular dynamic results, O2 molecule will be ionizes at time value of 1.000, energy of 0.430 kcal/mol, with temperature of 0.0104 K and pressure of 18498.320 barr. SCF calculation give the energy ionization potential value for N2, CO2, O2, H2, N2 and O2, CO2 and O2, CO2 N2 and O2 of 9.38 eV, 11.81 eV, 9.38 eV, 11.99 eV, 9.38 eV, 9.38 eV, 9.38 eV, respectively. Based on this calculation, the molecule with lowest potential ionization energy can ionized easier. N2, NO2, N2 gases and O2, CO2 and O2, CO2, N2 and O2 are ionized easier than gas CO2 and H2.
{"title":"Application of Molecular Dynamics Study and Homo Lumo Calculation on the Ionized Air for High Voltage Engineering","authors":"F. Murdiya, N. Frimayanti, Marzieh Yaeghoobi","doi":"10.1109/ICon-EEI.2018.8784338","DOIUrl":"https://doi.org/10.1109/ICon-EEI.2018.8784338","url":null,"abstract":"Air is a gas insulation in high voltage engineering. Generally, the air content consisted of several gas elements like N<inf>2</inf>, CO<inf>2</inf>, CO, H<inf>2</inf>, CO, and O<inf>2</inf>. Sunlight can cause the air ionization, the air ionization can resulted because of the high electric fields and also the interaction between electrons from gas molecules. The air which ionized in the high voltage, leads to the event of isolation failure or better known as the failure process of Streamer and Townsend. The main purpose of this research was to get a better insight of air ionization process. Tools such as molecular dynamic and SCF calculation can be used to achieve this goal. For the CO<inf>2</inf> molecule, the best pose was selected at the time value of 1.000 s with the energy of 0.0502 kcal/mol, at temperature of 120.440 K and pressure of 1260386 barr. While the other gas, N<inf>2</inf> molecule, is seems to be stable under ionization process. Thus, for this molecule, the best pose was found at the time value of 1.000 s, energy of 0.0526 kcal/mol, with temperature of 205.949 K and pressure of 78539.601 barr. Based on the molecular dynamic results, O<inf>2</inf> molecule will be ionizes at time value of 1.000, energy of 0.430 kcal/mol, with temperature of 0.0104 K and pressure of 18498.320 barr. SCF calculation give the energy ionization potential value for N<inf>2</inf>, CO<inf>2</inf>, O<inf>2</inf>, H<inf>2,</inf> N<inf>2</inf> and O<inf>2</inf>, CO<inf>2</inf> and O<inf>2</inf>, CO<inf>2</inf> N<inf>2</inf> and O<inf>2</inf> of 9.38 eV, 11.81 eV, 9.38 eV, 11.99 eV, 9.38 eV, 9.38 eV, 9.38 eV, respectively. Based on this calculation, the molecule with lowest potential ionization energy can ionized easier. N<inf>2,</inf> NO<inf>2</inf>, N<inf>2</inf> gases and O<inf>2</inf>, CO<inf>2</inf> and O<inf>2</inf>, CO<inf>2</inf>, N<inf>2</inf> and O<inf>2</inf> are ionized easier than gas CO<inf>2</inf> and H<inf>2</inf>.","PeriodicalId":114952,"journal":{"name":"2018 2nd International Conference on Electrical Engineering and Informatics (ICon EEI)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126006089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICon-EEI.2018.8784136
D. Nasien, Feri Candra, Delsavonita, D. Yulianti, Rahmat Rizal Andhi, M. H. Adiya
This paper describes a proposed algorithm for recognition of Korean Letters to the Latin language using Principle Component Analysis (PCA) and Back Propagation-Neural Network (BP-NN). The proposed algorithm uses input in the form of image of Korean letters in original 65×65 pixels that is taken from itself. Then, it will be done some processes namely, pre-processing converts image pixel into binary image 15×15 pixels. Further, it transforms from image Red Green Blue (RGB) into binary. Lastly, noise removal from the image. The image will be extracted to produce the image feature. The feature should be processed firstly using Principle Components Analysis (PCA). PCA is used to reduce dimension of image feature before entering classification stage. Classification stage uses a method that called BP-NN. Architecture of ANN uses three hidden layers. Each layer consists of 20, 20 and 5 neurons, and 1 neuron output. The proposed algorithm uses data sampling that is Korean vowels, are obtained from 25 different font types. Next, each font consists of normal sampling and bold sampling. Total data reaches 500 sampling. The data comprises 70% data training and 30% data testing. The result of experiments show that accuracy level is 95%.
{"title":"Off-line Handwritten Korean Letter using Principle Component Analysis and Back Propagation Neural Network","authors":"D. Nasien, Feri Candra, Delsavonita, D. Yulianti, Rahmat Rizal Andhi, M. H. Adiya","doi":"10.1109/ICon-EEI.2018.8784136","DOIUrl":"https://doi.org/10.1109/ICon-EEI.2018.8784136","url":null,"abstract":"This paper describes a proposed algorithm for recognition of Korean Letters to the Latin language using Principle Component Analysis (PCA) and Back Propagation-Neural Network (BP-NN). The proposed algorithm uses input in the form of image of Korean letters in original 65×65 pixels that is taken from itself. Then, it will be done some processes namely, pre-processing converts image pixel into binary image 15×15 pixels. Further, it transforms from image Red Green Blue (RGB) into binary. Lastly, noise removal from the image. The image will be extracted to produce the image feature. The feature should be processed firstly using Principle Components Analysis (PCA). PCA is used to reduce dimension of image feature before entering classification stage. Classification stage uses a method that called BP-NN. Architecture of ANN uses three hidden layers. Each layer consists of 20, 20 and 5 neurons, and 1 neuron output. The proposed algorithm uses data sampling that is Korean vowels, are obtained from 25 different font types. Next, each font consists of normal sampling and bold sampling. Total data reaches 500 sampling. The data comprises 70% data training and 30% data testing. The result of experiments show that accuracy level is 95%.","PeriodicalId":114952,"journal":{"name":"2018 2nd International Conference on Electrical Engineering and Informatics (ICon EEI)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124157877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICon-EEI.2018.8784315
A. Sandhyavitri, R. Amri, M. Yusa, D. Fermana, N. Ali
The objective of this paper is to explore the state of art in developing a package of early warning system in mitigating peat fire disasters. The system was developed based on the combination utilization of the fire sensors, wireless technology, and SMS gateways. The early warning system was conducted by installing a number of LM35 temperature sensors in the field in Riau, Indonesia, as well as Atmega8 microcontrollers as transmitters and receivers of the fire data. Then these data will be transmitted wirelessly to the microcontroller. This early warning software application package has been developed using various applications such as GSM Gateway Application, MySQL database, Apache web server with PHP engine. This system will display the exact locations of the burning field as real-time information to the designated numbers of mobile phones (in the form of SMS texts) or a dedicated PC computer (in the form of GIS maps).
{"title":"Early Warning Systems Using Fire Sensors, Wireless, and SMS Technology","authors":"A. Sandhyavitri, R. Amri, M. Yusa, D. Fermana, N. Ali","doi":"10.1109/ICon-EEI.2018.8784315","DOIUrl":"https://doi.org/10.1109/ICon-EEI.2018.8784315","url":null,"abstract":"The objective of this paper is to explore the state of art in developing a package of early warning system in mitigating peat fire disasters. The system was developed based on the combination utilization of the fire sensors, wireless technology, and SMS gateways. The early warning system was conducted by installing a number of LM35 temperature sensors in the field in Riau, Indonesia, as well as Atmega8 microcontrollers as transmitters and receivers of the fire data. Then these data will be transmitted wirelessly to the microcontroller. This early warning software application package has been developed using various applications such as GSM Gateway Application, MySQL database, Apache web server with PHP engine. This system will display the exact locations of the burning field as real-time information to the designated numbers of mobile phones (in the form of SMS texts) or a dedicated PC computer (in the form of GIS maps).","PeriodicalId":114952,"journal":{"name":"2018 2nd International Conference on Electrical Engineering and Informatics (ICon EEI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121020897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.1109/ICon-EEI.2018.8784320
Azriyenni Azhari Zakri, Syukri Darmawan, J. Usman, I. Rosma, Boy Ihsan
Power transmission lines are extremely important for the power system to deliver energy of electricity from the plant to the load. The short circuit of fault often occurs in the transmission line and may lead to disconnecting the power supply to the load. This study implements a hybrid technique that is Discrete Wavelet Transformation (DWT) and Support Vector Machine (SVM) for classification of fault in the transmission line. The DWT was created to extract the detailed signal of transient D8 and D9 (order of 4) at 50 kHz for sampling frequency. The value of Root Mean Square (RMS) will be determined by the coefficients D8 and D9 for training and test data using SVM technique. Furthermore, SVM is utilized to detect the fault for each phase and the ground is discovered in the type of fault. The SVM technique has been run using parameter C and kernel scale to achieve the great results of classification of the fault. Type of simulating fault has a variation of location of the fault, fault of resistance and initial angle. The training and test data run for the Test System of Riau, Indonesia. The test result for the classification of fault reaches the highest accuracy of 100%.
{"title":"Extract Fault Signal via DWT and Penetration of SVM for Fault Classification at Power System Transmission","authors":"Azriyenni Azhari Zakri, Syukri Darmawan, J. Usman, I. Rosma, Boy Ihsan","doi":"10.1109/ICon-EEI.2018.8784320","DOIUrl":"https://doi.org/10.1109/ICon-EEI.2018.8784320","url":null,"abstract":"Power transmission lines are extremely important for the power system to deliver energy of electricity from the plant to the load. The short circuit of fault often occurs in the transmission line and may lead to disconnecting the power supply to the load. This study implements a hybrid technique that is Discrete Wavelet Transformation (DWT) and Support Vector Machine (SVM) for classification of fault in the transmission line. The DWT was created to extract the detailed signal of transient D8 and D9 (order of 4) at 50 kHz for sampling frequency. The value of Root Mean Square (RMS) will be determined by the coefficients D8 and D9 for training and test data using SVM technique. Furthermore, SVM is utilized to detect the fault for each phase and the ground is discovered in the type of fault. The SVM technique has been run using parameter C and kernel scale to achieve the great results of classification of the fault. Type of simulating fault has a variation of location of the fault, fault of resistance and initial angle. The training and test data run for the Test System of Riau, Indonesia. The test result for the classification of fault reaches the highest accuracy of 100%.","PeriodicalId":114952,"journal":{"name":"2018 2nd International Conference on Electrical Engineering and Informatics (ICon EEI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133789614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：