Pub Date : 2019-02-01DOI: 10.1109/KBEI.2019.8734929
H. Ghasemi, Saeed Ansari-Rad, A. Kalhor, M. T. Masouleh
Autonomous quad-rotor flight systems have grabbed considerable attention for varied missions in rescue, inspection devices, and so forth. Accordingly, various control methods have been employed for hovering these devices. Recently, in order to extend the applications of quad-rotors, including, among the others, the pick-and-place, a robotic arm has been attached, which requires the analysis of both dynamic equations and control procedures. However, considering the coupled system as a case of robot-robot interaction, these state-of-the-art flight systems have rarely received attention due to much higher complexity of dynamic equations. Moreover, flight time expense is revealed as another critical issue in the flight systems with the attached arm, which requires effective solution due to excessive arm loads and power source limitations. To this end, in this paper, the dynamic equations of quad-rotor with a 3-link arm are obtained in order to be employed in designing suitable control methods. In this regard, by stabilizing the quad-rotor in desired coordinations and tracking desired paths for robotic arm, the dynamic interaction as the main challenge of the robot-robot interaction is successfully handled. Thereafter, a Linear Quadratic Regulator (LQR) is proposed to tackle the flight time issue in which by assigning optimal values to the state input weighting matrix, the motion of arm links reduced and as the result, the flight time effectively increases. In order to demonstrate the superiority of the proposed method, two well-known control approaches, namely, Sliding Mode Control (SMC) and Pole Placement are implemented in the same conditions. In simulation with Matlab software, the performance of the forgoing methods is compared by employing different indices, where it is inferred that despite presence of an external force resembling windy condition, the proposed LQR decreases the motion index by 24.14% in compare with SMC and Pole Placement methods, with approximately similar tracking index to them.
{"title":"Control of Quad-rotor in Cooperation with an Attached 3-DOF Manipulator","authors":"H. Ghasemi, Saeed Ansari-Rad, A. Kalhor, M. T. Masouleh","doi":"10.1109/KBEI.2019.8734929","DOIUrl":"https://doi.org/10.1109/KBEI.2019.8734929","url":null,"abstract":"Autonomous quad-rotor flight systems have grabbed considerable attention for varied missions in rescue, inspection devices, and so forth. Accordingly, various control methods have been employed for hovering these devices. Recently, in order to extend the applications of quad-rotors, including, among the others, the pick-and-place, a robotic arm has been attached, which requires the analysis of both dynamic equations and control procedures. However, considering the coupled system as a case of robot-robot interaction, these state-of-the-art flight systems have rarely received attention due to much higher complexity of dynamic equations. Moreover, flight time expense is revealed as another critical issue in the flight systems with the attached arm, which requires effective solution due to excessive arm loads and power source limitations. To this end, in this paper, the dynamic equations of quad-rotor with a 3-link arm are obtained in order to be employed in designing suitable control methods. In this regard, by stabilizing the quad-rotor in desired coordinations and tracking desired paths for robotic arm, the dynamic interaction as the main challenge of the robot-robot interaction is successfully handled. Thereafter, a Linear Quadratic Regulator (LQR) is proposed to tackle the flight time issue in which by assigning optimal values to the state input weighting matrix, the motion of arm links reduced and as the result, the flight time effectively increases. In order to demonstrate the superiority of the proposed method, two well-known control approaches, namely, Sliding Mode Control (SMC) and Pole Placement are implemented in the same conditions. In simulation with Matlab software, the performance of the forgoing methods is compared by employing different indices, where it is inferred that despite presence of an external force resembling windy condition, the proposed LQR decreases the motion index by 24.14% in compare with SMC and Pole Placement methods, with approximately similar tracking index to them.","PeriodicalId":339990,"journal":{"name":"2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128272025","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 : 2019-02-01DOI: 10.1109/KBEI.2019.8735050
Mostafa Soleymanifard, M. Hamghalam
One of the purposes from segmenting the brain tissues is to separate the damaged tissue in the patient's brain. In fact, brain tissue segmentation is one of the essential steps in the detection and treatment of brain abnormalities. This time-consuming task is usually performed by clinical experts who are not errorless. The proposed method in this paper is to automate the brain tumor segmentation with the aim of making the segmentation process more complete and closer to the clinical treatments. We propose a novel method that is a combination of neural networks and active contours to automatically segment the gliomas in MRI multi-modalities brain images. The proposed algorithm is trained locally by using a neural network at random points in tumor boundary patches, then, by combining the modality of the MRI images and the active contours, the complete tumor is segmented. The obtained results as well as the evaluation criteria such as DICE coefficient, show that the proposed model is highly competitive in comparison with the state of the art segmentation methods.
{"title":"Segmentation of Whole Tumor Using Localized Active Contour and Trained Neural Network in Boundaries","authors":"Mostafa Soleymanifard, M. Hamghalam","doi":"10.1109/KBEI.2019.8735050","DOIUrl":"https://doi.org/10.1109/KBEI.2019.8735050","url":null,"abstract":"One of the purposes from segmenting the brain tissues is to separate the damaged tissue in the patient's brain. In fact, brain tissue segmentation is one of the essential steps in the detection and treatment of brain abnormalities. This time-consuming task is usually performed by clinical experts who are not errorless. The proposed method in this paper is to automate the brain tumor segmentation with the aim of making the segmentation process more complete and closer to the clinical treatments. We propose a novel method that is a combination of neural networks and active contours to automatically segment the gliomas in MRI multi-modalities brain images. The proposed algorithm is trained locally by using a neural network at random points in tumor boundary patches, then, by combining the modality of the MRI images and the active contours, the complete tumor is segmented. The obtained results as well as the evaluation criteria such as DICE coefficient, show that the proposed model is highly competitive in comparison with the state of the art segmentation methods.","PeriodicalId":339990,"journal":{"name":"2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130189388","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 : 2019-02-01DOI: 10.1109/KBEI.2019.8734934
M. Navabi, A. Davoodi
Fuel slosh dynamics can disturb attitude of spacecraft which has a partially filled container, in orbital maneuvering. So, it is necessary to control this harmful phenomenon. This paper models coupled dynamics of fuel sloshing and attitude of the spacecraft by two-pendulum model, and designs a fuzzy controller to control sloshing and attitude dynamics of the vehicle. Also, effectiveness of this controller is illustrated by conducted simulation.
{"title":"2D Modeling and Fuzzy Control of Slosh Dynamics in a Spacecraft","authors":"M. Navabi, A. Davoodi","doi":"10.1109/KBEI.2019.8734934","DOIUrl":"https://doi.org/10.1109/KBEI.2019.8734934","url":null,"abstract":"Fuel slosh dynamics can disturb attitude of spacecraft which has a partially filled container, in orbital maneuvering. So, it is necessary to control this harmful phenomenon. This paper models coupled dynamics of fuel sloshing and attitude of the spacecraft by two-pendulum model, and designs a fuzzy controller to control sloshing and attitude dynamics of the vehicle. Also, effectiveness of this controller is illustrated by conducted simulation.","PeriodicalId":339990,"journal":{"name":"2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121620414","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 : 2019-02-01DOI: 10.1109/KBEI.2019.8734984
N. Orouji, A. Ramezani, M. Mosavi
The GPS-based navigation devices play a substantial role in modern life. The GPS receivers provide time, position, and velocity information which are crucial to precise and accurate navigation, especially in the aviation and marine industry. Due to the CDMA nature of the GPS signals, the acquisition and tracking stages are inseparable parts of a GPS receiver. Therefore, high efficiency, high speed, and accuracy are undeniable factors of a good receiver.In this paper, a hardware implementation of the acquisition stage is proposed and analyzed. This structure exploits the parallel frequency search method and utilizes the frequency domain simplifications through the Fourier transform. The structure is implemented and evaluated on the Xilinx ZedBoard which uses an XC7Z020 chip as the main processing unit. The structure's moderate resource usage has made it a good choice for a hardware implementation of GPS receiver.
{"title":"A Hardware Implementation for Acquisition Stage Based on the Parallel Frequency Search Method","authors":"N. Orouji, A. Ramezani, M. Mosavi","doi":"10.1109/KBEI.2019.8734984","DOIUrl":"https://doi.org/10.1109/KBEI.2019.8734984","url":null,"abstract":"The GPS-based navigation devices play a substantial role in modern life. The GPS receivers provide time, position, and velocity information which are crucial to precise and accurate navigation, especially in the aviation and marine industry. Due to the CDMA nature of the GPS signals, the acquisition and tracking stages are inseparable parts of a GPS receiver. Therefore, high efficiency, high speed, and accuracy are undeniable factors of a good receiver.In this paper, a hardware implementation of the acquisition stage is proposed and analyzed. This structure exploits the parallel frequency search method and utilizes the frequency domain simplifications through the Fourier transform. The structure is implemented and evaluated on the Xilinx ZedBoard which uses an XC7Z020 chip as the main processing unit. The structure's moderate resource usage has made it a good choice for a hardware implementation of GPS receiver.","PeriodicalId":339990,"journal":{"name":"2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127377843","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 : 2019-02-01DOI: 10.1109/KBEI.2019.8735022
Sara Sadat Hoseininasab, Hooman Nikmehr
Decimal multiplication is one of the most extensively used and complex computations in many commercial and financial applications. This paper presents a novel design for a single constant decimal multiplier with constant coefficients of 10 to 19. The parallel generation of partial products is performed using BCD-8421 or BCD-4221 encodings. Decimal multioperand addition has been used for partial product reduction stage. Also, a redundant to none-redundant converter for the last stage of the multiplier is proposed. To evaluate the architecture, a VHDL model is presented and synthesized in TSMC 130nm technology. The results of the implementation show that the parallel single constant decimal multiplier has an interesting delay, area, power consumption, and PDP compared to others decimal multipliers.
{"title":"A Method for Single Radix-10 constant multiplication","authors":"Sara Sadat Hoseininasab, Hooman Nikmehr","doi":"10.1109/KBEI.2019.8735022","DOIUrl":"https://doi.org/10.1109/KBEI.2019.8735022","url":null,"abstract":"Decimal multiplication is one of the most extensively used and complex computations in many commercial and financial applications. This paper presents a novel design for a single constant decimal multiplier with constant coefficients of 10 to 19. The parallel generation of partial products is performed using BCD-8421 or BCD-4221 encodings. Decimal multioperand addition has been used for partial product reduction stage. Also, a redundant to none-redundant converter for the last stage of the multiplier is proposed. To evaluate the architecture, a VHDL model is presented and synthesized in TSMC 130nm technology. The results of the implementation show that the parallel single constant decimal multiplier has an interesting delay, area, power consumption, and PDP compared to others decimal multipliers.","PeriodicalId":339990,"journal":{"name":"2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134179463","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 : 2019-02-01DOI: 10.1109/KBEI.2019.8734960
T. Gandomani, H. Faraji, Mahsa Radnejad
Software cost estimation has been always a serious concern among the software experts. Although, a few estimation models and techniques have been provided in disciplined based software methodologies, Agile methodologies most often use Planning Poker technique for software cost estimation. This technique promotes coming to consensus when suggesting size of each user requirement (known as User Story). However, most often software experts ask whether it is necessary to reach to a consensus or not. They also, offer considering the average of the suggested sizes (cost) of User Stories instead of focusing on consensus on them. The main aim of this paper is to present the results of a case study research which has been carried out to compare the accuracy of both disciplines. The results show less accuracy when team get an average size of the User Stories compared to coming to consensus about the size of User Stories.
{"title":"Planning Poker in cost estimation in Agile methods: Averaging Vs. Consensus","authors":"T. Gandomani, H. Faraji, Mahsa Radnejad","doi":"10.1109/KBEI.2019.8734960","DOIUrl":"https://doi.org/10.1109/KBEI.2019.8734960","url":null,"abstract":"Software cost estimation has been always a serious concern among the software experts. Although, a few estimation models and techniques have been provided in disciplined based software methodologies, Agile methodologies most often use Planning Poker technique for software cost estimation. This technique promotes coming to consensus when suggesting size of each user requirement (known as User Story). However, most often software experts ask whether it is necessary to reach to a consensus or not. They also, offer considering the average of the suggested sizes (cost) of User Stories instead of focusing on consensus on them. The main aim of this paper is to present the results of a case study research which has been carried out to compare the accuracy of both disciplines. The results show less accuracy when team get an average size of the User Stories compared to coming to consensus about the size of User Stories.","PeriodicalId":339990,"journal":{"name":"2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134314878","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 : 2019-02-01DOI: 10.1109/KBEI.2019.8735035
S. M. R. Hashemi, Ehsan Kozegar, M. M. Deramgozin, B. Minaei-Bidgoli
Artificial neural networks have been increasingly used in many problems of data classification because of their learning capacity, robustness and extendibility. Training in the neural networks accomplished by identifying the weight of neurons which is one of the main issues addressed in this field. The process of network learning by back-propagation algorithm which is based on gradient, commonly fall into a local optimum. Due to the importance of weights and neural network structure, evolutionary neural networks have been emerged to obtain suitable weight set. This paper will concentrate on training a feed-forward networks by a modified evolutionary algorithm based on asexual reproduction optimization (ARO) in order to data classification problems. The idea is to use real representation (rather the binary) for adjusting weights of the network. Experimental results show a better result in terms of speed and accuracy compared with other evolutionary algorithms including genetic algorithms, simulated annealing and particle swarm optimization.
{"title":"Training Feed-forward Neural Networks using Asexual Reproduction Optimization (ARO) Algorithm","authors":"S. M. R. Hashemi, Ehsan Kozegar, M. M. Deramgozin, B. Minaei-Bidgoli","doi":"10.1109/KBEI.2019.8735035","DOIUrl":"https://doi.org/10.1109/KBEI.2019.8735035","url":null,"abstract":"Artificial neural networks have been increasingly used in many problems of data classification because of their learning capacity, robustness and extendibility. Training in the neural networks accomplished by identifying the weight of neurons which is one of the main issues addressed in this field. The process of network learning by back-propagation algorithm which is based on gradient, commonly fall into a local optimum. Due to the importance of weights and neural network structure, evolutionary neural networks have been emerged to obtain suitable weight set. This paper will concentrate on training a feed-forward networks by a modified evolutionary algorithm based on asexual reproduction optimization (ARO) in order to data classification problems. The idea is to use real representation (rather the binary) for adjusting weights of the network. Experimental results show a better result in terms of speed and accuracy compared with other evolutionary algorithms including genetic algorithms, simulated annealing and particle swarm optimization.","PeriodicalId":339990,"journal":{"name":"2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132983466","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 : 2019-02-01DOI: 10.1109/KBEI.2019.8734919
Yoosof Mashayekhi, Ehsan Nazerfard, Arman Rahbar, Samira Sirzadeh Haji Mahmood
Fuzzy c-means (FCM) is one of the most popular fuzzy clustering methods and it is used in various applications in computer science. Most clustering methods including FCM, suffer from bad initialization problem. If initial cluster centers (membership degree initialization in FCM) are not selected appropriately, it may yield poor results. In this paper we propose a method called MinMax FCM to overcome this problem. A new objective function is designed in MinMax FCM to this aim. We use maximum variance of clusters as objective function. In this regard, high-variance clusters are penalized. We compare MinMax FCM with FCM in terms of sum of clusters’ variances, maximum variance of clusters, and execution time using a number of UCI datasets.
{"title":"The MinMax Fuzzy C-Means","authors":"Yoosof Mashayekhi, Ehsan Nazerfard, Arman Rahbar, Samira Sirzadeh Haji Mahmood","doi":"10.1109/KBEI.2019.8734919","DOIUrl":"https://doi.org/10.1109/KBEI.2019.8734919","url":null,"abstract":"Fuzzy c-means (FCM) is one of the most popular fuzzy clustering methods and it is used in various applications in computer science. Most clustering methods including FCM, suffer from bad initialization problem. If initial cluster centers (membership degree initialization in FCM) are not selected appropriately, it may yield poor results. In this paper we propose a method called MinMax FCM to overcome this problem. A new objective function is designed in MinMax FCM to this aim. We use maximum variance of clusters as objective function. In this regard, high-variance clusters are penalized. We compare MinMax FCM with FCM in terms of sum of clusters’ variances, maximum variance of clusters, and execution time using a number of UCI datasets.","PeriodicalId":339990,"journal":{"name":"2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133125118","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 : 2019-02-01DOI: 10.1109/KBEI.2019.8735019
Negar Nazem Bokaei, Mohammad Reza Keyvanpour
Mutation testing is a powerful and expensive method in software testing context. It is used as a test criterion to assess the quality of test suites or generate test suites which are able to kill mutants created by seeding artificial defects in the original program code. These test suites are high-quality tests with good ability to find probable faults in the program under test. Mutation testing has gained high attention recently through its superiority over other testing criteria in different aspects and is the main topic of researches in software testing area. As well as powerfulness of mutation testing, it has challenges and difficulties which are great barriers for industrial utilization. This paper provides a comprehensive classification of mutation testing issues and challenges. Furthermore, a comparative study is conducted on researches that made an effort to investigate issues and resolve challenges of mutation testing along with presenting a classification of these proposed approaches. This comparative structure suggests different research topics and makes a guideline for researchers interested in mutation testing context. This also can be used for the purpose of comparing the existing methods, selecting the best one and improving selected methods.
{"title":"A Comparative Study of Whole Issues and Challenges in Mutation Testing","authors":"Negar Nazem Bokaei, Mohammad Reza Keyvanpour","doi":"10.1109/KBEI.2019.8735019","DOIUrl":"https://doi.org/10.1109/KBEI.2019.8735019","url":null,"abstract":"Mutation testing is a powerful and expensive method in software testing context. It is used as a test criterion to assess the quality of test suites or generate test suites which are able to kill mutants created by seeding artificial defects in the original program code. These test suites are high-quality tests with good ability to find probable faults in the program under test. Mutation testing has gained high attention recently through its superiority over other testing criteria in different aspects and is the main topic of researches in software testing area. As well as powerfulness of mutation testing, it has challenges and difficulties which are great barriers for industrial utilization. This paper provides a comprehensive classification of mutation testing issues and challenges. Furthermore, a comparative study is conducted on researches that made an effort to investigate issues and resolve challenges of mutation testing along with presenting a classification of these proposed approaches. This comparative structure suggests different research topics and makes a guideline for researchers interested in mutation testing context. This also can be used for the purpose of comparing the existing methods, selecting the best one and improving selected methods.","PeriodicalId":339990,"journal":{"name":"2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)","volume":"272 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133887342","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 : 2019-02-01DOI: 10.1109/KBEI.2019.8735041
S. Hajiaghasi, Z. Rafiee, A. Salemnia, M. Aghamohammadi, Tohid Soleymaniaghdam
Broken rotor bar faults cause of motor malfunction and reduction of the life cycle. For the safe and appropriate performance of induction motors, the motor fault detection is a critical issue. This paper presents a new strategy for the broken rotor bar fault detection of the induction motors. Finite element method (FEM) is used for accurate fault modelling and the flux density under broken rotor bar faults has been comprehensively analyzed. Moreover, a new rotor bar fault detection method based on probabilistic neural network (PNN) and wavelet transform is presented. The proposed approach uses the stator current signal amplitude samples in the time-frequency domain to extract the appropriate coefficients where they are considered as inputs to a PNN. The output of the PNN classifies the status of the rotor to a healthy or faulty condition. The performance of the proposed method is verified using numerical simulation.
{"title":"A New Strategy for Induction Motor Fault Detection Based on Wavelet Transform and Probabilistic Neural Network","authors":"S. Hajiaghasi, Z. Rafiee, A. Salemnia, M. Aghamohammadi, Tohid Soleymaniaghdam","doi":"10.1109/KBEI.2019.8735041","DOIUrl":"https://doi.org/10.1109/KBEI.2019.8735041","url":null,"abstract":"Broken rotor bar faults cause of motor malfunction and reduction of the life cycle. For the safe and appropriate performance of induction motors, the motor fault detection is a critical issue. This paper presents a new strategy for the broken rotor bar fault detection of the induction motors. Finite element method (FEM) is used for accurate fault modelling and the flux density under broken rotor bar faults has been comprehensively analyzed. Moreover, a new rotor bar fault detection method based on probabilistic neural network (PNN) and wavelet transform is presented. The proposed approach uses the stator current signal amplitude samples in the time-frequency domain to extract the appropriate coefficients where they are considered as inputs to a PNN. The output of the PNN classifies the status of the rotor to a healthy or faulty condition. The performance of the proposed method is verified using numerical simulation.","PeriodicalId":339990,"journal":{"name":"2019 5th Conference on Knowledge Based Engineering and Innovation (KBEI)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133924675","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：