Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752375
B. Nandish, V. Pushparajesh
Energy disaggregation is one of the major concerns in the modern power management in domestic utilities. Main aim is to read the individual load appliance readings from the whole data. There are so many techniques to the field, deep learning being promising. This paper state about simulation of household appliances for data aggregation and energy disaggregation of individual appliances using deep learning technique. For data collection we have used data of individual standalone house for summer season. Deep learning technique such as complex tree and linear modules are studied in this paper with the incorporation of complex technique for better efficiency. The performance efficiency of both the modules are tested and evaluated in this paper. To make it cost-effective the system is simulated in MATLAB/SIMULINK for the different trial cases.
{"title":"Simulation of Household Appliances with Energy Disaggrigation using Deep Learning Technique","authors":"B. Nandish, V. Pushparajesh","doi":"10.1109/ComPE53109.2021.9752375","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752375","url":null,"abstract":"Energy disaggregation is one of the major concerns in the modern power management in domestic utilities. Main aim is to read the individual load appliance readings from the whole data. There are so many techniques to the field, deep learning being promising. This paper state about simulation of household appliances for data aggregation and energy disaggregation of individual appliances using deep learning technique. For data collection we have used data of individual standalone house for summer season. Deep learning technique such as complex tree and linear modules are studied in this paper with the incorporation of complex technique for better efficiency. The performance efficiency of both the modules are tested and evaluated in this paper. To make it cost-effective the system is simulated in MATLAB/SIMULINK for the different trial cases.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124962708","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}
This paper presents a blockchain-based Securitization Model, which simplifies the transactional methods. This paper elaborates upon integrating the components of Securitization with Distributed Ledger Technology (DTL) and provides a process flow of transactions occurring. The process which once led to the 2008 Financial Crisis has been improved in terms of security and reliability. Using this revolutionizing model, securities, which were once considered opaque & risky, will now be informative and gauged accordingly, thereby smoothening the process of transforming non-tradable assets into tradable securities. This paper highlights how blockchain features, i.e., smart contracts, decentralization, authentication & immutability, will increase efficiency. Furthermore, the paper explores boons of the amalgamation, i.e., reduced risk, enhanced transparency, lower costs, proficient processes and robust authentication without compromising information asymmetry, high transactional costs and nebulous portfolio rating. The goal of this paper is to portray how the integration will augment the cardinal Securitization process.
{"title":"An Intrinsic Review on Securitization using Blockchain","authors":"Varun Gupta, Saheb Gabadia, Menita Agarwal, Krishna Samdani","doi":"10.1109/ComPE53109.2021.9752154","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752154","url":null,"abstract":"This paper presents a blockchain-based Securitization Model, which simplifies the transactional methods. This paper elaborates upon integrating the components of Securitization with Distributed Ledger Technology (DTL) and provides a process flow of transactions occurring. The process which once led to the 2008 Financial Crisis has been improved in terms of security and reliability. Using this revolutionizing model, securities, which were once considered opaque & risky, will now be informative and gauged accordingly, thereby smoothening the process of transforming non-tradable assets into tradable securities. This paper highlights how blockchain features, i.e., smart contracts, decentralization, authentication & immutability, will increase efficiency. Furthermore, the paper explores boons of the amalgamation, i.e., reduced risk, enhanced transparency, lower costs, proficient processes and robust authentication without compromising information asymmetry, high transactional costs and nebulous portfolio rating. The goal of this paper is to portray how the integration will augment the cardinal Securitization process.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"121 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129407880","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752151
Himani Tyagi, Rajendra Kumar
The importance of the Internet of things in every sphere of human life is quite evident. However, with applications, many serious threats, vulnerabilities, and attacks are emerging from time to time. Thus, it is required to discuss the vulnerabilities and attacks to fully adopt this popular technology with security solutions intact. Therefore, this paper includes a survey from three aspects such as IoT market opportunities with security challenges, recently identified threats, vulnerabilities, and attacks on IoT with proposed solutions, and the importance of modern technologies such as machine learning, cloud computing, fog computing, edge computing and, blockchain for IoT security solutions. The main contribution of this work is to provide insights into IoT security challenges from various aspects like device and sensor based, software - application based, communication channel based, and future predictions.
{"title":"Analyzing Security Approaches for Threats, Vulnerabilities, and attacks in an IoT Environment","authors":"Himani Tyagi, Rajendra Kumar","doi":"10.1109/ComPE53109.2021.9752151","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752151","url":null,"abstract":"The importance of the Internet of things in every sphere of human life is quite evident. However, with applications, many serious threats, vulnerabilities, and attacks are emerging from time to time. Thus, it is required to discuss the vulnerabilities and attacks to fully adopt this popular technology with security solutions intact. Therefore, this paper includes a survey from three aspects such as IoT market opportunities with security challenges, recently identified threats, vulnerabilities, and attacks on IoT with proposed solutions, and the importance of modern technologies such as machine learning, cloud computing, fog computing, edge computing and, blockchain for IoT security solutions. The main contribution of this work is to provide insights into IoT security challenges from various aspects like device and sensor based, software - application based, communication channel based, and future predictions.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129499370","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751910
R. Lakshmi, N. Savarimuthu
The intelligent detection and diagnosis of plant diseases are one of the primary goals in sustainable agriculture. Although most disease symptoms are visible on plant leaves, it is time consuming and expensive process by manual observations. Automated detection of diseases is a significant concern in monitoring the plants to make timely decisions. The advent of recent deep learning models has led to several applications for automatic plant disease diagnosis. However, the diagnostic performance of these applications is substantially reduced when employed on test data sets due to overfitting. In this study, we propose a novel ensemble deep convolution neural network to classify the plant leaf diseases, and its performance was assessed with other benchmark deep learning models, namely, VGG16, ResNet152, Inceptionv3, DenseNet121. Three crops with 18 distinct categories were considered from the plant village dataset. Empirical findings show that the proposed model achieves 98.96% accuracy, significantly higher than other benchmark state-of-the-art models.
{"title":"A Novel Transfer Learning Ensemble based Deep Neural Network for Plant Disease Detection","authors":"R. Lakshmi, N. Savarimuthu","doi":"10.1109/ComPE53109.2021.9751910","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751910","url":null,"abstract":"The intelligent detection and diagnosis of plant diseases are one of the primary goals in sustainable agriculture. Although most disease symptoms are visible on plant leaves, it is time consuming and expensive process by manual observations. Automated detection of diseases is a significant concern in monitoring the plants to make timely decisions. The advent of recent deep learning models has led to several applications for automatic plant disease diagnosis. However, the diagnostic performance of these applications is substantially reduced when employed on test data sets due to overfitting. In this study, we propose a novel ensemble deep convolution neural network to classify the plant leaf diseases, and its performance was assessed with other benchmark deep learning models, namely, VGG16, ResNet152, Inceptionv3, DenseNet121. Three crops with 18 distinct categories were considered from the plant village dataset. Empirical findings show that the proposed model achieves 98.96% accuracy, significantly higher than other benchmark state-of-the-art models.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129737681","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752304
S. U, Punitha S, Girish Perakam, Vishnu Priya Palukuru, Jaswanth Varma Raghavaraju, Praveena R
Video games produce reactionary, resilient, or clever behavior, mostly on non-player characters (NPCs), who resemble Artificial Intelligence (AI). Since the launch of video games in the 1950s AI has become an important component. AI is a separate subfield in computer games that varies from AI. Instead of learning the machine or determining it is used to enhance the player experience. The concept of an AI opponent was popularized during the golden age of arcade videogames in the form of graded levels of difficulty, distinct action styles and events based on the player’s involvement. Modern games also apply current strategies such as path-finding and decision-making bodies to control NPCs’ actions. AI is used often in mechanisms, such as data mining and process content creation, which is not immediately accessible to the user. We were creating an AI Organization to use the same hyper parameter to learn how to play a variety of Atari games. Over time it became a more theory-oriented project, in which we discussed numerous ways to use our methods for deep learning, and Put them on a game, Pong, rather than a game package.
{"title":"Artificial Intelligence (AI) Prediction of Atari Game Strategy by using Reinforcement Learning Algorithms","authors":"S. U, Punitha S, Girish Perakam, Vishnu Priya Palukuru, Jaswanth Varma Raghavaraju, Praveena R","doi":"10.1109/ComPE53109.2021.9752304","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752304","url":null,"abstract":"Video games produce reactionary, resilient, or clever behavior, mostly on non-player characters (NPCs), who resemble Artificial Intelligence (AI). Since the launch of video games in the 1950s AI has become an important component. AI is a separate subfield in computer games that varies from AI. Instead of learning the machine or determining it is used to enhance the player experience. The concept of an AI opponent was popularized during the golden age of arcade videogames in the form of graded levels of difficulty, distinct action styles and events based on the player’s involvement. Modern games also apply current strategies such as path-finding and decision-making bodies to control NPCs’ actions. AI is used often in mechanisms, such as data mining and process content creation, which is not immediately accessible to the user. We were creating an AI Organization to use the same hyper parameter to learn how to play a variety of Atari games. Over time it became a more theory-oriented project, in which we discussed numerous ways to use our methods for deep learning, and Put them on a game, Pong, rather than a game package.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126782799","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751972
Sapam Rhison Singh, Piyali Das
Solar energy has emerged as a viable source of electricity due to its environmental friendliness and ability to reduce greenhouse gas emissions throughout the world. Solar energy has the potential to meet the world's energy demands, but our ability to transform it into electrical energy in an efficient and cost-effective manner is the sole constraint. Weather fluctuations and how much radiation falls on the panel or reflector determine how much power is generated from a PV cell. Solar trackers are required to ensure that the PV panel receives the greatest amount of sunlight. This paper looks at the Dual Axis Solar Tracking (DAST) system and a Simulink model is developed with MATLAB software to compare the efficiency of fixed and DAST systems.
太阳能因其环境友好性和减少全球温室气体排放的能力而成为一种可行的电力来源。太阳能有潜力满足世界的能源需求，但我们能否以高效和经济的方式将其转化为电能是唯一的限制。天气波动和落在面板或反射器上的辐射量决定了光伏电池产生的功率。需要太阳能跟踪器来确保光伏板接收到最大数量的阳光。本文以双轴太阳跟踪系统(Dual Axis Solar Tracking, DAST)为研究对象，利用MATLAB软件建立了Simulink模型，对固定系统和DAST系统的效率进行了比较。
{"title":"Performance Analysis of Dual Axis Solar Tracker","authors":"Sapam Rhison Singh, Piyali Das","doi":"10.1109/ComPE53109.2021.9751972","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751972","url":null,"abstract":"Solar energy has emerged as a viable source of electricity due to its environmental friendliness and ability to reduce greenhouse gas emissions throughout the world. Solar energy has the potential to meet the world's energy demands, but our ability to transform it into electrical energy in an efficient and cost-effective manner is the sole constraint. Weather fluctuations and how much radiation falls on the panel or reflector determine how much power is generated from a PV cell. Solar trackers are required to ensure that the PV panel receives the greatest amount of sunlight. This paper looks at the Dual Axis Solar Tracking (DAST) system and a Simulink model is developed with MATLAB software to compare the efficiency of fixed and DAST systems.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"45 13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123333212","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752150
Shikha Gupta, Harikishni Nain
This study attempts to provide an overview of the social media adoption in higher education by students in Delhi University, India in terms of a SWOT analysis. This is an exploratory study executed through qualitative data. The results of this study can be applied by academicians, students, and policy makers for blended learning in future.
{"title":"Examining the Role of Social Media in Higher Education through SWOT Analysis","authors":"Shikha Gupta, Harikishni Nain","doi":"10.1109/ComPE53109.2021.9752150","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752150","url":null,"abstract":"This study attempts to provide an overview of the social media adoption in higher education by students in Delhi University, India in terms of a SWOT analysis. This is an exploratory study executed through qualitative data. The results of this study can be applied by academicians, students, and policy makers for blended learning in future.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115312865","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752435
Akansha Singh, Nidhi Saxena
We are living in the age of big data, advanced analytics, and data science. Companies these days have realized the importance of data management and therefore are recruiting staff as data scientists and academics institutions and publications have accepted data science as one the trending career options. The current era of IT industry is evolving very rapidly. With the growing requirement of IT sector the demand of each sub-unit is also developing with huge pace. Introduction of distributed computing had resolved the issues of the industry but now analyzing the growth pace the requirements will be drastically challenging for the industry, organisations as well as society. If we want this science to serve and promote business effectively, it is important for us (i) to recognize its associations to other important technologies and concepts, and (ii) to initiate the classify the fundamental ideologies underlying data science. This paper has a systematic overview on data science, its application and its interactions to other important related perceptions. The combination of data science and distributed computing can resolve many issues of the industry.
{"title":"Data Science: Relationship with big data, data driven predictions and machine learning","authors":"Akansha Singh, Nidhi Saxena","doi":"10.1109/ComPE53109.2021.9752435","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752435","url":null,"abstract":"We are living in the age of big data, advanced analytics, and data science. Companies these days have realized the importance of data management and therefore are recruiting staff as data scientists and academics institutions and publications have accepted data science as one the trending career options. The current era of IT industry is evolving very rapidly. With the growing requirement of IT sector the demand of each sub-unit is also developing with huge pace. Introduction of distributed computing had resolved the issues of the industry but now analyzing the growth pace the requirements will be drastically challenging for the industry, organisations as well as society. If we want this science to serve and promote business effectively, it is important for us (i) to recognize its associations to other important technologies and concepts, and (ii) to initiate the classify the fundamental ideologies underlying data science. This paper has a systematic overview on data science, its application and its interactions to other important related perceptions. The combination of data science and distributed computing can resolve many issues of the industry.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125240501","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752188
Richa Gupta, V. Tripathi, A. Gupta
Natural eye is influenced by the distinctive eye illnesses some of them are great cause of vision loss. Many Artificial Intelligence (AI) approaches have been proposed for the identification of such diseases. The proposed method intends to plan an AI based automated network for eye illness identification and grouping to help the ophthalmologists all the more viably distinguishing and ordering of internal eye diseases like Choroid Neovascularisation (CNV), Diabetic Macular Edema (DME) and Drusen by utilizing the Optical Coherence Tomography (OCT) pictures portraying various tissues. The procedure utilized for planning this framework includes diverse deep learning convolutional neural organization (CNN) models. The proposed methodology is called efficient because it is performed on a large scale data-set which has four classes and improves the performance to a great level. The best picture subtitling model is chosen after execution investigation by looking at different picture inscribing frameworks for helping ophthalmologists to identify and order eye illnesses. The proposed methodology achieves the performance to a great level, 83.66% of accuracy for the test images when the data-set is divide in the format of 70-30 ratio.
{"title":"An Efficient Model for Detection and Classification of Internal Eye Diseases using Deep Learning","authors":"Richa Gupta, V. Tripathi, A. Gupta","doi":"10.1109/ComPE53109.2021.9752188","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752188","url":null,"abstract":"Natural eye is influenced by the distinctive eye illnesses some of them are great cause of vision loss. Many Artificial Intelligence (AI) approaches have been proposed for the identification of such diseases. The proposed method intends to plan an AI based automated network for eye illness identification and grouping to help the ophthalmologists all the more viably distinguishing and ordering of internal eye diseases like Choroid Neovascularisation (CNV), Diabetic Macular Edema (DME) and Drusen by utilizing the Optical Coherence Tomography (OCT) pictures portraying various tissues. The procedure utilized for planning this framework includes diverse deep learning convolutional neural organization (CNN) models. The proposed methodology is called efficient because it is performed on a large scale data-set which has four classes and improves the performance to a great level. The best picture subtitling model is chosen after execution investigation by looking at different picture inscribing frameworks for helping ophthalmologists to identify and order eye illnesses. The proposed methodology achieves the performance to a great level, 83.66% of accuracy for the test images when the data-set is divide in the format of 70-30 ratio.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122538070","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752453
Samiksha Chintawar, Snehal Ghodke, V. Khatavkar, Utkarsh Alset, Hrishikesh Mehta
In many applications, brushless direct current (BLDC) motor drives use fuzzy logic controllers for speed control owing to their advantages like auto-tuning of parameters, wide operational range, low computational requirements and low cost. However, the effect of different rulesets on the transient and steady-state speed Behaviour of BLDC motors has not been widely covered in the literature. The contribution of this paper includes speed characteristics of the triangular membership function (trimf) based fuzzy proportional-integral (FPI) controller is evaluated. Rulesets of 3 × 3, 5 × 5 and 7 × 7 formed using 3, 5 and 7 trimfs are compared for their Behaviour and time required for performing computations for speed benchmark of the BLDC motor used in comprehensive electric vehicle (EV) applications. The fuzzy logic control algorithm is implemented by means of Mathworks’ Fuzzy Logic Tool-set. The results are substantiated using MATLAB/Simulink. It is thereby concluded that increasing the number of membership functions improves the dynamic and steady-state behaviour of the BLDC motor.
{"title":"Performance Evaluation of Speed Behaviour of Fuzzy-PI Operated BLDC Motor Drive","authors":"Samiksha Chintawar, Snehal Ghodke, V. Khatavkar, Utkarsh Alset, Hrishikesh Mehta","doi":"10.1109/ComPE53109.2021.9752453","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752453","url":null,"abstract":"In many applications, brushless direct current (BLDC) motor drives use fuzzy logic controllers for speed control owing to their advantages like auto-tuning of parameters, wide operational range, low computational requirements and low cost. However, the effect of different rulesets on the transient and steady-state speed Behaviour of BLDC motors has not been widely covered in the literature. The contribution of this paper includes speed characteristics of the triangular membership function (trimf) based fuzzy proportional-integral (FPI) controller is evaluated. Rulesets of 3 × 3, 5 × 5 and 7 × 7 formed using 3, 5 and 7 trimfs are compared for their Behaviour and time required for performing computations for speed benchmark of the BLDC motor used in comprehensive electric vehicle (EV) applications. The fuzzy logic control algorithm is implemented by means of Mathworks’ Fuzzy Logic Tool-set. The results are substantiated using MATLAB/Simulink. It is thereby concluded that increasing the number of membership functions improves the dynamic and steady-state behaviour of the BLDC motor.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131481353","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：