Pub Date : 2020-11-30DOI: 10.37624/IJERT/13.11.2020.3564-3567
L. Galiullin, R. Valiev
At the stage of analyzing the application for the implementation of the structure allowing to optimize this task, the following tasks were performed: the analysis of the system's business processes was carried out; analysis of the system architecture; the problem is posed. At the next stage, the architecture of the structure of a unique identifier and its mathematical model were designed, and its uniqueness was tested and proved. At the last stage, the implementation, generator and application were described as a web service of the system. All the tasks and development requirements were met, the work was completed in full and on time. The unique identifier has surpassed the one in the .Net platform in performance, is compatible with all CLI languages, allows you to optimize the search not only for a specific relational database, but also for many other databases that use the principle of balancing unique values on the left N bytes in B-Tree, such bases are: MySQL, SQLite, MariaDB. The possibility of fast work with strings of one register and one encoding is revealed, due to the fast hashing algorithm.
{"title":"Method for Developing Unique Database Identifiers","authors":"L. Galiullin, R. Valiev","doi":"10.37624/IJERT/13.11.2020.3564-3567","DOIUrl":"https://doi.org/10.37624/IJERT/13.11.2020.3564-3567","url":null,"abstract":"At the stage of analyzing the application for the implementation of the structure allowing to optimize this task, the following tasks were performed: the analysis of the system's business processes was carried out; analysis of the system architecture; the problem is posed. At the next stage, the architecture of the structure of a unique identifier and its mathematical model were designed, and its uniqueness was tested and proved. At the last stage, the implementation, generator and application were described as a web service of the system. All the tasks and development requirements were met, the work was completed in full and on time. The unique identifier has surpassed the one in the .Net platform in performance, is compatible with all CLI languages, allows you to optimize the search not only for a specific relational database, but also for many other databases that use the principle of balancing unique values on the left N bytes in B-Tree, such bases are: MySQL, SQLite, MariaDB. The possibility of fast work with strings of one register and one encoding is revealed, due to the fast hashing algorithm.","PeriodicalId":14123,"journal":{"name":"International journal of engineering research and technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91425360","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 : 2020-11-30DOI: 10.37624/IJERT/13.11.2020.3367-3371
E. Casallas, Luis Alberto Jaime Hernández, Cristian Ancizar Bermúdez Bello
Design and implementation of an image capture module with different perspectives in non-stationary space exploration probes. It was developed on a reduced plate where the processing and storage of information for four strategically located cameras is centralized, obtaining a multidirectional spatial vision. The four cameras are controlled by a Script developed in an interpreted programming language (Python), and a digital switch was used for the multiplexing sequence. In the development of the Script, various libraries were used to capture images and process the encapsulation on a virtual environment, complementing the images with data information considered input parameters to the module. The video sections with autosave functionality are generated through bursts of images for fixed periods.
{"title":"On Screen Display Module","authors":"E. Casallas, Luis Alberto Jaime Hernández, Cristian Ancizar Bermúdez Bello","doi":"10.37624/IJERT/13.11.2020.3367-3371","DOIUrl":"https://doi.org/10.37624/IJERT/13.11.2020.3367-3371","url":null,"abstract":"Design and implementation of an image capture module with different perspectives in non-stationary space exploration probes. It was developed on a reduced plate where the processing and storage of information for four strategically located cameras is centralized, obtaining a multidirectional spatial vision. The four cameras are controlled by a Script developed in an interpreted programming language (Python), and a digital switch was used for the multiplexing sequence. In the development of the Script, various libraries were used to capture images and process the encapsulation on a virtual environment, complementing the images with data information considered input parameters to the module. The video sections with autosave functionality are generated through bursts of images for fixed periods.","PeriodicalId":14123,"journal":{"name":"International journal of engineering research and technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91351366","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 : 2020-11-30DOI: 10.37624/IJERT/13.11.2020.3568-3574
Kadochnikova E.I., Sungatullina L.B., Agzamova R. R., Abduazizova G. Sh
The authors used prospective estimates of revenue and accounts receivable, obtained on the basis of an additive trend-seasonal model, to forecast the poultry enterprise financial resources. The study highlights the fact that the classical decomposition of the trend-seasonal model into trend, seasonal and random components is possible and convenient for forecasting the financial resources of a poultry enterprise that has a seasonality in production. The forecast estimates presented in the article confirmed the main hypothesis of the study – if there are objective seasonal fluctuations for a poultry enterprise, there is a tendency to increase sales revenue and accounts receivable due to limited customer liquidity. The results of the obtained empirical estimates confirmed the practical use feasibility of an additive trend-seasonal model based on the classical decomposition for predicting the financial resources of a poultry enterprise.
{"title":"Perspective Evaluation of a Poultry-Breeding Enterprise Financial Resources Based on Seasonal Decomposition","authors":"Kadochnikova E.I., Sungatullina L.B., Agzamova R. R., Abduazizova G. Sh","doi":"10.37624/IJERT/13.11.2020.3568-3574","DOIUrl":"https://doi.org/10.37624/IJERT/13.11.2020.3568-3574","url":null,"abstract":"The authors used prospective estimates of revenue and accounts receivable, obtained on the basis of an additive trend-seasonal model, to forecast the poultry enterprise financial resources. The study highlights the fact that the classical decomposition of the trend-seasonal model into trend, seasonal and random components is possible and convenient for forecasting the financial resources of a poultry enterprise that has a seasonality in production. The forecast estimates presented in the article confirmed the main hypothesis of the study – if there are objective seasonal fluctuations for a poultry enterprise, there is a tendency to increase sales revenue and accounts receivable due to limited customer liquidity. The results of the obtained empirical estimates confirmed the practical use feasibility of an additive trend-seasonal model based on the classical decomposition for predicting the financial resources of a poultry enterprise.","PeriodicalId":14123,"journal":{"name":"International journal of engineering research and technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91368672","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 : 2020-11-30DOI: 10.37624/IJERT/13.11.2020.3987-3996
Kangseok Kim
This study proposes a methodology for anomaly detection in HIDS using supervised and semi-supervised anomaly detection approaches by applying GAN (Generative Adversarial Network) based data augmentation. An anomaly-based intrusion detection system detects abnormal patterns based on deviations from expected normal behaviors; however, such a system has a low detection rate. Also a detection accuracy may vary depending on whether abnormal samples are used during learning. Moreover, it may vary according to the degree of class imbalance that means the imbalance of data class distributions. To avoid the problem and to enhance the low predictive accuracy, it might need to augment minority datasets through the creation of new samples. Therefore, recently, some of existing studies have involved the development of intrusion detection models using machine/deep learning algorithms to overcome the limitations of existing anomaly-based intrusion detection methodologies and to avoid class imbalance problems. In a similar vein, this study proposes a method for improving classification performance of normal and abnormal data in anomaly-based intrusion detection systems by applying data augmentation using GAN. To verify the effectiveness of the proposed anomaly detection method, we use the ADFA-LD Dataset which consists of system call traces for attacks on the latest operating systems. Experiments were performed using SVM (Support Vector Machine) and CNN (Convolution Neural Network) for classification, and GAN and SMOTE for data augmentation, respectively. The experimental results indicated that GAN based approach provides a slightly more reliable way of working with data augmentation than SMOTE. In addition, it was confirmed based on the experimental results that the classification performance can be improved as the number of samples belonging to each imbalanced class increases.
{"title":"GAN based Augmentation for Improving Anomaly Detection Accuracy in Host-based Intrusion Detection Systems","authors":"Kangseok Kim","doi":"10.37624/IJERT/13.11.2020.3987-3996","DOIUrl":"https://doi.org/10.37624/IJERT/13.11.2020.3987-3996","url":null,"abstract":"This study proposes a methodology for anomaly detection in HIDS using supervised and semi-supervised anomaly detection approaches by applying GAN (Generative Adversarial Network) based data augmentation. An anomaly-based intrusion detection system detects abnormal patterns based on deviations from expected normal behaviors; however, such a system has a low detection rate. Also a detection accuracy may vary depending on whether abnormal samples are used during learning. Moreover, it may vary according to the degree of class imbalance that means the imbalance of data class distributions. To avoid the problem and to enhance the low predictive accuracy, it might need to augment minority datasets through the creation of new samples. Therefore, recently, some of existing studies have involved the development of intrusion detection models using machine/deep learning algorithms to overcome the limitations of existing anomaly-based intrusion detection methodologies and to avoid class imbalance problems. In a similar vein, this study proposes a method for improving classification performance of normal and abnormal data in anomaly-based intrusion detection systems by applying data augmentation using GAN. To verify the effectiveness of the proposed anomaly detection method, we use the ADFA-LD Dataset which consists of system call traces for attacks on the latest operating systems. Experiments were performed using SVM (Support Vector Machine) and CNN (Convolution Neural Network) for classification, and GAN and SMOTE for data augmentation, respectively. The experimental results indicated that GAN based approach provides a slightly more reliable way of working with data augmentation than SMOTE. In addition, it was confirmed based on the experimental results that the classification performance can be improved as the number of samples belonging to each imbalanced class increases.","PeriodicalId":14123,"journal":{"name":"International journal of engineering research and technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85593148","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 : 2020-11-30DOI: 10.37624/IJERT/13.11.2020.3398-3403
S KhotRahul, T. Venkateswararao
This paper presents the impact of the angle of the Laser incident beam on transformed induced plasticity (TRIP) steel sheet subjected to robotic arm assisted Nd: YAG high density laser beam. The continuous laser beam source mode is used to produce a butt weld joint using a 2 mm sheet of standard ASME E8 with maximum power is used as a 2200W with zero gap. The experiments are conducted on the samples with varying incident angle as 80°, 90° and 100° from horizontal parallel plane to work piece. Along with this the laser welding speed are varying from 25 mm/sec, 28 mm/sec and 30 mm/sec effects are analyzed. The result shows that there is a significant change in the strength and deformation of the joint by growing the beam incident angle with constant beam power of 2200W and changing welding speed. In order to understand the effect of the laser angle on the microstructure of the heat affected zone, FESEM is performed on tested samples from tensile tests.
{"title":"Investigation of Mechanical Behaviour of Laser Welded Butt Joint of Transformed Induced Plasticity (TRIP) Steel with effect Laser Incident Angle","authors":"S KhotRahul, T. Venkateswararao","doi":"10.37624/IJERT/13.11.2020.3398-3403","DOIUrl":"https://doi.org/10.37624/IJERT/13.11.2020.3398-3403","url":null,"abstract":"This paper presents the impact of the angle of the Laser incident beam on transformed induced plasticity (TRIP) steel sheet subjected to robotic arm assisted Nd: YAG high density laser beam. The continuous laser beam source mode is used to produce a butt weld joint using a 2 mm sheet of standard ASME E8 with maximum power is used as a 2200W with zero gap. The experiments are conducted on the samples with varying incident angle as 80°, 90° and 100° from horizontal parallel plane to work piece. Along with this the laser welding speed are varying from 25 mm/sec, 28 mm/sec and 30 mm/sec effects are analyzed. The result shows that there is a significant change in the strength and deformation of the joint by growing the beam incident angle with constant beam power of 2200W and changing welding speed. In order to understand the effect of the laser angle on the microstructure of the heat affected zone, FESEM is performed on tested samples from tensile tests.","PeriodicalId":14123,"journal":{"name":"International journal of engineering research and technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84624917","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 : 2020-11-30DOI: 10.2991/assehr.k.201201.249
Heri Sudarmaji, L. Nurlaela, E. Hariadi
Vocational education as one of the important role holders in preparing the workforce is demanded to be able to keep up with the changing and developing market demands. Vocational education is a part of the national education system that has very strategic roles for forming skillful employees. However, in reality, it shows that not all vocational education is capable of producing quality graduates as evidenced by the lack of knowledge and skills possessed. The purpose of this research is to analyze the influences of skill, knowledge, attitude, and morality toward achievement. This research is a causal research type by a quantitative approach. The population in this research is 278 people at government agencies as a user of the graduated student from the college under the supervision of the Center for Human Resources Development on Civil Aviation (CHRDCA). The sampling technique uses total sampling. Data collection uses questionnaires. The data analysis technique used is multiple linear regression analysis. As the results of this research, there are significant and positive influences of skill, knowledge, attitude, and morality on job achievement.
{"title":"Influences of Skill, Knowledge, Attitude, and Morality on Job Achievement","authors":"Heri Sudarmaji, L. Nurlaela, E. Hariadi","doi":"10.2991/assehr.k.201201.249","DOIUrl":"https://doi.org/10.2991/assehr.k.201201.249","url":null,"abstract":"Vocational education as one of the important role holders in preparing the workforce is demanded to be able to keep up with the changing and developing market demands. Vocational education is a part of the national education system that has very strategic roles for forming skillful employees. However, in reality, it shows that not all vocational education is capable of producing quality graduates as evidenced by the lack of knowledge and skills possessed. The purpose of this research is to analyze the influences of skill, knowledge, attitude, and morality toward achievement. This research is a causal research type by a quantitative approach. The population in this research is 278 people at government agencies as a user of the graduated student from the college under the supervision of the Center for Human Resources Development on Civil Aviation (CHRDCA). The sampling technique uses total sampling. Data collection uses questionnaires. The data analysis technique used is multiple linear regression analysis. As the results of this research, there are significant and positive influences of skill, knowledge, attitude, and morality on job achievement.","PeriodicalId":14123,"journal":{"name":"International journal of engineering research and technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90758534","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 : 2020-11-30DOI: 10.37624/IJERT/13.11.2020.3546-3550
A. Iliukhin, L. Galiullin
Describes the work on modern scientific achievements in graph theory, studying the developed algorithms, comparing their advantages and disadvantages, the reason for choosing the Ford-Bellman algorithm as a tool for solving the problem. The principle of the Ford-Bellman Algorithm and its structure were also described. The works on designing the architecture of Ford-Bellman algorithms in C # language, designing a class hierarchy for geometric objects modeling graphs, designing a model that implements threedimensional geometric space were described. The architecture of the graphical interface and the hierarchy of its classes were also described. The paper describes the implementation of the model, which searches for the shortest route between any two points of the graph, the implementation of the graphical interface through which the algorithm is controlled. As a result of the work, the design and development of the application for finding the shortest route in a weighted connected pseudograph was carried out. The algorithm has been tested. The algorithm works and successfully performs the task. The algorithm was encapsulated and allocated to a separate class library, which makes it possible to use it in many other projects of different industries. It can be used for engineering calculations in which the problem can be represented as a graph; in tasks where it is necessary to find the shortest path from one point to another; in robotics and systems with artificial intelligence.
{"title":"Method for Optimal Route","authors":"A. Iliukhin, L. Galiullin","doi":"10.37624/IJERT/13.11.2020.3546-3550","DOIUrl":"https://doi.org/10.37624/IJERT/13.11.2020.3546-3550","url":null,"abstract":"Describes the work on modern scientific achievements in graph theory, studying the developed algorithms, comparing their advantages and disadvantages, the reason for choosing the Ford-Bellman algorithm as a tool for solving the problem. The principle of the Ford-Bellman Algorithm and its structure were also described. The works on designing the architecture of Ford-Bellman algorithms in C # language, designing a class hierarchy for geometric objects modeling graphs, designing a model that implements threedimensional geometric space were described. The architecture of the graphical interface and the hierarchy of its classes were also described. The paper describes the implementation of the model, which searches for the shortest route between any two points of the graph, the implementation of the graphical interface through which the algorithm is controlled. As a result of the work, the design and development of the application for finding the shortest route in a weighted connected pseudograph was carried out. The algorithm has been tested. The algorithm works and successfully performs the task. The algorithm was encapsulated and allocated to a separate class library, which makes it possible to use it in many other projects of different industries. It can be used for engineering calculations in which the problem can be represented as a graph; in tasks where it is necessary to find the shortest path from one point to another; in robotics and systems with artificial intelligence.","PeriodicalId":14123,"journal":{"name":"International journal of engineering research and technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83155178","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 : 2020-11-30DOI: 10.37624/IJERT/13.11.2020.3428-3430
Ki-Seok Choi
In the recent years, the business environments in Korea, as in most other industrialized countries, have been going under revolutionary changes by adopting artificial intelligence (AI) technology. Since the technology gets popular widely in a short period, there are surging demands of AI manpower not only in the experienced level but also in the entry level. Specifically, we observed by analysing software (SW) job announcements that in about half the cases they require more than 4-year education in college for their new employees without previous job experiences in big data/AI job positions. With the increasing industrial demands in the new technology, there are on-going efforts in higher educational institutes to provide qualified graduates in the AI fields. We surveyed what skills are required in which application fields.
{"title":"Opportunities for Higher Education of Artificial Intelligence in Korea","authors":"Ki-Seok Choi","doi":"10.37624/IJERT/13.11.2020.3428-3430","DOIUrl":"https://doi.org/10.37624/IJERT/13.11.2020.3428-3430","url":null,"abstract":"In the recent years, the business environments in Korea, as in most other industrialized countries, have been going under revolutionary changes by adopting artificial intelligence (AI) technology. Since the technology gets popular widely in a short period, there are surging demands of AI manpower not only in the experienced level but also in the entry level. Specifically, we observed by analysing software (SW) job announcements that in about half the cases they require more than 4-year education in college for their new employees without previous job experiences in big data/AI job positions. With the increasing industrial demands in the new technology, there are on-going efforts in higher educational institutes to provide qualified graduates in the AI fields. We surveyed what skills are required in which application fields.","PeriodicalId":14123,"journal":{"name":"International journal of engineering research and technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84191797","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 : 2020-11-30DOI: 10.37624/IJERT/13.11.2020.3589-3595
Oleg Yuryevich Panischev, E. Ahmedshina, D. V. Kataseva, I. Anikin, A. Katasev, A. M. Akhmetvaleev, A. V. Nasybullin
This paper poses and solves the problem of developing the upto-date neuro-fuzzy model of formation of a knowledge base for an intelligent decision-making support system for selection of geological and technical measures in oil fields. The analysis of the traditional approach to the formation of fuzzy knowledge bases made it possible to reveal its shortcomings associated with the need to attract experts, structure and formalize the system of decision-making rules by them. This process is laborious and does not always provide an acceptable result. To eliminate the disadvantages of the traditional approach, we proposed an approach to the automatic formation of a knowledge base based on the construction of a neuro-fuzzy model of a collective of fuzzy neural networks. We formulated the requirements in view of the formed fuzzy rules. We developed a scheme for using the rules of the knowledge base to solve the problem of selecting geological and technical measures in oil fields. We tested the generated knowledge base on the example of solving the problem of selecting geological and technical measures for various wells of the Feofanovskoye Field. Application of the knowledge base made it possible to select a list of optimal measures for given wells. The experiment results are satisfactory and are confirmed by the positive expert assessments, selecting geological and technical measures at this field. KeywordsNeuro-Fuzzy Model, Knowledge Base, Geological And Technical Measures, Oil Field, DecisionMaking Support
{"title":"Neurofuzzy Model of Formation of Knowledge Bases for Selection of Geological and Technical Measures in Oil Fields","authors":"Oleg Yuryevich Panischev, E. Ahmedshina, D. V. Kataseva, I. Anikin, A. Katasev, A. M. Akhmetvaleev, A. V. Nasybullin","doi":"10.37624/IJERT/13.11.2020.3589-3595","DOIUrl":"https://doi.org/10.37624/IJERT/13.11.2020.3589-3595","url":null,"abstract":"This paper poses and solves the problem of developing the upto-date neuro-fuzzy model of formation of a knowledge base for an intelligent decision-making support system for selection of geological and technical measures in oil fields. The analysis of the traditional approach to the formation of fuzzy knowledge bases made it possible to reveal its shortcomings associated with the need to attract experts, structure and formalize the system of decision-making rules by them. This process is laborious and does not always provide an acceptable result. To eliminate the disadvantages of the traditional approach, we proposed an approach to the automatic formation of a knowledge base based on the construction of a neuro-fuzzy model of a collective of fuzzy neural networks. We formulated the requirements in view of the formed fuzzy rules. We developed a scheme for using the rules of the knowledge base to solve the problem of selecting geological and technical measures in oil fields. We tested the generated knowledge base on the example of solving the problem of selecting geological and technical measures for various wells of the Feofanovskoye Field. Application of the knowledge base made it possible to select a list of optimal measures for given wells. The experiment results are satisfactory and are confirmed by the positive expert assessments, selecting geological and technical measures at this field. KeywordsNeuro-Fuzzy Model, Knowledge Base, Geological And Technical Measures, Oil Field, DecisionMaking Support","PeriodicalId":14123,"journal":{"name":"International journal of engineering research and technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83350553","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 : 2020-11-30DOI: 10.37624/IJERT/13.11.2020.3240-3246
Jong-Hyun Lee, Hyun-Sil Kim, Insoo Lee
Lithium batteries are presently used in various applications, such as cell phones, electric vehicles, unmanned submarines, and energy storage systems, as main power sources. Therefore, for stable and safe use of this system, it is important to rapidly detect defects in the battery and accurately diagnose faults. Battery faults can be diagnosed by measuring their state of health (SOH), which is affected by various operating conditions. In this work, a battery SOH monitoring system is implemented to detect faults using a multilayer neural network state classifier (MNNSC) and an internal resistance state classifier (IRSC). In this system, the MNNSC uses discharge voltage data from a lithium battery operating at high temperatures. Further, the IRSC uses the open circuit voltage, terminal voltage, and current to calculate the internal resistance. Experimental results show that the proposed battery SOH monitoring method was high accuracy.
{"title":"State of Health Monitoring of a Battery Module Using Multilayer Neural Network and Internal Resistance","authors":"Jong-Hyun Lee, Hyun-Sil Kim, Insoo Lee","doi":"10.37624/IJERT/13.11.2020.3240-3246","DOIUrl":"https://doi.org/10.37624/IJERT/13.11.2020.3240-3246","url":null,"abstract":"Lithium batteries are presently used in various applications, such as cell phones, electric vehicles, unmanned submarines, and energy storage systems, as main power sources. Therefore, for stable and safe use of this system, it is important to rapidly detect defects in the battery and accurately diagnose faults. Battery faults can be diagnosed by measuring their state of health (SOH), which is affected by various operating conditions. In this work, a battery SOH monitoring system is implemented to detect faults using a multilayer neural network state classifier (MNNSC) and an internal resistance state classifier (IRSC). In this system, the MNNSC uses discharge voltage data from a lithium battery operating at high temperatures. Further, the IRSC uses the open circuit voltage, terminal voltage, and current to calculate the internal resistance. Experimental results show that the proposed battery SOH monitoring method was high accuracy.","PeriodicalId":14123,"journal":{"name":"International journal of engineering research and technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77928636","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}