Pub Date : 2019-12-01DOI: 10.1109/IEEM44572.2019.8978496
Tomoki Fukuba, Tetsuya Sato, T. Shiina, K. Tokoro
In this paper, we consider the application of mathematical optimization models to energy problems. Using the latest information technology, we try to utilize renewable energy whose output is unstable. Such efforts are collectively called smart communities. Stochastic programming deals with optimization under uncertain conditions. Since the output of solar power generation in a smart community is uncertain, application of stochastic programming is required. Considering practical operational constraints, this model becomes a stochastic programming problem involving nonlinear recourse, which cannot be solved with typical solvers directly. The problem can be reformulated as a large-scale mixed integer programming problem by piecewise linear approximation to obtain an optimal solution. In our algorithm, we add points for piecewise linear approximation iteratively and increase accuracy of the approximation. In numerical experiments, the effectiveness of the stochastic programming model is shown by comparing it with the deterministic model. Moreover, we calculate a recovery period of investment cost for photovoltaic generation and a storage battery and show usefulness of our model when evaluating a practical operation.
{"title":"Stochastic Nonlinear Programming Model for Power Plant Operation via Piecewise Linearization","authors":"Tomoki Fukuba, Tetsuya Sato, T. Shiina, K. Tokoro","doi":"10.1109/IEEM44572.2019.8978496","DOIUrl":"https://doi.org/10.1109/IEEM44572.2019.8978496","url":null,"abstract":"In this paper, we consider the application of mathematical optimization models to energy problems. Using the latest information technology, we try to utilize renewable energy whose output is unstable. Such efforts are collectively called smart communities. Stochastic programming deals with optimization under uncertain conditions. Since the output of solar power generation in a smart community is uncertain, application of stochastic programming is required. Considering practical operational constraints, this model becomes a stochastic programming problem involving nonlinear recourse, which cannot be solved with typical solvers directly. The problem can be reformulated as a large-scale mixed integer programming problem by piecewise linear approximation to obtain an optimal solution. In our algorithm, we add points for piecewise linear approximation iteratively and increase accuracy of the approximation. In numerical experiments, the effectiveness of the stochastic programming model is shown by comparing it with the deterministic model. Moreover, we calculate a recovery period of investment cost for photovoltaic generation and a storage battery and show usefulness of our model when evaluating a practical operation.","PeriodicalId":255418,"journal":{"name":"2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123802772","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 : 2019-12-01DOI: 10.1109/IEEM44572.2019.8978701
A. Telukdarie, M. Munsamy
The fourth industrial revolution, the digitization of industry, is driving business landscape and associated skills development, including tertiary education. Universities and institutions of higher learning have evolved into technological hubs, developing and delivering skills for the future. The operations and systems together with workflows of delivery at a tertiary institution should be modified to deliver services and a product that is 4IR savvy, more importantly, the systems and processes must be 4IR enabled so as to deliver a seamless, efficient, smart digital experience. This paper reviews tertiary institutional operations and provides an architecture to deliver digitization at institutional level. This research adopts a functional and architectural view of the system and systems of systems. A Digital Education Evaluation Model (DEEM) is proposed for evaluation of traditional and digitized practices, for identification of digitized technologies for adoption. The DEEM is demonstrated by comparatively analyzing traditional and virtual classrooms.
{"title":"Digitization of Higher Education Institutions","authors":"A. Telukdarie, M. Munsamy","doi":"10.1109/IEEM44572.2019.8978701","DOIUrl":"https://doi.org/10.1109/IEEM44572.2019.8978701","url":null,"abstract":"The fourth industrial revolution, the digitization of industry, is driving business landscape and associated skills development, including tertiary education. Universities and institutions of higher learning have evolved into technological hubs, developing and delivering skills for the future. The operations and systems together with workflows of delivery at a tertiary institution should be modified to deliver services and a product that is 4IR savvy, more importantly, the systems and processes must be 4IR enabled so as to deliver a seamless, efficient, smart digital experience. This paper reviews tertiary institutional operations and provides an architecture to deliver digitization at institutional level. This research adopts a functional and architectural view of the system and systems of systems. A Digital Education Evaluation Model (DEEM) is proposed for evaluation of traditional and digitized practices, for identification of digitized technologies for adoption. The DEEM is demonstrated by comparatively analyzing traditional and virtual classrooms.","PeriodicalId":255418,"journal":{"name":"2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121649427","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 : 2019-12-01DOI: 10.1109/IEEM44572.2019.8978558
S. Mukwakungu, Zandile Sibeko, C. Mbohwa
This paper presents the results of the evaluation of the effectiveness that rolling stock maintenance (RSM) has on quality assurance (QA) at the largest rail, port and pipeline company in South Africa, as a case study conducted at its Koedoespoort depots and factories. Using a quantitative approach descriptive in nature, the researchers aimed to gain an insight into the research problem and to investigate the effectiveness RSM has on QA at freight rail company. Data was collected from a sample of 30 employees randomly selected at the engineering division. The evidence collected shows that the engineering division does not have a criterion to monitor the effectiveness of the current maintenance plan, the division does not have a maintenance system that is well understood by the artisans as well as technicians. The recommendations emphasized on a continuous training program on quality planning and implementation for the whole engineering division to ensure that the proposed maintenance strategy delivers as expected right the first time.
{"title":"The Effectiveness of Rolling Stock Maintenance on Quality Assurance at the Largest South African Rail Company","authors":"S. Mukwakungu, Zandile Sibeko, C. Mbohwa","doi":"10.1109/IEEM44572.2019.8978558","DOIUrl":"https://doi.org/10.1109/IEEM44572.2019.8978558","url":null,"abstract":"This paper presents the results of the evaluation of the effectiveness that rolling stock maintenance (RSM) has on quality assurance (QA) at the largest rail, port and pipeline company in South Africa, as a case study conducted at its Koedoespoort depots and factories. Using a quantitative approach descriptive in nature, the researchers aimed to gain an insight into the research problem and to investigate the effectiveness RSM has on QA at freight rail company. Data was collected from a sample of 30 employees randomly selected at the engineering division. The evidence collected shows that the engineering division does not have a criterion to monitor the effectiveness of the current maintenance plan, the division does not have a maintenance system that is well understood by the artisans as well as technicians. The recommendations emphasized on a continuous training program on quality planning and implementation for the whole engineering division to ensure that the proposed maintenance strategy delivers as expected right the first time.","PeriodicalId":255418,"journal":{"name":"2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121750487","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 : 2019-12-01DOI: 10.1109/IEEM44572.2019.8978813
Ivonne Poves-Calderno, J. Ramirez-Mendoza, Victor Nuñez-Ponce, J. Alvarez-Merino
This study analyzes the influence of nonfulfillment of orders in a company that produces plastic sheets. The main cause of problems is the long unproductive times during the extrusion process, which decrease the index of the overall equipment effectiveness (OEE). An innovative proposal is presented to address this issue, involving the use of a systematic approach and combining the SMED and preventive maintenance techniques of the lean manufacturing methodology, with the aim of reducing unproductive times to improve the OEE index. To validate the effectiveness of the proposal, the systems were simulated using Arena simulation software and input analyzer, to determine the reduction of unproductive times. Results show that the proposal reduces the unproductive times bh 36.37% and improves the OEE index by 9.02%. This demonstrates the achievement of the objective of the project, which was to maximize the efficiency of the process and reduce the total time of the extrusion process, which will allow the company to fulfill the orders and avoid profit losses.
{"title":"Application of Lean Manufacturing Techniques in a Peruvian Plastic Company","authors":"Ivonne Poves-Calderno, J. Ramirez-Mendoza, Victor Nuñez-Ponce, J. Alvarez-Merino","doi":"10.1109/IEEM44572.2019.8978813","DOIUrl":"https://doi.org/10.1109/IEEM44572.2019.8978813","url":null,"abstract":"This study analyzes the influence of nonfulfillment of orders in a company that produces plastic sheets. The main cause of problems is the long unproductive times during the extrusion process, which decrease the index of the overall equipment effectiveness (OEE). An innovative proposal is presented to address this issue, involving the use of a systematic approach and combining the SMED and preventive maintenance techniques of the lean manufacturing methodology, with the aim of reducing unproductive times to improve the OEE index. To validate the effectiveness of the proposal, the systems were simulated using Arena simulation software and input analyzer, to determine the reduction of unproductive times. Results show that the proposal reduces the unproductive times bh 36.37% and improves the OEE index by 9.02%. This demonstrates the achievement of the objective of the project, which was to maximize the efficiency of the process and reduce the total time of the extrusion process, which will allow the company to fulfill the orders and avoid profit losses.","PeriodicalId":255418,"journal":{"name":"2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128714053","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 : 2019-12-01DOI: 10.1109/IEEM44572.2019.8978590
Takafumi Miyazaki, N. Ouchi
The Japanese government is increasingly promoting “work-style reform” and many Japanese companies are working on redressing long working hours. Several studies have suggested that long working hours play the role of a buffer to adjust labor costs when an economic negative shock occurs. However, the conditions under which long working hours are utilized as a buffer, are unclear. This study attempts to clarify what kind of industries utilize long working hours as a buffer. We calculate the contribution rate of non-scheduled hours worked to the rate of change of total labor costs and conduct correlation analysis between this rate and each index indicating industry characteristics. The results reveal that labor-intensive and growth industries utilized non-scheduled hours worked as a buffer. This suggests that there is a risk of losing such a buffer by redressing working hours, especially in these industries.
{"title":"Long Working Hours as a Buffer to Adjust Labor Costs","authors":"Takafumi Miyazaki, N. Ouchi","doi":"10.1109/IEEM44572.2019.8978590","DOIUrl":"https://doi.org/10.1109/IEEM44572.2019.8978590","url":null,"abstract":"The Japanese government is increasingly promoting “work-style reform” and many Japanese companies are working on redressing long working hours. Several studies have suggested that long working hours play the role of a buffer to adjust labor costs when an economic negative shock occurs. However, the conditions under which long working hours are utilized as a buffer, are unclear. This study attempts to clarify what kind of industries utilize long working hours as a buffer. We calculate the contribution rate of non-scheduled hours worked to the rate of change of total labor costs and conduct correlation analysis between this rate and each index indicating industry characteristics. The results reveal that labor-intensive and growth industries utilized non-scheduled hours worked as a buffer. This suggests that there is a risk of losing such a buffer by redressing working hours, especially in these industries.","PeriodicalId":255418,"journal":{"name":"2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130976753","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 : 2019-12-01DOI: 10.1109/IEEM44572.2019.8978548
H. Jia, R. Adland, Yuchen Wang
We implement machine learning techniques to predict the destination for Latin American crude oil exports. Utilizing a unique dataset of micro-level crude oil shipment data, derived from the Automatic Identification System (AIS) for ship tracking, we investigate the micro- and macro-level determinants of the destination choice. We use decision tree, Random Forests and boosted trees techniques in training a model to predict the export destinations which can help to identify seller/buyer groups with similar oil trade requirements. The results show that while macro data, such as regional oil price differences and crack spreads, impacts the crude oil flow, micro level information about the oil shipment are key attributes in the destination prediction. Our research has practical implications, particularly with regards to prediction of oil transportation demand, spatial price arbitrage and short-term forecasting of regional crack spreads.
{"title":"Latin American Oil Export Destination Choice: A Machine Learning Approach","authors":"H. Jia, R. Adland, Yuchen Wang","doi":"10.1109/IEEM44572.2019.8978548","DOIUrl":"https://doi.org/10.1109/IEEM44572.2019.8978548","url":null,"abstract":"We implement machine learning techniques to predict the destination for Latin American crude oil exports. Utilizing a unique dataset of micro-level crude oil shipment data, derived from the Automatic Identification System (AIS) for ship tracking, we investigate the micro- and macro-level determinants of the destination choice. We use decision tree, Random Forests and boosted trees techniques in training a model to predict the export destinations which can help to identify seller/buyer groups with similar oil trade requirements. The results show that while macro data, such as regional oil price differences and crack spreads, impacts the crude oil flow, micro level information about the oil shipment are key attributes in the destination prediction. Our research has practical implications, particularly with regards to prediction of oil transportation demand, spatial price arbitrage and short-term forecasting of regional crack spreads.","PeriodicalId":255418,"journal":{"name":"2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130834459","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 : 2019-12-01DOI: 10.1109/IEEM44572.2019.8978712
R. Chakrabortty, H. Rahman, H. Mo, M. Ryan
In the presence of increasingly dynamic environments, frequent uncertainties, high customer specifications, strict project deadlines, and stricter requirements on sustainability, modern project managers are challenged in their ability to schedule and control projects. Thus, in the context of sustainable project scheduling problem, two important elements are to be considered as decision variables: the input elements of a scheduling (e.g. resources: workforce, machine, money) that enable the realization of a schedule for a project and the output element that are consequences of the realization of the project (e.g. completion time, energy, noise, pollution, waste etc.). In this context, integration of innovative approaches and concepts under the framework of fourth generation industrial revolution is must to build up a sustainable project scheduling model (SPSM). Considering this burning issue, this paper introduces digital twin (DT) technology and cyber physical system (CPS) principles to develop effective and efficient sustainable project scheduling systems and proposes a framework to show how they are interconnected through physical and cyber layers. The proposed framework is also applied to a real-life energy system as a case study for identification of the degradation of a physical layer.
{"title":"Digital Twin-based Cyber Physical System for Sustainable Project Scheduling","authors":"R. Chakrabortty, H. Rahman, H. Mo, M. Ryan","doi":"10.1109/IEEM44572.2019.8978712","DOIUrl":"https://doi.org/10.1109/IEEM44572.2019.8978712","url":null,"abstract":"In the presence of increasingly dynamic environments, frequent uncertainties, high customer specifications, strict project deadlines, and stricter requirements on sustainability, modern project managers are challenged in their ability to schedule and control projects. Thus, in the context of sustainable project scheduling problem, two important elements are to be considered as decision variables: the input elements of a scheduling (e.g. resources: workforce, machine, money) that enable the realization of a schedule for a project and the output element that are consequences of the realization of the project (e.g. completion time, energy, noise, pollution, waste etc.). In this context, integration of innovative approaches and concepts under the framework of fourth generation industrial revolution is must to build up a sustainable project scheduling model (SPSM). Considering this burning issue, this paper introduces digital twin (DT) technology and cyber physical system (CPS) principles to develop effective and efficient sustainable project scheduling systems and proposes a framework to show how they are interconnected through physical and cyber layers. The proposed framework is also applied to a real-life energy system as a case study for identification of the degradation of a physical layer.","PeriodicalId":255418,"journal":{"name":"2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130326419","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 : 2019-12-01DOI: 10.1109/IEEM44572.2019.8978710
M. Ko, Tatsuya Inagi, Masaaki Takada, T. Yano
Multifunction peripheral (MFP) manufacturers provide customers with remote maintenance services, such as supplies provision and automatic firmware updates, to lower customer burdens and to avoid device downtime. Such remote services are required for maintenance so that Japanese machine manufacturers can deliver products to foreign markets, because service bases in overseas locales must cover broader geographical areas than those in Japan. When MFP devices experience a fault, they generally alert users of an error. Although some faults can be solved remotely, there are faults that require an engineer to perform on-site actions. To repair them on-site efficiently, online investigation and pre-assessment of fault factors will be effective. In this paper, we apply the Group Lasso regularization method for logistic regression to select features determined as error factors. We evaluate the engine on two kinds of error examples: those frequently causing alerts in MFP models in the past, and those causing alerts due to part wear. This engine is expected to help engineers determine causal factors of errors.
{"title":"Application of Feature Selection Method to Error Factor Extraction of Multifunction Peripheral","authors":"M. Ko, Tatsuya Inagi, Masaaki Takada, T. Yano","doi":"10.1109/IEEM44572.2019.8978710","DOIUrl":"https://doi.org/10.1109/IEEM44572.2019.8978710","url":null,"abstract":"Multifunction peripheral (MFP) manufacturers provide customers with remote maintenance services, such as supplies provision and automatic firmware updates, to lower customer burdens and to avoid device downtime. Such remote services are required for maintenance so that Japanese machine manufacturers can deliver products to foreign markets, because service bases in overseas locales must cover broader geographical areas than those in Japan. When MFP devices experience a fault, they generally alert users of an error. Although some faults can be solved remotely, there are faults that require an engineer to perform on-site actions. To repair them on-site efficiently, online investigation and pre-assessment of fault factors will be effective. In this paper, we apply the Group Lasso regularization method for logistic regression to select features determined as error factors. We evaluate the engine on two kinds of error examples: those frequently causing alerts in MFP models in the past, and those causing alerts due to part wear. This engine is expected to help engineers determine causal factors of errors.","PeriodicalId":255418,"journal":{"name":"2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130470762","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 : 2019-12-01DOI: 10.1109/IEEM44572.2019.8978643
D. Valis, L. Zák, Z. Vintr
Technical practice abounds with numerous diverse data records. Sometimes the data is complete, sometimes it is censored or truncated. It is not always easy and straightforward to record the data. And even after, the data processing is by no means simple, especially when the data forms a significant set of a huge size and large informational diversity. Typically, the data containing more observed variables, either dependent or independent, is called multidimensional. Also, if the multidimensional data contains numerous records, it is not easy to determine which dependent or independent variables are important for further study. Our aim and ambition is to introduce a couple of methods which are very suitable and sometimes absolutely necessary for exploratory data analysis. The methods help us to determine i) the level of significance of the data for single recorded variables, ii) the level of mutual dependence among the data, and iii) the choice of the best representatives for further data study. The recommended methods used for the exploratory data analysis are presented with practical examples.
{"title":"Perspective Exploratory Methods for Multidimensional Data Analysis","authors":"D. Valis, L. Zák, Z. Vintr","doi":"10.1109/IEEM44572.2019.8978643","DOIUrl":"https://doi.org/10.1109/IEEM44572.2019.8978643","url":null,"abstract":"Technical practice abounds with numerous diverse data records. Sometimes the data is complete, sometimes it is censored or truncated. It is not always easy and straightforward to record the data. And even after, the data processing is by no means simple, especially when the data forms a significant set of a huge size and large informational diversity. Typically, the data containing more observed variables, either dependent or independent, is called multidimensional. Also, if the multidimensional data contains numerous records, it is not easy to determine which dependent or independent variables are important for further study. Our aim and ambition is to introduce a couple of methods which are very suitable and sometimes absolutely necessary for exploratory data analysis. The methods help us to determine i) the level of significance of the data for single recorded variables, ii) the level of mutual dependence among the data, and iii) the choice of the best representatives for further data study. The recommended methods used for the exploratory data analysis are presented with practical examples.","PeriodicalId":255418,"journal":{"name":"2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130330579","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 : 2019-12-01DOI: 10.1109/IEEM44572.2019.8978873
Jiaqing Zhao, Zhongjian Dai, Zhongyao Chen, Hongen Ding, Puliang Du
In this paper, a fault location method considering distribution network partition based on deep learning is proposed, in which the Tensorflow framework is employed to establish and construct the fault location model of the distribution network. This method firstly collects the current and voltage data to form fault data vectors through the Feeder Terminal Unit. Combined with the complex network theory, each node degree is calculated to represent the node priority, and the topology of the distribution network is partitioned to form each regional model. Secondly, it builds a feature extracting network and a Deep Neural network to mine the mapping relations between fault data vectors and fault sections and form the final fault location model through training. Case studies show that compared to the back propagation (BP) neural network model and the support vector machine (SVM) model, the deep learning model has faster convergence speed and higher fault location accuracy.
{"title":"A Fault Location Method Considering Distribution Network Partition Based on Deep Learning","authors":"Jiaqing Zhao, Zhongjian Dai, Zhongyao Chen, Hongen Ding, Puliang Du","doi":"10.1109/IEEM44572.2019.8978873","DOIUrl":"https://doi.org/10.1109/IEEM44572.2019.8978873","url":null,"abstract":"In this paper, a fault location method considering distribution network partition based on deep learning is proposed, in which the Tensorflow framework is employed to establish and construct the fault location model of the distribution network. This method firstly collects the current and voltage data to form fault data vectors through the Feeder Terminal Unit. Combined with the complex network theory, each node degree is calculated to represent the node priority, and the topology of the distribution network is partitioned to form each regional model. Secondly, it builds a feature extracting network and a Deep Neural network to mine the mapping relations between fault data vectors and fault sections and form the final fault location model through training. Case studies show that compared to the back propagation (BP) neural network model and the support vector machine (SVM) model, the deep learning model has faster convergence speed and higher fault location accuracy.","PeriodicalId":255418,"journal":{"name":"2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128113993","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：