Pub Date : 2017-10-01DOI: 10.1109/ines.2017.8118541
C. Ionescu, Nicolas Van Oevelen, D. Copot, B. Paijmans, R. D. De Keyser
This paper introduces a novel method to control linear parameter varying (LPV) systems by employing methodologies and algorithms for deployment of — generally known as — fractional order controllers (FOC). The origin of FOC stems from fractional calculus where arbitrary order dynamic characterising functions can be used as envelop for varying dynamic properties of systems. The main feature employed here is the property of robustness, an intrinsic characteristic of FOC, if tuned accordingly. We present here the rationale and method for injecting a high degree of robustness for LPV dynamic systems. A study case from aerospace engineering is used to illustrate the proposed method and to demonstrate its usefulness. The realistic simulation results indicate that the proposed scheme works well and fulfils the imposed specifications.
{"title":"Control of LPV mechatronic systems in presence of dynamic uncertainties","authors":"C. Ionescu, Nicolas Van Oevelen, D. Copot, B. Paijmans, R. D. De Keyser","doi":"10.1109/ines.2017.8118541","DOIUrl":"https://doi.org/10.1109/ines.2017.8118541","url":null,"abstract":"This paper introduces a novel method to control linear parameter varying (LPV) systems by employing methodologies and algorithms for deployment of — generally known as — fractional order controllers (FOC). The origin of FOC stems from fractional calculus where arbitrary order dynamic characterising functions can be used as envelop for varying dynamic properties of systems. The main feature employed here is the property of robustness, an intrinsic characteristic of FOC, if tuned accordingly. We present here the rationale and method for injecting a high degree of robustness for LPV dynamic systems. A study case from aerospace engineering is used to illustrate the proposed method and to demonstrate its usefulness. The realistic simulation results indicate that the proposed scheme works well and fulfils the imposed specifications.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124913041","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 : 2017-10-01DOI: 10.1109/INES.2017.8118576
G. Oltean, L. Ivanciu, M. Gordan, I. Stoian, I. Kovacs
The interpretation of data gathered from dam monitoring directly influences the detection of abnormal behaviors. Using previously recorded data, predictive models can be developed, so that the signs of a possible failure are detected as early as possible. The paper presents a multi-step ahead predictive model to generate the values for the horizontal displacement of a dam, using previous values of the displacement, water level and temperature. The model is based on an autoregressive neural network that was trained and tested using historical data. The results show a good prediction accuracy (maximum 2.63% relative errors), especially for up to 8 months ahead prediction).
{"title":"Predictive model for the horizontal displacement of a dam using autoregressive neural network","authors":"G. Oltean, L. Ivanciu, M. Gordan, I. Stoian, I. Kovacs","doi":"10.1109/INES.2017.8118576","DOIUrl":"https://doi.org/10.1109/INES.2017.8118576","url":null,"abstract":"The interpretation of data gathered from dam monitoring directly influences the detection of abnormal behaviors. Using previously recorded data, predictive models can be developed, so that the signs of a possible failure are detected as early as possible. The paper presents a multi-step ahead predictive model to generate the values for the horizontal displacement of a dam, using previous values of the displacement, water level and temperature. The model is based on an autoregressive neural network that was trained and tested using historical data. The results show a good prediction accuracy (maximum 2.63% relative errors), especially for up to 8 months ahead prediction).","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131286127","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 : 2017-10-01DOI: 10.1109/INES.2017.8118553
M. Sarnovský, P. Bednar, Miroslav Smatana
The main objective of work presented in this paper is to introduce the architectural overview of the big data analytics platform for support of process industries. Our aim was to design and develop the cross-sectorial scalable environment, which will enable the data collection from different sources and support the development of predictive functions to help the process industries in optimizing of their production processes. This paper introduces the components of Big Data Storage and Analytics platform which is the core component of the developed cross-sectorial environment. Currently, it is built on top of the Apache Hadoop technology stack and relies on Hadoop distributed file system. On the other hand, we present the idea of integration of the data obtained from different production environments. Data integration is implemented using the Apache Nifi and we designed the workflows for processing both interval and real-time data from the production sites. In this case, we consider two pilot cases, an aluminium factory in France and a plastic molding factory in Portugal.
{"title":"Data integration in scalable data analytics platform for process industries","authors":"M. Sarnovský, P. Bednar, Miroslav Smatana","doi":"10.1109/INES.2017.8118553","DOIUrl":"https://doi.org/10.1109/INES.2017.8118553","url":null,"abstract":"The main objective of work presented in this paper is to introduce the architectural overview of the big data analytics platform for support of process industries. Our aim was to design and develop the cross-sectorial scalable environment, which will enable the data collection from different sources and support the development of predictive functions to help the process industries in optimizing of their production processes. This paper introduces the components of Big Data Storage and Analytics platform which is the core component of the developed cross-sectorial environment. Currently, it is built on top of the Apache Hadoop technology stack and relies on Hadoop distributed file system. On the other hand, we present the idea of integration of the data obtained from different production environments. Data integration is implemented using the Apache Nifi and we designed the workflows for processing both interval and real-time data from the production sites. In this case, we consider two pilot cases, an aluminium factory in France and a plastic molding factory in Portugal.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131844998","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 : 2017-10-01DOI: 10.1109/INES.2017.8118535
P. Tanuška, L. Spendla, M. Kebísek, P. Važan, Lukas Hrcka
In our paper, we have focused on data integration and transformation process in the automotive industry, with emphasis on production data collected from the shop floor. One of the main issues addressed, is that the data are not stored in a central data storage, but in individual devices and systems, utilising different data formats. Our paper briefly describes the main tasks, required to collect production data into the big data storage and transform them into a unified data structure. We have also provided results of the initial analyses that were performed on the integrated and transformed data set.
{"title":"Data integration and transformation proposal for big data analyses in automotive industry","authors":"P. Tanuška, L. Spendla, M. Kebísek, P. Važan, Lukas Hrcka","doi":"10.1109/INES.2017.8118535","DOIUrl":"https://doi.org/10.1109/INES.2017.8118535","url":null,"abstract":"In our paper, we have focused on data integration and transformation process in the automotive industry, with emphasis on production data collected from the shop floor. One of the main issues addressed, is that the data are not stored in a central data storage, but in individual devices and systems, utilising different data formats. Our paper briefly describes the main tasks, required to collect production data into the big data storage and transform them into a unified data structure. We have also provided results of the initial analyses that were performed on the integrated and transformed data set.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115113639","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 : 2017-10-01DOI: 10.1109/ines.2017.8118559
I. Nagy, Georgi Dinev, A. Dineva
The need of information fusion has become increasingly important in various disciplines of modern engineering and artificial intelligence. Aggregation operators are efficiently support the merge of information and data from different sources in order to make proper decisions or to represent and improve generic knowledge of various system. The range sensing is a foundation of intelligent mobile robotics. Intelligent processing of data obtained by combination of sensors allows extracting useful information to estimate the state of the robot's environment especially by potential field building method. The accuracy of a potential field is based on the distance estimate vector obtained by measurements of the agents. In order to introduce more realistic distance evaluation process we propose the application of the weighted ordered weighted averaging (WOWA) operator in the multi-agent system (MAS). The traditionally used weighting method that required the tuning of a gain factor is replaced with the aggregation operator. The proposed technique allows considering both the importance of measurements and the effects of uncertainties, measurement errors at the scan points. Simulation results validate that the proposed technique improves the accuracy of the built potential field besides applying lower number of agents.
{"title":"Aggregation operators in accurate potential field building","authors":"I. Nagy, Georgi Dinev, A. Dineva","doi":"10.1109/ines.2017.8118559","DOIUrl":"https://doi.org/10.1109/ines.2017.8118559","url":null,"abstract":"The need of information fusion has become increasingly important in various disciplines of modern engineering and artificial intelligence. Aggregation operators are efficiently support the merge of information and data from different sources in order to make proper decisions or to represent and improve generic knowledge of various system. The range sensing is a foundation of intelligent mobile robotics. Intelligent processing of data obtained by combination of sensors allows extracting useful information to estimate the state of the robot's environment especially by potential field building method. The accuracy of a potential field is based on the distance estimate vector obtained by measurements of the agents. In order to introduce more realistic distance evaluation process we propose the application of the weighted ordered weighted averaging (WOWA) operator in the multi-agent system (MAS). The traditionally used weighting method that required the tuning of a gain factor is replaced with the aggregation operator. The proposed technique allows considering both the importance of measurements and the effects of uncertainties, measurement errors at the scan points. Simulation results validate that the proposed technique improves the accuracy of the built potential field besides applying lower number of agents.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128215443","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 : 2017-10-01DOI: 10.1109/ines.2017.8118552
K. Dobrzyński, Z. Lubośny, J. Klucznik, Radosław Rekowski
The paper presents selected issues on the European UPGRID grant implemented by a consortium of companies from seven European states, including from Poland, on the monitoring and control of low voltage grid using measurement pre-registered data by smart AMI meters. The paper focuses on the issue of lack of information on the assignment of communal meters to individual phases.
{"title":"Identification of the customer meter assignment to phases in LV grid: Selected issues of UPGRID project realization","authors":"K. Dobrzyński, Z. Lubośny, J. Klucznik, Radosław Rekowski","doi":"10.1109/ines.2017.8118552","DOIUrl":"https://doi.org/10.1109/ines.2017.8118552","url":null,"abstract":"The paper presents selected issues on the European UPGRID grant implemented by a consortium of companies from seven European states, including from Poland, on the monitoring and control of low voltage grid using measurement pre-registered data by smart AMI meters. The paper focuses on the issue of lack of information on the assignment of communal meters to individual phases.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134371649","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 : 2017-10-01DOI: 10.1109/INES.2017.8118554
I. Orosz, T. Orosz
Cloud based technology created a new software abstraction layer above the implementation layers in and therefore changed the way how Enterprise Resource Planning (ERP) systems are developed and implemented over the hardware abstraction layers. The traditional release-by-release update methodology governed by main version change (from pre-alpha to gold release) was changed to a continuous release management. Within the cloud based Software as a Service (SaaS) model, the core business logic is implied above the physical implementation layer. This scenario can predict that the software product can have a longer lifetime, because it is segregated from the always changing physical implementation layer. As the sudden change of technology is present in nowadays IT architecture, the presence of this new abstraction layer seems logical, because the basic business processes are not changing this rapidly. The SaaS type life cycle management means that the heavily technology independent part are not describing the business processes anymore. Previous lifecycle implementations from the assessment phase to the post go-live and support phase dealt the business logic as one entity with its implementation. That means, that the question of code reusability has a different role as in the standard on premise model. This paper introduces a new method of encapsulating and identifying the software parts, which can be later reused in a cloud SaaS environment.
{"title":"Code reusability in cloud based ERP solutions","authors":"I. Orosz, T. Orosz","doi":"10.1109/INES.2017.8118554","DOIUrl":"https://doi.org/10.1109/INES.2017.8118554","url":null,"abstract":"Cloud based technology created a new software abstraction layer above the implementation layers in and therefore changed the way how Enterprise Resource Planning (ERP) systems are developed and implemented over the hardware abstraction layers. The traditional release-by-release update methodology governed by main version change (from pre-alpha to gold release) was changed to a continuous release management. Within the cloud based Software as a Service (SaaS) model, the core business logic is implied above the physical implementation layer. This scenario can predict that the software product can have a longer lifetime, because it is segregated from the always changing physical implementation layer. As the sudden change of technology is present in nowadays IT architecture, the presence of this new abstraction layer seems logical, because the basic business processes are not changing this rapidly. The SaaS type life cycle management means that the heavily technology independent part are not describing the business processes anymore. Previous lifecycle implementations from the assessment phase to the post go-live and support phase dealt the business logic as one entity with its implementation. That means, that the question of code reusability has a different role as in the standard on premise model. This paper introduces a new method of encapsulating and identifying the software parts, which can be later reused in a cloud SaaS environment.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"87 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133847670","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 : 2017-10-01DOI: 10.1109/INES.2017.8118573
J. Mojžiš, I. Budinská
News articles are currently the source of vast potential of various kinds of information. News articles contain potential preferences or profile information of their readers. In this paper we offer analysis of news articles based on number of discussion posts count. At this time, two main sources of news articles were selected. We offer an overview of most discussed topics. Also, we have identified several conjunctions between the same topics for different sources. Although, currently missing more advanced methodology, our results are rather interesting. We focus on discussions, readability keywords and various categories. Results are still being calculated.
{"title":"Analyzing news articles from the side of discussion threads","authors":"J. Mojžiš, I. Budinská","doi":"10.1109/INES.2017.8118573","DOIUrl":"https://doi.org/10.1109/INES.2017.8118573","url":null,"abstract":"News articles are currently the source of vast potential of various kinds of information. News articles contain potential preferences or profile information of their readers. In this paper we offer analysis of news articles based on number of discussion posts count. At this time, two main sources of news articles were selected. We offer an overview of most discussed topics. Also, we have identified several conjunctions between the same topics for different sources. Although, currently missing more advanced methodology, our results are rather interesting. We focus on discussions, readability keywords and various categories. Results are still being calculated.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128810048","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 : 2017-10-01DOI: 10.1109/INES.2017.8118568
J. Kinghorst, H. Bloch, A. Fay, B. Vogel‐Heuser
The aim of alarm flood detection is the identification of similar, frequently occurring sequences of alarm messages in historical alarm data and uses the results for root cause analysis or alarm flood reduction. Various promising approaches for alarm data of automated production systems exist. However, due to the high amount of alarm messages transmitted by industrial alarm systems, floods are often interrupted by alarms stemming from different root causes, leading to non-relevant or invalid results of purely data-driven flood detection approaches. To improve the results of data-driven approaches, this paper suggests considering a process plant's hierarchy to divide historical alarm data into independent sub-datasets. For this reason, the paper discusses necessary plant information to explain a process plant's hierarchy and analyzes existing approaches to extract this hierarchy automatically from information sources. It then discusses whether existing approaches for alarm flood detection consider this hierarchy and how it could improve the approaches' results.
{"title":"Integration of additional information sources for improved alarm flood detection","authors":"J. Kinghorst, H. Bloch, A. Fay, B. Vogel‐Heuser","doi":"10.1109/INES.2017.8118568","DOIUrl":"https://doi.org/10.1109/INES.2017.8118568","url":null,"abstract":"The aim of alarm flood detection is the identification of similar, frequently occurring sequences of alarm messages in historical alarm data and uses the results for root cause analysis or alarm flood reduction. Various promising approaches for alarm data of automated production systems exist. However, due to the high amount of alarm messages transmitted by industrial alarm systems, floods are often interrupted by alarms stemming from different root causes, leading to non-relevant or invalid results of purely data-driven flood detection approaches. To improve the results of data-driven approaches, this paper suggests considering a process plant's hierarchy to divide historical alarm data into independent sub-datasets. For this reason, the paper discusses necessary plant information to explain a process plant's hierarchy and analyzes existing approaches to extract this hierarchy automatically from information sources. It then discusses whether existing approaches for alarm flood detection consider this hierarchy and how it could improve the approaches' results.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115512460","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 : 2017-10-01DOI: 10.1109/INES.2017.8118562
V. A. Kartashevand, V. V. Kartashev
This report presents the way to ensure the safety of the operator in the working area of the robot by highlighting the areas of its work. The capabilities of existing technical means designed to solve this problem are compared. It is concluded that the technical vision based systems are the most convenient in use. The report focuses on the convenience of setting the boundary line and the reliability of its determination in a wide range of illumination conditions.
{"title":"Intellectual collaborative robot safety control system: Separating the working areas of the robot and operator","authors":"V. A. Kartashevand, V. V. Kartashev","doi":"10.1109/INES.2017.8118562","DOIUrl":"https://doi.org/10.1109/INES.2017.8118562","url":null,"abstract":"This report presents the way to ensure the safety of the operator in the working area of the robot by highlighting the areas of its work. The capabilities of existing technical means designed to solve this problem are compared. It is concluded that the technical vision based systems are the most convenient in use. The report focuses on the convenience of setting the boundary line and the reliability of its determination in a wide range of illumination conditions.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115369618","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：