Pub Date : 2018-07-18DOI: 10.1109/INDIN.2018.8471943
Reihane Rahimilarki, Zhiwei Gao
In this paper, a model identification method based on artificial neural networks (ANN) for wind turbine dynamics is studied. Due to the fact that wind turbine has a nonlinear dynamics with partially measured states, ANN cannot be applied directly. To cope with this problem, first a Luenberger observer is designed to estimate the states (both measured and unmeasured ones) and then, for the nonlinear part, a multi-input multi-output (MIMO) back propagation neural-network based observer is proposed. By having an ANN model as the reference, a fault detection method is studied based on the residual of the system. This algorithm is evaluated in simulation on a 4.8 MW wind turbine benchmark and the results approve satisfactory performance of the proposed approach.
{"title":"Grey-box Model Identification and Fault Detection of Wind Turbines Using Artificial Neural Networks","authors":"Reihane Rahimilarki, Zhiwei Gao","doi":"10.1109/INDIN.2018.8471943","DOIUrl":"https://doi.org/10.1109/INDIN.2018.8471943","url":null,"abstract":"In this paper, a model identification method based on artificial neural networks (ANN) for wind turbine dynamics is studied. Due to the fact that wind turbine has a nonlinear dynamics with partially measured states, ANN cannot be applied directly. To cope with this problem, first a Luenberger observer is designed to estimate the states (both measured and unmeasured ones) and then, for the nonlinear part, a multi-input multi-output (MIMO) back propagation neural-network based observer is proposed. By having an ANN model as the reference, a fault detection method is studied based on the residual of the system. This algorithm is evaluated in simulation on a 4.8 MW wind turbine benchmark and the results approve satisfactory performance of the proposed approach.","PeriodicalId":6467,"journal":{"name":"2018 IEEE 16th International Conference on Industrial Informatics (INDIN)","volume":"43 1","pages":"647-652"},"PeriodicalIF":0.0,"publicationDate":"2018-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88059626","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 : 2018-07-18DOI: 10.1109/INDIN.2018.8472064
René Lindorfer, R. Froschauer, Georg-Daniel Schwarz
Modeling assembly and manufacturing tasks accomplished by machines (i.e., robots) using offline programming is quite common today. Considering lot-size-one products human work is still necessary, whereas human tasks are often not considered during the modeling and offline programming process. Therefore this work presents a generic approach, which provides the ability to model variable work tasks of humans and machines together including the variability of any process data using a runtime-decision model. Depending on the detail level of the model it is possible to generate various assets such as work instructions, machine programs or human-machine interfaces. The ADAPT (Asset-Decision-Action-Property-RelaTionship) modeling approach is initially illustrated using a common LEGO assembly use case. Additionally we present a first implementation of a BPMN-based workflow designer that enables the user to model assembly and manufacturing processes in an intuitive way.
{"title":"ADAPT - A decision-model-based Approach for Modeling Collaborative Assembly and Manufacturing Tasks","authors":"René Lindorfer, R. Froschauer, Georg-Daniel Schwarz","doi":"10.1109/INDIN.2018.8472064","DOIUrl":"https://doi.org/10.1109/INDIN.2018.8472064","url":null,"abstract":"Modeling assembly and manufacturing tasks accomplished by machines (i.e., robots) using offline programming is quite common today. Considering lot-size-one products human work is still necessary, whereas human tasks are often not considered during the modeling and offline programming process. Therefore this work presents a generic approach, which provides the ability to model variable work tasks of humans and machines together including the variability of any process data using a runtime-decision model. Depending on the detail level of the model it is possible to generate various assets such as work instructions, machine programs or human-machine interfaces. The ADAPT (Asset-Decision-Action-Property-RelaTionship) modeling approach is initially illustrated using a common LEGO assembly use case. Additionally we present a first implementation of a BPMN-based workflow designer that enables the user to model assembly and manufacturing processes in an intuitive way.","PeriodicalId":6467,"journal":{"name":"2018 IEEE 16th International Conference on Industrial Informatics (INDIN)","volume":"9 1","pages":"559-564"},"PeriodicalIF":0.0,"publicationDate":"2018-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84282076","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 : 2018-07-01DOI: 10.1109/INDIN.2018.8471935
Yingying Zhao, Dongsheng Li, Qi Liu, Q. Lv, L. Shang
Privacy has been one of the major concerns for customers in smart grids. Randomized perturbation based privacy-preserving smart metering methods, which are efficient and easy to implement, have recently become one of the commonly adopted solutions. However, it is a challenging task to meet utility companies’ data collection requirements while protecting customer privacy. This paper analyzes the privacy protection capability of randomized perturbation based privacy-preserving smart metering methods. Both theoretical analysis and empirical studies show that statistical information of individual customers can still be accurately obtained from these randomly perturbed data. Also, an appliance usage inference method is proposed to accurately identify appliance operations of individual customers using randomly perturbed smart metering data. Evaluations using real-world smart metering data demonstrate that the proposed method can identify appliance operations with an accuracy between 92% and 99%.
{"title":"Deriving Customer Privacy from Randomly Perturbed Smart Metering Data","authors":"Yingying Zhao, Dongsheng Li, Qi Liu, Q. Lv, L. Shang","doi":"10.1109/INDIN.2018.8471935","DOIUrl":"https://doi.org/10.1109/INDIN.2018.8471935","url":null,"abstract":"Privacy has been one of the major concerns for customers in smart grids. Randomized perturbation based privacy-preserving smart metering methods, which are efficient and easy to implement, have recently become one of the commonly adopted solutions. However, it is a challenging task to meet utility companies’ data collection requirements while protecting customer privacy. This paper analyzes the privacy protection capability of randomized perturbation based privacy-preserving smart metering methods. Both theoretical analysis and empirical studies show that statistical information of individual customers can still be accurately obtained from these randomly perturbed data. Also, an appliance usage inference method is proposed to accurately identify appliance operations of individual customers using randomly perturbed smart metering data. Evaluations using real-world smart metering data demonstrate that the proposed method can identify appliance operations with an accuracy between 92% and 99%.","PeriodicalId":6467,"journal":{"name":"2018 IEEE 16th International Conference on Industrial Informatics (INDIN)","volume":"101 1","pages":"959-965"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73455153","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 : 2018-07-01DOI: 10.1109/INDIN.2018.8472075
M. Danishvar, Vasileia Vasilaki, Zhengwen Huang, E. Katsou, A. Mousavi
A number of data analytics techniques are deployed to measure the influence of various waste water treatment operational parameters against the nitrous oxide ($text{N}_{mathbf {2}}$O) emission. N2O is a major threat to the ozone layer and constitutes 80% of total Greenhouse Gas emissions of Waste Water Treatment Plants (WWTPs). The measurement and prediction of N2O emission from WWTP is challenging and costly. Thus, it is important to identify key control parameters that allows for accurately predicting and reducing N2O generation and emission. The current work compares various data driven techniques that identify key parameters and methods of predicting N2O emission. It provides insight to the suitability of each technique for control and optimisation of the target process. The main contribution of this research is introducing two new techniques that applied first time in WWTPs and could cover some current techniques shortcomings in real-time.
{"title":"Application of Data Driven techniques to Predict N2O Emission in Full-scale WWTPs","authors":"M. Danishvar, Vasileia Vasilaki, Zhengwen Huang, E. Katsou, A. Mousavi","doi":"10.1109/INDIN.2018.8472075","DOIUrl":"https://doi.org/10.1109/INDIN.2018.8472075","url":null,"abstract":"A number of data analytics techniques are deployed to measure the influence of various waste water treatment operational parameters against the nitrous oxide ($text{N}_{mathbf {2}}$O) emission. N2O is a major threat to the ozone layer and constitutes 80% of total Greenhouse Gas emissions of Waste Water Treatment Plants (WWTPs). The measurement and prediction of N2O emission from WWTP is challenging and costly. Thus, it is important to identify key control parameters that allows for accurately predicting and reducing N2O generation and emission. The current work compares various data driven techniques that identify key parameters and methods of predicting N2O emission. It provides insight to the suitability of each technique for control and optimisation of the target process. The main contribution of this research is introducing two new techniques that applied first time in WWTPs and could cover some current techniques shortcomings in real-time.","PeriodicalId":6467,"journal":{"name":"2018 IEEE 16th International Conference on Industrial Informatics (INDIN)","volume":"29 1","pages":"993-997"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73726731","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 : 2018-07-01DOI: 10.1109/INDIN.2018.8472038
P. Waibel, Svetoslav Videnov, M. Borkowski, C. Hochreiner, Stefan Schulte, J. Mendling
Cloud manufacturing supports companies to create cross-organizational elastic process landscapes with flexible and scalable processes. In recent years, the Business Process Model and Notation language gained interest in the cloud manufacturing domain not only as a modeling language but also as a base for process enactment. During this enactment of manufacturing processes, accurate knowledge about when a machine is needed is of great importance. While such planning is simple in a static production environment, it becomes a challenging task in an elastic cloud manufacturing environment with a variety of flexible and scalable processes. Hence, we propose an approach that performs enactment simulations before an actual manufacturing process is carried out. The goal is to reserve manufacturing machines at the time at which they will be needed in a machine reservation timetable. By discussing different use case scenarios, we further elaborate on the benefits of our approach.
{"title":"Process Simulation for Machine Reservation in Cloud Manufacturing","authors":"P. Waibel, Svetoslav Videnov, M. Borkowski, C. Hochreiner, Stefan Schulte, J. Mendling","doi":"10.1109/INDIN.2018.8472038","DOIUrl":"https://doi.org/10.1109/INDIN.2018.8472038","url":null,"abstract":"Cloud manufacturing supports companies to create cross-organizational elastic process landscapes with flexible and scalable processes. In recent years, the Business Process Model and Notation language gained interest in the cloud manufacturing domain not only as a modeling language but also as a base for process enactment. During this enactment of manufacturing processes, accurate knowledge about when a machine is needed is of great importance. While such planning is simple in a static production environment, it becomes a challenging task in an elastic cloud manufacturing environment with a variety of flexible and scalable processes. Hence, we propose an approach that performs enactment simulations before an actual manufacturing process is carried out. The goal is to reserve manufacturing machines at the time at which they will be needed in a machine reservation timetable. By discussing different use case scenarios, we further elaborate on the benefits of our approach.","PeriodicalId":6467,"journal":{"name":"2018 IEEE 16th International Conference on Industrial Informatics (INDIN)","volume":"1 1","pages":"270-277"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74620190","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 : 2018-07-01DOI: 10.1109/INDIN.2018.8472037
Benjamin Neef, Jonathan Bartels, S. Thiede
In this paper a machine learning approach for tool wear monitoring (TWM) and surface quality detection is proposed using high frequency current samples of a CNC turning machine main terminal. Significant frequency based features related to tool wear and surface quality are selected by univariate filter methods. Supervised machine learning methods including Support Vector Machine (SVM) and Random Forest Ensemble (RFE) are used to estimate tool wear and surface quality. Best hyper-parameter combinations of the proposed models are evaluated and found by grid search methods. Experimental studies are conducted on a CNC turning machine using a test work piece and the classification and accuracy results are presented. The presented methodology makes the set up of an on-line system for tool condition monitoring and an estimation of the work piece surface quality by the use of inexpensive and easy to install measurement hardware possible.
{"title":"Tool Wear and Surface Quality Monitoring Using High Frequency CNC Machine Tool Current Signature","authors":"Benjamin Neef, Jonathan Bartels, S. Thiede","doi":"10.1109/INDIN.2018.8472037","DOIUrl":"https://doi.org/10.1109/INDIN.2018.8472037","url":null,"abstract":"In this paper a machine learning approach for tool wear monitoring (TWM) and surface quality detection is proposed using high frequency current samples of a CNC turning machine main terminal. Significant frequency based features related to tool wear and surface quality are selected by univariate filter methods. Supervised machine learning methods including Support Vector Machine (SVM) and Random Forest Ensemble (RFE) are used to estimate tool wear and surface quality. Best hyper-parameter combinations of the proposed models are evaluated and found by grid search methods. Experimental studies are conducted on a CNC turning machine using a test work piece and the classification and accuracy results are presented. The presented methodology makes the set up of an on-line system for tool condition monitoring and an estimation of the work piece surface quality by the use of inexpensive and easy to install measurement hardware possible.","PeriodicalId":6467,"journal":{"name":"2018 IEEE 16th International Conference on Industrial Informatics (INDIN)","volume":"132 1","pages":"1045-1050"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74888162","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 : 2018-07-01DOI: 10.1109/INDIN.2018.8471955
Paul Danny, P. Ferreira, N. Lohse, K. Dorofeev
Assembly systems today are facing significant pressure to deliver high performance process executions, while being responsive to the fluctuating market demands. However, the implementation the trending Cyber Physical Systems concepts via ‘Plug-and-Produce’ devices produces some communication overheads. In this direction, the openMOS project aims to decouple the elements that are responsible for adaptation and general operations of the system. This allows the system to have two parallel processes. Towards this end, the priority is to deliver high performance process executions, while the other process focuses on delivering the required agility. The focus of this work is narrowed down to the development of task execution tables that guarantees high performance process executions. In this direction, the definition of task execution table is based on an existing AutomationML (AML) model that highlights the explicit relationships between the Product, Process and Resource (PPR) domains. A new decisional attribute has been added to the existing ‘Skill’ concept, which provides the flexibility to incorporate eventbased process alternatives. An insight description on how the system handles process executions during run-time failures is also provided. Finally, this paper illustrates the run-time implementation of the execution table with a help of an industrial case study that has been used for a demonstration activity within the openMOS project.
{"title":"An Event-Based AutomationML Model for the Process Execution of Plug-and-Produce’ Assembly Systems","authors":"Paul Danny, P. Ferreira, N. Lohse, K. Dorofeev","doi":"10.1109/INDIN.2018.8471955","DOIUrl":"https://doi.org/10.1109/INDIN.2018.8471955","url":null,"abstract":"Assembly systems today are facing significant pressure to deliver high performance process executions, while being responsive to the fluctuating market demands. However, the implementation the trending Cyber Physical Systems concepts via ‘Plug-and-Produce’ devices produces some communication overheads. In this direction, the openMOS project aims to decouple the elements that are responsible for adaptation and general operations of the system. This allows the system to have two parallel processes. Towards this end, the priority is to deliver high performance process executions, while the other process focuses on delivering the required agility. The focus of this work is narrowed down to the development of task execution tables that guarantees high performance process executions. In this direction, the definition of task execution table is based on an existing AutomationML (AML) model that highlights the explicit relationships between the Product, Process and Resource (PPR) domains. A new decisional attribute has been added to the existing ‘Skill’ concept, which provides the flexibility to incorporate eventbased process alternatives. An insight description on how the system handles process executions during run-time failures is also provided. Finally, this paper illustrates the run-time implementation of the execution table with a help of an industrial case study that has been used for a demonstration activity within the openMOS project.","PeriodicalId":6467,"journal":{"name":"2018 IEEE 16th International Conference on Industrial Informatics (INDIN)","volume":"304 1","pages":"49-54"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79793940","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 : 2018-07-01DOI: 10.1109/INDIN.2018.8471979
Fengjia Yao, Alexander Keller, Mussawar Ahmad, B. Ahmad, R. Harrison, A. Colombo
Autonomous Guided Vehicles (AGVs) are considered as one of the key enablers of smart factories which make possible smart and flexible transportation of pallets and material on shopfloor. However, existing AGV fleet management solutions often suffer from poor integration with real-time manufacturing operations information systems, which negatively affects scheduling of AGVs. To exploit the full potential of AGVs in achieving just-intime (JIT) transportation, there is a need for intelligent AGV fleet management system which not only integrate with manufacturing information technology (IT) and operational technology (OT) but also provide prediction for the shop-floor logistic based on real-time manufacturing operations information to optimize scheduling of AGVs. This paper presents an approach for a Smart AGV Management System (SAMS), which combines the real-time data analysis and digital twin models that can be deployed within complex manufacturing environments for optimized scheduling. For a proof of concept, a case study of a line side supply of components to a manual assembly station is presented.
{"title":"Optimizing the Scheduling of Autonomous Guided Vehicle in a Manufacturing Process","authors":"Fengjia Yao, Alexander Keller, Mussawar Ahmad, B. Ahmad, R. Harrison, A. Colombo","doi":"10.1109/INDIN.2018.8471979","DOIUrl":"https://doi.org/10.1109/INDIN.2018.8471979","url":null,"abstract":"Autonomous Guided Vehicles (AGVs) are considered as one of the key enablers of smart factories which make possible smart and flexible transportation of pallets and material on shopfloor. However, existing AGV fleet management solutions often suffer from poor integration with real-time manufacturing operations information systems, which negatively affects scheduling of AGVs. To exploit the full potential of AGVs in achieving just-intime (JIT) transportation, there is a need for intelligent AGV fleet management system which not only integrate with manufacturing information technology (IT) and operational technology (OT) but also provide prediction for the shop-floor logistic based on real-time manufacturing operations information to optimize scheduling of AGVs. This paper presents an approach for a Smart AGV Management System (SAMS), which combines the real-time data analysis and digital twin models that can be deployed within complex manufacturing environments for optimized scheduling. For a proof of concept, a case study of a line side supply of components to a manual assembly station is presented.","PeriodicalId":6467,"journal":{"name":"2018 IEEE 16th International Conference on Industrial Informatics (INDIN)","volume":"63 1","pages":"264-269"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73406135","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：