Pub Date : 2018-09-01DOI: 10.1109/ETFA.2018.8502540
Carlos A. Garcia, J. Naranjo, T. P. Zambrano, David Lanas, Marcelo V. García
In the current industrial paradigm, the use of traditional and straight-line production systems are being replaced with the objective of generating flexible and modular production process. To achieve this goal, one of the main alternatives used by enterprises is the integration of robotic systems in the production cells. New generation industrial robots are developed to integrate high-performance processing units which can operate under embedded software. This characteristic, indirectly allows robots to be compatible with the concept of Cyber-Physical Production Systems (CPPS), where the high processing and communication capabilities of the devices allows better and faster data exchange among the devices in a distributed system. IEC-61499 provides high-level design capabilities by combining easily software components with independence of the hardware platform used for the generation of CPPSs. This paper discusses an approach of CPPS flexible architecture under IEC-61499 for industrial control of Kuka youBot® robotic arm in industrial welding tasks, using a low-cost device like Raspberry Pi 3B board as industrial controller.
{"title":"Low-Cost Cyber-Physical Production Systems for Industrial Control Robots Under IEC 61499","authors":"Carlos A. Garcia, J. Naranjo, T. P. Zambrano, David Lanas, Marcelo V. García","doi":"10.1109/ETFA.2018.8502540","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502540","url":null,"abstract":"In the current industrial paradigm, the use of traditional and straight-line production systems are being replaced with the objective of generating flexible and modular production process. To achieve this goal, one of the main alternatives used by enterprises is the integration of robotic systems in the production cells. New generation industrial robots are developed to integrate high-performance processing units which can operate under embedded software. This characteristic, indirectly allows robots to be compatible with the concept of Cyber-Physical Production Systems (CPPS), where the high processing and communication capabilities of the devices allows better and faster data exchange among the devices in a distributed system. IEC-61499 provides high-level design capabilities by combining easily software components with independence of the hardware platform used for the generation of CPPSs. This paper discusses an approach of CPPS flexible architecture under IEC-61499 for industrial control of Kuka youBot® robotic arm in industrial welding tasks, using a low-cost device like Raspberry Pi 3B board as industrial controller.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"10 1","pages":"1281-1284"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74735768","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 : 2018-09-01DOI: 10.1109/etfa.2018.8502552
{"title":"Industrial Internet for the Factories of the Future","authors":"","doi":"10.1109/etfa.2018.8502552","DOIUrl":"https://doi.org/10.1109/etfa.2018.8502552","url":null,"abstract":"","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"86 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78253900","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 : 2018-09-01DOI: 10.1109/ETFA.2018.8502567
S. Sarkar, Gloria Vashi, P. Abdulla
Container technology enables designers to build (micro)service-oriented systems with on-demand scalability and availability easily, provided the original system has been well-modularized to begin with. Industry automation applications, built a long time ago, aim to adopt this technology to become more flexible and ready to be a part of the internet of thing based next-generation industrial system. In this paper, we share our work-in-progress experience of transforming a complex, distributed industrial automation system to a microservice based containerized architecture. We propose a containerized architecture of the “to-be” system and observe that despite being distributed, the “as-is” system tend to follow a monolithic architecture with strong coupling among the participating components. Consequently it becomes difficult to achieve the proposed microservice based architecture without a significant change. We also discuss the workload handling, resource utilization and reliability aspects of the “to-be” architecture using a prototype implementation.
{"title":"Towards Transforming an Industrial Automation System from Monolithic to Microservices","authors":"S. Sarkar, Gloria Vashi, P. Abdulla","doi":"10.1109/ETFA.2018.8502567","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502567","url":null,"abstract":"Container technology enables designers to build (micro)service-oriented systems with on-demand scalability and availability easily, provided the original system has been well-modularized to begin with. Industry automation applications, built a long time ago, aim to adopt this technology to become more flexible and ready to be a part of the internet of thing based next-generation industrial system. In this paper, we share our work-in-progress experience of transforming a complex, distributed industrial automation system to a microservice based containerized architecture. We propose a containerized architecture of the “to-be” system and observe that despite being distributed, the “as-is” system tend to follow a monolithic architecture with strong coupling among the participating components. Consequently it becomes difficult to achieve the proposed microservice based architecture without a significant change. We also discuss the workload handling, resource utilization and reliability aspects of the “to-be” architecture using a prototype implementation.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"36 1","pages":"1256-1259"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80645300","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 : 2018-09-01DOI: 10.1109/ETFA.2018.8502638
Ilber Puci, R. Vilanova, C. Ferrer
The variable frequency has an important usage in industrial applications. Electrical energy produced by Power Stations is normally 50/60 Hz and is not applicable for many domestic and industrial applications. There are some electrical and electromechanical devices, which need variable frequency than the fixed power supply frequency. Permanent Magnet Synchronous Motor is one of the best examples of variable frequency drives. The Permanent Magnet Synchronous Motor is widely used in the low to medium power system due to its characteristics of high efficiency, high torque to inertia ratio, high reliability, and fast dynamic performance. The Permanent Magnet Synchronous Motor and variable frequency drive have the large sum of demand in industrial and power generation applications. The frequency converter is such device, which generates the variable frequency. In this paper, the vector control of Permanent Magnet Synchronous Motor fed by a frequency converter is modelled and simulated by using PI controller and Fuzzy controller, one of the intelligent methods used in electric drives. Waveforms derived from the simulation of the vector control of Permanent Magnet Synchronous Motor fed a frequency converter are examined comparatively for PI and Fuzzy Controllers. Thus, this project strongly recommends the frequency converter for Permanent Magnet Synchronous Motor application using a Fuzzy controller.
{"title":"Comparison of Speed Control of Permanent Magnet Synchronous Motor using PI and Fuzzy Controller","authors":"Ilber Puci, R. Vilanova, C. Ferrer","doi":"10.1109/ETFA.2018.8502638","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502638","url":null,"abstract":"The variable frequency has an important usage in industrial applications. Electrical energy produced by Power Stations is normally 50/60 Hz and is not applicable for many domestic and industrial applications. There are some electrical and electromechanical devices, which need variable frequency than the fixed power supply frequency. Permanent Magnet Synchronous Motor is one of the best examples of variable frequency drives. The Permanent Magnet Synchronous Motor is widely used in the low to medium power system due to its characteristics of high efficiency, high torque to inertia ratio, high reliability, and fast dynamic performance. The Permanent Magnet Synchronous Motor and variable frequency drive have the large sum of demand in industrial and power generation applications. The frequency converter is such device, which generates the variable frequency. In this paper, the vector control of Permanent Magnet Synchronous Motor fed by a frequency converter is modelled and simulated by using PI controller and Fuzzy controller, one of the intelligent methods used in electric drives. Waveforms derived from the simulation of the vector control of Permanent Magnet Synchronous Motor fed a frequency converter are examined comparatively for PI and Fuzzy Controllers. Thus, this project strongly recommends the frequency converter for Permanent Magnet Synchronous Motor application using a Fuzzy controller.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"95 1","pages":"566-573"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76850757","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 : 2018-09-01DOI: 10.1109/ETFA.2018.8502576
Avijit Mandal, Devina Mohan, R. Jetley, Sreeja Nair, Meenakshi D'Souza
Software used to monitor and control operations within an automation system is defined using domain-specific languages. Latent errors in the control code, if left undetected, can lead to unexpected system failures compromising the safety and the security of the automation system. Traditional analysis techniques are insufficient to detect such errors as they do not cater specifically to the underlying domain-specific language. However, given the diversity of different automation domains, there is no standard platform for analysis of these languages. This paper proposes a generic static analysis framework for domain-specific languages used in the automation domain. The analysis approach exhaustively detects runtime errors in control code and ensures compliance to good programming practices. These runtime errors and coding violations are checked against abstract syntax trees and control flow graphs derived from the code. Data Flow Analysis (DFA), Abstract interpretation and pattern-based matching techniques are used to identify domain specific errors and coding violations for control languages.
{"title":"A Generic Static Analysis Framework for Domain-specific Languages","authors":"Avijit Mandal, Devina Mohan, R. Jetley, Sreeja Nair, Meenakshi D'Souza","doi":"10.1109/ETFA.2018.8502576","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502576","url":null,"abstract":"Software used to monitor and control operations within an automation system is defined using domain-specific languages. Latent errors in the control code, if left undetected, can lead to unexpected system failures compromising the safety and the security of the automation system. Traditional analysis techniques are insufficient to detect such errors as they do not cater specifically to the underlying domain-specific language. However, given the diversity of different automation domains, there is no standard platform for analysis of these languages. This paper proposes a generic static analysis framework for domain-specific languages used in the automation domain. The analysis approach exhaustively detects runtime errors in control code and ensures compliance to good programming practices. These runtime errors and coding violations are checked against abstract syntax trees and control flow graphs derived from the code. Data Flow Analysis (DFA), Abstract interpretation and pattern-based matching techniques are used to identify domain specific errors and coding violations for control languages.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"1 6 1","pages":"27-34"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76030164","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 : 2018-09-01DOI: 10.1109/ETFA.2018.8502529
P. Bonhomme
This paper deals with a state estimation technique in a decentralized context for discrete events dynamic systems modeled by P-Time Petri nets (P-TPN). Indeed, the observation is distributed over a set of distinct sites, each of which has its own local view of the system. Thus, thanks to a coordinator the local information transmitted by the different sites will be used to determine the set of states consistent with the current observation. The proposed method relies on an iterative procedure and the schedulability analysis of particular firing sequences called time explanations.
{"title":"Towards a Decentralized State Estimation of P-Time Petri Net Systems","authors":"P. Bonhomme","doi":"10.1109/ETFA.2018.8502529","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502529","url":null,"abstract":"This paper deals with a state estimation technique in a decentralized context for discrete events dynamic systems modeled by P-Time Petri nets (P-TPN). Indeed, the observation is distributed over a set of distinct sites, each of which has its own local view of the system. Thus, thanks to a coordinator the local information transmitted by the different sites will be used to determine the set of states consistent with the current observation. The proposed method relies on an iterative procedure and the schedulability analysis of particular firing sequences called time explanations.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"1 1","pages":"532-539"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76406846","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 : 2018-09-01DOI: 10.1109/ETFA.2018.8502627
Benjamin Brandenbourger, F. Durand
In variable automation systems the encapsulation of sub-systems is a key factor for fast reconfiguration of modern production plants. This contribution proposes a generic and recursive design pattern for decomposing or aggregating automation systems into standardized abstract units. Depending on the use case, the top-down or bottom-up methodology is favorable for classifying the identified entities in different hierarchy levels. The intuitive, cross-domain approach creates commonly understandable, abstracted digital twins of the entities in form of integrated mechatronic models. The encapsulation of the entities allows a better exchangeability on each hierarchical level and paves the way for faster commissioning in variable automation systems. The approach is evaluated by means of a production cell presented at the automatica 2018 trade fair.
{"title":"Design Pattern for Decomposition or Aggregation of Automation Systems into Hierarchy Levels","authors":"Benjamin Brandenbourger, F. Durand","doi":"10.1109/ETFA.2018.8502627","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502627","url":null,"abstract":"In variable automation systems the encapsulation of sub-systems is a key factor for fast reconfiguration of modern production plants. This contribution proposes a generic and recursive design pattern for decomposing or aggregating automation systems into standardized abstract units. Depending on the use case, the top-down or bottom-up methodology is favorable for classifying the identified entities in different hierarchy levels. The intuitive, cross-domain approach creates commonly understandable, abstracted digital twins of the entities in form of integrated mechatronic models. The encapsulation of the entities allows a better exchangeability on each hierarchical level and paves the way for faster commissioning in variable automation systems. The approach is evaluated by means of a production cell presented at the automatica 2018 trade fair.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"54 1","pages":"895-901"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81252131","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 : 2018-09-01DOI: 10.1109/ETFA.2018.8502461
R. French, W. Yeadon, G. Kapellmann-Zafra, H. Marin-Reyes
The development of a Vision System for TIG Welding has the potential to help realize a real time process monitoring system for joining tasks which require automated welding. A key application of this technique is in the Nuclear Industry; where industrial components require several passes (layers of welding) to achieve robust joints. Through monitoring a welding process such as this in real time, material and time waste could be drastically reduced as faults could be instantly identified. A TIG welding arc is a very intense source of both light and heat, making the creation of a vision system for it challenging. Higher currents result in; brighter TIG welding arcs, higher energy input and deeper and wider weld pools. Nuclear industry applications require deep penetration welding but bright TIG welding arcs can overwhelm the intensity of an auxiliary illumination laser reducing the image clarity of an observing camera system. Thus, a balance between a wide weld bead with clear features applicable to deep penetration but without a brightness level which overwhelms that of the laser must be found. This paper is a Work-in-Progress study of a vision system for TIG welding using an automated TIG welding system and a camera with a laser illumination system. Welding was performed using a Miller Dynasty 350 at 100A with a 3B class laser used to illuminate the weld pool.
{"title":"Development of a Vision System for TIG Welding - A Work-in-Progress Study","authors":"R. French, W. Yeadon, G. Kapellmann-Zafra, H. Marin-Reyes","doi":"10.1109/ETFA.2018.8502461","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502461","url":null,"abstract":"The development of a Vision System for TIG Welding has the potential to help realize a real time process monitoring system for joining tasks which require automated welding. A key application of this technique is in the Nuclear Industry; where industrial components require several passes (layers of welding) to achieve robust joints. Through monitoring a welding process such as this in real time, material and time waste could be drastically reduced as faults could be instantly identified. A TIG welding arc is a very intense source of both light and heat, making the creation of a vision system for it challenging. Higher currents result in; brighter TIG welding arcs, higher energy input and deeper and wider weld pools. Nuclear industry applications require deep penetration welding but bright TIG welding arcs can overwhelm the intensity of an auxiliary illumination laser reducing the image clarity of an observing camera system. Thus, a balance between a wide weld bead with clear features applicable to deep penetration but without a brightness level which overwhelms that of the laser must be found. This paper is a Work-in-Progress study of a vision system for TIG welding using an automated TIG welding system and a camera with a laser illumination system. Welding was performed using a Miller Dynasty 350 at 100A with a 3B class laser used to illuminate the weld pool.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"10 1","pages":"1193-1196"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86877125","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 : 2018-09-01DOI: 10.1109/ETFA.2018.8502583
J. J. Dorantes, Miguel Delgado Prieto, Jesus Adolfo Carino-Corrales, R. Osornio-Ríos, L. Romeral, R. Romero-Troncoso
A great deal of investigations are being carried out towards the effective implementation of the 4.0 Industry new paradigm. Indeed, most of the machinery involved in industrial processes are intended to be digitalized aiming to obtain enhanced information to be used for an optimized operation of the whole manufacturing process. In this regard, condition monitoring strategies are being also reconsidered to include improved performances and functionalities. Thus, the contribution of this research work lies in the proposal of an incremental learning framework approach applied to the condition monitoring of electromechanical systems. The proposed strategy is divided in three main steps, first, different available physical magnitudes are characterized through the calculation of a set of statistical-time based features. Second, a modelling of the considered conditions is performed by means of self-organizing maps in order to preserve the topology of the data; and finally, a novelty detection is carried out by a comparison among the quantization error value achieved in the data modelling for each of the considered conditions. The effectiveness of the proposed novelty fault identification condition monitoring methodology is proved by means of the evaluation of a complete experimental database acquired during the continuous working conditions of an electromechanical system.
{"title":"Incremental Learning Framework-based Condition Monitoring for Novelty Fault Identification Applied to Electromechanical Systems","authors":"J. J. Dorantes, Miguel Delgado Prieto, Jesus Adolfo Carino-Corrales, R. Osornio-Ríos, L. Romeral, R. Romero-Troncoso","doi":"10.1109/ETFA.2018.8502583","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502583","url":null,"abstract":"A great deal of investigations are being carried out towards the effective implementation of the 4.0 Industry new paradigm. Indeed, most of the machinery involved in industrial processes are intended to be digitalized aiming to obtain enhanced information to be used for an optimized operation of the whole manufacturing process. In this regard, condition monitoring strategies are being also reconsidered to include improved performances and functionalities. Thus, the contribution of this research work lies in the proposal of an incremental learning framework approach applied to the condition monitoring of electromechanical systems. The proposed strategy is divided in three main steps, first, different available physical magnitudes are characterized through the calculation of a set of statistical-time based features. Second, a modelling of the considered conditions is performed by means of self-organizing maps in order to preserve the topology of the data; and finally, a novelty detection is carried out by a comparison among the quantization error value achieved in the data modelling for each of the considered conditions. The effectiveness of the proposed novelty fault identification condition monitoring methodology is proved by means of the evaluation of a complete experimental database acquired during the continuous working conditions of an electromechanical system.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"12 1","pages":"1359-1364"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85137406","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 : 2018-09-01DOI: 10.1109/ETFA.2018.8502474
Tarek Stiebel, Marcel Bosling, A. Steffens, T. Pretz, D. Merhof
Waste treatment, especially treatment of plastic waste, is arguably one of the biggest challenges that humanity faces in context of preserving the environment besides global warming. This work presents a visual inspection system for plastic classification and proposes a classification algorithm that is based on near-infrared spectroscopy and convolutional neural networks. The method allows for a highly accurate classification of several main polymer types while being robust against image disturbances occurring in a real world scenario. Most importantly, it is able to cope with layers of multiple materials. This work therefore offers for the very first time a solution to multi-material classification in the context of plastic recycling. Since the manual creation and annotation of layered materials is a cumbersome task due to the manifold of possible combinations, it is also shown how the creation of artificial data can greatly facilitate the ground truth generation.
{"title":"An Inspection System for Multi-Label Polymer Classification","authors":"Tarek Stiebel, Marcel Bosling, A. Steffens, T. Pretz, D. Merhof","doi":"10.1109/ETFA.2018.8502474","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502474","url":null,"abstract":"Waste treatment, especially treatment of plastic waste, is arguably one of the biggest challenges that humanity faces in context of preserving the environment besides global warming. This work presents a visual inspection system for plastic classification and proposes a classification algorithm that is based on near-infrared spectroscopy and convolutional neural networks. The method allows for a highly accurate classification of several main polymer types while being robust against image disturbances occurring in a real world scenario. Most importantly, it is able to cope with layers of multiple materials. This work therefore offers for the very first time a solution to multi-material classification in the context of plastic recycling. Since the manual creation and annotation of layered materials is a cumbersome task due to the manifold of possible combinations, it is also shown how the creation of artificial data can greatly facilitate the ground truth generation.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"79 1","pages":"623-630"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90189844","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：