Pub Date : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613325
Nima Enayati, O. D. Ramos-Cantor, T. Neugebauer, F. Dai, Thomas Hansen, T. Musiol, Monique Düngen, R. Kirsten, M. Aleksy
This paper describes our work towards preliminary evaluation of LTE/5G cellular communication for robotics motion planning and control. The work comprises the development of communication architecture, motion planning and a demonstrator that validates the feasibility of the proposed approach. In the demonstrated use case, a stationary robot arm picks and places workpieces from/onto a moving mobile platform while relying only on the mobile platform's localization measurements communicated over LTE connection and not using any external sensors. We describe the approach, obtained results, shortcomings, and promising future directions.
{"title":"Using Cellular Connectivity for On-the-move Cooperation of Stationary Manipulator and Mobile Platform","authors":"Nima Enayati, O. D. Ramos-Cantor, T. Neugebauer, F. Dai, Thomas Hansen, T. Musiol, Monique Düngen, R. Kirsten, M. Aleksy","doi":"10.1109/ETFA45728.2021.9613325","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613325","url":null,"abstract":"This paper describes our work towards preliminary evaluation of LTE/5G cellular communication for robotics motion planning and control. The work comprises the development of communication architecture, motion planning and a demonstrator that validates the feasibility of the proposed approach. In the demonstrated use case, a stationary robot arm picks and places workpieces from/onto a moving mobile platform while relying only on the mobile platform's localization measurements communicated over LTE connection and not using any external sensors. We describe the approach, obtained results, shortcomings, and promising future directions.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125107810","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613601
J. Jost, T. Kirks, Stuart Chapman, G. Rinkenauer
In today's production plants, close cooperation between mobile robots and humans is becoming increasingly important. Several research papers have shown that proxemics is a suitable theoretical concept for predicting the distance behavior of humans when cooperating with robots. Our study was conducted within the framework of this concept. However, such studies often only focus on the different characteristics of the robot, so we further investigate the effects of human characteristics on the distance control. As independent variables, we systematically varied the characteristics of a transportation robot (speed, height, emotional expression) and additionally collected the characteristics of our 29 subjects (gender, experience with robots, experience with pets, attitude toward Robots). As a dependent variable, the distance of the subjects to the robot was measured using a motion capture system. Our research hypotheses were formulated based on the proxemics concept. As results show, the distance increases with the size of the robot or decreases with a friendly expression of the robot. In general, our results suggest that both the characteristics of the robot and the characteristics of the human partner influence distance regulation.
{"title":"Keep Distance with a Smile - User Characteristics in Human-Robot Collaboration","authors":"J. Jost, T. Kirks, Stuart Chapman, G. Rinkenauer","doi":"10.1109/ETFA45728.2021.9613601","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613601","url":null,"abstract":"In today's production plants, close cooperation between mobile robots and humans is becoming increasingly important. Several research papers have shown that proxemics is a suitable theoretical concept for predicting the distance behavior of humans when cooperating with robots. Our study was conducted within the framework of this concept. However, such studies often only focus on the different characteristics of the robot, so we further investigate the effects of human characteristics on the distance control. As independent variables, we systematically varied the characteristics of a transportation robot (speed, height, emotional expression) and additionally collected the characteristics of our 29 subjects (gender, experience with robots, experience with pets, attitude toward Robots). As a dependent variable, the distance of the subjects to the robot was measured using a motion capture system. Our research hypotheses were formulated based on the proxemics concept. As results show, the distance increases with the size of the robot or decreases with a friendly expression of the robot. In general, our results suggest that both the characteristics of the robot and the characteristics of the human partner influence distance regulation.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130340217","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613676
Dominik I. Braun, Wolfgang Schloegl, M. Weyrich
The success of the reconfiguration of existing manufacturing systems, so called brownfield systems, heavily relies on the knowledge about the system. Reconfiguration can be planned, supported and simplified with the Digital Twin of the system providing this knowledge. However, digital models as the basis of a Digital Twin are usually missing for these plants. This article presents a data-driven approach to gain knowledge about a brownfield system to create the digital models of a Digital Twin and their relations. Finally, a proof of concept shows that process data and position data as data sources deliver the relations between the models of the Digital Twin.
{"title":"Automated data-driven creation of the Digital Twin of a brownfield plant","authors":"Dominik I. Braun, Wolfgang Schloegl, M. Weyrich","doi":"10.1109/ETFA45728.2021.9613676","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613676","url":null,"abstract":"The success of the reconfiguration of existing manufacturing systems, so called brownfield systems, heavily relies on the knowledge about the system. Reconfiguration can be planned, supported and simplified with the Digital Twin of the system providing this knowledge. However, digital models as the basis of a Digital Twin are usually missing for these plants. This article presents a data-driven approach to gain knowledge about a brownfield system to create the digital models of a Digital Twin and their relations. Finally, a proof of concept shows that process data and position data as data sources deliver the relations between the models of the Digital Twin.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124180670","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613592
Abdullah Aziz, O. Schelén, Ulf Bodin
In the industrial automation domain, data integration between heterogeneous systems and architectures is a challenge. Companies and factories are impatient with the selection of technical solutions that are beneficial to local requirements, therefore facing problems of data integration and incompatibility between other systems. There is a need to bridge heterogeneous industrial systems to provide data integration. This article aims to provide guidelines to industrial managers and solution designers to achieve data integration between heterogeneous industrial systems according to their requirements. For this purpose, we have explored the implementation of two data integration models that can be selected based on the state and needs of industrial systems. The first data integration model is based on event-driven architecture (EDA), where Message Queuing Telemetry Transport (MQTT) is deployed as an event broker. The second model is based on the Arrowhead Framework, which is designed by using service-oriented architecture (SOA) principles, where EventHandler provides SOA-based event-driven communication. We conceptually compare and analyze them based on selected criteria essential in an industrial environment. The qualitative analysis of these models is based on proof-of-concept implementations made available for our evaluation.
{"title":"Data Integration Models for Heterogeneous Industrial Systems: A Conceptual Analysis","authors":"Abdullah Aziz, O. Schelén, Ulf Bodin","doi":"10.1109/ETFA45728.2021.9613592","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613592","url":null,"abstract":"In the industrial automation domain, data integration between heterogeneous systems and architectures is a challenge. Companies and factories are impatient with the selection of technical solutions that are beneficial to local requirements, therefore facing problems of data integration and incompatibility between other systems. There is a need to bridge heterogeneous industrial systems to provide data integration. This article aims to provide guidelines to industrial managers and solution designers to achieve data integration between heterogeneous industrial systems according to their requirements. For this purpose, we have explored the implementation of two data integration models that can be selected based on the state and needs of industrial systems. The first data integration model is based on event-driven architecture (EDA), where Message Queuing Telemetry Transport (MQTT) is deployed as an event broker. The second model is based on the Arrowhead Framework, which is designed by using service-oriented architecture (SOA) principles, where EventHandler provides SOA-based event-driven communication. We conceptually compare and analyze them based on selected criteria essential in an industrial environment. The qualitative analysis of these models is based on proof-of-concept implementations made available for our evaluation.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"14 151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121329770","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613448
Yugma P.N. Fernando, Kasun Gunasekara, Kumary P. Sirikumara, Upeksha E. Galappaththi, Thusithanjana Thilakarathna, D. Kasthurirathna
The elderly population constitutes a large percentage of the society hence making elderly care a top priority. Falls have been identified as a leading issue among major problems faced by them. Concerning this, many monitoring devices have been developed, most of them focusing solely on one specific health care aspect or related to fall detection, and are based on sensors and wearable devices which are usually uncomfortable for daily use. Considering these aspects, the solution proposed in this research is a real time computer vision-based system that monitors behavior and detects anomalies through deep learning. The monitoring is mainly focused on detecting unusual behavior including falls, and monitoring routine activities to detect deviations. A device approach is used to deploy the deep learning models and consists of IP camera-based monitoring which uses a special privacy protected procedure that ensures the detection is done based on meta data and therefore no camera image or footage is stored. The research is mainly focused on four major components which are user identification, fall detection, routine variance detection and device configuration.
{"title":"Computer Vision Based Privacy Protected Fall Detection and Behavior Monitoring System for the Care of the Elderly","authors":"Yugma P.N. Fernando, Kasun Gunasekara, Kumary P. Sirikumara, Upeksha E. Galappaththi, Thusithanjana Thilakarathna, D. Kasthurirathna","doi":"10.1109/ETFA45728.2021.9613448","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613448","url":null,"abstract":"The elderly population constitutes a large percentage of the society hence making elderly care a top priority. Falls have been identified as a leading issue among major problems faced by them. Concerning this, many monitoring devices have been developed, most of them focusing solely on one specific health care aspect or related to fall detection, and are based on sensors and wearable devices which are usually uncomfortable for daily use. Considering these aspects, the solution proposed in this research is a real time computer vision-based system that monitors behavior and detects anomalies through deep learning. The monitoring is mainly focused on detecting unusual behavior including falls, and monitoring routine activities to detect deviations. A device approach is used to deploy the deep learning models and consists of IP camera-based monitoring which uses a special privacy protected procedure that ensures the detection is done based on meta data and therefore no camera image or footage is stored. The research is mainly focused on four major components which are user identification, fall detection, routine variance detection and device configuration.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121503479","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613183
Muhammad Arsalan, Avik Santra, Mateusz Chmurski, Moamen El-Masry, Gianfranco Mauro, V. Issakov
Hand gesture recognition has become an increasingly important functionality in intelligent human-computer interfaces, finding applications in automotive, gaming and consumer industries. In this paper, we present an embedded gesture recognition system using frequency modulated continuous wave radar operating at 60 GHz. To facilitate low-power and low latency operation of the proposed system, spiking neural networks are used which are sparse in time and space, and event-driven. The experimental results demonstrate that the proposed neuromorphic implementation is capable of achieving a high recognition rate of 97.5% which is comparable to its deep learning counterparts in identifying radar gestures, namely up-down, down-up, swipe and finger rub.
{"title":"Radar-Based Gesture Recognition System using Spiking Neural Network","authors":"Muhammad Arsalan, Avik Santra, Mateusz Chmurski, Moamen El-Masry, Gianfranco Mauro, V. Issakov","doi":"10.1109/ETFA45728.2021.9613183","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613183","url":null,"abstract":"Hand gesture recognition has become an increasingly important functionality in intelligent human-computer interfaces, finding applications in automotive, gaming and consumer industries. In this paper, we present an embedded gesture recognition system using frequency modulated continuous wave radar operating at 60 GHz. To facilitate low-power and low latency operation of the proposed system, spiking neural networks are used which are sparse in time and space, and event-driven. The experimental results demonstrate that the proposed neuromorphic implementation is capable of achieving a high recognition rate of 97.5% which is comparable to its deep learning counterparts in identifying radar gestures, namely up-down, down-up, swipe and finger rub.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127894163","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613713
Oana Hotescu, A. Finzi
Nowadays, most of cyber-physical systems in avionics, automotive or recent Industry 4.0 domains require networked communication for mixed-critical applications. Ethernet-based networks such as AFDX, TTEthernet or TSN are capable to support transmission of both safety-critical and non-critical flows. This paper focuses on the TTEthernet network compliant with the avionics ARINC 664-P7 standard supporting time-triggered communication (TT) together with rate-constrained (RC) and best-effort (BE) traffic. Due to a global synchronization, TT communication with low latency and minimal jitter is ensured with static schedules computed offline. For event-triggered RC flows, bounded jitter at the source and end-to-end latency are guaranteed with worst-case analysis methods. With the increasing demands of applications, flows with Quality of Service (QoS) requirements such as video or audio may be transmitted as BE flows. However, on current configurations, no guarantees are offered to BE flows. In this paper, we aim at increasing the maximum RC utilization and improving the QoS of BE flows to allow the transmission of video or audio traffic with low jitter and end-to-end delay requirements. For this, we focus on the scheduling mechanisms and propose a scheduling approach based on a static slotted table that is applied at end systems. This table integrates the TT schedules usually obtained with Satisfiability Modulo Theories (SMT) approaches and establishes offsets of RC flows that reduce the end-to-end delay of BE flows. Several strategies for offset computations are proposed based on the distribution of flows locally at end system or globally at switch. We show that local strategies perform better than the global ones to reduce end-to-end delay of BE flows.
{"title":"Scheduling Rate Constrained traffic in End Systems of Time-Aware Networks","authors":"Oana Hotescu, A. Finzi","doi":"10.1109/ETFA45728.2021.9613713","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613713","url":null,"abstract":"Nowadays, most of cyber-physical systems in avionics, automotive or recent Industry 4.0 domains require networked communication for mixed-critical applications. Ethernet-based networks such as AFDX, TTEthernet or TSN are capable to support transmission of both safety-critical and non-critical flows. This paper focuses on the TTEthernet network compliant with the avionics ARINC 664-P7 standard supporting time-triggered communication (TT) together with rate-constrained (RC) and best-effort (BE) traffic. Due to a global synchronization, TT communication with low latency and minimal jitter is ensured with static schedules computed offline. For event-triggered RC flows, bounded jitter at the source and end-to-end latency are guaranteed with worst-case analysis methods. With the increasing demands of applications, flows with Quality of Service (QoS) requirements such as video or audio may be transmitted as BE flows. However, on current configurations, no guarantees are offered to BE flows. In this paper, we aim at increasing the maximum RC utilization and improving the QoS of BE flows to allow the transmission of video or audio traffic with low jitter and end-to-end delay requirements. For this, we focus on the scheduling mechanisms and propose a scheduling approach based on a static slotted table that is applied at end systems. This table integrates the TT schedules usually obtained with Satisfiability Modulo Theories (SMT) approaches and establishes offsets of RC flows that reduce the end-to-end delay of BE flows. Several strategies for offset computations are proposed based on the distribution of flows locally at end system or globally at switch. We show that local strategies perform better than the global ones to reduce end-to-end delay of BE flows.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126217311","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613384
F. R. Golra, M. Engel
As manufacturing, in general, is adopting Industry 4.0, OPC UA is gaining traction to become the de facto architecture for overcoming the issues of interoperability. Even though semiconductor equipment manufacturers need to comply with the existing and now mature SEMI11SEMI is a semiconductor association that defines standards. All SEMI standards referenced in this article are accessible at https://www.semi.org standards, it is worthwhile to explore the possibilities of harmonizing them with other automation standards. Following the same motivation, OPC Foundation has developed standardized companion specifications for different other standards like ISA-95, PROFINET, IO-Link, etc. In the absence of a companion specification for semiconductor industry, this work compares the architectural choices for the development of an information model for semiconductor industry. We share the lessons learned from our endeavors in implementing OPC UA information models for semiconductor domain.
{"title":"An industrial feedback on the use of OPC UA for the vertical integration of semiconductor front-ends","authors":"F. R. Golra, M. Engel","doi":"10.1109/ETFA45728.2021.9613384","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613384","url":null,"abstract":"As manufacturing, in general, is adopting Industry 4.0, OPC UA is gaining traction to become the de facto architecture for overcoming the issues of interoperability. Even though semiconductor equipment manufacturers need to comply with the existing and now mature SEMI11SEMI is a semiconductor association that defines standards. All SEMI standards referenced in this article are accessible at https://www.semi.org standards, it is worthwhile to explore the possibilities of harmonizing them with other automation standards. Following the same motivation, OPC Foundation has developed standardized companion specifications for different other standards like ISA-95, PROFINET, IO-Link, etc. In the absence of a companion specification for semiconductor industry, this work compares the architectural choices for the development of an information model for semiconductor industry. We share the lessons learned from our endeavors in implementing OPC UA information models for semiconductor domain.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125457980","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613427
David Arengas
Industrial nozzles play a relevant role in several processes such as varnishing in car production, cleaning of reactor tanks or in cooling applications. Nozzle production is performed in several steps from machining to quality tests. The type of nozzle considered in this application is firstly placed in the production center and then machined in different stations. An automation solution is proposed to integrate a collaborative robot (Cobot) into a current production center. The Cobot is used for picking, inspection and placing nozzles into the machining center. An industrial Raspberry Pi (RevPi) is used for signal processing and as communication interface between the Cobot and existing automation devices. The proposed solution enhances the current process as reliable continuous feeding of the machining center can be guaranteed and non-planned maintenance for replacement of machine tools is reduced by nozzle inspection.
{"title":"On the Integration of a Collaborative Robot for Automatic Production of Industrial Nozzles","authors":"David Arengas","doi":"10.1109/ETFA45728.2021.9613427","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613427","url":null,"abstract":"Industrial nozzles play a relevant role in several processes such as varnishing in car production, cleaning of reactor tanks or in cooling applications. Nozzle production is performed in several steps from machining to quality tests. The type of nozzle considered in this application is firstly placed in the production center and then machined in different stations. An automation solution is proposed to integrate a collaborative robot (Cobot) into a current production center. The Cobot is used for picking, inspection and placing nozzles into the machining center. An industrial Raspberry Pi (RevPi) is used for signal processing and as communication interface between the Cobot and existing automation devices. The proposed solution enhances the current process as reliable continuous feeding of the machining center can be guaranteed and non-planned maintenance for replacement of machine tools is reduced by nozzle inspection.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121859867","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613697
Tibor Kohlheb, M. Sinapius, C. Pommer, A. Boschmann
Condition monitoring measures on industrial rotating machinery, such as pumps, turbines or generators are highly desirable to detect faults at an early stage and thus minimize operation-dependent downtimes, save costs and improve safety. In this article, an evaluation method implemented on an embedded system is presented that is able to detect the condition of rotating machines via vibration and acoustic measurement and to assess it using artificial neural networks. In terms of industrializability, an unsupervised learning method in the form of autoencoders is used, which is trained based on the nominal machine operation and embedded in a microsystem. Thus, the measurement system is primarily used for the identification of deviating machine behavior and threshold-based classification of operational capability. The system has been developed and validated using a test rig that simulates bearing damage and imbalances as defective conditions in addition to intact operation. This resulted in an F-score of 95.9 % of the applied smart condition monitoring system.
{"title":"Embedded autoencoder-based condition monitoring of rotating machinery","authors":"Tibor Kohlheb, M. Sinapius, C. Pommer, A. Boschmann","doi":"10.1109/ETFA45728.2021.9613697","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613697","url":null,"abstract":"Condition monitoring measures on industrial rotating machinery, such as pumps, turbines or generators are highly desirable to detect faults at an early stage and thus minimize operation-dependent downtimes, save costs and improve safety. In this article, an evaluation method implemented on an embedded system is presented that is able to detect the condition of rotating machines via vibration and acoustic measurement and to assess it using artificial neural networks. In terms of industrializability, an unsupervised learning method in the form of autoencoders is used, which is trained based on the nominal machine operation and embedded in a microsystem. Thus, the measurement system is primarily used for the identification of deviating machine behavior and threshold-based classification of operational capability. The system has been developed and validated using a test rig that simulates bearing damage and imbalances as defective conditions in addition to intact operation. This resulted in an F-score of 95.9 % of the applied smart condition monitoring system.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130092281","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：