Pub Date : 2021-07-21DOI: 10.1109/INDIN45523.2021.9557555
Hsien-I Lin, A. Singh
Force measurement and control for the automatic process are crucial in automation, especially in the insertion (mating) task. This fragile task is needs to be automated for safety and economical purposes. One small mistake and misjudgement by operators could damage the fragile component, and also cause the company material loss. In this paper, the mating process is implemented by an articulated robot with a force sensor mounted on it. We propose a data-driven approach for the procedure to automate the mating process of the slimstack Board-to-Board (BtB) insertion process. The force data is recorded and encoded to a recurrence 2D plot. Then the 2D image is used to predict the position and alignment of the male and female Board-toBoard connector. By using the encoding approach, the system can classify each corresponding force based on its status of BtB insertion and provide a safety procedure in the insertion process. The proposed model is compared with the efficient time series LSTM model.
{"title":"Board-to-Board connector mating using data-driven approach","authors":"Hsien-I Lin, A. Singh","doi":"10.1109/INDIN45523.2021.9557555","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557555","url":null,"abstract":"Force measurement and control for the automatic process are crucial in automation, especially in the insertion (mating) task. This fragile task is needs to be automated for safety and economical purposes. One small mistake and misjudgement by operators could damage the fragile component, and also cause the company material loss. In this paper, the mating process is implemented by an articulated robot with a force sensor mounted on it. We propose a data-driven approach for the procedure to automate the mating process of the slimstack Board-to-Board (BtB) insertion process. The force data is recorded and encoded to a recurrence 2D plot. Then the 2D image is used to predict the position and alignment of the male and female Board-toBoard connector. By using the encoding approach, the system can classify each corresponding force based on its status of BtB insertion and provide a safety procedure in the insertion process. The proposed model is compared with the efficient time series LSTM model.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"39 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133494277","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 : 2021-07-21DOI: 10.1109/INDIN45523.2021.9557409
Bernhard Girsule, Gernot Rottermanner, C. Jandl, T. Moser
In the metal processing industry, there are time-consuming repetitive tasks, e.g. checking parts if they are producible on a certain machine. In order to relieve the production manager and save time, this paper presents a self-learning system that carries out this task independently. Expert knowledge was collected, a synthetic data generator, a machine learning model based on a neuronal network for part classification as well as feedback modalities for experts were developed together with an Austrian sheet metal profile manufacturer. The solution was well accepted by the target group, but it became clear that it is important to integrate them into the whole development process. Furthermore, they can imagine that they trust the machine learning prediction after several weeks and thus the test of producibility could be automated. Tests on synthetic data showed a data collection period of approx. two years is necessary to provide satisfactory prediction accuracy if the model is trained from scratch. This time can be shortened by using pre-trained models.
{"title":"Machine Learning Support for Repetitive Tasks in Metal Processing SMEs","authors":"Bernhard Girsule, Gernot Rottermanner, C. Jandl, T. Moser","doi":"10.1109/INDIN45523.2021.9557409","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557409","url":null,"abstract":"In the metal processing industry, there are time-consuming repetitive tasks, e.g. checking parts if they are producible on a certain machine. In order to relieve the production manager and save time, this paper presents a self-learning system that carries out this task independently. Expert knowledge was collected, a synthetic data generator, a machine learning model based on a neuronal network for part classification as well as feedback modalities for experts were developed together with an Austrian sheet metal profile manufacturer. The solution was well accepted by the target group, but it became clear that it is important to integrate them into the whole development process. Furthermore, they can imagine that they trust the machine learning prediction after several weeks and thus the test of producibility could be automated. Tests on synthetic data showed a data collection period of approx. two years is necessary to provide satisfactory prediction accuracy if the model is trained from scratch. This time can be shortened by using pre-trained models.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"423 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123035950","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 : 2021-07-21DOI: 10.1109/INDIN45523.2021.9557357
J. Fischer, B. Vogel‐Heuser, C. Huber, Mark E. Felger, Matthias Bengel
In the automated Production Systems (aPS) domain, companies need to continuously decrease their systems’ development times while maintaining quality to stay globally competitive. Industry 4.0 imposes additional boundary conditions, e.g., a high degree of customization, that need to be met by aPS, which frequently have to be adapted to changing requirements during their long life cycles. Since control software implements an increasing share of aPS functionality, reusing well-tested software modules can significantly contribute to saving development time and increasing its comprehensibility and maintainability. However, planned reuse of control software modules still represents a major challenge in practice, e.g., the data exchange between software modules causes dependencies, which are often not directly visible and, thus, hinder reuse. This paper presents a metric-based concept for assessing the reusability of control software modules, focusing on different implementation types of indirect data exchange. Depending on company-specific boundary conditions, the approach can be integrated at various development process steps for continuous or one-time reuse assessment. The concept has been developed and evaluated with two industrial software projects and continuous feedback from domain experts.
{"title":"Reuse Assessment of IEC 61131-3 Control Software Modules Using Metrics – An Industrial Case Study","authors":"J. Fischer, B. Vogel‐Heuser, C. Huber, Mark E. Felger, Matthias Bengel","doi":"10.1109/INDIN45523.2021.9557357","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557357","url":null,"abstract":"In the automated Production Systems (aPS) domain, companies need to continuously decrease their systems’ development times while maintaining quality to stay globally competitive. Industry 4.0 imposes additional boundary conditions, e.g., a high degree of customization, that need to be met by aPS, which frequently have to be adapted to changing requirements during their long life cycles. Since control software implements an increasing share of aPS functionality, reusing well-tested software modules can significantly contribute to saving development time and increasing its comprehensibility and maintainability. However, planned reuse of control software modules still represents a major challenge in practice, e.g., the data exchange between software modules causes dependencies, which are often not directly visible and, thus, hinder reuse. This paper presents a metric-based concept for assessing the reusability of control software modules, focusing on different implementation types of indirect data exchange. Depending on company-specific boundary conditions, the approach can be integrated at various development process steps for continuous or one-time reuse assessment. The concept has been developed and evaluated with two industrial software projects and continuous feedback from domain experts.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115544785","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 : 2021-07-21DOI: 10.1109/INDIN45523.2021.9557410
S. Álvarez-Napagao, B. Ashmore, Marta Barroso, C. Barrué, C. Beecks, Fabian Berns, Ilaria Bosi, S. Chala, N. Ciulli, M. Garcia-Gasulla, Alexander Grass, D. Ioannidis, Natalia Jakubiak, K. Köpke, Ville Lämsä, Pedro Megias, Alexandros Nizamis, C. Pastrone, R. Rossini, M. Sànchez-Marrè, Luca Ziliotti
AI is one of the biggest megatrends towards the 4th industrial revolution. Although these technologies promise business sustainability as well as product and process quality, it seems that the ever-changing market demands, the complexity of technologies and fair concerns about privacy, impede broad application and reuse of Artificial Intelligence (AI) models across the industry. To break the entry barriers for these technologies and unleash its full potential, the knowlEdge project will develop a new generation of AI methods, systems, and data management infrastructure. Subsequently, as part of the knowlEdge project we propose several major innovations in the areas of data management, data analytics and knowledge management including (i) a set of AI services that allows the usage of edge deployments as computational and live data infrastructure as well as a continuous learning execution pipeline on the edge, (ii) a digital twin of the shop-floor able to test AI models, (iii) a data management framework deployed along the edge-to-cloud continuum ensuring data quality, privacy and confidentiality, (iv) Human-AI Collaboration and Domain Knowledge Fusion tools for domain experts to inject their experience into the system, (v) a set of standardisation mechanisms for the exchange of trained AI models from one context to another, and (vi) a knowledge marketplace platform to distribute and interchange trained AI models. In this paper, we present a short overview of the EU Project knowlEdge –Towards Artificial Intelligence powered manufacturing services, processes, and products in an edge-to-cloud-knowledge continuum for humans [in-the-loop], which is funded by the Horizon 2020 (H2020) Framework Programme of the European Commission under Grant Agreement 957331. Our overview includes a description of the project’s main concept and methodology as well as the envisioned innovations.
{"title":"knowlEdge Project –Concept, Methodology and Innovations for Artificial Intelligence in Industry 4.0","authors":"S. Álvarez-Napagao, B. Ashmore, Marta Barroso, C. Barrué, C. Beecks, Fabian Berns, Ilaria Bosi, S. Chala, N. Ciulli, M. Garcia-Gasulla, Alexander Grass, D. Ioannidis, Natalia Jakubiak, K. Köpke, Ville Lämsä, Pedro Megias, Alexandros Nizamis, C. Pastrone, R. Rossini, M. Sànchez-Marrè, Luca Ziliotti","doi":"10.1109/INDIN45523.2021.9557410","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557410","url":null,"abstract":"AI is one of the biggest megatrends towards the 4th industrial revolution. Although these technologies promise business sustainability as well as product and process quality, it seems that the ever-changing market demands, the complexity of technologies and fair concerns about privacy, impede broad application and reuse of Artificial Intelligence (AI) models across the industry. To break the entry barriers for these technologies and unleash its full potential, the knowlEdge project will develop a new generation of AI methods, systems, and data management infrastructure. Subsequently, as part of the knowlEdge project we propose several major innovations in the areas of data management, data analytics and knowledge management including (i) a set of AI services that allows the usage of edge deployments as computational and live data infrastructure as well as a continuous learning execution pipeline on the edge, (ii) a digital twin of the shop-floor able to test AI models, (iii) a data management framework deployed along the edge-to-cloud continuum ensuring data quality, privacy and confidentiality, (iv) Human-AI Collaboration and Domain Knowledge Fusion tools for domain experts to inject their experience into the system, (v) a set of standardisation mechanisms for the exchange of trained AI models from one context to another, and (vi) a knowledge marketplace platform to distribute and interchange trained AI models. In this paper, we present a short overview of the EU Project knowlEdge –Towards Artificial Intelligence powered manufacturing services, processes, and products in an edge-to-cloud-knowledge continuum for humans [in-the-loop], which is funded by the Horizon 2020 (H2020) Framework Programme of the European Commission under Grant Agreement 957331. Our overview includes a description of the project’s main concept and methodology as well as the envisioned innovations.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125304466","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 : 2021-07-21DOI: 10.1109/INDIN45523.2021.9557565
E. Peter, W. Endemann, R. Kays
Parallel sequence spread spectrum (PSSS) is a novel physical layer (PHY) broadband technique, that offers a flexible resource allocation and benefits against fading on wireless channels at a relatively low complexity. This spread spectrum method may especially be used in industrial radio and for high data rates in the THz range. In this paper, we first present the characteristics of the root-raised cosine (RRC) pulse shaped PSSS signal. We examine the amplitude distribution and the peak-to-average power ratio (PAPR) for different roll-off factors. Surprisingly, for large roll-off values high amplitudes become more likely. We then analyze the performance of PSSS under the influence of a memoryless nonlinearity introduced by a solid-state power amplifier (SSPA) using baseband simulation. This power amplifier (PA) is modeled using the well-established Rapp model. We compare the system to a basic orthogonal frequency-division multiplexing (OFDM) implementation.
{"title":"Influence of Roll-off Pulse Shaping on a Parallel Sequence Spread Spectrum Signal","authors":"E. Peter, W. Endemann, R. Kays","doi":"10.1109/INDIN45523.2021.9557565","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557565","url":null,"abstract":"Parallel sequence spread spectrum (PSSS) is a novel physical layer (PHY) broadband technique, that offers a flexible resource allocation and benefits against fading on wireless channels at a relatively low complexity. This spread spectrum method may especially be used in industrial radio and for high data rates in the THz range. In this paper, we first present the characteristics of the root-raised cosine (RRC) pulse shaped PSSS signal. We examine the amplitude distribution and the peak-to-average power ratio (PAPR) for different roll-off factors. Surprisingly, for large roll-off values high amplitudes become more likely. We then analyze the performance of PSSS under the influence of a memoryless nonlinearity introduced by a solid-state power amplifier (SSPA) using baseband simulation. This power amplifier (PA) is modeled using the well-established Rapp model. We compare the system to a basic orthogonal frequency-division multiplexing (OFDM) implementation.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129257427","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 : 2021-07-21DOI: 10.1109/INDIN45523.2021.9557474
Jimmy Ma, Z. Salcic
In this paper, a real-time, real-life, novel license plate localisation (LPL) based on deep learning (DL) and accelerated by field-programmable gate array (FPGA), and Open Visual Inference and Neural network Optimization (OpenVINO) toolkit, is proposed and prototyped. The solution was tested against two popular international research databases and achieves state-of- the-art results, proving the viability of FPGA in real-life latency- oriented application. Using novel asynchronized DL inference that prepares next result while current inference is ongoing, the system increases computational efficiency without buffering frames, allowing for reduced latency. Comparisons show that the proposed LPL system has lower latency and better performance per watt than other related solutions.
{"title":"Deep Learning with Accelerated Execution: A Real-Time License Plate Localisation System","authors":"Jimmy Ma, Z. Salcic","doi":"10.1109/INDIN45523.2021.9557474","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557474","url":null,"abstract":"In this paper, a real-time, real-life, novel license plate localisation (LPL) based on deep learning (DL) and accelerated by field-programmable gate array (FPGA), and Open Visual Inference and Neural network Optimization (OpenVINO) toolkit, is proposed and prototyped. The solution was tested against two popular international research databases and achieves state-of- the-art results, proving the viability of FPGA in real-life latency- oriented application. Using novel asynchronized DL inference that prepares next result while current inference is ongoing, the system increases computational efficiency without buffering frames, allowing for reduced latency. Comparisons show that the proposed LPL system has lower latency and better performance per watt than other related solutions.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126140913","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}
Recently AI technologies, especially Deep Neural Network (DNN), have been widely used in the financial industry, such as stock price and movement prediction. In order to develop an AI-based solution for the global financial market, daily-based DNN model training for each stock is required to need collaboration among a large scale of entities. However, it is usually challenging due to data privacy, the cost of AI computing, and the lack of motivation to share information. This research proposes a novel Blockchain based platform, which utilizes the decentralized network, federated learning, and master-node to tackle these issues. The decentralized computing framework of federated learning, along with transfer learning, is applied to meet the data privacy requirements. Furthermore, the proposed federated learning platform with collaborative training is built on a decentralized AI computing cloud, which is highly affordable compared to centralized AI clouds. The master-node of Blockchain technology is further employed to enable the scalable global financial service, and effective rewards are applied to incentivize information sharing as well. We have applied the proposed Blockchain based platform to the stock prediction global service, which demonstrates the platform is practical and useful.
{"title":"Blockchain Based Global Financial Service Platform","authors":"Mingyang Zhang, Yingjun Li, Chonghe Zheng, Xu Han, Haisong Gu, Heping Pan","doi":"10.1109/INDIN45523.2021.9557501","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557501","url":null,"abstract":"Recently AI technologies, especially Deep Neural Network (DNN), have been widely used in the financial industry, such as stock price and movement prediction. In order to develop an AI-based solution for the global financial market, daily-based DNN model training for each stock is required to need collaboration among a large scale of entities. However, it is usually challenging due to data privacy, the cost of AI computing, and the lack of motivation to share information. This research proposes a novel Blockchain based platform, which utilizes the decentralized network, federated learning, and master-node to tackle these issues. The decentralized computing framework of federated learning, along with transfer learning, is applied to meet the data privacy requirements. Furthermore, the proposed federated learning platform with collaborative training is built on a decentralized AI computing cloud, which is highly affordable compared to centralized AI clouds. The master-node of Blockchain technology is further employed to enable the scalable global financial service, and effective rewards are applied to incentivize information sharing as well. We have applied the proposed Blockchain based platform to the stock prediction global service, which demonstrates the platform is practical and useful.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"260 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122928503","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 : 2021-07-21DOI: 10.1109/indin45523.2021.9557493
{"title":"[INDIN 2021 Front cover]","authors":"","doi":"10.1109/indin45523.2021.9557493","DOIUrl":"https://doi.org/10.1109/indin45523.2021.9557493","url":null,"abstract":"","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114074539","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 : 2021-07-21DOI: 10.1109/INDIN45523.2021.9557546
Fan Yang, Lei Shu, Xuying Wang
Wireless Sensor Networks (WSNs) have been widely used in agricultural productions. As a critical problems in WSNs, node deployment has a direct impact on the effectiveness of routing and data fusion operations as well as on the accuracy of anticipated coverage in several agricultural scenarios, e.g., mono-crop and mixed-crop farmlands. Network simulations are necessary for testing the effectiveness of deployment algorithms, but some of them lack the accuracy of real-world deployments. This is due to the fact that analogue maps in these network simulations do not take into account the nature of the terrain, for example obstacles such as buildings and trees in the line of vision for sensors, uneven surfaces and elevations for hilly terrains, the node locations obtained by the deployment algorithms in these analogue maps cannot be mapped to the actual farmland. In this paper, we present a methodology of constructing analogue map called AnaMap for providing both simulation and visualization of the actual farmland with the characteristic of partition structure and irregular boundary to assist the investigation of node deployment algorithms in agricultural environment. One case study is described to prove the usability of AnaMap.
{"title":"AnaMap: A Methodology of Simulation and Visualization for Actual Farmland Topography","authors":"Fan Yang, Lei Shu, Xuying Wang","doi":"10.1109/INDIN45523.2021.9557546","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557546","url":null,"abstract":"Wireless Sensor Networks (WSNs) have been widely used in agricultural productions. As a critical problems in WSNs, node deployment has a direct impact on the effectiveness of routing and data fusion operations as well as on the accuracy of anticipated coverage in several agricultural scenarios, e.g., mono-crop and mixed-crop farmlands. Network simulations are necessary for testing the effectiveness of deployment algorithms, but some of them lack the accuracy of real-world deployments. This is due to the fact that analogue maps in these network simulations do not take into account the nature of the terrain, for example obstacles such as buildings and trees in the line of vision for sensors, uneven surfaces and elevations for hilly terrains, the node locations obtained by the deployment algorithms in these analogue maps cannot be mapped to the actual farmland. In this paper, we present a methodology of constructing analogue map called AnaMap for providing both simulation and visualization of the actual farmland with the characteristic of partition structure and irregular boundary to assist the investigation of node deployment algorithms in agricultural environment. One case study is described to prove the usability of AnaMap.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127900479","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 : 2021-07-21DOI: 10.1109/INDIN45523.2021.9557368
Benedikt Schmidt, Reuben Borrison, M. Gärtler, Sylvia Maczey, A. Kotriwala
A high degree of automation is an essential factor for smooth operation, to be economically viable and in many parts of the industry a de-facto standard. Nevertheless, manual interventions and operations are ever present, especially in those sectors that deal with large variations and uncertainties. For example, in waste incineration, the composition of waste varies significantly making a steady, efficient, and automated incineration very difficult. Similarly, the recovery from safety-/load-related trips is often not automated due to the large number of potential causes. These manual activities are recorded as part of the regular audit trail and stored in historians or databases. Yet, they are rarely analyzed which makes them a blind spot in the ongoing activities for digitization and Industry 4.0. We provide an overview of state-of-the-art techniques to perform case and workflow mining, our experience in analyzing two industrial data sets and our pipelines established during that activity.
{"title":"Practical Aspects for Exploration and Analysis of Manual Interventions in Process Plants","authors":"Benedikt Schmidt, Reuben Borrison, M. Gärtler, Sylvia Maczey, A. Kotriwala","doi":"10.1109/INDIN45523.2021.9557368","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557368","url":null,"abstract":"A high degree of automation is an essential factor for smooth operation, to be economically viable and in many parts of the industry a de-facto standard. Nevertheless, manual interventions and operations are ever present, especially in those sectors that deal with large variations and uncertainties. For example, in waste incineration, the composition of waste varies significantly making a steady, efficient, and automated incineration very difficult. Similarly, the recovery from safety-/load-related trips is often not automated due to the large number of potential causes. These manual activities are recorded as part of the regular audit trail and stored in historians or databases. Yet, they are rarely analyzed which makes them a blind spot in the ongoing activities for digitization and Industry 4.0. We provide an overview of state-of-the-art techniques to perform case and workflow mining, our experience in analyzing two industrial data sets and our pipelines established during that activity.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125903112","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：