Pub Date : 2021-07-21DOI: 10.1109/INDIN45523.2021.9557514
Ehsan Shahri, P. Pedreiras, L. Almeida
MQTT is an application-layer protocol that eventually became popular in the Internet of Things (IoT) and Industrial IoT (IIoT) thanks to its simplicity and effective publisher-subscriber messaging model that enables its use in embedded resource-constrained devices. However, MQTT features a limited set of Quality-of-Service classes addressing exclusively message delivery, impairing its use in IIoT applications subject to timeliness requirements. This limitation of MQTT has been addressed in the literature, but with focus on the broker real-time operation, only. This paper adds to the state-of-the-art, by proposing a set of extensions to the MQTT protocol grounded on Software-Defined Networking (SDN) that enable, at the network level, attaining real-time communication services. Simulation results validate the benefits of the proposed extensions.
{"title":"Enhancing MQTT with Real-Time and Reliable Communication Services","authors":"Ehsan Shahri, P. Pedreiras, L. Almeida","doi":"10.1109/INDIN45523.2021.9557514","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557514","url":null,"abstract":"MQTT is an application-layer protocol that eventually became popular in the Internet of Things (IoT) and Industrial IoT (IIoT) thanks to its simplicity and effective publisher-subscriber messaging model that enables its use in embedded resource-constrained devices. However, MQTT features a limited set of Quality-of-Service classes addressing exclusively message delivery, impairing its use in IIoT applications subject to timeliness requirements. This limitation of MQTT has been addressed in the literature, but with focus on the broker real-time operation, only. This paper adds to the state-of-the-art, by proposing a set of extensions to the MQTT protocol grounded on Software-Defined Networking (SDN) that enable, at the network level, attaining real-time communication services. Simulation results validate the benefits of the proposed extensions.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"15 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":"115472673","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/INDIN45523.2021.9557416
Midhun Xavier, Sandeep Patil, V. Vyatkin
This paper introduces a problem-oriented notation within the IEC 61499 syntax to be used for creating formal closed-loop models of cyber-physical automation systems. The proposed notation enables creation of a comprehensive tool-chain that can combine design, simulation, formal verification and distributed deployment of automation software. The proposed notation allows for definition of non-deterministic transitions in ECC of basic function blocks of IEC 61499.The tool chain includes an IEC 61499 compliant engineering environment, fb2smv converter of functions blocks to SMV code, the NuSMV model-checker and utilities for interpreting counterexamples.
{"title":"Cyber-physical automation systems modelling with IEC 61499 for their formal verification","authors":"Midhun Xavier, Sandeep Patil, V. Vyatkin","doi":"10.1109/INDIN45523.2021.9557416","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557416","url":null,"abstract":"This paper introduces a problem-oriented notation within the IEC 61499 syntax to be used for creating formal closed-loop models of cyber-physical automation systems. The proposed notation enables creation of a comprehensive tool-chain that can combine design, simulation, formal verification and distributed deployment of automation software. The proposed notation allows for definition of non-deterministic transitions in ECC of basic function blocks of IEC 61499.The tool chain includes an IEC 61499 compliant engineering environment, fb2smv converter of functions blocks to SMV code, the NuSMV model-checker and utilities for interpreting counterexamples.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"44 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":"115244978","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/INDIN45523.2021.9557380
Jonathan Fuchs, Ruwen Schneider, S. J. Oks, Jörg Franke
Due to increasing complexity on the shop floor associated with the digital transformation and growing penetration of modern production environments with smart services, the operational phase of automated production facilities is gaining additional importance. The growing range of hybrid service bundles, i.e., the combination of digital services and cyber-physical production systems (CPPS), is expanding the scope of utilization and requires the application of platform-based solutions for service integration. Efficient, scalable IT infrastructures as well as technological flexibility and independence are premises for the successful implementation of these platforms. The availability of ubiquitous communication for seamless networking of all entities also plays a central role. These prerequisites enable the vertical integration of automation components on the shop floor up to the context of strategic business processes based on continuous data and information models. This paper presents an approach for integrating CPPS elements into scalable, highly available service platforms and shows how modern control approaches can be successfully linked with smart service concepts. The exemplary use case for this is a test bench for electric drives.
{"title":"Service-based integration of modular control components in digital manufacturing platforms","authors":"Jonathan Fuchs, Ruwen Schneider, S. J. Oks, Jörg Franke","doi":"10.1109/INDIN45523.2021.9557380","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557380","url":null,"abstract":"Due to increasing complexity on the shop floor associated with the digital transformation and growing penetration of modern production environments with smart services, the operational phase of automated production facilities is gaining additional importance. The growing range of hybrid service bundles, i.e., the combination of digital services and cyber-physical production systems (CPPS), is expanding the scope of utilization and requires the application of platform-based solutions for service integration. Efficient, scalable IT infrastructures as well as technological flexibility and independence are premises for the successful implementation of these platforms. The availability of ubiquitous communication for seamless networking of all entities also plays a central role. These prerequisites enable the vertical integration of automation components on the shop floor up to the context of strategic business processes based on continuous data and information models. This paper presents an approach for integrating CPPS elements into scalable, highly available service platforms and shows how modern control approaches can be successfully linked with smart service concepts. The exemplary use case for this is a test bench for electric drives.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"4 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":"128408089","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/INDIN45523.2021.9557430
Cheng-Huan Wang, Bo Li, Haichao Zhang, B. Xiao, Wenquan Gong
This work investigates the fixed-time trajectory tracking control problem of a wheeled mobile robot (WMR) under external disturbances. Firstly, the dynamic error system of the WMR is transformed into a second-order attitude error subsystem and a third-order position error subsystem, respectively. Subsequently, the super-twisting-like algorithms are proposed for the trajectory tracking of the WMR, and the fixed-time stability of the two subsystems are guaranteed. Finally, the effectiveness of the proposed control schemes is demonstrated by simulation and experiment results.
{"title":"Fixed-time Trajectory Tracking Control of a Wheeled Mobile Robot","authors":"Cheng-Huan Wang, Bo Li, Haichao Zhang, B. Xiao, Wenquan Gong","doi":"10.1109/INDIN45523.2021.9557430","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557430","url":null,"abstract":"This work investigates the fixed-time trajectory tracking control problem of a wheeled mobile robot (WMR) under external disturbances. Firstly, the dynamic error system of the WMR is transformed into a second-order attitude error subsystem and a third-order position error subsystem, respectively. Subsequently, the super-twisting-like algorithms are proposed for the trajectory tracking of the WMR, and the fixed-time stability of the two subsystems are guaranteed. Finally, the effectiveness of the proposed control schemes is demonstrated by simulation and experiment results.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"1 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":"128670222","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/INDIN45523.2021.9557415
Bruno Guilherme Carvalho, R. E. V. Vargas, R. M. Salgado, C. J. Munaro, F. M. Varejão
Flow instability is a class of abnormal operation in subsea oil wells. Applying machine learning models and improving detection and classification performance is decisive to reduce operational costs and downtime. In this paper we evaluate a pipeline of methods in order to increase correct classification rates. Our strategy is defined to avoid the similarity bias and approaches the binary problem in two distinct ways: A) using normal labels as negative and B) using both normal labels and all other kind of defects as negative, leveraging all data in the available dataset. The workflow includes feature extraction, hyperparameter tuning, feature selection with sequential algorithms, hybrid ranking wrapper and also with genetic algorithm. We show that hyperparameter tuning produces minor improvements and due to problem complexity a robust feature selection algorithm is required to deliver higher results.
{"title":"Hyperparameter Tuning and Feature Selection for Improving Flow Instability Detection in Offshore Oil Wells","authors":"Bruno Guilherme Carvalho, R. E. V. Vargas, R. M. Salgado, C. J. Munaro, F. M. Varejão","doi":"10.1109/INDIN45523.2021.9557415","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557415","url":null,"abstract":"Flow instability is a class of abnormal operation in subsea oil wells. Applying machine learning models and improving detection and classification performance is decisive to reduce operational costs and downtime. In this paper we evaluate a pipeline of methods in order to increase correct classification rates. Our strategy is defined to avoid the similarity bias and approaches the binary problem in two distinct ways: A) using normal labels as negative and B) using both normal labels and all other kind of defects as negative, leveraging all data in the available dataset. The workflow includes feature extraction, hyperparameter tuning, feature selection with sequential algorithms, hybrid ranking wrapper and also with genetic algorithm. We show that hyperparameter tuning produces minor improvements and due to problem complexity a robust feature selection algorithm is required to deliver higher results.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"1 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":"130673442","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/INDIN45523.2021.9557543
H. Khorasgani, Haiyan Wang, Chetan Gupta, Susumu Serita
Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on real-world physical systems remains limited. Despite the advancements in RL algorithms, the industries often prefer traditional control strategies. Traditional methods are simple, computationally efficient and easy to adjust. In this paper, we first propose a new Q-learning algorithm for continuous action space, which can bridge the control and RL algorithms and bring us the best of both worlds. Our method can learn complex policies to achieve long-term goals and at the same time it can be easily adjusted to address short-term requirements without retraining. Next, we present an approximation of our algorithm which can be applied to address short-term requirements of any pre-trained RL algorithm. The case studies demonstrate that both our proposed method as well as its practical approximation can achieve short-term and long-term goals without complex reward functions.
{"title":"Deep Reinforcement Learning with Adjustments","authors":"H. Khorasgani, Haiyan Wang, Chetan Gupta, Susumu Serita","doi":"10.1109/INDIN45523.2021.9557543","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557543","url":null,"abstract":"Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on real-world physical systems remains limited. Despite the advancements in RL algorithms, the industries often prefer traditional control strategies. Traditional methods are simple, computationally efficient and easy to adjust. In this paper, we first propose a new Q-learning algorithm for continuous action space, which can bridge the control and RL algorithms and bring us the best of both worlds. Our method can learn complex policies to achieve long-term goals and at the same time it can be easily adjusted to address short-term requirements without retraining. Next, we present an approximation of our algorithm which can be applied to address short-term requirements of any pre-trained RL algorithm. The case studies demonstrate that both our proposed method as well as its practical approximation can achieve short-term and long-term goals without complex reward functions.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"1 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":"130677656","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/INDIN45523.2021.9557487
G. Veselov, Aline Ingabire
This paper presents the procedure of the synergetic control of fixed-wing unmanned aerial vehicles (UAVs) in the presence of wind disturbances. In recent times, innovative organizations are using UAVs as an element of the healthcare delivery system, notably, UAVs are used to deliver critical and lifesaving medicine to thousands of hospitals serving millions of people in multiple countries with poor road networks. However, the reliability of the UAV's control system is a guarantee of delivering medicines on time and to their final destination. Having said that, the effect of wind disturbances on the UAV is one of the main factors affecting the reliability of using the UAV for solving such tasks. The paper proposes a new approach of synergetic control theory (SCT) to control the dynamics of a fixed-wing UAV in the presence of wind disturbances. The simulation results show that the synthesized control system of UAV provide asymptotic stability of the closed-loop control system, as well as invariance to the effect of external unmeasurable disturbances.
{"title":"Synergetic Control of Fixed-wing UAVs in the Presence of Wind Disturbances","authors":"G. Veselov, Aline Ingabire","doi":"10.1109/INDIN45523.2021.9557487","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557487","url":null,"abstract":"This paper presents the procedure of the synergetic control of fixed-wing unmanned aerial vehicles (UAVs) in the presence of wind disturbances. In recent times, innovative organizations are using UAVs as an element of the healthcare delivery system, notably, UAVs are used to deliver critical and lifesaving medicine to thousands of hospitals serving millions of people in multiple countries with poor road networks. However, the reliability of the UAV's control system is a guarantee of delivering medicines on time and to their final destination. Having said that, the effect of wind disturbances on the UAV is one of the main factors affecting the reliability of using the UAV for solving such tasks. The paper proposes a new approach of synergetic control theory (SCT) to control the dynamics of a fixed-wing UAV in the presence of wind disturbances. The simulation results show that the synthesized control system of UAV provide asymptotic stability of the closed-loop control system, as well as invariance to the effect of external unmeasurable disturbances.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"1 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":"114078639","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/INDIN45523.2021.9557405
Abdelkader Dairi, F. Harrou, Ying Sun
Accurately forecasting solar irradiance is indispensable in optimally managing and designing photovoltaic systems. It enables the efficient integration of photovoltaic systems in the smart grid. This paper introduces an innovative deep attention-driven model for solar irradiance forecasting. Notably, an extended version of the variational autoencoder (VAE) is introduced by amalgamating the desirable characteristics of the bidirectional LSTM (BiLSTM) and attention mechanism with the VAE model. Specifically, the introduced approach enables the conventional VAE’s ability to model temporal dependencies by incorporating BiLSTM at the VAE’s encoder side to better extract and learn temporal dependencies embed on the solar irradiance concentration measurements. In addition, the self-attention mechanism is embedded in the VAE’s encoder side following the BiLSTM to highlight pertinent features. The performance of the proposed model is evaluated through comparisons with the recurrent neural network (RNN), gated recurrent unit (GRU), LSTM, and BiLSTM. Measurements of solar irradiance in the US and Turkey are used to evaluate the investigated models. Results confirm the superior performance of the proposed model for solar irradiance forecasting over the other models (i.e., RNN, GRU, LSTM, and BiLSTM).
{"title":"A deep attention-driven model to forecast solar irradiance","authors":"Abdelkader Dairi, F. Harrou, Ying Sun","doi":"10.1109/INDIN45523.2021.9557405","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557405","url":null,"abstract":"Accurately forecasting solar irradiance is indispensable in optimally managing and designing photovoltaic systems. It enables the efficient integration of photovoltaic systems in the smart grid. This paper introduces an innovative deep attention-driven model for solar irradiance forecasting. Notably, an extended version of the variational autoencoder (VAE) is introduced by amalgamating the desirable characteristics of the bidirectional LSTM (BiLSTM) and attention mechanism with the VAE model. Specifically, the introduced approach enables the conventional VAE’s ability to model temporal dependencies by incorporating BiLSTM at the VAE’s encoder side to better extract and learn temporal dependencies embed on the solar irradiance concentration measurements. In addition, the self-attention mechanism is embedded in the VAE’s encoder side following the BiLSTM to highlight pertinent features. The performance of the proposed model is evaluated through comparisons with the recurrent neural network (RNN), gated recurrent unit (GRU), LSTM, and BiLSTM. Measurements of solar irradiance in the US and Turkey are used to evaluate the investigated models. Results confirm the superior performance of the proposed model for solar irradiance forecasting over the other models (i.e., RNN, GRU, LSTM, and BiLSTM).","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"10 3 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":"121639343","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/INDIN45523.2021.9557440
Udayanto Dwi Atmojo, Mohammad Azangoo, V. Vyatkin, I. Seilonen
The COVID19 pandemic has created tremendous challenges in the learning and education sector. Schools and universities are forced to close and most teaching activities have to be organized with very limited physical and social interaction between the teachers and students, and also among students. This is particularly difficult for certain learning activity, such as laboratory work where it usually involve the student’s direct interaction with equipments in the school and sometimes the need to work together with the their peers in the same space while interacting with the equipments. This paper presents an experience in shifting the delivery method of a process automation laboratory course at Aalto University from face to face teaching into hybrid due to the restrictionc caused by the pandemic. This paper describes the rework process of the course to realize this shift, and after the course, feedbacks are gathered from the student to see if the approach taken is welcomed by the students. The feedback appears promising, indicating 66% of the respondents agree that they like the hybrid method approach considered.
{"title":"From Face to Face to Hybrid Teaching: an Experience on Process Plant Automation Laboratory Course during Global Pandemic","authors":"Udayanto Dwi Atmojo, Mohammad Azangoo, V. Vyatkin, I. Seilonen","doi":"10.1109/INDIN45523.2021.9557440","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557440","url":null,"abstract":"The COVID19 pandemic has created tremendous challenges in the learning and education sector. Schools and universities are forced to close and most teaching activities have to be organized with very limited physical and social interaction between the teachers and students, and also among students. This is particularly difficult for certain learning activity, such as laboratory work where it usually involve the student’s direct interaction with equipments in the school and sometimes the need to work together with the their peers in the same space while interacting with the equipments. This paper presents an experience in shifting the delivery method of a process automation laboratory course at Aalto University from face to face teaching into hybrid due to the restrictionc caused by the pandemic. This paper describes the rework process of the course to realize this shift, and after the course, feedbacks are gathered from the student to see if the approach taken is welcomed by the students. The feedback appears promising, indicating 66% of the respondents agree that they like the hybrid method approach considered.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"19 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":"114764261","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/INDIN45523.2021.9557382
Katsiaryna Haitsiukevich, S. Bergman, C. D. A. Filho, F. Corona, A. Ilin
We propose a grid-like computational model of tubular reactors. The architecture is inspired by the computations performed by solvers of partial differential equations which describe the dynamics of the chemical process inside a tubular reactor. The proposed model may be entirely based on the known form of the partial differential equations or it may contain generic machine learning components such as multi-layer perceptrons. We show that the proposed model can be trained using limited amounts of data to describe the state of a fixed-bed catalytic reactor. The trained model can reconstruct unmeasured states such as the catalyst activity using the measurements of inlet concentrations and temperatures along the reactor.
{"title":"A Grid-Structured Model of Tubular Reactors","authors":"Katsiaryna Haitsiukevich, S. Bergman, C. D. A. Filho, F. Corona, A. Ilin","doi":"10.1109/INDIN45523.2021.9557382","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557382","url":null,"abstract":"We propose a grid-like computational model of tubular reactors. The architecture is inspired by the computations performed by solvers of partial differential equations which describe the dynamics of the chemical process inside a tubular reactor. The proposed model may be entirely based on the known form of the partial differential equations or it may contain generic machine learning components such as multi-layer perceptrons. We show that the proposed model can be trained using limited amounts of data to describe the state of a fixed-bed catalytic reactor. The trained model can reconstruct unmeasured states such as the catalyst activity using the measurements of inlet concentrations and temperatures along the reactor.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"389 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":"124299774","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：