Pub Date : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976111
Midhun Xavier, V. Dubinin, Sandeep Patil, V. Vyatkin
In this paper, we discuss how process mining techniques can be applied in industrial control systems for modeling, verification, and enhancement of the cyber-physical system based on recorded data logs. Process mining is used for extracting the process models in different notations from the recorded behavioral traces of the system. The output model of the system’s behavior is mainly derived using an open-source tool called ProM. The model can be used for such applications as anomaly detection, detection of cyber-attacks and alarm analysis in industrial control systems with the help of various control flow discovery algorithms. The extracted process model can be used to verify how the event log deviates from it by replaying the log on Petri net for conformance analysis.
{"title":"Process mining in industrial control systems","authors":"Midhun Xavier, V. Dubinin, Sandeep Patil, V. Vyatkin","doi":"10.1109/INDIN51773.2022.9976111","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976111","url":null,"abstract":"In this paper, we discuss how process mining techniques can be applied in industrial control systems for modeling, verification, and enhancement of the cyber-physical system based on recorded data logs. Process mining is used for extracting the process models in different notations from the recorded behavioral traces of the system. The output model of the system’s behavior is mainly derived using an open-source tool called ProM. The model can be used for such applications as anomaly detection, detection of cyber-attacks and alarm analysis in industrial control systems with the help of various control flow discovery algorithms. The extracted process model can be used to verify how the event log deviates from it by replaying the log on Petri net for conformance analysis.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124967291","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976166
Anna Florea, A. Lobov, T. Minav
Digital twins serve as a source of new insights about industrial processes and systems performance and enable the use of cutting-edge technologies for their optimization. Solution vendors offer a variety of tools for digital twin implementation. As the amount of such solutions grows, the need to integrate and navigate the variety of digital twins in large-scale systems arises. The complexity of modern industrial systems requires an approach, where the integration process will happen in an organized way, allowing engineers to make informed decisions and communicate clearly project goals and transfer them into actual design and solution.This work presents results from investigating the applicability of concepts, building blocks, and engineering processes for Distributed Interactive Simulation (DIS) standards to perform such tasks. It provides an example of integration between two simulation tools used for digital twin development and illustrates how DIS aligns with such a development process.
{"title":"Applying IEEE 1278.1-2012 Concepts to Support Integration of Digital Twins in Industrial Applications","authors":"Anna Florea, A. Lobov, T. Minav","doi":"10.1109/INDIN51773.2022.9976166","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976166","url":null,"abstract":"Digital twins serve as a source of new insights about industrial processes and systems performance and enable the use of cutting-edge technologies for their optimization. Solution vendors offer a variety of tools for digital twin implementation. As the amount of such solutions grows, the need to integrate and navigate the variety of digital twins in large-scale systems arises. The complexity of modern industrial systems requires an approach, where the integration process will happen in an organized way, allowing engineers to make informed decisions and communicate clearly project goals and transfer them into actual design and solution.This work presents results from investigating the applicability of concepts, building blocks, and engineering processes for Distributed Interactive Simulation (DIS) standards to perform such tasks. It provides an example of integration between two simulation tools used for digital twin development and illustrates how DIS aligns with such a development process.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129532025","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976139
Gianluca Manca, A. Fay
Alarm flood classification (AFC) methods are used to support human operators to identify and assess recurring alarm floods in industrial process plants. State-of-the-art AFC methods, however, show shortcomings in handling an ambiguity of the activations and order of alarms and the detection of previously unobserved alarm floods. To solve these limitations, we present a novel three-tier AFC method that uses alarm series as input. In the classification stage, a linear ridge regression classifier with a convolutional kernel-based transformation (MultiRocket) is used to classify alarm floods according to their dynamic properties. In the detection stage, a novelty detection method based on the "local outlier probability" (LoOP) is used to decide whether an unknown alarm flood belongs to a known class or a novel one. Finally, we improve the classification results using an ensemble approach. Our proposed method is compared to two naïve baselines and three relevant methods from the literature using a publicly available dataset based on the "Tennessee-Eastman" process. It is evident that our method shows the highest overall classification performance and robustness of all of the considered methods and effectively overcomes existing challenges in AFC.
{"title":"Identification of Industrial Alarm Floods Using Time Series Classification and Novelty Detection","authors":"Gianluca Manca, A. Fay","doi":"10.1109/INDIN51773.2022.9976139","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976139","url":null,"abstract":"Alarm flood classification (AFC) methods are used to support human operators to identify and assess recurring alarm floods in industrial process plants. State-of-the-art AFC methods, however, show shortcomings in handling an ambiguity of the activations and order of alarms and the detection of previously unobserved alarm floods. To solve these limitations, we present a novel three-tier AFC method that uses alarm series as input. In the classification stage, a linear ridge regression classifier with a convolutional kernel-based transformation (MultiRocket) is used to classify alarm floods according to their dynamic properties. In the detection stage, a novelty detection method based on the \"local outlier probability\" (LoOP) is used to decide whether an unknown alarm flood belongs to a known class or a novel one. Finally, we improve the classification results using an ensemble approach. Our proposed method is compared to two naïve baselines and three relevant methods from the literature using a publicly available dataset based on the \"Tennessee-Eastman\" process. It is evident that our method shows the highest overall classification performance and robustness of all of the considered methods and effectively overcomes existing challenges in AFC.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127613515","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976140
Felix Specht, J. Otto, Jens Eickmeyer
Cyberattacks on cyber-physical production systems lead to manipulation of the physical process and pose a serious threat to machines and employees. Preventing cyberattacks and reducing their negative impact is an important aspect of security. This paper presents an approach to reduce the impact of cyberattacks. The approach uses software-defined networking (SDN) in combination with network metrics. The network metrics enable measuring the impact of cyberattacks and the impact reduction by the SDN approach. The SDN approach utilizes four different prevention techniques as countermeasures. Scenarios from discrete manufacturing are used to evaluate the approach. The approach reduces the average impact of the selected cyber-attacks from 82.9% to 98.1%.
{"title":"Cyberattack Impact Reduction using Software-Defined Networking for Cyber-Physical Production Systems","authors":"Felix Specht, J. Otto, Jens Eickmeyer","doi":"10.1109/INDIN51773.2022.9976140","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976140","url":null,"abstract":"Cyberattacks on cyber-physical production systems lead to manipulation of the physical process and pose a serious threat to machines and employees. Preventing cyberattacks and reducing their negative impact is an important aspect of security. This paper presents an approach to reduce the impact of cyberattacks. The approach uses software-defined networking (SDN) in combination with network metrics. The network metrics enable measuring the impact of cyberattacks and the impact reduction by the SDN approach. The SDN approach utilizes four different prevention techniques as countermeasures. Scenarios from discrete manufacturing are used to evaluate the approach. The approach reduces the average impact of the selected cyber-attacks from 82.9% to 98.1%.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124652293","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976097
Robert F. Maack, Hasan Tercan, Tobias Meisen
The assembly line production of electrical consumer products is a highly streamlined process in which the product quality is continuously evaluated using automated checks. However, some products include manual processing due to customer requests that are not covered by standardized production plans. In such situations, quality issues frequently remain unnoticed leading to high reversal costs and customer dissatisfaction. We address this problem in a practical case study for a specific product family that is subject to highly versatile and error-prone configurations of externally exposed hardware connectors. In this setting, the worker must be visually assisted such that potentially faulty configurations are highlighted. Therefore, we investigate the applicability of state-of-the-art approaches for Anomaly Detection (AD) and Anomaly Localization (AL) on image data using pre-trained models and normalizing flows and compare against baseline Variational Auto-Encoders (VAEs). We show that those methods are not only applicable to well-established benchmarks on industrial image data but also have the potential to be used in a practical use case.
{"title":"Deep Learning based Visual Quality Inspection for Industrial Assembly Line Production using Normalizing Flows","authors":"Robert F. Maack, Hasan Tercan, Tobias Meisen","doi":"10.1109/INDIN51773.2022.9976097","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976097","url":null,"abstract":"The assembly line production of electrical consumer products is a highly streamlined process in which the product quality is continuously evaluated using automated checks. However, some products include manual processing due to customer requests that are not covered by standardized production plans. In such situations, quality issues frequently remain unnoticed leading to high reversal costs and customer dissatisfaction. We address this problem in a practical case study for a specific product family that is subject to highly versatile and error-prone configurations of externally exposed hardware connectors. In this setting, the worker must be visually assisted such that potentially faulty configurations are highlighted. Therefore, we investigate the applicability of state-of-the-art approaches for Anomaly Detection (AD) and Anomaly Localization (AL) on image data using pre-trained models and normalizing flows and compare against baseline Variational Auto-Encoders (VAEs). We show that those methods are not only applicable to well-established benchmarks on industrial image data but also have the potential to be used in a practical use case.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128399897","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976067
Yuan Li, Luiz Cesar Gualberto Veras Inoue, R. Sinha
Unknown and unplanned downtime events during production cause significant disruption and loss of productivity. Investigating, identifying and addressing such events is a pressing need. The primary objective of this study is to examine downtime, performance loss, and quality control in the manufacturing process. Specifically, we propose a solution that provides real-time data processing and visualization of the factory floor. This solution was implemented for a major food manufacturer based in New Zealand. The company provided historical data covering over six years of operation and access to real-time data through their Industrial Internet of Things (IIoT) systems executing on Programmable Logic Controllers (PLCs). Our solution is an Overall Equipment Effectiveness (OEE) standardized Supervisory Control and Data Acquisition (SCADA) system that visualizes the manufacturing process in real-time. Analysis of the data collected during this research shows that by implementing the OEE and employing shift adjustment, there was a significant increase in production output. OEE can help improve manufacturing performance by pinpointing the root of the loss of performance in all areas monitored.
{"title":"Real-time OEE visualisation for downtime detection","authors":"Yuan Li, Luiz Cesar Gualberto Veras Inoue, R. Sinha","doi":"10.1109/INDIN51773.2022.9976067","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976067","url":null,"abstract":"Unknown and unplanned downtime events during production cause significant disruption and loss of productivity. Investigating, identifying and addressing such events is a pressing need. The primary objective of this study is to examine downtime, performance loss, and quality control in the manufacturing process. Specifically, we propose a solution that provides real-time data processing and visualization of the factory floor. This solution was implemented for a major food manufacturer based in New Zealand. The company provided historical data covering over six years of operation and access to real-time data through their Industrial Internet of Things (IIoT) systems executing on Programmable Logic Controllers (PLCs). Our solution is an Overall Equipment Effectiveness (OEE) standardized Supervisory Control and Data Acquisition (SCADA) system that visualizes the manufacturing process in real-time. Analysis of the data collected during this research shows that by implementing the OEE and employing shift adjustment, there was a significant increase in production output. OEE can help improve manufacturing performance by pinpointing the root of the loss of performance in all areas monitored.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128442528","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976090
M. Hittawe, S. Langodan, Ouadi Beya, I. Hoteit, O. Knio
Prediction of Surface Sea Temperature (SST) is of great importance in seasonal forecasts in the region and beyond, mainly due to its significant role in global atmospheric circulation. On the other hand, SST predicting from given multivariate sequences using historical ocean variables is vital to investigate how SST physical phenomena generated. This paper seeks to significantly improve the prediction of Surface Sea Temperature (SST) by combining two machine learning methodologies: short-term memory networks (LSTM) added to Gaussian Process Regression (GPR). We developed a data-driven approach based on deep learning and GPR modeling to improve the prediction of SST levels in the red sea based on meteorological variables, including the hourly wind speed (WS), air temperature at 2m (T2), and relative humidity (RH) variables. The coupled GPR-LSTM model may potentially carry both flexibility and feature extraction capacity, which could describe temporal dependencies in SST time-series and improve the prediction accuracy of SST. It is necessary to indicate that these types of hybrid-based approach architectures have not used before in SST time-series prediction, so it is a new approach to deal with these types of problems. The results demonstrate a significant improvement when this hybrid model is compared to LSTM and the most frequently used ensemble learning models.
{"title":"Efficient SST prediction in the Red Sea using hybrid deep learning-based approach","authors":"M. Hittawe, S. Langodan, Ouadi Beya, I. Hoteit, O. Knio","doi":"10.1109/INDIN51773.2022.9976090","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976090","url":null,"abstract":"Prediction of Surface Sea Temperature (SST) is of great importance in seasonal forecasts in the region and beyond, mainly due to its significant role in global atmospheric circulation. On the other hand, SST predicting from given multivariate sequences using historical ocean variables is vital to investigate how SST physical phenomena generated. This paper seeks to significantly improve the prediction of Surface Sea Temperature (SST) by combining two machine learning methodologies: short-term memory networks (LSTM) added to Gaussian Process Regression (GPR). We developed a data-driven approach based on deep learning and GPR modeling to improve the prediction of SST levels in the red sea based on meteorological variables, including the hourly wind speed (WS), air temperature at 2m (T2), and relative humidity (RH) variables. The coupled GPR-LSTM model may potentially carry both flexibility and feature extraction capacity, which could describe temporal dependencies in SST time-series and improve the prediction accuracy of SST. It is necessary to indicate that these types of hybrid-based approach architectures have not used before in SST time-series prediction, so it is a new approach to deal with these types of problems. The results demonstrate a significant improvement when this hybrid model is compared to LSTM and the most frequently used ensemble learning models.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126975222","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976159
Luis Alberto Cruz Salazar, B. Vogel‐Heuser
“Artificial Intelligence in Industry 4.0”, a technical report published by the working groups "Technological and Application Scenarios" and "Artificial Intelligence" (AI) of the Industry 4.0 (I4.0) platform, presents an innovative Industrial AI concept. Above all, it concludes that I4.0 experts and scientists must become accustomed to the behavior of autonomous AI-controlled systems, collaborate with them and comply with learnability requirements (predictability). Industrial AI instantly raises a set of concerns about existing norms and new standardizations. These frequently provide guidelines and, in some cases, offer procedures and implementations using design patterns. One way to produce AI in I4.0 systems is through Industrial Agents (IAs) due to their natural autonomy and additional intelligent characteristics, e.g., reactiveness, proactiveness, and human cooperativeness. Multi-Agent Systems (MASs) are particularly well suited for representing distributable AI that can develop I4.0 components being applied to various I4.0 scenarios. Considering the properties of IAs and the corresponding standards, an MAS architecture is used to understand the aspects of the flexible, intelligent, and automated Cyber-Physical Production System (CPPS). This article proposes a predictive IA for I4.0 (Agent4.0) to an agent-based CPPS architecture, leveraging IA design patterns and logical structure for implementing MAS. As a result, relevant standardized IA design patterns for I4.0 show how MAS can be created with the help of the Industrial AI requirements and Agent4.0 skills (functions) identified.
{"title":"Industrial Artificial Intelligence: A Predictive Agent Concept for Industry 4.0","authors":"Luis Alberto Cruz Salazar, B. Vogel‐Heuser","doi":"10.1109/INDIN51773.2022.9976159","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976159","url":null,"abstract":"“Artificial Intelligence in Industry 4.0”, a technical report published by the working groups \"Technological and Application Scenarios\" and \"Artificial Intelligence\" (AI) of the Industry 4.0 (I4.0) platform, presents an innovative Industrial AI concept. Above all, it concludes that I4.0 experts and scientists must become accustomed to the behavior of autonomous AI-controlled systems, collaborate with them and comply with learnability requirements (predictability). Industrial AI instantly raises a set of concerns about existing norms and new standardizations. These frequently provide guidelines and, in some cases, offer procedures and implementations using design patterns. One way to produce AI in I4.0 systems is through Industrial Agents (IAs) due to their natural autonomy and additional intelligent characteristics, e.g., reactiveness, proactiveness, and human cooperativeness. Multi-Agent Systems (MASs) are particularly well suited for representing distributable AI that can develop I4.0 components being applied to various I4.0 scenarios. Considering the properties of IAs and the corresponding standards, an MAS architecture is used to understand the aspects of the flexible, intelligent, and automated Cyber-Physical Production System (CPPS). This article proposes a predictive IA for I4.0 (Agent4.0) to an agent-based CPPS architecture, leveraging IA design patterns and logical structure for implementing MAS. As a result, relevant standardized IA design patterns for I4.0 show how MAS can be created with the help of the Industrial AI requirements and Agent4.0 skills (functions) identified.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115029671","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976080
A. Abdallah, I. Fan
Over the past decade, advancement in computing and information technology has led to digitization of aircraft operations and maintenance standards and processes. Aircraft maintenance records are increasingly being stored in maintenance repair and overhaul (MRO) information systems. However, harmonisation and interoperability between heterogenous MRO systems has emerged as a key challenge in integrating maintenance records over the lifespan of an aircraft. This adds to the time and cost to maintain aircraft continuous airworthiness, configuration management and valuation. The role of ontologies for knowledge management provides an effective means of using formal semantics for data integration and improved knowledge representation of a domain. In this paper, we examine the application of ontologies for integrating heterogenous aircraft maintenance records. We investigate the key challenges of developing ontology-based applications in practice and reflected on the research efforts needed to counter the challenges. We described 3 research directions and proposed an integrated approach — Agile Development for Ontology-Based Applications (ADOBA) by taking a fine-grained look at the gap between ontological and software engineering methodologies. The proposed approach is part of a research work aimed at creating and validating an ontology model for aircraft through-life support and developing prototypical demonstration as part of the Cranfield Digital Aviation initiative.
{"title":"Towards Building Ontology-Based Applications for Integrating Heterogeneous Aircraft Maintenance Records","authors":"A. Abdallah, I. Fan","doi":"10.1109/INDIN51773.2022.9976080","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976080","url":null,"abstract":"Over the past decade, advancement in computing and information technology has led to digitization of aircraft operations and maintenance standards and processes. Aircraft maintenance records are increasingly being stored in maintenance repair and overhaul (MRO) information systems. However, harmonisation and interoperability between heterogenous MRO systems has emerged as a key challenge in integrating maintenance records over the lifespan of an aircraft. This adds to the time and cost to maintain aircraft continuous airworthiness, configuration management and valuation. The role of ontologies for knowledge management provides an effective means of using formal semantics for data integration and improved knowledge representation of a domain. In this paper, we examine the application of ontologies for integrating heterogenous aircraft maintenance records. We investigate the key challenges of developing ontology-based applications in practice and reflected on the research efforts needed to counter the challenges. We described 3 research directions and proposed an integrated approach — Agile Development for Ontology-Based Applications (ADOBA) by taking a fine-grained look at the gap between ontological and software engineering methodologies. The proposed approach is part of a research work aimed at creating and validating an ontology model for aircraft through-life support and developing prototypical demonstration as part of the Cranfield Digital Aviation initiative.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115137028","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 : 2022-07-25DOI: 10.1109/INDIN51773.2022.9976123
K. Iwamoto
In order to solve the shortage of skilled workers, a training / support system that can present task instructions according to the work situation is being developed. To achieve this, a display that presents high-resolution stereoscopic images with the naked eye and a system that presents haptic sensations have been developed. By using this system, it is possible not only to instruct tasks with text information, but also to present virtual objects with a high sense of reality and to handle virtual objects using work tools. With this function, it is possible to construct an environment in which real and virtual objects coexist and treat both objects in the same way. It feels more realistic than an environment where everything is composed of virtual objects. This makes it possible to perform early task training even if all the parts are not yet available. Alternatively, even at the design stage, the design can be changed while checking the ease of assembling and maintaining the product. In this paper, the environment where real objects and virtual objects coexist is discussed. Then, the prototype system for realizing it is introduced, and the results of evaluation experiments in which both objects are handled by the same operation are reported.
{"title":"Mixed Environment of Real and Virtual Objects for Task Training using Binocular Video See-through Display and Haptic Device","authors":"K. Iwamoto","doi":"10.1109/INDIN51773.2022.9976123","DOIUrl":"https://doi.org/10.1109/INDIN51773.2022.9976123","url":null,"abstract":"In order to solve the shortage of skilled workers, a training / support system that can present task instructions according to the work situation is being developed. To achieve this, a display that presents high-resolution stereoscopic images with the naked eye and a system that presents haptic sensations have been developed. By using this system, it is possible not only to instruct tasks with text information, but also to present virtual objects with a high sense of reality and to handle virtual objects using work tools. With this function, it is possible to construct an environment in which real and virtual objects coexist and treat both objects in the same way. It feels more realistic than an environment where everything is composed of virtual objects. This makes it possible to perform early task training even if all the parts are not yet available. Alternatively, even at the design stage, the design can be changed while checking the ease of assembling and maintaining the product. In this paper, the environment where real objects and virtual objects coexist is discussed. Then, the prototype system for realizing it is introduced, and the results of evaluation experiments in which both objects are handled by the same operation are reported.","PeriodicalId":359190,"journal":{"name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120925082","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：