首页期刊导航|Computers in Industry
期刊信息/Journal information
Computers in Industry
Elsevier Science B.V.
Computers in Industry

Elsevier Science B.V.

0166-3615

Computers in Industry/Journal Computers in IndustrySCIAHCIISTPEI
正式出版
收录年代

    AFMT: Maintaining the safety-security of industrial control systems

    Kumar, RajeshNarra, BhaveshKela, RohanSingh, Siddhant...
    16页
    查看更多>>摘要：Modern day industrial control systems are overwhelmingly complex. These systems feature intricate interactions between the cyber and the physical components. At the same time, they need to be trustworthy and deliver their services continuously. Underpinning, a crucial industrial activity to ensure the dependability of such critical systems is through timely maintenance, inspections and repairs. Several strategies exist here: "fix it when it breaks" (reactive maintenance), monitor and maintain a system in pre-established time intervals (preventive maintenance), preventive action based upon detected symptoms of failures condition-based maintenance (CBM), etc. In literature, the question of optimal maintenance frequency have been a subject of intense study. However, most papers, do not take information security aspects into account. This paper provides an automated tool-supported quantitative risk analysis framework, Attack-FaultMaintenance Trees, AFMTs, that will enable practitioners to make informed choice on: (a) identifying the critical component(s) necessary for uninterrupted systems; (b) a decision support system that will provide informed choices on policy measures, countermeasures and safeguards that will reduce the disruptions; (c) run the "what-if" scenarios to find the optimal trade-offs between system attributes (safety, security, usability and maintenance). The front-end of the tool is a domain-specific language geared to represent the system architecture using graphical-constructs. The back-end of the framework remains hidden to the practitioner. It consists of a mathematical engine based on statistical model-checking techniques. A case study of oil-pipeline is used to demonstrate the efficacy of our framework. (C) 2021 Elsevier B.V. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    A lightweight detector based on attention mechanism for aluminum strip surface defect detection

    Ma, ZhuxiLi, YiboHuang, MinghuiHuang, Qianbin...
    14页
    查看更多>>摘要：Many problems associated with the visual inspection of surface defects on aluminum strips remain to be solved, including the inapplicability of large-scale algorithm and computing equipment on site, and the balance between detection speed and accuracy. This paper proposes a novel and lightweight detection method based on attention mechanism, and focuses on the industrial application of aluminum strip defect inspection. On the basis of the YOLOv4 framework, the backbone network YOLO-DCSAM is constructed to utilize depthwise separable convolution and to design a parallel dual-channel attention module. It compresses the network scale and better enhances the effect of different channels on the feature map. At the same time, the neck network is redesigned and lightweighted for feature fusion, which can increase the receptive field and further simplify the network through SPPM-PANet module. Moreover, by optimization measure, such as the anchor box size of the cluster and improved loss function, the pertinence of model is strengthened to defect objects. The proposed method is trained and tested on the straightening aluminum strip surface data collected from the cold rolling workshop of Liuzhou Yinhai Aluminum Co., Ltd. Experiments show that the proposed method achieves a mAP of 96.28%, thereby outperforming the original YOLOv4 model. Moreover, as compared with YOLOv4, the model volume is reduced by 83.38% and the detection speed is increased by 3 times, thereby exhibiting the potential for real-time detection on the embedded systems. (C) 2021 Elsevier B.V. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    A framework for data-driven digitial twins of smart manufacturing systems

    Friederich, JonasFrancis, Deena P.Lazarova-Molnar, SanjaMohamed, Nader...
    13页
    查看更多>>摘要：Adoption of digital twins in smart factories, that model real statuses of manufacturing systems through simulation with real time actualization, are manifested in the form of increased productivity, as well as reduction in costs and energy consumption. The sharp increase in changing customer demands has resulted in factories transitioning rapidly and yielding shorter product life cycles. Traditional modeling and simulation approaches are not suited to handle such scenarios. As a possible solution, we propose a generic data-driven framework for automated generation of simulation models as basis for digital twins for smart factories. The novelty of our proposed framework is in the data-driven approach that exploits advancements in machine learning and process mining techniques, as well as continuous model improvement and validation. The goal of the framework is to minimize and fully define, or even eliminate, the need for expert knowledge in the extraction of the corresponding simulation models. We illustrate our framework through a case study. (C) 2021 The Author(s). Published by Elsevier B.V.
      原文链接:
    • NSTL
    • Elsevier

    A new approach to 3D pattern-making for the apparel industry: Graphic coding-based localization

    Lei, GeLi, Xiaohui
    11页
    查看更多>>摘要：Pattern making is one of the most vital parts of product development in the apparel or other textile industry. However, the traditional 2D pattern-making method is tedious, abstract, and time-consuming. Although several 2D techniques are available in the current research for automatic pattern generation, most of them have been limited to fixed styles. To solve the problem in pattern making, here a new 3D pattern making approach based on graphic coding is proposed. The textile with coded graphics as a flexible coordinate is used to establish the mapping relationship between 2D patterns and 3D garments, which allows a draped 3D shape to a 2D plane. The images with micro encoding graphics of key points are acquired to obtain 2D localization information from the fabric in 3D form. Based on image processing and encoding/decoding, the pattern can be generated according to the coordinate value of key points. The approach realizes the intuitive, accurate and rapid garment pattern generation, which offers possibilities for fashion designers or other users with little expertise in 2D pattern drafting to make patterns in any constructions. Also, as it can be effective in enhancing the efficiency and accuracy of MTM (Made-to-Measure). In addition to the apparel industry, the method also shows great application potential in shoes, home textiles, flexible digital tablets, and other related areas. (C) 2021 Elsevier B.V. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    AYOLOv3-Tiny: An improved convolutional neural network architecture for real-time defect detection of PAD light guide plates

    Yao, JiahuiLi, Junfeng
    14页
    查看更多>>摘要：Light guide plates (LGPs) are the main component of the backlight unit of liquid crystal display (LCD) devices, and defective LGPs directly affect the display effect of LCDs. In view of the features of portable Android device (PAD) LGP images, such as complex texture background, low contrast, different defect sizes and various defect types and their optical properties, light-spot distribution, defect formation principle and imaging characteristics, this paper proposes an AYOLOv3-Tiny network for the defect detection of LGPs. First, by combining overlapping pooling and the spatial attention mechanism, the overlapping pooling spatial attention module (OSM) is constructed to replace the traditional convolution operation of the YOLOv3-Tiny backbone network. Overlapping pooling can improve the accuracy and prevent overfitting, and the spatial attention mechanism can help the network better extract defect features. Second, a dilated convolution module (DCM) is constructed in the detection branch. The module can expand the receptive field of the convolution kernel and improve the detection ability of large defects by integrating the dilated convolution into the residual network structure. Third, a large number of experiments based on the self-built dataset PAD LGP SDD are carried out. The experimental results show that the mean average precision (mAP) and F1-score of the LGP defect detection system can reach 99.50% and 99.61% respectively, and the detection speed can reach 144 fps. Finally, by testing on the PAD LGP images with defects, it is verified that the proposed network meets the application requirements of high precision and real-time online detection of PAD LGP images. (C) 2021 Elsevier B.V. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    A framework for Seveso-compliant cyber-physical security testing in sensitive industrial plants

    Coppolino, LuigiD'Antonio, SalvatoreGiuliano, VincenzoMazzeo, Giovanni...
    15页
    查看更多>>摘要：The InfraStress-EU framework was defined in the context of the H2020 project InfraStress, to provide operators of sensitive industrial sites - i.e., industrial plants where dangerous substances are handled and are thus subject to the Seveso III Directive (2012/18/EU) - with a technically sound approach and an accompanying simulation tool for the prevention of accidents. The framework enables reliable and effective cybersecurity testing of industrial infrastructures, with the ultimate goal of improving the resilience of critical processes to cyber-physical attacks. It takes a cue from the TIBER-EU initiative, of which it extends the core penetration testing phases to "hybrid"-meaning consisting of a mix of real and simulated components-setups. By doing so, it relieves operators from their main concern, i.e., the risk of compromising the normal functioning of control systems when performing key security testing activities, such as gathering information on cyber-threats and/or trying out alternative response strategies. InfraStress-EU was implemented and evaluated in close cooperation with five operators, who contributed the requirements of real setups in their respective industrial sectors. (C) 2021 Elsevier B.V. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    A collaborative knowledge-based method for the interactive development of cabin systems in virtual reality

    Fuchs, MaraBeckert, FlorianBiedermann, JoernNagel, Bjorn...
    10页
    查看更多>>摘要：Progressive digitization in the development phase of systems is leading to shorter development times and lower costs. At the same time, the interactions in more complex systems are increasing and become more nested, which affects the understanding of system dependencies for humans as well as modeling these. This results in the challenge of digitizing the knowledge (rules, regulations, requirements, etc.) required to describe the system and its interrelationships. An example of such a system is the aircraft. In practice, usually, the technical design of the cabin and its systems is done separately from the preliminary aircraft design and the cabin results will be integrated late in the aircraft development process. In this paper, a proposal is given for a conceptual design method that enables a cabin systems layout based on preliminary aircraft design data (parameter set). Therefore, a central data model is developed that links cabin components to several disciplines to enable an automated layout. Here, knowledge is stored in an ontology. Linking the ontology with design rules and importing external parameters, missing information needed for preliminary design of cabin systems can be generated. The design rules are based on requirements, safety regulations as well as expert knowledge for design interpretation that has been collected and formalized. Using the ontology, an XML data structure can be instantiated which contains all information about properties, system relationships and requirements. So, the metadata and results of heterogenous domain-specific models and software tools are accessible for all experts of the layout process in a holistic manner and ensure data consistency. Using this XML data structure, a 3D virtual cabin mockup is created in which users have the possibility to interact with cabin modules and system components via controllers. This virtual development platform enables an interaction with complex product data sets like the XML file by visualizing metadata and analysis results along with the cabin geometry, making it even better comprehensible and processable for humans. So, various new cabin system designs can be iterated, evaluated, and optimized at low cost before the concepts are validated in a real prototype. For this, the virtual environment provides a platform that integrates all related disciplines, experts, research partners or the entire supply chain to improve communication among all stakeholders by directly participating and intervening in the evaluation and optimization process. Moreover, the use of VR is being investigated as a new technology in pre-design phase to exploit the potential of knowledge acquisition in immersive environments early in the development stage. (C) 2021 The Authors. Published by Elsevier B.V.
      原文链接:
    • NSTL
    • Elsevier

    Network-based - Quality Function Deployment (NB-QFD): The combination of traditional QFD with network science approach and techniques

    Kulcsar, EdinaGyurika, Istvan GaborCsiszer, Tamas
    12页
    查看更多>>摘要：This paper aims to introduce a possible way of applying network science in Quality Function Deployment by supporting a CNC machine tool development project. Our central thesis was that by extending the QFD methodology with network assessment techniques, product developers could make more established decisions. Our work has started with an online survey, in which participants were asked to define and rank general requirements for CNC machines. Then some of the essential technical parameters were described by CNC experts. Finally, the answers' evaluation was then performed using traditional QFD methodology and the one combined with network research. We showed that the newly developed network-based QFD method offers better visualization of the matrixes. We proved by introducing new indicators such as the significance, sensitivity, and influence of the technical parameters that, also considering the correlation between the technical parameters when calculating their importance, the directions for development can be defined more precisely. Based on the results, we concluded that Network-Based - QFD could support the setting of development goals with a much more detailed analysis. (C) 2021 The Author(s). Published by Elsevier B.V.
      原文链接:
    • NSTL
    • Elsevier

    Circular production and maintenance of automotive parts: An Internet of Things (IoT) data framework and practice review

    Okorie, O.Emmanouilidis, C.Oyekan, J.Turner, C....
    15页
    查看更多>>摘要：The adoption of the Circular Economy paradigm by industry leads to increased responsibility of manufacturing to ensure a holistic awareness of the environmental impact of its operations. In mitigating negative effects in the environment, current maintenance practice must be considered for its potential contribution to a more sustainable lifecycle for the manufacturing operation, its products and related services. Focusing on the matching of digital technologies to maintenance practice in the automotive sector, this paper outlines a framework for organisations pursuing the integration of environmentally aware solutions in their production systems. This research sets out an agenda and framework for digital maintenance practice within the Circular Economy and the utilisation of Industry 4.0 technologies for this purpose. (C) 2022 The Authors. Published by Elsevier B.V.
      原文链接:
    • NSTL
    • Elsevier

    Digital twin-enabled smart modular integrated construction system for on-site assembly

    Jiang, YishuoLi, MingGuo, DaqiangWu, Wei...
    18页
    查看更多>>摘要：Modular Integrated Construction (MiC) is a game-changing approach with enhanced quality, productivity, and sustainability, which transforms cast-in-situ into on-site assembly of prefabricated modules. On-site assembly is an uncertain and complex stage in MiC scenario, due to high variability of outside conditions, organization of multi-contractors, and geographic dispersion of activities. Information and Communication Technology (ICT) is adopted to support the reengineering of on-site assembly, however, on-site resources couldn't be efficiently and consistently digitalized and the cyber-physical interoperation is fragmented and out-of-date. Digital twin is a key enabler of ICT revolution to address these challenges towards automated and intelligent construction. This paper introduces a digital twin-enabled smart MiC system (DT-SMiCS) with a robotic demonstration for reengineered on-site assembly. On-site resources are converted into Smart MiC Objects (SMiCOs) attaching with UWB and RFID devices to collect and integrate real-time nD data, such as identity, location, cost, and construction progress. Digital twins of SMiCOs with similar properties and behaviors are instantiated from unified object-oriented templates for item-level mapping and characterizing. Through smart mobile gateway, various on-site resources and activities could be real-timely interoperated with their corresponding digital twins. Cloud-based services are provided for real-time monitoring through high-fidelity virtual models, and remote control with automatic navigations. A testbed robotic demonstration is conducted to verify DT-SMiCS for reengineered on-site assembly. (C) 2021 Published by Elsevier B.V.
      原文链接:
    • NSTL
    • Elsevier