查看更多>>摘要：? 2021 Elsevier B.V.This article has been retracted: please see Elsevier Policy on Article Withdrawal (https://www.elsevier.com/about/our-business/policies/article-withdrawal). This article has been retracted at the request of the Editor-in-Chief. The article has been retracted due to overlap with the paper below by the same authors in applying a similar model to solve different engineering problems. It has been deemed the papers display excessive similarity in model, structure and several figures to the extent that this does not warrant two publications. All the authors have agreed to retract this article.
查看更多>>摘要：? 2021Predictive maintenance, quality management, and zero-defect manufacturing are among the most prominent smart manufacturing use cases in the Industry4.0 era. Nevertheless, the development of such systems is still challenging because of the need to integrate multiple fragmented data sources, to apply advanced machine learning techniques for multi-objective optimizations, and to implement configurable digital twins that can flexibly adapt to changing industrial configurations. This paper presents the architecture, design, practical implementation, and evaluation of an end-to-end platform that addresses these challenges. The platform provides the means for collecting, managing, and routing data streams from heterogeneous cyber physical production systems, in configurable and interoperable ways. Moreover, it supports advanced data analytics by means of a novel machine learning framework that leverages quantitative rule mining. The presented platform has been successfully deployed in various industrial settings and has been positively evaluated in terms of its ability to accelerate application development, reduce unscheduled downtimes, provide increased Overall Equipment Efficiency (OEE), compute production process parameter configurations that lower the percentage of product defects, and predict product defects before they occur.
查看更多>>摘要：? 2021 Elsevier B.V.This paper is about modeling vulnerability patch prioritization in complex and interdependent systems such as the operational technology or Industrial Control Systems (ICSs). In these environments, often patching is neither automated nor cost-effective, demanding large manual administrative efforts in a timely manner with as much less system downtime as possible. The impact or risk of a vulnerability could depend on the network characteristics, context that defines the vulnerability and circumstances that led to it. Moreover, not all vulnerabilities are always exploited by the attackers; and not all vulnerabilities can be patched due to the resource constraints such as people, infrastructure, tools and time available to patch every vulnerability. Also, ICSs such as SCADA have strict requirements of system uptime and availability. These constraints place significant importance on the patch prioritization of networks and devices, which needs to be strategic and efficient. Addressing this challenge in the prioritization of patches in ICSs, we present SmartPatch a three-step, systematic patch prioritization method to address patch sequencing in an interdependent and complex network. SmartPatch is a seamless integration of system modeling, risk management and game theory. SmartPatch utilizes prior knowledge, learnings and experiences about the system dynamics and identifies an efficient and effective defensive strategy. The framework's output is a patch prioritization strategy that is cost-constrained and reduces the impact of the possible attacks to a large extent. We propose a security metric called the “Residual Impact Score” (RIS) to analyze the impact of all discovered vulnerabilities on the system. We validate the applicability of SmartPatch by considering the case study of an interdependent, complex SCADA chain in the smart grid system using the IEEE 5-Bus system. Our comparative analysis of the proposed approach with state-of-the-art approaches demonstrates that SmartPatch reduces RIS by a faster rate i.e. after each iteration, the RIS value for SmartPatch is the least.
查看更多>>摘要：? 2022 Elsevier B.V.With the advent of Industry 4.0, failure anticipation is becoming one of the key objectives in industrial research. In this context, predictive maintenance is an active research area for various applications. This paper presents an approach to predict high importance errors using log data emitted by machine tools. It uses the concept of bag to summarize events (or errors) provided by remote machines, available within log files. The idea of bag is inspired by the Multiple Instance Learning paradigm introduced by Dietterich et al. However, our proposal follows a different strategy to label bags, that we wanted as simple as possible. Three main setting parameters are defined to build the training set allowing the model to fine-tune the trade-off between early warning, historical data informativeness and time accuracy. The effectiveness of the approach is demonstrated using a real industrial application where failures can be predicted up to seven days in advance thanks to a classification model.
查看更多>>摘要：? 2022 The AuthorsThe emergence of IoT has propelled the traditionally known Product-Service System (PSS) to be characterized by smarter technologies, enabling them to collect and process data from the operational stage and facilitate communication between the customer and the provider. Commonly referred to as Smart Product-Service Systems (Smart PSS), these systems promise to create value at a personal level by collecting and effectively utilizing the operational data. However, one of the fundamental challenges is the lack of awareness as to what kind of data can be collected from the operational stage and what can be achieved from this data. This paper systematically reviews scientific literature to underline the kind of data being collected from the operational stage, the purposes being achieved from that data, and how they lead to value creation. The systematic review of 60 representative studies enabled the definition of the operational scenario that comprises 4 dimensions of data and 10 classes of data within these dimensions to generically identify what kind of data is being collected. The intend presented by various authors led to the generalization of 5 themes that target different purposes of collecting data. Further, the papers were classified with regards to functional or non-functional requirements to see how data in different approaches are leveraged for value creation. Finally, the discussion highlights the current gaps in the literature and raises several opportunities for future contributions.
查看更多>>摘要：? 2022 Elsevier B.V.In the age of the industrial internet, manufacturers of industrial equipment compete through the offering of digital product-service solutions. These are built integrating smart connected products (SCP) and data-driven services, such as remote control, data analytics, diagnostic and predictive maintenance services. These services strongly influence the value created in the customer context and, consequently, the attractiveness of the integrated offering. A great issue remains about how these services should be designed by manufacturers of industrial equipment. Through integrative literature review over multiple domains, this paper provides a conceptual model that shows: i) which benefits can be created from smart product-service systems offerings at both business and individual level, in the customer organization; ii) how these benefits are linked to the choices about design and delivery of data-driven services. In respect to the second point, this study merges service science theory and data management to show how the data autonomously collected by SCP can be transformed into insights that deliver value, as far as the customer and the supplier interact, share resources and apply their specialized competences. Applying these concepts, we elaborate four exemplary archetypes of data-driven services that differ in respect to the kind of customer-supplier interactions along this data life cycle, bringing these options to different kind of customer value co-creation. Linking the mechanisms of value co-creation to design options of data-driven services, this paper has therefore notably implications for the research on servitization and smart product-service systems.
查看更多>>摘要：? 2022 Elsevier B.V.Integrity and availability attacks can cause serious damage to modern industrial cyber-physical systems (ICPS). It is critical to detect and identify these attacks promptly and accurately. This paper investigates the anomaly detection for ICPS in the process industry. Three typical attacks, the Stuxnet-like, denial-of-service, and false data injection, are taken as specific defense targets. We propose to detect anomalies by quantifying the dynamic variations of generalized model implied by operating data, and present a mode division as the novel detection framework. The subspace technique and a quantization method for the amplitude-frequency characteristic deviation are employed to design the detector, which can be deployed independently in the active ICPS and does not cause any loss of control performance. An attack-defense experimental platform is developed to evaluate the detector under the attack scenarios of interest. The results show that the detector can detect any of the three attacks in a maximum of 28 s after the attack onset, and that these attacks can be distinguished by combining the state estimation residuals and system errors.
查看更多>>摘要：? 2022 Elsevier B.V.Knowledge graph (KG) is an effective tool for knowledge management, particularly in the architecture, engineering and construction (AEC) industry, where knowledge is fragmented and complicated. However, research on KG updates in the industry is scarce, with most current research focusing on text-based KG updates. Considering the superiority of visual data over textual data in terms of accuracy and timeliness, the potential of computer vision technology for explicit relationship extraction in KG updates is yet to be explored. This paper combines zero-shot human-object interaction detection techniques with general KGs to propose a novel framework called Image2Triplets that can extract explicit visual relationships from images to update the construction activity KG. Comprehensive experiments on the images of architectural decoration processes have been performed to validate the proposed framework. The results and insights will contribute new knowledge and evidence to human-object interaction detection, KG update and construction informatics from the theoretical perspective.
查看更多>>摘要：? 2022 Elsevier B.V.Cyber security risks are considered to be one of the foremost challenges that face organisations intending to leverage the benefits of the Smart Manufacturing paradigm. Due to the rising number of cyber-attacks that target critical Industrial Cyber-Physical Systems (ICPS), organisations are required to consider such attacks as severe business risks. Therefore, identifying potential cyber threats and analysing their impacts is crucial to business continuity planning. This paper proposes a structured threat modelling approach for ICPS that enables prediction and analysis of cyber risks to protect industrial assets from potential cyber-attacks. The method involves classifying ICPS assets based on criticality, and then analysing the cyber security vulnerabilities, threats, risks, impacts, and countermeasures. The proposed methodology enables end-to-end threat modelling through the development of a new framework that is integrated with VueOne digital twin tool to model and analyse threats throughout ICPS lifecycle, identifying cyber risks and proposing mitigation controls. Moreover, it uses meta-data extracted from VueOne tool to automatically generate the software code and hardware configurations that can be directly deployed on ICPS assets in order to implement the countermeasures, thereby protecting them from these potential cyber-attacks. The proposed solution has been implemented on a Festo test rig prototype production line.
查看更多>>摘要：? 2022 The Author(s)Process mining aims to improve operational processes in a data-driven manner. To this end, process mining offers methods and techniques for systematically analyzing event data. These data are generated during the execution of processes and stored in organizations' information systems. Process discovery, a key discipline in process mining, comprises techniques used to (automatically) learn a process model from event data. However, existing algorithms typically provide low-quality models from real-life event data due to data-quality issues and incompletely captured process behavior. Automated filtering of event data is valuable in obtaining better process models. At the same time, it is often too rigorous, i.e., it also removes valuable and correct data. In many cases, prior knowledge about the process under investigation can be additionally used for process discovery besides event data. Therefore, a new family of discovery algorithms has been developed that utilizes domain knowledge about the process in addition to event data. To organize this research, we present a literature review of process discovery approaches exploiting domain knowledge. We define a taxonomy that systematically classifies and compares existing approaches. Finally, we identify remaining challenges for future work.
NSTL
Elsevier