查看更多>>摘要：? 2022 Elsevier B.V.This work deals with the customer-supplier relationship and concerns offer definition in Engineer-To-Order situations (ETO), by adopting the supplier point of view. In such cases, when the offer definition relies simply on key design choices without a detailed design, there is a specific risk (ETO-specific risk) that customer expectations cannot be fulfilled. This kind of risk is in addition to the conventional risks (non ETO-specific risk) involved in any delivery process (machine break down, resource not available, scrapped part…). In order to minimize the supplier risk of not being able to complete the offer as accepted and contracted by the customer, a knowledge-based system can be used to assist risk engineering. Consequently, this article proposes two interrelated knowledge modeling contributions. Firstly, a risk knowledge model which, when implemented in a knowledge-based system that supports risk characterization and risk treatment by using knowledge re-use techniques, is proposed and discussed. Secondly, two knowledge typologies for risk characterizations and treatments (both for ETO and non-ETO situations) in order to support risk knowledge, identification and modeling are also proposed and discussed. These contributions are innovative and groundbreaking in terms of both academics and applications: they provide a formal model to structure risk knowledge and a first list of risks and treatments to be taken into account in ETO and non ETO situations. After an introduction that presents the research gap, our objectives and an analysis of related works, our two contributions are described in two sections with respect to ISO31000 recommendations. The first section covers risk identification and evaluation while the second deals with risk treatments.
查看更多>>摘要：? 2022 Elsevier B.V.Programmable Logic Controllers (PLCs) play a prominent role in critical infrastructures, such as power grid, transportation, and petrochemical industry. Suffering from data tampering attacks, PLCs are fragile as the forged data could cause significant damage to industrial machines and human safety. However, less attention has been paid to develop resilience mechanisms for automatically recovering PLCs systems from anomalous states under malicious attacks. In this work, we present the first resilience approach for protecting PLCs against data tampering attacks. The key observation we leverage is that the programmable characteristic of a PLC enables a defender to ensure its data integrity by embedding security mechanism into its control logic. In particular, we design a novel data authentication mechanism to generate and authenticate the message digest of the communication data between PLCs. An anomaly alert will be triggered if the data authentication fails. The execution on received malicious commands is disabled to avoid detrimental effect and keep the system stable. Furthermore, to recover real data from malicious modifications, a data sender is required to encrypt data using the proposed RC5-based data recovery algorithm and re-transmit it. The data authentication and recovery approaches can be implemented on the programmable logic circuit of PLCs through code updating, which requires no alterations to its current hardware architecture. We present the prototype of our resilience scheme and conduct real-world experiments to validate its efficacy under 12 typical attack scenarios. Our results show that our approach achieves 97.4% of accuracy in data authentication and 98.1% of success rate in abnormal state recovery. Finally, we assess the practicality of the proposed mechanism in terms of execution delay.
查看更多>>摘要：? 2022 The Author(s)After the initial hype on RPA, companies have more realistic expectations of this technology. Its current mature vision relegates the end-to-end robotic automation to a less suitable place and considers the human-robot collaboration as the most natural way for automating robotic processes in real-world settings. This hybrid RPA implies a vertical segmentation of process activities, i.e., some activities are conducted by humans while robots do others. The literature lacks a general method that considers the technical aspect of the solution, the psychological impact of the automation, and the governance mechanisms that a running hybrid process requires. In this sense, this paper proposes an iterative method dealing with all these aspects and results from a series of industrial experiences. Additionally, the paper deeply discusses the role of process mining in this kind of method and how it can continuously boost its iterations. The initial validation of the method in real-world processes reports substantial benefits in terms of efficiency.
查看更多>>摘要：? 2022 Elsevier B.V.This paper presents the architectural design and implementation of DIGICOR — a collaborative Industry 4.0 (I4.0) platform aimed at enabling SMEs to dynamically form supply-chain collaborations so as to pool production capacities and capabilities and jointly address complex supply chain requests. The DIGICOR architecture builds on the event-driven service-oriented architecture (EDSOA) model to support the collaboration between SMEs, dynamic modelling of their systems and services, and their integration in the supply chains of large OEMs, enforcing digital platform governance rules for knowledge protection and security. In contrast to the extant platforms assessed through our systematic review, the proposed architecture supports the entire lifecycle of I4.0 collaborations, from creation of viable teams to deployment and operation. The architecture provides an open and extensible solution for (i) creating a marketplace for the collaboration partners, (ii) providing services for planning and controlling the collaborative production, logistics, and risk management, while supporting APIs for third parties to provide complementary services such as advanced analytics, simulation, and optimization; and (iii) seamless connectivity to automation solutions, smart objects and real-time data sources. We report on the design of the architecture and its innovative artefacts such as the component model description and the semantic model constructs created for meaningful event exchanges between architectural end-points. We also describe a running use case demonstrating implementation scenarios.
查看更多>>摘要：? 2022 Elsevier B.V.The Internet of Things (IoT) and the relevant technologies have had a significant impact on smart farming as a major sub-domain within the field of agriculture. Modern technology supports data collection from IoT devices through several farming processes. The extensive amount of collected smart farming data can be utilized for daily decision making and analysis such as yield prediction, growth analysis, quality maintenance, animal and aquaculture, as well as farm management. This survey focuses on three major aspects of contemporary smart farming. First, it highlights various types of big data generated through smart farming and makes a broad categorization of such data. Second, this paper discusses a comprehensive set of typical applications of big data in smart farming. Third, it identifies and introduces the principal big data and machine learning techniques that are utilized in smart farming data analysis. In doing so, this survey also identifies some of the major, current challenges in smart farming big data analysis.This paper provides a discussion on potential pathways toward more effective smart farming through relevant analytics-guided decision making.
查看更多>>摘要：? 2022 Elsevier B.V.Smart service innovation is the process of creating smart product-service systems (PSS) and novel data-driven service offerings. It is particularly challenging for manufacturing firms as they have to cope with the two transformational forces of digitalization and servitization at the same time, i.e., they have to both evaluate the potential of digital technologies for creating new business opportunities and overthink established business logics from transactional product sales towards relationship-oriented service and solution business. To support the early phases of corresponding innovation processes already at the design time of smart PSS, this article presents the Pattern-Based Smart Service Innovation (PBSSI) method. The method was developed following a design science research approach that involved a Delphi study for deriving value proposition patterns as one of its core elements and a multiple case study with manufacturing firms to demonstrate and evaluate the method's utility for practitioners. The PBSSI method combines existing approaches to service design with newly developed and empirically grounded value proposition patterns for smart service. Evaluation feedback indicates that the PBSSI method is useful for online workshops and that it effectively supports the exploration and ideation in smart service innovation. In particular, it helps manufacturing firms to approach smart service innovation in a more customer-centric and systematic manner.
查看更多>>摘要：? 2022 Elsevier B.V.Lexical taxonomies are widely used to foster information retrieval and exchange in several domains and applications. When there are multiple taxonomies, heterogeneity among them is a severe problem for efficient collaboration processes. In this paper, we propose WETA, a domain-independent, knowledge-poor method for automatic taxonomy alignment via word embeddings. WETA associates all the leaf terms of the origin taxonomy to one or many concepts in the destination taxonomy, employing a scoring function, which merges the score of a hierarchical method based on cosine similarity and the score of a classification task. WETA is developed in the context of an EU Grant aiming at bridging the national taxonomies of EU countries towards the European Skills, Competences, Qualifications and Occupations taxonomy (ESCO) using AI Algorithms. The results, validated within the EU project activities for bridging the Italian occupation taxonomy CP and ESCO, confirm the usefulness of WETA in supporting the automatic alignment of national labor taxonomies. WETA reaches a 0.8 accuracy on recommending top-5 occupations and a wMRR of 0.72. WETA reduces the human effort needed for building a mapping from scratch: it would allow domain experts to concentrate on the validation task and decrease the incoherence due to multiple judgments. It would also make the approach reproducible and transparent to policymakers.
查看更多>>摘要：? 2022 The AuthorsIndustrial collaborative robots will be used in unstructured scenarios and a large variety of tasks in the near future. These robots shall collaborate with humans, who will add uncertainty and safety constraints to the execution of industrial robotic tasks. Hence, trustworthy collaborative robots must be able to reason about their collaboration's requirements (e.g., safety), as well as the adaptation of their plans due to unexpected situations. A common approach to reasoning is to represent the knowledge of interest using logic-based formalisms, such as ontologies. However, there is not an established ontology defining notions such as collaboration or adaptation yet. In this article, we propose an Ontology for Collaborative Robotics and Adaptation (OCRA), which is built around two main notions: collaboration, and plan adaptation. OCRA ensures a reliable human-robot collaboration, since robots can formalize, and reason about their plan adaptations and collaborations in unstructured collaborative robotic scenarios. Furthermore, our ontology enhances the reusability of the domain's terminology, allowing robots to represent their knowledge about different collaborative and adaptive situations. We validate our formal model, first, by demonstrating that a robot may answer a set of competency questions using OCRA. Second, by studying the formalization's performance in limit cases that include instances with incongruent and incomplete axioms. For both validations, the example use case consists in a human and a robot collaborating on the filling of a tray.
查看更多>>摘要：? 2022 Elsevier B.V.Computer-vision technology plays a vital role in automated fabric defect classification. In this paper, a novel prototypical network is presented for improving the fabric defect classification performance, especially in the case of an imbalanced distribution over the number of class samples. A traditional neural network (such as a convolutional neural network) usually inputs a batch of samples each time in training until the entire training dataset is covered, and thus it is not robust to cope with imbalanced data. The proposed network follows an N-way K-shot paradigm to split the training set into a support set and query set, and thereby forces the number of samples within each class to be uniformly distributed. The support set is used to learn the common knowledge of each class, whereas the query set is utilized to fine-tune the model parameters gained from the respective support set. The prototype of each class in the support set is computed as the representation of the class. For samples in the query set, the loss function is designed to match them with the corresponding prototypes as accurately as possible. In addition, the class activation mapping is used to visualize and interpret the discriminative regions of interest most relevant to specific defect classes. The classification performance of the proposed method is tested against five existing models on a labeled dataset of fabric defect images collected by a commercial inspection system. The proposed method achieves the highest classification accuracy (96.04%) over seven defect categories among the six tested methods.
查看更多>>摘要：? 2022 The AuthorsDigital Twins (DT) are of particular interest in the domain of Product-Service Systems (PSS), to predict hardware availability, to inform about the needed features of new solutions, and to forecast the expected performances of new configurations in operation. The aim of this paper is to shed light on the extent to which ‘twins’ are applied today across the PSS life cycle, and to spotlight the ability of DT-related case studies to capture a full value perspective vs. simply attempting to represent hardware and services in the digital realm. By means of a systematic literature review combined with a mapping study, the paper reveals how only a minimal part of the existing literature is able to demonstrate how real-time physical-to-virtual and virtual-to-physical connections can be used to improve the design of servitized solutions. The analysis shows how contributions in the topic are mostly proposing frameworks and methods, as opposed to models and tools, as well as how ‘evaluation’, ‘validation’ tasks are largely neglected. As a result, the paper proposes a specialized definition of the PSS DT, together with a set of research questions that need to be answered to empower the engineering teams with relevant DT for PSS design.
NSTL
Elsevier