The advent of Industry 4.0 has resulted in the widespread usage of novel paradigms and digital technologies within industrial production and manufacturing systems. The objective of making industrial operations monitoring easier also implied the usage of more effective data-driven predictive maintenance approaches, including those based on machine learning. Although those approaches are becoming increasingly popular, most of the traditional machine learning and deep learning algorithms experience the following three major challenges: 1) lack of training data (especially faulty data), 2) incompatible computation power, and 3) discrepancy in data distribution. A new data-driven technique, such as transfer learning, can be developed to overcome the issues related to traditional machine learning and deep learning for predictive maintenance. Motivated by the recent big interest towards transfer learning within computer science and artificial intelligence, in this paper we provide a systematic literature review addressing related research with a focus on predictive maintenance. The review aims to define transfer learning in the context of predictive maintenance by introducing a specific taxonomy based on relevant perspectives. We also discuss current advances, challenges, open-source datasets, and future directions of transfer learning applications in predictive maintenance from both theoretical and practical viewpoints.

A SARS-CoV-2 virus-specific reverse transcriptase-polymerase chain reaction (RT-PCR) test is usually used to diagnose COVID-19. However, this test requires up to 2 days for completion. Moreover, to avoid false-negative outcomes, serial testing may be essential. The availability of RT-PCR test kits is currently limited, highlighting the need for alternative approaches for the precise and rapid diagnosis of COVID-19. Patients suspected to be infected with SARS-CoV-2 can be assessed using chest CT scan images. However, CT images alone cannot be used for ruling out SARS-CoV-2 infection because individual patients may exhibit normal radiological results in the primary phases of the disease. A machine learning (ML)-based recognition and segmentation system was developed to spontaneously discover and compute infection areas in CT scans of COVID-19 patients. The computable assessment exhibited suitable performance for automatic infection region allocation. The ML models developed were suitable for the direct detection of COVID-19 (+). ML was confirmed to be a complementary diagnostic technique for diagnosing COVID-19(+) by forefront medical specialists. The complete manual delineation of COVID-19 often requires up to 225.5 min; however, the proposed RILML method decreases the delineation time to 7 min after four iterations of model updating.

A constitutive model for isotropic, semi-crystalline polymers is proposed. The model is Eulerian in the sense that it is independent of measures of total deformation and plastic/inelastic deformations. It is able to account for such essential phenomena as strain-rate dependence, work hardening, stress relaxation, volumetric inelastic deformations, and damage. The model was applied to uniaxial tension tests performed on polyoxymethylene (POM), which is a semi-crystalline polymer widely used in the industry. Three types of tests were conducted: monotonic tests at different strain rates, stress relaxation tests, and loading-unloading tests. The model was able to reproduce the experimental results well. The proposed model was also implemented as a VUMAT in Abaqus, and the deformation of a 3D geometry was simulated.

Architecting a self-adaptive system with decentralized control is challenging. Indeed, architects shall consider several different and interdependent design dimensions and devise multiple control loops to coordinate and timely perform the correct adaptations. To support this task, we propose Decor, a reasoning framework for architecting and evaluating decentralized control. Decor provides (i) multi-paradigm modeling support, (ii) a modeling environment for MAPE-K style decentralized control, and (iii) a co-simulation environment for simulating the decentralized control together with the managed system and estimating the quality attributes of interest. We apply the Decor in three case studies: an intelligent transportation system, a smart power grid, and a cloud computing application. The studies demonstrate the framework’s capabilities to support informed architectural decisions on decentralized control and adaptation strategies.

The assurance case arguments are created to demonstrate acceptable system safety and/or security. In this regard, a series of propositions expressed by natural language statements (claims) are broken down into sub-claims representing a logical chain of reasoning until the corresponding evidence is obtained. The review and update of assurance arguments for aligning with the process and product counterparts used for their construction are essential tasks. These tasks are perceived as challenging but can be efficiently supported by using Natural Language Processing (NLP). To date, however, the published studies on assurance cases have not leveraged the NLP. Accordingly, this paper presents our NLP-based assurance framework called ATTEST. At first, the text preprocessing is carried out by using NLP tasks. The rules are created, in which both syntactic and semantic features are captured. The former is captured by using NLP tasks, while the latter is captured by the internal structure of models as well as the mappings across them. The created rules are triggered for argument comprehension, well-formedness, sufficiency checks, and identifying defeaters and counter-evidence selection. Besides the process, product, and assurance case models produced during the design and development phase, the operational data is gathered from the configured simulation environments and used for identifying problems as well as the measures for resolving them. Finally, the affected parts of assurance case models are highlighted and the underlying reasoning for their adaptation is presented. The applicability of the proposed framework is demonstrated by reviewing and updating assurance cases constructed for vehicular Accelerator Control System (ACS) with Electronic Throttle Control (ETC).

A prototype CCT dipole magnet developed by a collaboration between Swedish universities, Swedish industry and CERN will be tested at Uppsala University. This 1 m long double-aperture magnet can provide a field strength of 3.3 T at 85 A in a 70 mm aperture with an integrated field of 2.8 Tm. It is intended to replace the current LHC orbit corrector magnets which are reaching the end of their expected life due to the radiation load. The new magnet is designed to handle the radiation dose of the upgrade to the high-luminosity LHC, which will deliver about ten times the current radiation dose. It must therefore be more resistant to radiation and meet strict requirements in terms of electrical insulation while matching the original field quality and self-protective capability, mechanical volume, and maximum excitation current. This paper will present the latest of the design and manufacturing work, including the results of simulations of the mechanical field and the mechanical stress. Details of the various tests performed before machining the parts are also presented.

Sleep-stage and apnea-hypopnea index (AHI) are the most important metrics in the diagnosis of sleep syndrome disease. In previous studies, these two tasks are usually implemented separately, which is both time- and resource-consuming. In this work, we propose a novel single electroencephalogram (EEG)-based collaborative learning network (EEG-CLNet) for simultaneous sleep staging and obstructive sleep apnea (OSA) event detection through multitask collaborative learning. The EEG-CLNet regards different tasks as a common unit to extract features from intragroups via both local parameter sharing and cross-task knowledge distillation (CTKD), rather than just sharing parameters or shortening the distance between different tasks. Our approach has been validated on two datasets with the same or better performance than other methods. The experimental results show that our method achieves a performance gain of 1%-5% compared with the baseline. Compared to previous works where two or even more models were required to perform sleep staging and OSA event detection, the EEG-CLNet could reduce the total number of model parameters and facilitate the model to mine the hidden relationships between different task semantic information. More importantly, it effectively alleviates the task bias problem in hard parameter sharing. As a consequence, this approach has notable potential to be a solution for a lightweight wearable sleep monitoring system in the future.

With the advent of new technologies such as the Artificial Intelligence of Things (AIoT), big data, fog computing, and edge computing, smart city applications have suffered from issues, such as leakage of confidential and sensitive information. To envision smart cities, it will be necessary to integrate federated learning (FL) with smart city applications. FL integration with smart city applications can provide privacy preservation and sensitive information protection. In this paper, we present a comprehensive overview of the current and future developments of FL for smart cities. Furthermore, we highlight the societal, industrial, and technological trends driving FL for smart cities. Then, we discuss the concept of FL for smart cities, and numerous FL integrated smart city applications, including smart transportation systems, smart healthcare, smart grid, smart governance, smart disaster management, smart industries, and UAVs for smart city monitoring, as well as alternative solutions and research enhancements for the future. Finally, we outline and analyze various research challenges and prospects for the development of FL for smart cities.

Gravel roads form a significant share of the global road network, usually in sparsely populated rural areas. They are important, especially in agriculture, tourism, and forestry, connecting rural to urban areas. This systematic literature study comprises 105 reviewed publications on gravel road maintenance. Review articles on maintenance management practices, especially concerning objective condition assessment and data-driven methods (DDMs), are lacking. Therefore, this review provides a concise overview of current gravel road maintenance practices and ongoing research on objective condition assessment and DDMs for gravel road maintenance. It offers researchers in gravel road maintenance and other related fields a clear indication of where to focus their research efforts, as it suggests the direction for future research. Visual assessment methods are predominant for monitoring the condition of gravel roads, while objective methods and DDMs are not common. Research on gravel roads and their maintenance has increased in the last two decades, especially in North America and Northern Europe. Condition assessment is shifting from subjective to objective methods, utilizing knowledge from technological advancements in image processing, vibration and acoustics analysis, and so forth. There are some excellent research initiatives for objectively assessing the condition of gravel roads and DDMs, but the practical implementation is limited. Implementing objective assessment methods and DDMs generally improves the management of gravel roads with regard to decision-making, maintenance costs, safety, and the stability and comfort of the ride. Objective condition assessment and DMs have the potential to enhance maintenance practices in the maintenance of gravel roads.

Forests are essential for life, providing various ecological, social, and economic benefits worldwide. However, one of the main challenges faced by the world is the forest damage caused by biotic and abiotic factors. In any case, the forest damages threaten the environment, biodiversity, and ecosystem. Climate change and anthropogenic activities, such as illegal logging and industrial waste, are among the principal elements contributing to forest damage. To achieve the United Nations' Sustainable Development Goals (SDGs) related to forests and climate change, detecting and analyzing forest damages, and taking appropriate measures to prevent or reduce the damages are essential. To that end, we envision establishing a Smart Forest Observatories (SFOs) network, as shown below, which can be either a local area or a wide area network involving remote forests. The basic idea is to use Monitor, Analyze, Plan, Execute, and Knowledge (MAPE-K) architecture from autonomic computing and self-adaptive software systems domain to design and develop the SFOs network. The SFOs are planned to collect, analyze, and share the collected data and analysis results using state-of-the-art methods. The principal objective of the SFOs network is to provide accurate and real-time data to policymakers and forest managers, enabling them to develop effective policies and management strategies for global forest conservation that help to achieve SDGs related to forests and climate change.

COVID-19 is not the last virus; there would be many others viruses we may face in the future. We already witnessed the loss of economy and daily life through the lockdown. In addition, vaccine, medication, and treatment strategies take clinical trials, so there is a need to tracking and tracing approach. Suitably, exhibiting and computing social evolution is critical for refining the epidemic, but maybe crippled by location data ineptitude of inaccessibility. It is complex and time consuming to identify and detect the chain of virus spread from one person to another through the terabytes of spatiotemporal GPS data. The proposed research aims a HPE edge line computing and big data analytic supported virus outbreak tracing and tracking approach that consumes terabytes of spatiotemporal data. Proposed STRENUOUS system discovers the prospect of applying an individual’s mobility to label mobility streams and forecast a virus-like COVID-19 epidemic transmission. The method and the mechanical assembly further contained an alert component to demonstrate a suspected case if there was a potential exposure with the confirmed subject. The proposed system tracks location data related to a suspected subject in the confirmed subject route, where the location data expresses one or more geographic locations of each user over a period. It recognizes a subcategory of the suspected subject who is expected to transmit a contagion based on the location data. System measure an exposure level of a carrier to the infection based on contaminated location data and a subset of carriers connected with the second location carrier. They investigated whether the people in the confirmed subject’s cross-path can be infected and suggest quarantine followed by testing. The Proposed STRENUOUS system produces a report specifying that the people have been exposed to the virus.

Many companies, e.g., Facebook and YouTube, use the REST architecture and provide REST APIs to their clients. Like any other software systems, REST APIs need maintenance and must evolve to improve and stay relevant. Antipatterns—poor design practices—hinder this maintenance and evolution. Although the literature defines many antipatterns and proposes approaches for their (automatic) detection, their correction did not receive much attention. Therefore, we apply a mixed-method approach to study REST APIs and REST antipatterns with the objectives to recommend corrections or, when possible, actually correct the REST antipatterns. Qualitatively, via case studies, we analyse the evolution of 11 REST APIs, including Facebook, Twitter, and YouTube, over six years. We detect occurrences of eight REST antipatterns in the years 2014, 2017, and 2020 in 17 versions of 11 REST APIs. Thus, we show that (1) REST APIs and antipatterns evolve over time and (2) developers seem to remove antipatterns. Qualitatively via a discourse analysis, we analyse developers’ forums and report that developers are concerned with the occurrences of REST antipatterns and discuss corrections to these antipatterns. Following these qualitative studies, using an engineering-research approach, we propose the following novel and unique contributions: (1) we describe and compare the corrections of eight REST antipatterns from the academic literature and from developers’ forums; (2) we devise and describe algorithms to recommend corrections to some of these antipatterns; (3) we present algorithms and a tool to correct some of these antipatterns by intercepting and modifying responses from REST APIs; and, (4) we validate the recommendations and the corrections manually and via a survey answered by 24 REST developers. Thus, we propose to REST API developers and researchers the first, grounded approach to correct REST antipatterns.

Tactile sensors are among the most important devices used in industrial and biomedical fields. Sensors' profiles are significantly affected by their structures and material used. This article presents a robust, low-cost, low noise, accurate and simple fabrication capacitive tactile sensor as a single taxel fabricated on foam. This highly scalable design provides excellent noise immunity, accuracy, and due to a unique printable elastic conductor, it is flexible and stretchable with more than 200% strain. Furthermore, the taxel is based on the capacitive Wheatstone bridge. As a result, noise immunity and stability in case of temperature fluctuation is accomplished. Additionally, the sensor's innovative, simple fabrication, made of Polyurethane foam and printable elastic conductor, allows the system to adapt and achieve relevant results necessary for the purpose of the sensor's application. Therefore, the proposed sensor has potential applications in industrial and biomedical contexts, such as sleep monitoring, etc.

Anisotropic elasticity and inelasticity is of relevance in many practical applications. The Eulerian formulation for anisotropic elastic and inelastic response based on microstructural vectors is used here to model an injection-moulded low-density polyethylene. In contrast with Lagrangian models of inelasticity, the Eulerian formulation is insensitive to arbitrariness of the reference and intermediate configurations as well as to measures of total and inelastic deformations. A specific strain-space-type anisotropic yield function is proposed that depends on anisotropic measures of elastic deformation and anisotropic hardening variables. Use is also made of a rate-independent model with a smooth elastic-inelastic transition. The material parameters were calibrated to reproduce uniaxial test data for loading in three directions in the moulding plane. In addition, a strongly objective numerical implementation is presented and used to simulate stretching of a plate with a circular hole. In contrast with metals, this polyethylene experiences elastic deformations of about 10%. Although the inelastic spin rate could not be determined by the available test data, simulations of loadings in different material directions yield observable influences of inelastic spin rate.

The gravel road network is an important function for rural residents and entrepreneurs. Traditional maintenance of gravel roads is well-functioning but provides a relatively high maintenance cost per unit length of the road, and every maintenance action as well as extraction and transport of new gravel contributes to increased climate impact and resource depletion. Today, maintenance planning is carried out periodically based on the maintenance history, which also is reflected in the economic models and procurement methods. Current maintenance plans may be enhanced and will not be a reliable basis in the future, e.g. due to climate change. Instead, real needs and conditions must be given greater consideration. Today, appropriate maintenance management systems are lacking, e.g. in order to be able to evaluate maintenance deficiencies, prioritize objects and choose the appropriate maintenance action. Moreover, the knowledge available at specific stakeholders is not shared with other actors. In this paper, an Information and Communication Technology (ICT) system for gravel road maintenance is proposed in the form of a cloud-based system covering the information needs of stakeholders in the gravel road maintenance ecosystem. Requirement specifications are given for the sub-systems intended for the maintenance executioner and the maintenance planner. The specifications are based on workshops and interviews conducted with stakeholders, where requirements were acquired e.g. in the form of User stories.

Modern systems produce and handle a large volume of sensitive enterprise data. Therefore, security vulnerabilities in the software systems must be identified and resolved early to prevent security breaches and failures. Predicting security vulnerabilities is an alternative to identifying them as developers write code. In this study, we studied the ability of several machine learning algorithms to predict security vulnerabilities. We created two datasets containing security vulnerability information from two open-source systems: (1) Apache Tomcat (versions 4.x and five 2.5.x minor versions). We also computed source code metrics for these versions of both systems. We examined four classifiers, including Naive Bayes, Decision Tree, XGBoost Classifier, and Logistic Regression, to show their ability to predict security vulnerabilities. Moreover, an ensemble learner was introduced using a stacking classifier to see whether the prediction performance could be improved. We performed cross-version and cross-project predictions to assess the effectiveness of the best-performing model. Our results showed that the XGBoost classifier performed best compared to other learners, i.e., with an average accuracy of 97% in both datasets. The stacking classifier performed with an average accuracy of 92% in Struts and 71% in Tomcat. Our best-performing model-XGBoost-could predict with an average accuracy of 87% in Tomcat and 99% in Struts in a cross-version setup.

Artificial Intelligence (AI) is becoming pervasive in most engineering domains, and railway transport is no exception. However, due to the plethora of different new terms and meanings associated with them, there is a risk that railway practitioners, as several other categories, will get lost in those ambiguities and fuzzy boundaries, and hence fail to catch the real opportunities and potential of machine learning, artificial vision, and big data analytics, just to name a few of the most promising approaches connected to AI. The scope of this paper is to introduce the basic concepts and possible applications of AI to railway academics and practitioners. To that aim, this paper presents a structured taxonomy to guide researchers and practitioners to understand AI techniques, research fields, disciplines, and applications, both in general terms and in close connection with railway applications such as autonomous driving, maintenance, and traffic management. The important aspects of ethics and explainability of AI in railways are also introduced. The connection between AI concepts and railway subdomains has been supported by relevant research addressing existing and planned applications in order to provide some pointers to promising directions.

Approximately 300,000 km of the Swedish road network consists of gravel roads. These roads contribute to accessibility and accessibility throughout Sweden, which is especially important in rural areas. An annual operation and maintenance grant is paid to these roads to be maintained and kept open to public transport, but the grant covers only part of the total maintenance costs. Some of the costliest maintenance activities are planing and gravelling. When gravelling, natural resources in the form of rock and gravel are used, which is an energy-intensive process that has a negative impact on the environment. A couple of methods exist for recycling of gravel from the roads, but the utilization is rather limited. In order to promote and motivate recycling of gravel, it is important to highlight the environmental benefits of using recycled gravel, but also to be able to assess the economic impact as additional costs may arise. The overall purpose of the paper is to gain deeper understanding of the environmental and economic effects of recycling of gravel during gravel road maintenance. To achieve this, a calculation model is developed to estimate the environmental impact and economic effects of gravel road maintenance. The purpose of the calculation model is to be able to compare alternative methods for gravelling. The calculation model is evaluated through a test scenario with three alternative methods for gravelling; two where gravel recycling is performed by the means of two different methods and one in which new gravel is used. The test scenario shows that it is economically and environmentally beneficial, in a life cycle perspective, to use recycled gravel for road gravelling.

Internet of Things (IoT) is a growing technology that relies on connected 'things' that gather data from peer devices and send data to servers via APIs (Application Programming Interfaces). The design quality of those APIs has a direct impact on their understandability and reusability. This study focuses on the linguistic design quality of REST APIs for IoT applications and assesses their linguistic quality by performing the detection of linguistic patterns and antipatterns in REST APIs for IoT applications. Linguistic antipatterns are considered poor practices in the naming, documentation, and choice of identifiers. In contrast, linguistic patterns represent best practices to APIs design. The linguistic patterns and their corresponding antipatterns are hence contrasting pairs. We propose the SARAv2 (Semantic Analysis of REST APIs version two) approach to perform syntactic and semantic analyses of REST APIs for IoT applications. Based on the SARAv2 approach, we develop the REST-Ling tool and empirically validate the detection results of nine linguistic antipatterns. We analyse 19 REST APIs for IoT applications. Our detection results show that the linguistic antipatterns are prevalent and the REST-Ling tool can detect linguistic patterns and antipatterns in REST APIs for IoT applications with an average accuracy of over 80%. Moreover, the tool performs the detection of linguistic antipatterns on average in the order of seconds, i.e., 8.396 s. We found that APIs generally follow good linguistic practices, although the prevalence of poor practices exists. (C) 2022 The Author(s). Published by Elsevier Inc.

We study numerically the conjugate heat transfer between the walls of a parallel plate microchannel and ahomogeneous porous medium fully saturated with a liquid that is found in motion due to an external pressuregradient. The origin of this problem is caused by a uniform heat flux imposed at the external surfaces of the walls of themicrochannel that have a finite thermal conductivity. In this manner, the competition and heat transfer mechanismsbetween both regions characterized by the thermal resistances, conduct to a conjugate formulation that originates adimensionless conjugate parameter αc. This parameter measures the ratio of both thermal resistances, and, for largevalues of this parameter, the longitudinal heat conduction effects in the walls are very important and suffer significantdeviations when compared with the case with finite values for this parameter. The dimensionless governing equationsfor both regions are established with the corresponding boundary conditions, and the numerical results show that theaspect ratios of both regions, controlled through the dimensionless parameters ϵh and ϵ, play an important role indistinguishing the presence of the longitudinal heat conduction effects in the walls. For instance, if the ratios αc∕ϵ2h25 and αc∕ϵ2 1, the longitudinal effects of heat transfer are very important in the walls of the microchannel,whereas in the porous matrix there are effects of heat transfer in both directions, whereas if αc∕ϵ2h αc∕ϵ2 25 onlythe longitudinal conduction effects are significant for both regions.

This study examines the mediating effects of physical/engineering asset management on the relationship between continuous quality improvement and business performance. Using empirical data based on survey data from six European countries (i.e. Greece, Poland, Slovakia, Slovenia, Sweden and Turkey), this study used mediation analysis to address the research problem. A macro for SPSS was used to estimate the size of an indirect effect of continuous quality improvement on business performance by a proposed mediator. The results of this study show that physical asset management mediates the effect of continuous quality improvement on business performance. This study provides valuable insights into mechanisms that have the potential to improve business performance. The results contribute to a better understanding of how companies could achieve higher performance outcomes through the introduction of continuous quality improvement and through physical asset management practices. 

The object recognition concept is being widely used a result of increasing CCTV surveillance and the need for automatic object or activity detection from images or video. Increases in the use of various sensor networks have also raised the need of lightweight process frameworks. Much research has been carried out in this area, but the research scope is colossal as it deals with open-ended problems such as being able to achieve high accuracy in little time using lightweight process frameworks. Convolution Neural Networks and their variants are widely used in various computer vision activities, but most of the architectures of CNN are application-specific. There is always a need for generic architectures with better performance. This paper introduces the Dimension-Based Generic Convolution Block (DBGC), which can be used with any CNN to make the architecture generic and provide a dimension-wise selection of various height, width, and depth kernels. This single unit which uses the separable convolution concept provides multiple combinations using various dimension-based kernels. This single unit can be used for height-based, width-based, or depth-based dimensions; the same unit can even be used for height and width, width and depth, and depth and height dimensions. It can also be used for combinations involving all three dimensions of height, width, and depth. The main novelty of DBGC lies in the dimension selector block included in the proposed architecture. Proposed unoptimized kernel dimensions reduce FLOPs by around one third and also reduce the accuracy by around one half; semi-optimized kernel dimensions yield almost the same or higher accuracy with half the FLOPs of the original architecture, while optimized kernel dimensions provide 5 to 6% higher accuracy with around a 10 M reduction in FLOPs.

The High Luminosity LHC requires dipole orbit correctors grouped in double aperture magnet assemblies. They provide a field of 3.1 T at 100 A in an aperture of 70 mm. The current standard design is a classical cosine-theta layout made with ribbon cable. However, the electric insulation of this cable is not radiation-resistant enough to withstand the radiation load expected in the coming years of LHC operation. A new design, based on a cable with polyimide insulator, that can replace the existing orbit correctors, is needed. The challenge is to design a magnet that fits directly into the existing positions and that can operate with the same busbars, passive quench protection, and power supplies. The new orbit corrector design meets high requirements on the field quality while keeping within the same mechanical volume and maximum excitation current. A collaboration of Swedish universities and Swedish industry has been formed for the development and production of a prototype magnet following a concurrent engineering methodology to reduce the time needed to produce a CCT magnet. The magnet has a 1 m long CCT dipole layout consisting of two coils. The superconductor is a commercially available 0.33 mm wire with polyimide insulation in a 6-around-1 cable. The channels in the coil formers, that determine the CCT layout, allow for 2 x 5 cable layers. A total of 70 windings makes that the coil current can be kept below 100 A. We will present the detailed design and preliminary quench simulations.

Purpose This paper presents a concept for digitalised maintenance (DM), maps the conceptualised DM to maintenance problems in industries and highlights challenges that might be faced when realizing this concept. Design/methodology/approach First, maintenance problems that are faced by the industry are presented, followed by a conceptualisation of DM. Next, a typical operational scenario is used as an exemplification to show system dynamics. The characteristics of this conceptualised DM are then mapped to the identified maintenance problems of industry. Then, interesting initiatives in this domain are highlighted, and finally, the challenges to realize this approach are discussed. Findings This paper identified a set of problems related to maintenance in industry. In order to solve current industrial problems, exploit emerging digital technologies and elevate future industries, it will be necessary to develop new maintenance approaches. The mapping between the criteria of DM and maintenance problems shows the potential of this concept and gives a reason to examine it empirically in future work. Originality/value This paper aims to help maintenance professionals from both academia and industry to understand and reflect on the problems related to maintenance, as well as to comprehend the requirements of a digitalised maintenance and challenges that may arise.

In recent years, we have seen many performance fiascos in the deployment of new systems, such as the US health insurance web. This paper describes the functionality and architecture, as well as success stories, of a tool that helps address these types of issues. The tool allows assessing software designs regarding quality, in particular performance and reliability. Starting from a UML design with quality annotations, the tool applies model-transformation techniques to yield analyzable models. Such models are then leveraged by the tool to compute quality metrics. Finally, quality results, over the design, are presented to the engineer, in terms of the problem domain. Hence, the tool is an asset for the software engineer to evaluate system quality through software designs. While leveraging the Eclipse platform, the tool uses UML and the MARTE, DAM and DICE profiles for the system design and the quality modeling.

Simple Summary The engineering of self-organising cyber-physical systems can benefit from a variety of "logical devices", including digital twins, virtual devices, and (augmented) collective digital twins. In particular, collective digital twins provide for a design construct towards collective computing, which can be augmented with virtual devices to improve the performance of existing self-organising applications-as shown through swarm exploration and navigation scenarios. The engineering of large-scale cyber-physical systems (CPS) increasingly relies on principles from self-organisation and collective computing, enabling these systems to cooperate and adapt in dynamic environments. CPS engineering also often leverages digital twins that provide synchronised logical counterparts of physical entities. In contrast, sensor networks rely on the different but related concept of virtual device that provides an abstraction of a group of sensors. In this work, we study how such concepts can contribute to the engineering of self-organising CPSs. To that end, we analyse the concepts and devise modelling constructs, distinguishing between identity correspondence and execution relationships. Based on this analysis, we then contribute to the novel concept of "collective digital twin" (CDT) that captures the logical counterpart of a collection of physical devices. A CDT can also be "augmented" with purely virtual devices, which may be exploited to steer the self-organisation process of the CDT and its physical counterpart. We underpin the novel concept with experiments in the context of the pulverisation framework of aggregate computing, showing how augmented CDTs provide a holistic, modular, and cyber-physically integrated system view that can foster the engineering of self-organising CPSs.

The Internet of Things (IoT) have shown numerous potential applications that can enhance our quality of life. IoT is becoming a core technology to bring smart homes, smart cities, and smart industries into reality. However, with potential benefits comes a challenge of sustainability, and one major concern is to minimize energy consumption. In a citywide area, managing the operation of such large-scale IoT networking is one of the complex tasks. One of the ways is to utilize dynamic sensing scheduling where the IoT device goes to the sleep mode and prevents unnecessary data transmission. In this paper, we propose a dynamic sensing (DynaSens) algorithm for an IoT-based waste management system. This algorithm helps to reduce the waste bin overflowing, thus, provides better sanitation, and it is also helpful in reducing the fuel cost of waste collection vehicles. Our work utilizes measured values such as current consumption, LiDAR measurement time, and LoRa transmission time as the input data for the simulation experiment to evaluate energy consumption. We also assessed DynaSens using a real dataset obtained from a recycling house. We use Pycom LoPy4 micro-controller as a development board. For a number of garbage-thrown scenarios, DynaSens enables longer battery longevity by reducing the repeated execution of the same tasks. © 2022 IEEE.

Rotating equipment is considered as a key component in several industrial sectors. In fact, the continuous operation of many industrial machines such as sub-sea pumps and gas turbines relies on the correct performance of their rotating equipment. In order to reduce the probability of malfunctions in this equipment, condition monitoring, and fault diagnosis systems are essential. In this work, a novel approach is proposed to perform fault diagnosis in rotating equipment based on permutation entropy, signal processing, and artificial intelligence. To that aim, vibration signals are employed for an indication of bearing performance. In order to facilitate fault diagnosis, fault detection and isolation are performed in two separate steps. As first, once a vibration signal is received, the faulty state of the bearing is determined by permutation entropy. In case a faulty state is detected, the fault type is determined using an approach based on signal processing and artificial intelligence. Wavelet packet transform and envelope analysis of the vibration signals are utilized to extract the frequency components of the fault. The proposed approach allows for the automatic selection of a frequency band that includes the characteristic resonance frequency of the fault, which is subject to change in different operational conditions. The method works by extracting the proper features of the signals that are used to decide about the faulty bearing’s condition by a multi-output adaptive neuro-fuzzy inference system classifier. The effectiveness of the approach is assessed by the Case Western Reserve University dataset: the analysis demonstrates the proposed method’s capabilities in accurately diagnosing faults in rotating equipment as compared to existing approaches.

It is hard to attract young persons to engineering and other science, technology, engineering, and mathematics (STEM) fields of education in Sweden. Factors, such as interest and ability, are affecting the educational orientation of students, and many studies suggest that there are gender related differences in students’ perceptions regarding different subject areas. Nevertheless, it is not fully evident why students’ make their educational choices. In this paper, Swedish upper secondary school students’ perceptions of interest and self-efficacy are studied in the form of a questionnaire survey to gain deeper understanding on the choices that are made. Open-ended questions regarding subject interest, as well as questions connecting STEM-related situations with perceived emotions were included, in addition to direct questions regarding interest and self-efficacy. Differences were seen both with respect to educational orientation and to gender, which confirms previous studies. Male students were interested in subjects that are accurate, logical, and scientific, while the female students emphasized the analytical and challenging aspects, in the sense that the subjects forced them to think. Interest and future opportunities affected the choice of program, while the student’s own perceived ability seemed less important. Results with respect to emotions showed that the female students in this study felt insecure and scared in STEM-related situations to higher degree than male students did. Students on the social science program were bored and uninterested, while natural science and technology program students were more interested and confident in STEM-related scenarios. These findings help us to understand how students approach STEM situations, and how to take necessary measures to equalize these situations using a norm-critical approach. 

An essential aspect of resilience within Cyber-Physical Systems stands in their capacity of early detection of faults before they generate failures. Faults can be of any origin, either natural or intentional. Detection of faults enables predictive maintenance, where faults are managed through diagnosis and prognosis. In this paper we focus on intelligent predictive maintenance based on a class of machine learning techniques, namely transfer learning, which overcomes some limitations of traditional approaches in terms of availability of appropriate training datasets and discrepancy of data distribution. We provide a conceptual approach and a reference architecture supporting transfer learning within intelligent predictive maintenance applications for cyber-physical systems. The approach is based on the emerging paradigms of Industry 4.0, the industrial Internet of Things, and Digital Twins hosting run-time models for providing the training data set for the target domain. Although we mainly focus on health monitoring and prognostics of industrial machinery as a reference application, the general approach is suitable to both physical- and cyber-threat detection, and to any combination of them within the same system, or even in complex systems-of-systems such as critical infrastructures. We show how transfer learning can aid predictive maintenance with intelligent fault detection, diagnosis and prognosis, and describe some the challenges that need to be addressed for its effective adoption in real industrial applications.

In the past years, machine learning (ML) has become a popular approach to support self-Adaptation. While ML techniques enable dealing with several problems in self-Adaptation, such as scalable decision-making, they are also subject to inherent challenges. In this paper, we focus on one such challenge that is particularly important for self-Adaptation: ML techniques are designed to deal with a set of predefined tasks associated with an operational domain; they have problems to deal with new emerging tasks, such as concept shift in input data that is used for learning. To tackle this challenge, we present lifelong self-Adaptation: A novel approach to self-Adaptation that enhances self-Adaptive systems that use ML techniques with a lifelong ML layer. The lifelong ML layer tracks the running system and its environment, associates this knowledge with the current tasks, identifies new tasks based on differentiations, and updates the learning models of the self-Adaptive system accordingly. We present a reusable architecture for lifelong self-Adaptation and apply it to the case of concept drift caused by unforeseen changes of the input data of a learning model that is used for decision-making in self-Adaptation. We validate lifelong self-Adaptation for two types of concept drift using two cases.

Microscopic investigation

Reliable simulations of the DTH drilling cycle are important in understanding the physics related todrilling, which in turn enables development of robust performance and condition monitoring methodologies. The DTH models available today model different aspects of the system like impact, hydraulics etc. separately. There are models available that incorporates hydraulics/pneumatics with onedimensional structural dynamics of the system. A common drawback of such models is that the effectof rotation is neglected. In reality rotation is an integral part of the DTH system and is interconnectedwith other parameters of drilling. This paper focuses on a simple model that combines rotation of thedrill string with the impact and hydraulic mechanics. The aim is to build upon this basic model tofacilitate the development of a more robust and accurate model that represents the condition andperformance monitoring problem.

Oil-filled electrical transformers are critical equipment for modern societies where a sustainable energy supply is required. Recently, many severe fire and explosion accidents of transformers have been reported due to copper corrosion problems in the form of copper sulfide deposits on the windings. The most negative impact of such accidents is safety threats to workers and people near the site, which can expose them to toxic chemicals, heat, sound pressure, etc. Another impact is the economic losses due to power outages and loss of profits. These accidents happen even though applying maintenance strategies for fault detection and diagnosis in power plants. Reviewing literature in the related topics revealed the inability of the applied maintenance strategies to detect copper corrosion problems due to shortcomings of an effective Condition Monitoring (CM) procedure that can be used to detect and track such problems in the initial stage, as well as a lack of a clear diagnosis model for defining a threshold that can early trigger an alarm before fault incidence. The main currently applied monitoring parameters are measuring corrosive sulfur compounds, evaluating the corrosivity level of the oil by corrosion tests, and measuring specific gases in the oil. Other parameters are also included, such as onsite electrical testing and online sensor device technology. All these parameters are insufficient for the early detection of copper corrosion problems. The main research problem addressed in this thesis is: how to establish an effective Condition-Based Maintenance (CBM) strategy for oil-filled electrical transformers to reduce copper corrosion problems and provide sustainable energy? The research is a mix of exploratory and explanatory approaches. For studying the current maintenance practices and identifying suitable ways for detecting and solving copper corrosion problems, literature reviews and experimental work were carried out, while artefact building and empirical studies were used for developing and testing solutions. One important result was identifying relevant parameters, such as hydrogen sulfide gas and toluene compound, which are by-products of the corrosion reaction. The finding was utilized in creating a procedure for early fault detection for the purpose of establishing an effective CBM strategy. In this strategy, the corrosion problems can be detected based on the relevant parameters and an Early Fault Diagnosis (EFD) model using a novel numerical method for defining an alarm threshold. The procedure was successfully verified and validated in two empirical studies in a power plant. The relationship between maintenance and sustainability was also explored to study the role of an effective maintenance strategy toward supplying sustainable energy. A framework for approaching sustainable maintenance was proposed based on three pillars, i.e., eco-efficiency indicator, asset management, and digitalization. In this context, a procedure called ABCD was used in an empirical study to assess the sustainability condition and find the prioritized actions toward sustainable energy. The main conclusion of this thesis is that the established CBM strategy, based on the proposed CM procedure, has the capability to reduce the probability of transformer accidents and their negative effects on social, environmental, and economic aspects, as well as provide sustainable energy to the society.

Process compliance with relevant regulations and de-facto standards is a mandatory requirement for certifying critical systems. However, it is often carried out manually, and therefore perceived as complex and labour-intensive. Ontology-based Natural Language Processing (NLP) provides an efficient support for compliance management with critical software system engineering standards. This, however, has not been considered in the literature. Accordingly, the approach presented in this paper focuses on ontology-based NLP for compliance management of software engineering processes with standard documents. In the developed ontology, the process concerns, such as stakeholders, tasks and work products are captured for better interpretation. The rules are created for extracting and structuring information, in which both syntactic features (captured using NLP tasks) and semantic features (captured using ontology) are encoded. During the planning phase, we supported the generation of requirements, process models and compliance mappings in Eclipse Process Framework (EPF) Composer. In the context of reverse compliance, the gaps with standard documents are detected, potential measures for their resolution are provided, and adaptions are made after the process engineer approval. The applicability of the proposed approach is demonstrated by processing ECSS-E-ST-40C, a space software engineering standard, generating models and mappings, as well as reverse compliance management of extended process model.

What happens if we see a suitable font for our design work but we do not know its name? Visual Font Recognition (VFR) systems are used to identify the font typeface in an image. These systems can assist graphic designers in identifying fonts used in images. A VFR system also aids in improving the speed and accuracy of Optical Character Recognition (OCR) systems. In this paper, we proposed the first publicly available datasets in the field of Persian font recognition and employed Convolutional Neural Networks (CNN) to address the Persian font recognition problem. The results show that the proposed pipeline obtained 78.0% top-1 accuracy on our new datasets, 89.1% in the IDPL-PFOD dataset, and 94.5% in the KAFD dataset. Furthermore, the average time spent in the entire pipeline for one sample of our proposed datasets is 0.54 and 0.017 seconds for CPU and GPU, respectively. We conclude that CNN methods can be used to recognize Persian fonts without the need for additional pre-processing steps such as feature extraction, binarization, normalization, etc.

This paper reports the tool developments for electrochemical machining (ECM) of precision parts for automotive industry using polymer3D printed inserts. The role of these inserts is to control the fluid flow in the inter-electrode gap as well as to prevent stray machiningby providing insulation. Initial trial and error machining experiments with various tool insert shapes yielded positive outcomes in terms ofcontrolling stray dissolution. It became evident that by 3D printing the entire machining cell structure with integrated, exchangeable toolinserts, all made from polymer, can further enhance the ECM process. This cell-insert assembly enabled better control of the electrochemicaldissolution process and allowed for less restrictive flow of the electrolyte, reducing turbulence in the inter-electrode gap. Thus, by improvingthe electrolyte flow conditions and providing appropriate insulation to prevent stray machining, the 3D printed cell/insert assemblies enabledECM to achieve a shaped profile of an auto engine component to required tolerances.

Solidification processes play an important role in several industrial processes, such as weldingand additive manufacturing, and the resulting residual stress state is often critical for thestructural integrity of the material. A thermomechanical model was developed for the analysisand prediction of such solidification processes. The approach is based on a model proposed byRubin (Int. J. Eng. Sci. 25, 1175-1191, 1987). This plasticity model was formulated for finitestrains using an Eulerian evolution equation for a unimodular elastic distortional deformationtensor. This evolution equation automatically ensures thermodynamic consistency andpreservation of isochoric inelastic deformations. A 2D problem in the form of a butt weld jointwas analyzed. The main outcome from the analyses were the residual stress distributions. Theresults are compared to experimental data from the literature.

Self-Adaptation equips a software system with a feedback loop that automates tasks that otherwise need to be performed by operators. Such feedback loops have found their way to a variety of practical applications, one typical example is an elastic cloud. Yet, the state of the practice in self-Adaptation is currently not clear. To get insights into the use of self-Adaptation in practice, we are running a largescale survey with industry. This paper reports preliminary results based on survey data that we obtained from 113 practitioners spread over 16 countries, 62 of them work with concrete self-Adaptive systems. We highlight the main insights obtained so far: motivations for self-Adaptation, concrete use cases, and difficulties encountered when applying self-Adaptation in practice. We conclude the paper with outlining our plans for the remainder of the study. © 2022 ACM.

Vertical integration of supply chains has enabled industrialised house-building companies to develop and use product platforms. Constant changes in the external business environment, such as customer needs, legal requirements and demand fluctuations, continually compel companies to strategically align their product platforms with market position and offering accordingly. Achieving alignment is often hindered by a lack of understanding of the interplay between the external business environment, product platform, offering and market position. The knowledge on product platform alignment in this industry exists in the literature; however, a coherent description of product platform alignment is missing. The aim of this research was, therefore, to expand the knowledge on the strategic aspects of product platforms by describing product platform alignment in industrialised house building. Empirical data were collected in two Swedish companies producing timber-frame single-family houses. The developed model provides a coherent description of product platform alignment via five alignment modes that group interplays between product platform, business model and the external business environment, whereas identified challenges additionally enrich the description. Formalisation of the product platform knowledge and the changeability of manufacturing systems are identified as two main enablers of achieving product platform alignment.

In the last years, there has been a growing interest in the emerging concept of Digital Twins (DTs) among software engineers and researchers. DTs represent a promising paradigm to enhance the predictability, safety, and reliability of cyber-physical systems. They can play a key role in different domains, as it is also witnessed by several ongoing standardisation activities. However, several challenging issues have to be faced in order to effectively adopt DTs, in particular when dealing with critical systems. This work provides a review of the scientific literature on DTs in the railway sector, with a special focus on their relationship with Artificial Intelligence. Challenges and opportunities for the usage of DTs in railways have been identified, with interoperability being the most discussed challenge. One difficulty is to transmit operational data in real-time from edge systems to the cloud in order to achieve timely decision making. We also provide some guidelines to support the design of DTs with a focus on machine learning for railway maintenance. 

The rise of wood buildings in the skylines of cities forces structural dynamic and timber experts to team up to solve one of the new civil-engineering challenges, namely comfort at the higher levels, in light weight buildings, with respect to wind-induced vibrations. Large laminated timber structures with mechanical joints are exposed to turbulent horizontal excitation with most of the wind energy blowing around the lowest resonance frequencies of 50 to 150 m tall buildings. Good knowledge of the spatial distribution of mass, stiffness and damping is needed to predict and mitigate the sway in lighter, flexible buildings. This paper presents vibration tests and reductions of a detailed FE-model of a truss with dowel-type connections leading to models that will be useful for structural engineers. The models also enable further investigations about the parameters of the slotted-in steel plates and dowels connections governing the dynamical response of timber trusses.

Modern software systems often have to cope with uncertain operation conditions, such as changing workloads or fluctuating interference in a wireless network. To ensure that these systems meet their goals these uncertainties have to be mitigated. One approach to realize this is self-adaptation that equips a system with a feedback loop. The feedback loop implements four core functions - monitor, analyze, plan, and execute - that share knowledge in the form of runtime models. For systems with a large number of adaptation options, i.e., large adaptation spaces, deciding which option to select for adaptation may be time consuming or even infeasible within the available time window to make an adaptation decision. This is particularly the case when rigorous analysis techniques are used to select adaptation options, such as formal verification at runtime, which is widely adopted. One technique to deal with the analysis of a large number of adaptation options is reducing the adaptation space using machine learning. State of the art has showed the effectiveness of this technique, yet, a systematic solution that is able to handle different types of goals is lacking. In this paper, we present ML2ASR+, short for Machine Learning to Adaptation Space Reduction Plus. Central to ML2ASR+ is a configurable machine learning pipeline that supports effective analysis of large adaptation spaces for threshold, optimization, and setpoint goals. We evaluate ML2ASR+ for two applications with different sizes of adaptation spaces: an Internet-of-Things application and a service-based system. The results demonstrate that ML2ASR+ can be applied to deal with different types of goals and is able to reduce the adaptation space and hence the time to make adaptation decisions with over 90%, with negligible effect on the realization of the adaptation goals. (C) 2022 The Authors. Published by Elsevier Inc.

It is known that damage or inelastic softening can cause an ill-posed problem leading to localization and mesh-dependence in finite element simulations. In this paper, a nonlocal hardening variable, ̄𝜅 , is introduced in a finite deformation Eulerian formulation of inelasticity with a rate-independent smooth elastic–inelastic transition. This nonlocal variable is defined over an Eulerian region of nonlocality, which is a sphere with radius equal to the characteristic length, 𝐿c, defined in the current deformed geometry of the material. Two models of this nonlocal hardening variable are explored. One model where ̄ 𝜅 is the minimum value of the local hardening 𝜅 within the region of nonlocality, and another model where  ̄𝜅 is the average of 𝜅 in the same region. The influence of the nonlocal hardening variable is studied using an example of a plate that is loaded by a prescribed boundary displacement causing formation of a shear band. Predictions of the applied load vs. displacement curves and contour plots of the total distortional deformation of the plate and the hardening variable 𝜅 are studied. The model based on the minimum value of 𝜅 in the nonlocal region predicts mesh-independent post-peak response of the load vs. displacement curve. Also, it is shown that the characteristic material length, 𝐿c, controls the structure of the shear band developed in the plate.