Search

The advent of Internet of Things and artificial intelligence in the era of Industry 4.0 has transformed decision-making within production systems. In particular, many decisions that previously required significant human activity are now made automatically with minimal human intervention via so-called digital twins (DTs). In the context of maintenance and reliability modeling, this naturally calls for new paradigms that can be seamlessly integrated within DTs for decision-making. The input data for time to failure needed in reliability computations are directly collected from the work center in a digital setting and often do not satisfy a known distribution. A neural network (NN) is proposed here to bypass this difficulty within the DT. Further, an algorithm inspired from machine learning is employed to solve the underlying semi-Markov decision process, whose transition model is captured via the NN. Numerical studies are carried out to demonstrate the usefulness of the approach. Finally, convergence properties of the algorithm are analyzed mathematically. [ABSTRACT FROM AUTHOR]

Digital twins (DTs) provide accurate, data-driven, real-time modeling to create a digital representation of the physical world. The integration of new technologies, such as virtual/mixed reality, artificial intelligence, and DTs, enables modeling and research into ways to achieve better sustainability, greater efficiency, and improved safety in Industry 4.0/5.0 technologies. This paper discusses concepts, limitations, future trends, and potential research directions to provide the infrastructure and underlying intelligence for large-scale semi-automated DT building environments. Grouping these technologies along these lines allows for a better consideration of their individual risk factors and use of available data, resulting in an approach to generate holistic virtual representations (DTs) to facilitate predictive analyses in industrial practices. Artificial intelligence-based DTs are becoming a new tool for monitoring, simulating, and optimizing systems, and the widespread implementation and mastery of this technology will lead to significant improvements in performance, reliability, and profitability. Despite advances, the aforementioned technology still requires research, improvement, and investment. This article's contribution is a concept that, if adopted instead of the traditional approach, can become standard practice rather than an advanced operation and can accelerate this development. [ABSTRACT FROM AUTHOR]

The current outdoor thermal comfort index assessment is either based on thermal sensation votes collected through field surveys/questionnaires or using equations fundamentally backed by thermodynamics, such as the widely used UTCI and PET indices. The predictive ability of all methods suffers from discrepancies as multi-sensory attributes, cultural, emotional, and psychological cognition factors are ignored. These factors are proven to influence the thermal sensation and duration people spend outdoors, and are equally prominent factors as air temperature, solar radiation, and relative humidity. The studies that adopted machine learning models, such as Artificial Neural Networks (ANNs), concentrated on improving the predictive capability of PET, thereby making the field of Artificial Intelligence (AI) domain underexplored. Furthermore, universally adopted outdoor thermal comfort indices under-predict a neutral thermal range, for a reason that is linked to the fact that all indices were validated on European/American subjects living in temperate, cold regions. The review highlighted gaps and challenges in outdoor thermal comfort prediction accuracy by comparing traditional methods and Industry 4.0. Additionally, a further recommendation to improve prediction accuracy by exploiting Industry 4.0 (machine learning, artificial reality, brain–computer interface, geo-spatial digital twin) is examined through Knowledge Translation. [ABSTRACT FROM AUTHOR]

Demands for more accurate machine learning models have given rise to rethinking current modeling approaches that were deemed unsuitable, primarily due to their computational complexity and the lack of availability and accessibility to representative data. In Industry 4.0, rapid advancements in Digital Twin (DT) technologies and the pervasiveness of cost-effective sensor technologies have pushed the incorporation of artificial intelligence, particularly data-driven machine learning models, for use in smart manufacturing. However, the persistent issue with such models is their high sensitivity to the training data and the lack of interpretability in the outcomes, at times generating unrealistic results. The incorporation of knowledge into the machine learning pipeline has been earmarked as the most promising approach to address such issues. This paper aims to answer this call through a Knowledge-embedded Machine Learning (KML) framework for smart manufacturing, which embeds knowledge from experience and, or physics information into the machine learning pipeline, thus making the outcomes from these models more representative of real applications. The merits of KML were then presented through comparative studies showing its capability to outperform knowledge-based and data-driven models. This promising outcome led to the development of frameworks that can potentially incorporate KML for smart manufacturing applications such as Prognostics and Health Management (PHM) and DT, further supporting the usefulness of the proposed KML framework. [ABSTRACT FROM AUTHOR]

Digital twin is the digital representation of an entity, and it drives Industry 4.0. This paper presents a bibliometric analysis of digital twin in the supply chain to help researchers, industry practitioners, and academics to understand the trend, development, and focus of the areas of digital twin in the supply chain. This paper found several key clusters of research, including the designing of a digital twin model, integration of a digital twin model, application of digital twin in quality control, and digital twin in digitalization. In the embryonic stage of research, digital twin was tested in the production line with limited optimization. In the development stage, the importance of digital twin in Industry 4.0 was observed, as big data, machine learning, Industrial Internet of Things, blockchain, edge computing, and cloud-based systems complemented digital twin models. Digital twin was applied to improve sustainability in manufacturing and production logistics. In the current prosperity stage with high annual publications, the recent trends of this topic focus on the integration of deep learning, data models, and artificial intelligence for digitalization. This bibliometric analysis also found that the COVID-19 pandemic drove the start of the prosperity stage of digital twin research in the supply chain. Researchers in this field are slowly moving towards applying digital twin for human-centric systems and mass personalization to prepare to transit to Industry 5.0. [ABSTRACT FROM AUTHOR]

Modern manufacturing has to cope with dynamic and changing circumstances. Market fluctuations, the effects caused by unpredictable material shortages, highly variable product demand, and worker availability all require system robustness, flexibility, and resilience. To adapt to these new requirements, manufacturers should consider investigating, investing in, and implementing system autonomy. Autonomy is being adopted in multiple industrial contexts, but divergences arise when formalizing the concept of autonomous systems. To develop an implementation of autonomous manufacturing systems, it is essential to specify what autonomy means, how autonomous manufacturing systems are different from other autonomous systems, and how autonomous manufacturing systems are identified and achieved through the main features and enabling technologies. With a comprehensive literature review, this paper provides a definition of autonomy in the manufacturing context, infers the features of autonomy from different engineering domains, and presents a five-level model of autonomy — associated with maturity levels for the features — to ensure the complete identification and evaluation of autonomous manufacturing systems. The paper also presents the evaluation of a real autonomous system that serves as a use-case and a validation of the model. [ABSTRACT FROM AUTHOR]

Robotic systems have become a standard tool in modern manufacturing due to their unique characteristics, such as repeatability, precision, and speed, among others. One of the main challenges of robotic manipulators is the low degree of reliability. Low reliability increases the probability of disruption in manufacturing processes, minimizing in this way the productivity and by extension the profit of the company. To address the abovementioned challenges, this research work proposes a robotic cell reliability optimization method based on digital twin and predictive maintenance. Concretely, the simulation of the robot is provided, and emphasis is given to the reliability optimization of the robotic cell's critical component. A supervised machine learning model is trained, aiming to detect and classify the faulty behavior of the critical component. Furthermore, a framework is proposed for the remaining useful life prediction with the aim to improve the reliability of the robotic cell. Thus, following the results of the current research work, appropriate maintenance tasks can be applied, preventing the robotic cell from serious failures and ensuring high reliability. [ABSTRACT FROM AUTHOR]

As companies are trying to build more resilient supply chains using digital twins created by smart manufacturing technologies, it is imperative that senior executives and technology providers understand the crucial role of process simulation and AI in quantifying the uncertainties of these complex systems. The resulting digital twins enable users to replay history, gain predictive visibility into the future, and identify corrective actions to optimize future performance. In this article, we define process digital twins and their four foundational elements. We discuss how key digital twin functions and enabling AI and simulation technologies integrate to describe, predict, and optimize supply chains for Industry 4.0 implementations. [ABSTRACT FROM AUTHOR]

There is significant interest in emerging technologies. Universities, companies and other adopters are researching how and when these technologies should be implemented. However, this research area still lacks ways to evaluate the maturity level of the technologies and rapid experimentation concepts for testing the new technologies. This paper addresses the research gap by providing a new evaluation method and a rapid experimentation concept. This method and concept were successfully used in twenty-five Flash-projects, where five emerging digital Industry 4.0 themes evaluated. [ABSTRACT FROM AUTHOR]

As an emerging technology in the era of Industry 4.0, digital twin is gaining unprecedented attention because of its promise to further optimize process design, quality control, health monitoring, decision- and policy-making, and more, by comprehensively modeling the physical world as a group of interconnected digital models. In a two-part series of papers, we examine the fundamental role of different modeling techniques, twinning enabling technologies, and uncertainty quantification and optimization methods commonly used in digital twins. This second paper presents a literature review of key enabling technologies of digital twins, with an emphasis on uncertainty quantification, optimization methods, open-source datasets and tools, major findings, challenges, and future directions. Discussions focus on current methods of uncertainty quantification and optimization and how they are applied in different dimensions of a digital twin. Additionally, this paper presents a case study where a battery digital twin is constructed and tested to illustrate some of the modeling and twinning methods reviewed in this two-part review. Code and preprocessed data for generating all the results and figures presented in the case study are available on Github. [ABSTRACT FROM AUTHOR]

The digital twin has recently become a popular topic in research related to manufacturing, such as Industry 4.0, the industrial internet of things, and cyber-physical systems. In addition, digital twins are the focus of several research areas: construction, urban management, digital transformation of the economy, medicine, virtual reality, software testing, and others. The concept is not yet fully defined, its scope seems unlimited, and the topic is relatively new; all this can present a barrier to research. The main goal of this paper is to develop a proper methodology for visualizing the digital-twin science landscape using modern bibliometric tools, text-mining and topic-modeling, based on machine learning models—Latent Dirichlet Allocation (LDA) and BERTopic (Bidirectional Encoder Representations from Transformers). The scope of the study includes 8693 publications on the topic selected from the Scopus database, published between January 1993 and September 2022. Keyword co-occurrence analysis and topic-modeling indicate that studies on digital twins are still in the early stage of development. At the same time, the core of the topic is growing, and some topic clusters are emerging. More than 100 topics can be identified; the most popular and fastest-growing topic is 'digital twins of industrial robots, production lines and objects.' Further efforts are needed to verify the proposed methodology, which can be achieved by analyzing other research fields. [ABSTRACT FROM AUTHOR]

This work describes a structured solution that integrates digital twin models, machine-learning algorithms, and Industry 4.0 technologies (Internet of Things in particular) with the ultimate aim of detecting the presence of anomalies in the functioning of industrial systems. The proposed solution has been designed to be suitable for implementation in industrial plants not directly designed for Industry 4.0 applications. More precisely, this manuscript delineates an approach for implementing three machine-learning algorithms into a digital twin environment and then applying them to a real plant. This paper is based on two previous studies in which the digital twin environment was first developed for the industrial plant under investigation, and then used for monitoring selected plant parameters. Findings from the previous studies are exploited in this work and advanced by implementing and testing the machine-learning algorithms. The results show that two out of the three machine-learning algorithms are effective enough in predicting anomalies, thus suggesting their implementation for enhancing the safety of employees working at industrial plants. [ABSTRACT FROM AUTHOR]