Hasil untuk "Industrial medicine. Industrial hygiene"

Yiran Ma, Jerome Le Ny, Zhichao Chen et al.

In modern process industries, data-driven models are important tools for real-time monitoring when key performance indicators are difficult to measure directly. While accurate predictions are essential, reliable uncertainty quantification (UQ) is equally critical for safety, reliability, and decision-making, but remains a major challenge in current data-driven approaches. In this work, we introduce a diffusion-based posterior sampling framework that inherently produces well-calibrated predictive uncertainty via faithful posterior sampling, eliminating the need for post-hoc calibration. In extensive evaluations on synthetic distributions, the Raman-based phenylacetic acid soft sensor benchmark, and a real ammonia synthesis case study, our method achieves practical improvements over existing UQ techniques in both uncertainty calibration and predictive accuracy. These results highlight diffusion samplers as a principled and scalable paradigm for advancing uncertainty-aware modeling in industrial applications.

Haonan Li, Elizabeth A. Holzhausen, Devendra Paudel et al.

Abstract This study investigates independent and joint effects of fine particulate matter (PM2.5) components on early childhood neurodevelopment and explores emission sources of key toxic components. We included 165 mother-infant dyads from Southern California. Annual average concentrations of 15 PM2.5 components, including carbonaceous components, secondary inorganic salts, and trace elements, were estimated for the birth year. Neurodevelopment across cognitive, language, motor, social-emotional, and adaptive behavior domains was assessed at age 2 using Bayley-III Scales. Mixture effects and key contributors were evaluated using weighted quantile sum (WQS) and Bayesian kernel machine regression (BKMR). Source inference was conducted through inter-component clustering and spatial analysis. Linear regression showed PM2.5, sulfate (SO4 2−), nitrate (NO3 −), ammonium (NH4 +), copper (Cu), nickel (Ni), lead (Pb), and vanadium (V) were inversely, while calcium (Ca) and zinc (Zn) were positively, associated with adaptive behavior scores (p < 0.05). WQS showed negative associations between the mixture and adaptive behavior (p = 0.02–0.06), with Ni, Cu, V, and SO₄²⁻ as key contributors. BKMR showed similar trends. Ni, V, and SO4 2− likely originate from heavy oil combustion, and Cu from brake wear. Findings suggest that PM2.5 components, particularly from traffic and marine fuel combustion, may adversely affect adaptive behavior in early childhood.

Dan Parii, Evelyne Janssen, Guangzhi Tang et al.

Accurately predicting the lifespan of critical device components is essential for maintenance planning and production optimization, making it a topic of significant interest in both academia and industry. In this work, we investigate the use of survival analysis for predicting the lifespan of production printheads developed by Canon Production Printing. Specifically, we focus on the application of five techniques to estimate survival probabilities and failure rates: the Kaplan-Meier estimator, Cox proportional hazard model, Weibull accelerated failure time model, random survival forest, and gradient boosting. The resulting estimates are further refined using isotonic regression and subsequently aggregated to determine the expected number of failures. The predictions are then validated against real-world ground truth data across multiple time windows to assess model reliability. Our quantitative evaluation using three performance metrics demonstrates that survival analysis outperforms industry-standard baseline methods for printhead lifespan prediction.

Tong Nie, Jian Sun, Wei Ma

Networked urban systems facilitate the flow of people, resources, and services, and are essential for economic and social interactions. These systems often involve complex processes with unknown governing rules, observed by sensor-based time series. To aid decision-making in industrial and engineering contexts, data-driven predictive models are used to forecast spatiotemporal dynamics of urban systems. Current models such as graph neural networks have shown promise but face a trade-off between efficacy and efficiency due to computational demands. Hence, their applications in large-scale networks still require further efforts. This paper addresses this trade-off challenge by drawing inspiration from physical laws to inform essential model designs that align with fundamental principles and avoid architectural redundancy. By understanding both micro- and macro-processes, we present a principled interpretable neural diffusion scheme based on Transformer-like structures whose attention layers are induced by low-dimensional embeddings. The proposed scalable spatiotemporal Transformer (ScaleSTF), with linear complexity, is validated on large-scale urban systems including traffic flow, solar power, and smart meters, showing state-of-the-art performance and remarkable scalability. Our results constitute a fresh perspective on the dynamics prediction in large-scale urban networks.

Ray Wai Man Kong, Ding Ning, Theodore Ho Tin Kong

This article presents applied research on line balancing within the modern garment industry, focusing on the significant impact of intelligent hanger systems and hanger lines on the stitching process, by Lean Methodology for garment modernization. It explores the application of line balancing in the modern garment industry, focusing on the significant impact of intelligent hanger systems and hanger lines on the stitching process. It aligns with Lean Methodology principles for garment modernization. Without the implementation of line balancing technology, the garment manufacturing process using hanger systems cannot improve output rates. The case study demonstrates that implementing intelligent line balancing in a straightforward practical setup facilitates lean practices combined with a digitalization system and automaton. This approach illustrates how to enhance output and reduce accumulated work in progress.

Tuo Liu, Melissa A. Furlong, Justin M. Snider et al.

Abstract Background Firefighters have frequent exposure to carcinogens and an increased risk of cancer. Wildland-urban interface (WUI) fires, which involve both structures and undeveloped wildland fuels, pose unique challenges to the health of firefighters. However, the extent of health risks associated with these fires remains underexplored. Objectives This study aims to identify altered urine metabolites and metabolic processes among male firefighters that were associated with WUI fires as compared with municipal structure fires (MSF). Methods Untargeted metabolomic profiling was applied to pre-exposure (baseline) and postfire urine samples collected from firefighters responding to WUI and MSF fires. Differential analysis was conducted by fitting linear mixed effects regression models on preprocessed ion intensity and exposure status while adjusting for demographic covariates. Differential metabolites by post-exposure status were identified using a false discovery rate (FDR) threshold of < 0.05. Pathway analysis was performed to identify pathways that were significantly perturbed at a Bonferroni adjusted p-value < 0.05 level. We conducted differential and pathway analyses in both the WUI and MSF cohorts and compared the two fire types in terms of the number of differentially expressed metabolites and patterns of metabolic pathway enrichment. Results Eighty-five firefighters contributed paired baseline and post-fire samples from WUI events, and 98 firefighters contributed paired baseline and post-fire samples from MSF events. We performed metabolic profiling on baseline and postfire urine samples from WUI and MSF using four modes: HILIC(-), HILIC(+), C18(-), and C18(+) and identified metabolites against an in-house library. We identified 244, 297, 320, and 266 level-1 metabolites from the four respective modes. In the statistical analysis, the main model identified a total of 176 differential metabolites from WUI fires. For MSF, the model identified a total of 652 differential metabolites from the four respective modes. Most metabolites with significant changes after a WUI fire also changed significantly after an MSF event. Two metabolic pathways were significantly enriched after WUI fires, while 7 pathways were significantly enriched after MSF exposure and 2 pathways overlapped between the two types of fires. Conclusion Fire exposure induces numerous metabolic perturbations in firefighters responding to WUI fires, potentially contributing to their elevated cancer risk. Although individual metabolites changed in a similar fashion across both WUI and MSF, MSF were associated with an increased number of metabolite changes and some of the enriched pathways differed between exposures to WUI fires vs. MSF. These findings suggest that WUI and MSF exposures may share common biological responses while also posing unique health risks to firefighters.

Paula Fraga-Lamas, Tiago M Fernandez-Carames, Oscar Blanco-Novoa et al.

Shipbuilding companies are upgrading their inner workings in order to create Shipyards 4.0, where the principles of Industry 4.0 are paving the way to further digitalized and optimized processes in an integrated network. Among the different Industry 4.0 technologies, this article focuses on Augmented Reality, whose application in the industrial field has led to the concept of Industrial Augmented Reality (IAR). This article first describes the basics of IAR and then carries out a thorough analysis of the latest IAR systems for industrial and shipbuilding applications. Then, in order to build a practical IAR system for shipyard workers, the main hardware and software solutions are compared. Finally, as a conclusion after reviewing all the aspects related to IAR for shipbuilding, it is proposed an IAR system architecture that combines Cloudlets and Fog Computing, which reduce latency response and accelerate rendering tasks while offloading compute intensive tasks from the Cloud.

Dan Lehman, Tim J. Schoonbeek, Shao-Hsuan Hung et al.

Recognizing errors in assembly and maintenance procedures is valuable for industrial applications, since it can increase worker efficiency and prevent unplanned down-time. Although assembly state recognition is gaining attention, none of the current works investigate assembly error localization. Therefore, we propose StateDiffNet, which localizes assembly errors based on detecting the differences between a (correct) intended assembly state and a test image from a similar viewpoint. StateDiffNet is trained on synthetically generated image pairs, providing full control over the type of meaningful change that should be detected. The proposed approach is the first to correctly localize assembly errors taken from real ego-centric video data for both states and error types that are never presented during training. Furthermore, the deployment of change detection to this industrial application provides valuable insights and considerations into the mechanisms of state-of-the-art change detection algorithms. The code and data generation pipeline are publicly available at: https://timschoonbeek.github.io/error_seg.

Alexander Windmann, Philipp Wittenberg, Marvin Schieseck et al.

In Industry 4.0, Cyber-Physical Systems (CPS) generate vast data sets that can be leveraged by Artificial Intelligence (AI) for applications including predictive maintenance and production planning. However, despite the demonstrated potential of AI, its widespread adoption in sectors like manufacturing remains limited. Our comprehensive review of recent literature, including standards and reports, pinpoints key challenges: system integration, data-related issues, managing workforce-related concerns and ensuring trustworthy AI. A quantitative analysis highlights particular challenges and topics that are important for practitioners but still need to be sufficiently investigated by academics. The paper briefly discusses existing solutions to these challenges and proposes avenues for future research. We hope that this survey serves as a resource for practitioners evaluating the cost-benefit implications of AI in CPS and for researchers aiming to address these urgent challenges.

Tiago M. Fernández-Caramés, Paula Fraga-Lamas

The Metaverse is a concept that proposes to immerse users into real-time rendered 3D content virtual worlds delivered through Extended Reality (XR) devices like Augmented and Mixed Reality (AR/MR) smart glasses and Virtual Reality (VR) headsets. When the Metaverse concept is applied to industrial environments, it is called Industrial Metaverse, a hybrid world where industrial operators work by using some of the latest technologies. Currently, such technologies are related to the ones fostered by Industry 4.0, which is evolving towards Industry 5.0, a paradigm that enhances Industry 4.0 by creating a sustainable and resilient world of industrial human-centric applications. The Industrial Metaverse can benefit from Industry 5.0, since it implies making use of dynamic and up-to-date content, as well as fast human-to-machine interactions. To enable such enhancements, this article proposes the concept of Meta-Operator: an Industry 5.0 worker that interacts with Industrial Metaverse applications and with his/her surroundings through advanced XR devices. This article provides a description of the technologies that support Meta-Operators: the main components of the Industrial Metaverse, the latest XR technologies and the use of Opportunistic Edge Computing communications (to interact with surrounding IoT/IioT devices). Moreover, this paper analyzes how to create the next generation of Industrial Metaverse applications based on Industry 5.0, including the integration of AR/MR devices with IoT/IIoT solutions, the development of advanced communications or the creation of shared experiences. Finally, this article provides a list of potential Industry 5.0 applications for the Industrial Metaverse and analyzes the main challenges and research lines. Thus, this article provides useful guidelines for the researchers that will create the next generation of applications for the Industrial Metaverse.

Idalmis Acosta Pérez , Fernando Marrero Delgado , José Ángel Espinosa Acosta et al.

Introducción: La inclusión de la gestión de riesgos de Seguridad y Salud en el Trabajo en la planificación estratégica constituye una herramienta necesaria para que la organización pueda anticiparse y mitigar posibles amenazas e identificar oportunidades para el crecimiento y la mejora continua. Objetivo: Diseñar un procedimiento, científicamente fundamentado, que permita la inclusión de la gestión de riesgos de Seguridad y Salud dentro de la proyección estratégica, en aras de mejorar el sistema de gestión y por ende, el entorno laboral y las condiciones de trabajo. Métodos: Incluyó el diseño de un procedimiento para la gestión estratégica de los riesgos de Seguridad y Salud, con una secuencia lógica de cuatro fases, que incluye métodos empíricos como el criterio de expertos y revisión de la documentación legal en materia de gestión de riesgo. Además, el procedimiento contiene pasos para la realización de un diagnostico estratégico donde se definen la política y la filosofía en materia de gestión de riesgos, se identifican los riesgos y se evalúan según la severidad, ocurrencia y detectatibilidad, para luego calcular el Nivel del Prioridad del Riesgo (NPR). Resultados: Se logró la inclusión de los riesgos de Seguridad y Salud desde la planificación estratégica, además, se conoce el Nivel de Percepción de Convergencia Estratégica en la Gestión de Riesgos de SST (NCERSST). Conclusiones: El procedimiento diseñado permitirá identificar las principales debilidades que presenta la organización relacionada con la gestión estratégica de sus riesgos Introduction: The inclusion of Occupational Health and Safety risk management in strategic planning constitutes a necessary tool so that the organization can anticipate and mitigate possible threats and identify opportunities for growth and continuous improvement. Objective: To design a scientifically based procedure, which allows the inclusion of Health and Safety risk management within the strategic projection, in order to improve the management system and therefore, the work environment and the working conditions. Methods: Included the design of a procedure for the strategic management of Health and Safety risks, with a logical sequence of four phases, which includes empirical methods such as expert judgment and review of legal documentation on risk management. In addition, the procedure includes steps to carry out a strategic diagnosis where the policy and philosophy regarding risk management are defined, risks are identified and evaluated according to severity, occurrence and detectability, and then calculate the Priority Level of Risk (PLR). Results: The inclusion of Health and Safety risks is achieved from the strategic planning, in addition, the Level of Perception of Strategic Convergence in (Security and health at work) Risk Management (NCERSST) is known. Conclusions: The designed procedure will allow identifying the main weaknesses that the organization presents related to the strategic management of its risks

Yunyi Wang, Ke Xu, Xiao Gao et al.

Abstract Background Increasing attention is being paid to the environmental and health impacts of nanoplastics (NPs) pollution. Exposure to nanoplastics (NPs) with different charges and functional groups may have different adverse effects after ingestion by organisms, yet the potential ramifications on mammalian blood glucose levels, and the risk of diabetes remain unexplored. Results Mice were exposed to PS-NPs/COOH/NH2 at a dose of 5 mg/kg/day for nine weeks, either alone or in a T2DM model. The findings demonstrated that exposure to PS-NPs modified by different functional groups caused a notable rise in fasting blood glucose (FBG) levels, glucose intolerance, and insulin resistance in a mouse model of T2DM. Exposure to PS-NPs-NH2 alone can also lead the above effects to a certain degree. PS-NPs exposure could induce glycogen accumulation and hepatocellular edema, as well as injury to the pancreas. Comparing the effect of different functional groups or charges on T2DM, the PS-NPs-NH2 group exhibited the most significant FBG elevation, glycogen accumulation, and insulin resistance. The phosphorylation of AKT and FoxO1 was found to be inhibited by PS-NPs exposure. Treatment with SC79, the selective AKT activator was shown to effectively rescue this process and attenuate T2DM like lesions. Conclusions Exposure to PS-NPs with different functional groups (charges) induced T2DM-like lesions. Amino-modified PS-NPs cause more serious T2DM-like lesions than pristine PS-NPs or carboxyl functionalized PS-NPs. The underlying mechanisms involved the inhibition of P-AKT/P-FoxO1. This study highlights the potential risk of NPs pollution on T2DM, and provides a new perspective for evaluating the impact of plastics aging.

Christos Anagnostopoulos, Georgios Mylonas, Apostolos P. Fournaris et al.

Virtual and augmented reality are currently enjoying a great deal of attention from the research community and the industry towards their adoption within industrial spaces and processes. However, the current design and implementation landscape is still very fluid, while the community as a whole has not yet consolidated into concrete design directions, other than basic patterns. Other open issues include the choice over a cloud or edge-based architecture when designing such systems. Within this work, we present our approach for a monitoring intervention inside a factory space utilizing both VR and AR, based primarily on edge computing, while also utilizing the cloud. We discuss its main design directions, as well as a basic ontology to aid in simple description of factory assets. In order to highlight the design aspects of our approach, we present a prototype implementation, based on a use case scenario in a factory site, within the context of the ENERMAN H2020 project.

Sicong Xie, Binbin Hu, Fengze Li et al.

Aiming at helping users locally discovery retail services (e.g., entertainment and dinning), Online to Offline (O2O) service platforms have become popular in recent years, which greatly challenge current recommender systems. With the real data in Alipay, a feeds-like scenario for O2O services, we find that recurrence based temporal patterns and position biases commonly exist in our scenarios, which seriously threaten the recommendation effectiveness. To this end, we propose COUPA, an industrial system targeting for characterizing user preference with following two considerations: (1) Time aware preference: we employ the continuous time aware point process equipped with an attention mechanism to fully capture temporal patterns for recommendation. (2) Position aware preference: a position selector component equipped with a position personalization module is elaborately designed to mitigate position bias in a personalized manner. Finally, we carefully implement and deploy COUPA on Alipay with a cooperation of edge, streaming and batch computing, as well as a two-stage online serving mode, to support several popular recommendation scenarios. We conduct extensive experiments to demonstrate that COUPA consistently achieves superior performance and has potential to provide intuitive evidences for recommendation

Fikret Basic, Christian Steger, Christian Seifert et al.

With the advent of clean energy awareness and systems that rely on extensive battery usage, the community has seen an increased interest in the development of more complex and secure Battery Management Systems (BMS). In particular, the inclusion of BMS in modern complex systems like electric vehicles and power grids has presented a new set of security-related challenges. A concern is shown when BMS are intended to extend their communication with external system networks, as their interaction can leave many backdoors open that potential attackers could exploit. Hence, it is highly desirable to find a general design that can be used for BMS and its system inclusion. In this work, a security architecture solution is proposed intended for the communication between BMS and other system devices. The aim of the proposed architecture is to be easily applicable in different industrial settings and systems, while at the same time keeping the design lightweight in nature.

Eduard Hirsch, Simon Hoher, Stefan Huber

Industry 4.0 factories are complex and data-driven. Data is yielded from many sources, including sensors, PLCs, and other devices, but also from IT, like ERP or CRM systems. We ask how to collect and process this data in a way, such that it includes metadata and can be used for industrial analytics or to derive intelligent support systems. This paper describes a new, query model based approach, which uses a big data architecture to capture data from various sources using OPC UA as a foundation. It buffers and preprocesses the information for the purpose of harmonizing and providing a holistic state space of a factory, as well as mappings to the current state of a production site. That information can be made available to multiple processing sinks, decoupled from the data sources, which enables them to work with the information without interfering with devices of the production, disturbing the network devices they are working in, or influencing the production process negatively. Metadata and connected semantic information is kept throughout the process, allowing to feed algorithms with meaningful data, so that it can be accessed in its entirety to perform time series analysis, machine learning or similar evaluations as well as replaying the data from the buffer for repeatable simulations.

Mihai-Horia Băieş, Vlad-Dan Cotuţiu, Marina Spînu et al.

Internal parasitic diseases of swine constitute a major welfare and health concern in low-input livestock farming. Due to an increase in chemical resistance, phytotherapeutic remedies have become an alternative for the prophylaxis and therapy of digestive parasitosis, albeit few remedies have been subjected to scientific validation. Low-input swine farming in Romania has adopted the traditional use of phytotherapy for controlling pathogens in livestock. The current study aimed to assess the antiparasitic potential of <i>Calendula officinalis</i> and <i>Satureja hortensis</i> against digestive parasites of swine in two low-input farms. The fecal samples were collected from sows, fatteners, and weaners, and were tested using the following coproparasitological methods: centrifugal sedimentation, flotation (Willis, McMaster egg counting technique), Ziehl–Neelsen stain modified by Henricksen, modified Blagg method, and in vitro nematode larvae/protozoan oocyst cultures. Six species of digestive parasites were diagnosed, namely <i>Ascaris suum</i>, <i>Trichuris suis</i>, <i>Oesophagostomum</i> spp., <i>Balantioides coli</i>, <i>Eimeria</i> spp., and <i>Cryptosporidium</i> spp., in various combinations, dependent on the swine category. A dose of 140 mg/kg bw/day of <i>C. officinalis</i> and 100 mg/kg bw/day of <i>S. hortensis</i> powders administered for 10 consecutive days revealed a strong antiprotozoal and anthelmintic activity on the aforementioned parasites. The curative efficacy can be attributed to the presence of polyphenols, sterols, tocopherols, and methoxylated flavones. In conclusion, our results indicate that <i>S. hortensis</i> and <i>C. officinalis</i> are promising alternatives to the commercially available antiparasitics, enabling their use as natural antiparasitic products against gastrointestinal parasites in pigs.

Geetanjali Rathee, Farhan Ahmad, Naveen Jaglan et al.

Industrial Internet-of-Things (IIoT) is a powerful IoT application which remodels the growth of industries by ensuring transparent communication among various entities such as hubs, manufacturing places and packaging units. Introducing data science techniques within the IIoT improves the ability to analyze the collected data in a more efficient manner, which current IIoT architectures lack due to their distributed nature. From a security perspective, network anomalies/attackers pose high security risk in IIoT. In this paper, we have addressed this problem, where a coordinator IoT device is elected to compute the trust of IoT devices to prevent the malicious devices to be part of network. Further, the transparency of the data is ensured by integrating a blockchain-based data model. The performance of the proposed framework is validated extensively and rigorously via MATLAB against various security metrics such as attack strength, message alteration, and probability of false authentication. The simulation results suggest that the proposed solution increases IIoT network security by efficiently detecting malicious attacks in the network.

Chandan Sharma, Roopak Sinha, Paulo Leitao

The ongoing fourth Industrial Revolution depends mainly on robust Industrial Cyber-Physical Systems (ICPS). ICPS includes computing (software and hardware) abilities to control complex physical processes in distributed industrial environments. Industrial agents, originating from the well-established multi-agent systems field, provide complex and cooperative control mechanisms at the software level, allowing us to develop larger and more feature-rich ICPS. The IEEE P2660.1 standardisation project, "Recommended Practices on Industrial Agents: Integration of Software Agents and Low Level Automation Functions" focuses on identifying Industrial Agent practices that can benefit ICPS systems of the future. A key problem within this project is identifying the best-fit industrial agent practices for a given ICPS. This paper reports on the design and development of a tool to address this challenge. This tool, called IASelect, is built using graph databases and provides the ability to flexibly and visually query a growing repository of industrial agent practices relevant to ICPS. IASelect includes a front-end that allows industry practitioners to interactively identify best-fit practices without having to write manual queries.

Simone Grimaldi, Aamir Mahmood, Syed Ali Hassan et al.

The limited coexistence capabilities of current Internet-of-things (IoT) wireless standards produce inefficient spectrum utilization and mutual performance impairment. The entity of the issue escalates in industrial IoT (IIoT) applications, which instead have stringent quality-of-service requirements and exhibit very-low error tolerance. The constant growth of wireless applications over unlicensed bands mandates then the adoption of dynamic spectrum access techniques, which can greatly benefit from interference mapping over multiple dimensions of the radio space. In this article, the authors analyze the critical role of real-time interference detection and classification mechanisms that rely on IIoT devices only, without the added complexity of specialized hardware. The trade-offs between classification performance and feasibility are analyzed in connection with the implementation on low-complexity IIoT devices. Moreover, the authors explain how to use such mechanisms for enabling IIoT networks to construct and maintain multidimensional interference maps at run-time in an autonomous fashion. Lastly, the authors give an overview of the opportunities and challenges of using interference maps to enhance the performance of IIoT networks under interference.