Hasil untuk "Industrial hygiene. Industrial welfare"

Pengfei Yue, Xiaokang Jiang, Yilin Lu et al.

Industrial Anomaly Detection (IAD) is vital for manufacturing, yet traditional methods face significant challenges: unsupervised approaches yield rough localizations requiring manual thresholds, while supervised methods overfit due to scarce, imbalanced data. Both suffer from the "One Anomaly Class, One Model" limitation. To address this, we propose Referring Industrial Anomaly Segmentation (RIAS), a paradigm leveraging language to guide detection. RIAS generates precise masks from text descriptions without manual thresholds and uses universal prompts to detect diverse anomalies with a single model. We introduce the MVTec-Ref dataset to support this, designed with diverse referring expressions and focusing on anomaly patterns, notably with 95% small anomalies. We also propose the Dual Query Token with Mask Group Transformer (DQFormer) benchmark, enhanced by Language-Gated Multi-Level Aggregation (LMA) to improve multi-scale segmentation. Unlike traditional methods using redundant queries, DQFormer employs only "Anomaly" and "Background" tokens for efficient visual-textual integration. Experiments demonstrate RIAS's effectiveness in advancing IAD toward open-set capabilities. Code: https://github.com/swagger-coder/RIAS-MVTec-Ref.

Rocco Loris Del Vecchio, Paolo Bracciano, Francesca Borghi et al.

<b>Background:</b> Carcinogenic, Mutagenic, and Reprotoxic (CMR) substances are among the most significant occupational health hazards in healthcare and research laboratories. Despite preventive measures and regulations, exposure assessment and risk management remain complex due to varied working practices, mixed exposures, and the lack of harmonized monitoring protocols. This systematic review investigates occupational exposure to CMR substances in laboratory and healthcare environments. <b>Methods:</b> Searches were conducted in PubMed, Scopus, and Web of Science up to February 2025 using tailored keyword strategies. Studies published between 2020 and 2025 reporting exposure assessment, monitoring, and/or risk management of CMR chemicals were included; non-English papers and irrelevant studies were excluded. Titles/abstracts and full texts were screened independently by two reviewers with arbitration by a third. Risk of bias was assessed by three authors who independently evaluated each study. A narrative synthesis with frequency tables was performed; no meta-analysis was conducted. <b>Results:</b> Of 446 screened records, 50 studies were included. Formaldehyde (25 studies) and antineoplastic drugs (18 studies) were most frequently examined. Healthcare settings—e.g., hospital pharmacies, oncology wards, and pathology laboratories—were predominant, while research laboratories were underrepresented. Inhalation was the main exposure route for formaldehyde, whereas dermal uptake and surface contamination predominated for antineoplastic drugs. Monitoring methods included air sampling, surface wipe testing, and biological assays; preventive strategies varied and were inconsistently applied. Most included studies involved environmental monitoring and did not report participant numbers, so a total number of participants cannot be aggregated; for the main outcomes, participant counts were often not available. Limitations of the evidence include marked heterogeneity across settings, matrices, analytical methods, and reporting units, which precluded meta-analysis, as well as imprecision and incomplete reporting in several studies. <b>Conclusions:</b> Findings reveal persistent gaps in harmonized exposure limits, monitoring standards, and long-term health surveillance, underscoring the need for comprehensive prevention strategies. This review was not registered and did not receive any external funding.

Jannick Stranghöner, Philipp Hartmann, Marco Braun et al.

High-mix low-volume (HMLV) industrial assembly, common in small and medium-sized enterprises (SMEs), requires the same precision, safety, and reliability as high-volume automation while remaining flexible to product variation and environmental uncertainty. Current robotic systems struggle to meet these demands. Manual programming is brittle and costly to adapt, while learning-based methods suffer from poor sample efficiency and unsafe exploration in contact-rich tasks. To address this, we present SHaRe-RL, a reinforcement learning framework that leverages multiple sources of prior knowledge. By (i) structuring skills into manipulation primitives, (ii) incorporating human demonstrations and online corrections, and (iii) bounding interaction forces with per-axis compliance, SHaRe-RL enables efficient and safe online learning for long-horizon, contact-rich industrial assembly tasks. Experiments on the insertion of industrial Harting connector modules with 0.2-0.4 mm clearance demonstrate that SHaRe-RL achieves reliable performance within practical time budgets. Our results show that process expertise, without requiring robotics or RL knowledge, can meaningfully contribute to learning, enabling safer, more robust, and more economically viable deployment of RL for industrial assembly.

Parul Khanna, Sameer Prabhu, Ramin Karim et al.

The construction industry is presently going through a transformation led by adopting digital technologies that leverage Artificial Intelligence (AI). These industrial AI solutions assist in various phases of the construction process, including planning, design, production and management. In particular, the production phase offers unique potential for the integration of such AI-based solutions. These AI-based solutions assist site managers, project engineers, coordinators and other key roles in making final decisions. To facilitate the decision-making process in the production phase of construction through a human-centric AI-based solution, it is important to understand the needs and challenges faced by the end users who interact with these AI-based solutions to enhance the effectiveness and usability of these systems. Without this understanding, the potential usage of these AI-based solutions may be limited. Hence, the purpose of this research study is to explore, identify and describe the key factors crucial for developing AI solutions in the construction industry. This study further identifies the correlation between these key factors. This was done by developing a demonstrator and collecting quantifiable feedback through a questionnaire targeting the end users, such as site managers and construction professionals. This research study will offer insights into developing and improving these industrial AI solutions, focusing on Human-System Interaction aspects to enhance decision support, usability, and overall AI solution adoption.

Oscar Adamuz-Hinojosa, Felix Delgado-Ferro, Núria Domènech et al.

The digital transformation driven by Industry 4.0 relies on networks that support diverse traffic types with strict deterministic end-to-end latency and mobility requirements. To meet these requirements, future industrial automation networks will use time-sensitive networking, integrating 5G as wireless access points to connect production lines with time-sensitive networking bridges and the enterprise edge cloud. However, achieving deterministic end-to-end latency remains a challenge, particularly due to the variable packet transmission delay introduced by the 5G system. While time-sensitive networking bridges typically operate with latencies in the range of hundreds of microseconds, 5G systems may experience delays ranging from a few to several hundred milliseconds. This paper investigates the potential of configuring the 5G time division duplex pattern to minimize packet transmission delay in industrial environments. Through empirical measurements using a commercial 5G system, we evaluate different TDD configurations under varying traffic loads, packet sizes and full buffer status report activation. Based on our findings, we provide practical configuration recommendations for satisfying requirements in industrial automation, helping private network providers increase the adoption of 5G.

Anwar Ahmed Khan, Shama Siddiqui, Indrakshi Dey

Industrial Internet of Things (IIoT) promises to revolutionize industrial operations and productions through utilizing Machine-to-Machine (M2M) communications. Since each node in such environments generates various types of data with diverse service requirements, MAC protocol holds crucial importance to ensure efficient delivery. In this context, simple to complex MAC schemes are found in literature. This paper focuses on evaluating the performance of two major techniques "slot stealing" and "packet fragmentation" for the IIoT; representative protocols SS-MAC and FROG-MAC have been chosen from each category respectively. We conducted realistic simulations for the two protocols using Contiki. Delay and packet loss comparison for SS-MAC and FROG-MAC indicates the superiority of FROG-MAC due to reduction in the waiting time for urgent traffic. Thus, a simple fragmentation scheme could be deployed for efficient scheduling of heterogenous traffic in the industrial environments.

Karina M. Sindermann, Esma S. Gel, Nesim K. Erkip

Industrial Vending Machines (IVMs) automate the dispensing of a variety of supplies like safety equipment and tools at customer sites, providing 24/7 access while tracking inventory in real-time. Industrial distribution companies typically manage the replenishment of IVMs using periodic schedules, which do not take advantage of these advanced real-time monitoring capabilities. We develop two approaches to optimize the long-term average cost of replenishments and stockouts per unit time: a state-dependent optimal control policy that jointly considers all inventory levels (referred to as trigger set policy) and a fixed cycle policy that optimizes replenishment frequency. We prove the monotonicity of the optimal trigger set policy and leverage it to design a computationally efficient approximate online control framework. Unlike existing methods, which typically handle a very limited number of items due to computational constraints, our approach scales to hundreds of items while achieving near-optimal performance. Leveraging transaction data from our industrial partner, we conduct an extensive set of numerical experiments to demonstrate this claim. Our results show that optimal fixed cycle replenishment reduces costs by 61.7 to 78.6% compared to current practice, with our online control framework delivering an additional 4.1 to 22.9% improvement. Our novel theoretical results provide practical tools for effective replenishment management in this modern vendor-managed inventory context.

Liangtao Lin, Zhaomeng Zhu, Tianwei Zhang et al.

Mission-critical industrial infrastructure, such as data centers, increasingly depends on complex management software. Its operations, however, pose significant challenges due to the escalating system complexity, multi-vendor integration, and a shortage of expert operators. While Robotic Process Automation (RPA) offers partial automation through handcrafted scripts, it suffers from limited flexibility and high maintenance costs. Recent advances in Large Language Model (LLM)-based graphical user interface (GUI) agents have enabled more flexible automation, yet these general-purpose agents face five critical challenges when applied to industrial management, including unfamiliar element understanding, precision and efficiency, state localization, deployment constraints, and safety requirements. To address these issues, we propose InfraMind, a novel exploration-based GUI agentic framework specifically tailored for industrial management systems. InfraMind integrates five innovative modules to systematically resolve different challenges in industrial management: (1) systematic search-based exploration with virtual machine snapshots for autonomous understanding of complex GUIs; (2) memory-driven planning to ensure high-precision and efficient task execution; (3) advanced state identification for robust localization in hierarchical interfaces; (4) structured knowledge distillation for efficient deployment with lightweight models; and (5) comprehensive, multi-layered safety mechanisms to safeguard sensitive operations. Extensive experiments on both open-source and commercial DCIM platforms demonstrate that our approach consistently outperforms existing frameworks in terms of task success rate and operational efficiency, providing a rigorous and scalable solution for industrial management automation.

John Oyekan, Christopher Turner, Michael Bax et al.

The rapid advancement of Large Language Models (LLMs) has resulted in interest in their potential applications within manufacturing systems, particularly in the context of Industry 5.0. However, determining when to implement LLMs versus other Natural Language Processing (NLP) techniques, ontologies or knowledge graphs, remains an open question. This paper offers decision-making guidance for selecting the most suitable technique in various industrial contexts, emphasizing human-robot collaboration and resilience in manufacturing. We examine the origins and unique strengths of LLMs, ontologies, and knowledge graphs, assessing their effectiveness across different industrial scenarios based on the number of domains or disciplines required to bring a product from design to manufacture. Through this comparative framework, we explore specific use cases where LLMs could enhance robotics for human-robot collaboration, while underscoring the continued relevance of ontologies and knowledge graphs in low-dependency or resource-constrained sectors. Additionally, we address the practical challenges of deploying these technologies, such as computational cost and interpretability, providing a roadmap for manufacturers to navigate the evolving landscape of Language based AI tools in Industry 5.0. Our findings offer a foundation for informed decision-making, helping industry professionals optimize the use of Language Based models for sustainable, resilient, and human-centric manufacturing. We also propose a Large Knowledge Language Model architecture that offers the potential for transparency and configuration based on complexity of task and computing resources available.

Miguel Antonio Fudolig, Robert E. Davis, Kavita Batra et al.

Maintaining proper hand hygiene is crucial in preventing the spread of infections and other communicable diseases. It is imperative to determine the factors that affect the likelihood of initiating and maintaining the recommended handwashing behavior, especially during a pandemic. This quantitative, secondary study employed a latent profile analysis (LPA) to identify the different attitudes toward behavior change based on the Multi-Theory Model (MTM) framework in the context of following the guidelines provided by the Centers for Disease Control and Prevention (CDC) during the COVID-19 pandemic. Data were collected from 602 college students at a large university in the southern region of the United States (U.S.) in 2020. Seven distinct profiles were identified, each reflecting unique attitudes toward following the recommended handwashing guidelines. Age (<i>p</i> < 0.01) and gender (<i>p</i> < 0.01) disparities were observed between profiles. This study is the first to apply LPA within the MTM framework and provides new insights for the development of targeted interventions based on the construct score profile.

Mike Allenspach, Michael Pantic, Rik Girod et al.

In real-world industrial environments, modern robots often rely on human operators for crucial decision-making and mission synthesis from individual tasks. Effective and safe collaboration between humans and robots requires systems that can adjust their motion based on human intentions, enabling dynamic task planning and adaptation. Addressing the needs of industrial applications, we propose a motion control framework that (i) removes the need for manual control of the robot's movement; (ii) facilitates the formulation and combination of complex tasks; and (iii) allows the seamless integration of human intent recognition and robot motion planning. For this purpose, we leverage a modular and purely reactive approach for task parametrization and motion generation, embodied by Riemannian Motion Policies. The effectiveness of our method is demonstrated, evaluated, and compared to \remove{state-of-the-art approaches}\add{a representative state-of-the-art approach} in experimental scenarios inspired by realistic industrial Human-Robot Interaction settings.

N. Nikonoshina, O. Dolgikh

Introduction. Benzo(a)pyrene induces disorders of immune and neurohumoral regulation that are aggravated by the influence of unfavourable climatic and geographical factors in the Far North. In this regard, studies of the features of the immune and neurohumoral profile are of particular relevance for the identification of markers of early health disorders of the population of industrially developed circumpolar territories (using the example of benzo(a)pyrene). Materials and methods. Five hundred 3-6 year children living in the circumpolar territory of Eastern Siberia were examined. Observation group consisted of 352 children living in conditions of exposure to benzo(a)pyrene. Comparison group included 148 children residing at a relatively clean territory. Determination of the content of benzo(a)pyrene in the blood was carried out by HPLC. Phenotyping of CD3+-, CD19+-, CD3+CD95+-, Annexin V-FITC+7AAD- and Annexin V-FITC+7AAD+-lymphocytes was performed by flow cytofluorometry. The level of IgA, IgM, IgG was determined by Mancini radial immunodiffusion, the IgG content to benzo(a)pyrene was determined by allergosorbent testing. The content of acetylcholine, serotonin, and neurotropin-3 was determined by ELISA. Results. Children living in the industrially developed circumpolar territory of Eastern Siberia have an increased level of blood contamination with benzo(a)pyrene (p<0.05). The immune profile is characterized by inhibition of cellular (CD3+ deficiency) and humoral immunity (decreased IgA, IgM, IgG with an excess of CD19+). Violations of apoptosis (decrease in Annexin V-FITC+7AAD-, Annexin V-FITC+7AAD+-lymphocytes; increase in Bcl-2 and CD95+) were revealed (p<0.05). An increased IgG to benz(a)pyrene content were found (p<0.05). The neurohumoral profile of the examined children is characterized by hyperexpression of serotonin with acetylcholine and neurotropin-3 deficiency (p<0.05). Limitations. The results of the study are intended for specialists in the field of hygiene, immunology and allergology. Conclusion. Revealed features of the immune status (deficiency of CD3+, Annexin V-FITC+7AAD-, and Annexin V-FITC+7AAD+-lymphocytes IgA, IgM, IgG, excess CD19+, CD95+, Bcl-2, IgG to benzo(a)pyrene), associated with changes in sympathetic-parasympathetic balance (excess serotonin, deficiency of acetylcholine, neurotropin-3) characterize the features of the immune and neurohumoral profile in the children population of the circumpolar territories of Eastern Siberia under the conditions of exposure to benzo(a)pyrene.

Ahmad Rostami, Dhruvin Patel, Madhusudan Giyyarpuram et al.

5G non-public networks (NPNs) play a key role in enabling critical Industrial Internet of Things (IoT) applications in various vertical industries. Among other features, 5G NPNs enable novel operation models, where the roles and responsibilities for setting up and operating the network can be distributed among several stakeholders, i.e., among the public mobile network operators (MNOs), the industrial party who uses the 5G NPN services and 3rd parties. This results in many theoretically feasible operation models for 5G NPN, each with its own advantages and disadvantages. We investigate the resulting operation models and identify a set of nine prime models taking into account today's practical considerations. Additionally, we define a framework to qualitatively analyze the operation models and use it to evaluate and compare the identified operation models.

Francesco Ragusa, Rosario Leonardi, Michele Mazzamuto et al.

ENIGMA-51 is a new egocentric dataset acquired in an industrial scenario by 19 subjects who followed instructions to complete the repair of electrical boards using industrial tools (e.g., electric screwdriver) and equipments (e.g., oscilloscope). The 51 egocentric video sequences are densely annotated with a rich set of labels that enable the systematic study of human behavior in the industrial domain. We provide benchmarks on four tasks related to human behavior: 1) untrimmed temporal detection of human-object interactions, 2) egocentric human-object interaction detection, 3) short-term object interaction anticipation and 4) natural language understanding of intents and entities. Baseline results show that the ENIGMA-51 dataset poses a challenging benchmark to study human behavior in industrial scenarios. We publicly release the dataset at https://iplab.dmi.unict.it/ENIGMA-51.

Johannes Vrana, Ripudaman Singh

The Fourth Industrial Revolution, ushered by the deeper integration of digital technologies into professional and social spaces, provides an opportunity to meaningfully serve society. Humans have tremendous capability to innovatively improve social well-being when the situation is clear. Which was not the case during the first three revolutions. Thus, society has been accepting lifestyle changes willingly and several negative consequences unwillingly. Since the fourth one is still in its infancy, we can control it better. This paper presents a unified model of the industrialized ecosystem covering value creation, value consumption, enabling infrastructure, required skills, and additional governance. This design thinking viewpoint, which includes the consumer side of digital transformation, sets the stage for the next major lifestyle change, termed Digital Transfiguration. For validation and ease of comprehension, the model draws upon the well-understood automobile industry. This model unifies the digital penetration of both industrial creation and social consumption, in a manner that aligns several stakeholders on their transformation journey.

V. Pankova, M. Vilk, E. Zibarev et al.

Introduction. In the period from 2013 to 2021, industrial enterprises saw a reduction in jobs that did not meet sanitary and hygienic requirements for the level of exposure to noise, vibration, illumination, microclimate parameters and electromagnetic fields on the workers' bodies. However, the proportion of unfavorable workplaces that do not meet the standards for noise levels remains the largest, which determines the peculiarities of the structure of the occupational pathology of workers in the Russian Federation: professional pathology of the hearing organ - professional sensorineural hearing loss - remains in the first place. The transport industry is among the sectors of the economy with the most significant indicators of occupational diseases exceeding the average Russian indicator. The study aims to analyze additional causes of pathogenetic significance in the development of professional hearing loss using the example of employees of the driving professions of railway transport and flight professions of civil aviation aircraft. Materials and methods. We have analyzed the state of the auditory function in members of locomotive crews of JSC Russian Railways for 2017-2021 according to the Territorial Administration of Rospotrebnadzor for Railway Transport and persons of flight professions of civil aviation aircraft of the Russian Federation for 2010-2020 according to the data of the Federal Center for Hygiene and Epidemiology. Results. Professional sensorineural hearing loss prevails in the structure of occupational morbidity of railway and aviation transport workers. Despite the absence of excess in-cabin noise levels, the leading professional group for hearing loss in railway transport are locomotive drivers and assistants, in civil aviation - aircraft commanders and co-pilots. The complexity of the professional activities of persons of these professions, a high degree of responsibility for the safety of transportation of passengers and cargo, readiness to act in non-standard conditions, loads on visual and auditory analyzers, create a high degree of labor intensity that causes chronic stress. The factor of chronic stress causes a violation of adaptive mechanisms and causes a number of complex neuro-reflex and neurohumoral shifts in the body, as a result of which labor intensity need to consider as a pathogenetically significant factor in the development of professional sensorineural hearing loss. Conclusions. Chronic sensorineural hearing loss is a priority occupational disease in persons of driving and flying professions, it is registered even in persons working in conditions of regulatory levels of industrial noise and a high degree of labor intensity. It is necessary to discuss the possibility of including labor intensity indicators as an additional etiological, pathogenetically significant factor in the expert criteria for establishing the connection of hearing loss with professional activity.

Sumit K. Das, Mohammad Helal Uddin, Sabur Baidya

Digital Twin technology is playing a pivotal role in the modern industrial evolution. Especially, with the technological progress in the Internet-of-Things (IoT) and the increasing trend in autonomy, multi-sensor equipped robotics can create practical digital twin, which is particularly useful in the industrial applications for operations, maintenance and safety. Herein, we demonstrate a real-world digital twin of a safety-critical robotics applications with a Franka-Emika-Panda robotic arm. We develop and showcase an edge-assisted collaborative digital twin for dynamic obstacle avoidance which can be useful in real-time adaptation of the robots while operating in the uncertain and dynamic environments in industrial IoT.

Rafik Ayari, Matteo Pantano, David Paulius

In this preliminary work, we propose to design an activity recognition system that is suitable for Industrie 4.0 (I4.0) applications, especially focusing on Learning from Demonstration (LfD) in collaborative robot tasks. More precisely, we focus on the issue of data exchange between an activity recognition system and a collaborative robotic system. We propose an activity recognition system with linked data using functional object-oriented network (FOON) to facilitate industrial use cases. Initially, we drafted a FOON for our use case. Afterwards, an action is estimated by using object and hand recognition systems coupled with a recurrent neural network, which refers to FOON objects and states. Finally, the detected action is shared via a context broker using an existing linked data model, thus enabling the robotic system to interpret the action and execute it afterwards. Our initial results show that FOON can be used for an industrial use case and that we can use existing linked data models in LfD applications.

Geri Skenderi, Christian Joppi, Matteo Denitto et al.

The fashion industry is one of the most active and competitive markets in the world, manufacturing millions of products and reaching large audiences every year. A plethora of business processes are involved in this large-scale industry, but due to the generally short life-cycle of clothing items, supply-chain management and retailing strategies are crucial for good market performance. Correctly understanding the wants and needs of clients, managing logistic issues and marketing the correct products are high-level problems with a lot of uncertainty associated to them given the number of influencing factors, but most importantly due to the unpredictability often associated with the future. It is therefore straightforward that forecasting methods, which generate predictions of the future, are indispensable in order to ameliorate all the various business processes that deal with the true purpose and meaning of fashion: having a lot of people wear a particular product or style, rendering these items, people and consequently brands fashionable. In this paper, we provide an overview of three concrete forecasting tasks that any fashion company can apply in order to improve their industrial and market impact. We underline advances and issues in all three tasks and argue about their importance and the impact they can have at an industrial level. Finally, we highlight issues and directions of future work, reflecting on how learning-based forecasting methods can further aid the fashion industry.

Birgit Vogel-Heuser, Eva-Maria Neumann, Juliane Fischer

automated Production Systems (aPS) are highly complex, mechatronic systems that usually have to operate reliably for many decades. Standardization and reuse of control software modules is a core prerequisite to achieve the required system quality in increasingly shorter development cycles. However, industrial case studies in the field of aPS show that many aPS companies still struggle with strategically reusing software. This paper proposes a metric-based approach to objectively measure the maturity of industrial IEC 61131-based control software in aPS (MICOSE4aPS) to identify potential weaknesses and quality issues hampering systematic reuse. Module developers in the machine and plant manufacturing industry can directly benefit as the metric calculation is integrated into the software engineering workflow. An in-depth industrial evaluation in a top-ranked machine manufacturing company in food packaging and an expert evaluation with different companies confirmed the benefit to efficiently manage the quality of control software.