Hasil untuk "Industrial safety. Industrial accident prevention"

Abdul Kadir, Surindar K. Dhesi, Vanisha Dwi Amalinda et al.

Occupational Health and Safety (OHS) in educational settings is a vital responsibility that is often inconsistently implemented. There is a need for research to bridge the gap between policy and practice. This study employed a cross-sectional mixed-methods design in six schools in the capital city of Indonesia to identify key implementation barriers, strategies, and compliance levels in OHS. Data were collected from 217 teachers using a structured KPAP (Knowledge, Attitudes, Perceptions, Practices) survey and from an additional 38 teachers via Focus Group Discussions (FGDs). Quantitatively, teachers showed highly positive attitudes (99.4% viewing OHS as a professional duty) and generally positive perceptions but implementation practices were sub-optimal (e.g., low participation in drills and PPE usage), showing a gap between awareness and action. Qualitatively, the main barriers identified were a lack of specific OHS regulation or guidance for schools, limited resources/infrastructure, and the perception of OHS as a low priority. Management strategies focused on external collaboration and ongoing in-school initiatives. In conclusion, a significant gap exists between OHS awareness and its integration into school management, highlighting the urgent need for strengthened governance, comprehensive policies, and sustained capacity-building to ensure a proactive, safe, and sustainable school environment for staff and students.

Slavica Bogović

Di Wen, Kunyu Peng, Junwei Zheng et al.

Industrial workflows demand adaptive and trustworthy assistance that can operate under limited computing, connectivity, and strict privacy constraints. In this work, we present MICA (Multi-Agent Industrial Coordination Assistant), a perception-grounded and speech-interactive system that delivers real-time guidance for assembly, troubleshooting, part queries, and maintenance. MICA coordinates five role-specialized language agents, audited by a safety checker, to ensure accurate and compliant support. To achieve robust step understanding, we introduce Adaptive Step Fusion (ASF), which dynamically blends expert reasoning with online adaptation from natural speech feedback. Furthermore, we establish a new multi-agent coordination benchmark across representative task categories and propose evaluation metrics tailored to industrial assistance, enabling systematic comparison of different coordination topologies. Our experiments demonstrate that MICA consistently improves task success, reliability, and responsiveness over baseline structures, while remaining deployable on practical offline hardware. Together, these contributions highlight MICA as a step toward deployable, privacy-preserving multi-agent assistants for dynamic factory environments. The source code will be made publicly available at https://github.com/Kratos-Wen/MICA.

Cheng Li, Keyuan Zhou, Tong Liu et al.

Traffic accidents present complex challenges for autonomous driving, often featuring unpredictable scenarios that hinder accurate system interpretation and responses. Nonetheless, prevailing methodologies fall short in elucidating the causes of accidents and proposing preventive measures due to the paucity of training data specific to accident scenarios. In this work, we introduce AVD2 (Accident Video Diffusion for Accident Video Description), a novel framework that enhances accident scene understanding by generating accident videos that aligned with detailed natural language descriptions and reasoning, resulting in the contributed EMM-AU (Enhanced Multi-Modal Accident Video Understanding) dataset. Empirical results reveal that the integration of the EMM-AU dataset establishes state-of-the-art performance across both automated metrics and human evaluations, markedly advancing the domains of accident analysis and prevention. Project resources are available at https://an-answer-tree.github.io

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.

Walter Zimmer, Ross Greer, Xingcheng Zhou et al.

Even though a significant amount of work has been done to increase the safety of transportation networks, accidents still occur regularly. They must be understood as an unavoidable and sporadic outcome of traffic networks. We present the TUM Traffic Accident (TUMTraf-A) dataset, a collection of real-world highway accidents. It contains ten sequences of vehicle crashes at high-speed driving with 294,924 labeled 2D and 93,012 labeled 3D boxes and track IDs within 48,144 labeled frames recorded from four roadside cameras and LiDARs at 10 Hz. The dataset contains ten object classes and is provided in the OpenLABEL format. We propose Accid3nD, an accident detection model that combines a rule-based approach with a learning-based one. Experiments and ablation studies on our dataset show the robustness of our proposed method. The dataset, model, and code are available on our project website: https://tum-traffic-dataset.github.io/tumtraf-a.

Junfeng Jiao, Saleh Afroogh, Kevin Chen et al.

The rise of Generative AI (GAI) and Large Language Models (LLMs) has transformed industrial landscapes, offering unprecedented opportunities for efficiency and innovation while raising critical ethical, regulatory, and operational challenges. This study conducts a text-based analysis of 160 guidelines and policy statements across fourteen industrial sectors, utilizing systematic methods and text-mining techniques to evaluate the governance of these technologies. By examining global directives, industry practices, and sector-specific policies, the paper highlights the complexities of balancing innovation with ethical accountability and equitable access. The findings provide actionable insights and recommendations for fostering responsible, transparent, and safe integration of GAI and LLMs in diverse industry contexts.

Despina Tomkou, George Fatouros, Andreas Andreou et al.

This paper introduces a novel integration of Retrieval-Augmented Generation (RAG) enhanced Large Language Models (LLMs) with Extended Reality (XR) technologies to address knowledge transfer challenges in industrial environments. The proposed system embeds domain-specific industrial knowledge into XR environments through a natural language interface, enabling hands-free, context-aware expert guidance for workers. We present the architecture of the proposed system consisting of an LLM Chat Engine with dynamic tool orchestration and an XR application featuring voice-driven interaction. Performance evaluation of various chunking strategies, embedding models, and vector databases reveals that semantic chunking, balanced embedding models, and efficient vector stores deliver optimal performance for industrial knowledge retrieval. The system's potential is demonstrated through early implementation in multiple industrial use cases, including robotic assembly, smart infrastructure maintenance, and aerospace component servicing. Results indicate potential for enhancing training efficiency, remote assistance capabilities, and operational guidance in alignment with Industry 5.0's human-centric and resilient approach to industrial development.

Ruiyang Ma, Tianhao Wei, Jiaxi Zhang et al.

As hardware design complexity increases, hardware fuzzing emerges as a promising tool for automating the verification process. However, a significant gap still exists before it can be applied in industry. This paper aims to summarize the current progress of hardware fuzzing from an industry-use perspective and propose solutions to bridge the gap between hardware fuzzing and industrial verification. First, we review recent hardware fuzzing methods and analyze their compatibilities with industrial verification. We establish criteria to assess whether a hardware fuzzing approach is compatible. Second, we examine whether current verification tools can efficiently support hardware fuzzing. We identify the bottlenecks in hardware fuzzing performance caused by insufficient support from the industrial environment. To overcome the bottlenecks, we propose a prototype, HwFuzzEnv, providing the necessary support for hardware fuzzing. With this prototype, the previous hardware fuzzing method can achieve a several hundred times speedup in industrial settings. Our work could serve as a reference for EDA companies, encouraging them to enhance their tools to support hardware fuzzing efficiently in industrial verification.

Dmytro Chopa, Anatolii Derevianchuk , Denis Moskalenko et al.

В сучасних умовах артилерійський підрозділ у взаємодії з безпілотним авіаційним комплексом за своїми можливостями стає розвідувально-вогневим комплексом, основними компонентами якого є підсистеми розвідки, управління та ураження. Це дає змогу: виявляти ціль на місцевості, визначати її координати, ставити завдання обслузі вогневого засобу, наводити вогневий засіб на ціль, готувати до пострілу та здійснювати постріл, корегувати вогонь тощо. Широке застосування безпілотних авіаційних комплексів в інтересах виконання вогневих завдань артилерією свідчить про їх перевагу порівняно з іншими засобами розвідки. Тому інтеграція безпілотних авіаційних комплексів у бойові дії артилерійських підрозділів вимагає відповідної підготовки як особового складу вогневого підрозділу, так і екіпажу безпілотного авіаційного комплексу. Метою статті є проведення аналізу процесів функціонування мінометної обслуги та розгляд підходу стосовно створення віртуальних тренажерних комплексів (3D моделей) для практичної підготовки особового складу вогневого підрозділу у складі розвідувально-вогневого комплексу. Під час проведення дослідження застосовувались такі методи: аналіз, систематизація, вдосконалення, обґрунтування, 3D моделювання для практичної підготовки мінометної обслуги у складі розвідувально-вогневого комплексу. Зазначений методологічний підхід дав змогу: розробити схему алгоритму дії складової розвідувально-вогневого комплексу, а саме обслуги вогневого підрозділу, чітко визначити обсяг функціональних завдань основних суб’єктів вогневого підрозділу та здійснити віртуалізацію процесу кожної операції. Запропоновано послідовність підбору навчального контенту і його віртуалізації, що забезпечують якісну підготовку мінометної обслуги у стислі терміни. Отримані результати дослідження забезпечать: підвищення ефективності процесу підготовки особового складу розвідувально-вогневого комплексу, будуть сприяти покращенню рівня засвоєння навчального матеріалу, закріплення практичних навичок та приймання правильних рішень у позаштатних ситуаціях. Віртуальні тренажерні комплекси можуть використовуватися як у навчальних центрах підготовки підрозділів, так і в освітньому процесі вищих військових навчальних закладів та військових навчальних підрозділів закладів вищої освіти.

Linda Kölbel, Markus Hornsteiner, Stefan Schönig

In industry, the networking and automation of machines through the Internet of Things (IoT) continues to increase, leading to greater digitalization of production processes. Traditionally, business and production processes are controlled, optimized and monitored using business process management methods that require process discovery. However, these methods cannot be fully applied to industrial production processes. Nevertheless, processes in the industry must also be monitored and discovered for this purpose. The aim of this paper is to develop an approach for process discovery methods and to adapt existing process discovery methods for application to industrial processes. The adaptations of classic discovery methods are presented as universally applicable guidelines specifically for the Industrial Internet of Things (IIoT). In order to create an optimal process model based on process evaluation, different methods are combined into a standardized discovery approach that is both efficient and cost-effective.

Marta Lagomarsino, Marta Lorenzini, Elena De Momi et al.

Despite impressive advancements of industrial collaborative robots, their potential remains largely untapped due to the difficulty in balancing human safety and comfort with fast production constraints. To help address this challenge, we present PRO-MIND, a novel human-in-the-loop framework that leverages valuable data about the human co-worker to optimise robot trajectories. By estimating human attention and mental effort, our method dynamically adjusts safety zones and enables on-the-fly alterations of the robot path to enhance human comfort and optimal stopping conditions. Moreover, we formulate a multi-objective optimisation to adapt the robot's trajectory execution time and smoothness based on the current human psycho-physical stress, estimated from heart rate variability and frantic movements. These adaptations exploit the properties of B-spline curves to preserve continuity and smoothness, which are crucial factors in improving motion predictability and comfort. Evaluation in two realistic case studies showcases the framework's ability to restrain the operators' workload and stress and to ensure their safety while enhancing human-robot productivity. Further strengths of PRO-MIND include its adaptability to each individual's specific needs and sensitivity to variations in attention, mental effort, and stress during task execution.

Surya N Reddy, Vaibhav Kurrey, Mayank Nagar et al.

Proper use of personal protective equipment (PPE) can save the lives of industry workers and it is a widely used application of computer vision in the large manufacturing industries. However, most of the applications deployed generate a lot of false alarms (violations) because they tend to generalize the requirements of PPE across the industry and tasks. The key to resolving this issue is to understand the action being performed by the worker and customize the inference for the specific PPE requirements of that action. In this paper, we propose a system that employs activity recognition models to first understand the action being performed and then use object detection techniques to check for violations. This leads to a 23% improvement in the F1-score compared to the PPE-based approach on our test dataset of 109 videos.

Xi Jiang, Jian Li, Hanqiu Deng et al.

In the field of industrial inspection, Multimodal Large Language Models (MLLMs) have a high potential to renew the paradigms in practical applications due to their robust language capabilities and generalization abilities. However, despite their impressive problem-solving skills in many domains, MLLMs' ability in industrial anomaly detection has not been systematically studied. To bridge this gap, we present MMAD, the first-ever full-spectrum MLLMs benchmark in industrial Anomaly Detection. We defined seven key subtasks of MLLMs in industrial inspection and designed a novel pipeline to generate the MMAD dataset with 39,672 questions for 8,366 industrial images. With MMAD, we have conducted a comprehensive, quantitative evaluation of various state-of-the-art MLLMs. The commercial models performed the best, with the average accuracy of GPT-4o models reaching 74.9%. However, this result falls far short of industrial requirements. Our analysis reveals that current MLLMs still have significant room for improvement in answering questions related to industrial anomalies and defects. We further explore two training-free performance enhancement strategies to help models improve in industrial scenarios, highlighting their promising potential for future research.

Dianhui Wang, Matthew J. Felicetti

Real-time predictive modelling with desired accuracy is highly expected in industrial artificial intelligence (IAI), where neural networks play a key role. Neural networks in IAI require powerful, high-performance computing devices to operate a large number of floating point data. Based on stochastic configuration networks (SCNs), this paper proposes a new randomized learner model, termed stochastic configuration machines (SCMs), to stress effective modelling and data size saving that are useful and valuable for industrial applications. Compared to SCNs and random vector functional-link (RVFL) nets with binarized implementation, the model storage of SCMs can be significantly compressed while retaining favourable prediction performance. Besides the architecture of the SCM learner model and its learning algorithm, as an important part of this contribution, we also provide a theoretical basis on the learning capacity of SCMs by analysing the model's complexity. Experimental studies are carried out over some benchmark datasets and three industrial applications. The results demonstrate that SCM has great potential for dealing with industrial data analytics.

Dmytro Kalinovskyi, Serhii Osiievskyi , Inna Dziuba

У статті розглянуто вимоги до розробки системи підтримки прийняття рішення з використанням бази знань в залежності від положення Стратегічного оборонного бюлетеня України, формалізованого процесу прийняття воєнного рішення на основі стандартів НАТО та особливостей архітектури C4ISR. З точки зору проектування програмного забезпечення враховано стандарт направлений на процеси і організацію життєвого циклу ІС та маніфест гнучкої розробки. Розглянуті вимоги являються частковим переліком, який необхідний для побудови діаграм структури та поведінки, які описують автоматизоване управління військами на основі визначених принципів управління, ознак класифікації та базових функцій систем в країнах – членах НАТО. Розроблена функціональна модель процесу управління військами з використанням положень С4ISR, яка враховує послідовність виконання процесу ППВР та дозволяє дослідити вплив кожної підсистеми на загальний результат. Враховуючи формуляри програмного комплексу “Віраж-Планшет”, визначено кількісні показники інформації про повітряні об’єкти та засоби повітряного нападу які використовуються особою яка приймає рішення. Оцінена кількісна міра інформації, яка використана для визначення точок прийняття рішення відносно повітряних об’єктів які супроводжуються.

Mahmoud M. Nour, Yahia M. Aly, William E. Field

Availability of summarized occupational injury data is essential for establishing complete incident surveillance systems, targeting incident preventative efforts, assessing the efficacy of prevention programs, and enhancing workplace safety. There are currently limited automated injury monitoring systems for summarizing occupational injuries obtained from electronic news and other sources, or for visualizing real-time data through an output platform. A “near” real-time surveillance tool could enable researchers to visualize data as it is being collected and provide a more rapid monitoring method to identify patterns in injury data. An automated data pipeline method could provide more current, consistent, and reliable information for injury surveillance systems and injury prevention purposes. Such a system could help public policy makers, epidemiologists, and injury prevention professionals spend less time and effort on classifying cases, increase confidence in the data, and respond quicker to “patterns” of specific types of incidents. Currently, injury surveillance approaches generally rely on manual coding of injury data, resulting in inconsistencies in classification of incident, and contributing factors and considerable delays in publishing results. This study focused on developing and testing a more automated coding methodology for use with incident narratives for further data mining, analysis, and interpretation. The concept was tested on 491 documented fatalities or serious injuries involving agricultural waste storage, handling, and transport operations. The approach provided current and real-time summarization of incident data along with data analysis and visualization by using a standard questionnaire for record-keeping, Python data frames, and the MySQL database. Findings in this study provided evidence for the reliability of classifying injury news clipping narratives into external real-time incident categories. Results showed a very encouraging performance for the chosen model to monitor injury and fatality incidents with efficiency, simplicity, data quality, timeliness, and a consistent coding process.

Maria Krantz, Alexander Windmann, Rene Heesch et al.

The increasing complexity of Cyber-Physical Systems (CPS) makes industrial automation challenging. Large amounts of data recorded by sensors need to be processed to adequately perform tasks such as diagnosis in case of fault. A promising approach to deal with this complexity is the concept of causality. However, most research on causality has focused on inferring causal relations between parts of an unknown system. Engineering uses causality in a fundamentally different way: complex systems are constructed by combining components with known, controllable behavior. As CPS are constructed by the second approach, most data-based causality models are not suited for industrial automation. To bridge this gap, a Uniform Causality Model for various application areas of industrial automation is proposed, which will allow better communication and better data usage across disciplines. The resulting model describes the behavior of CPS mathematically and, as the model is evaluated on the unique requirements of the application areas, it is shown that the Uniform Causality Model can work as a basis for the application of new approaches in industrial automation that focus on machine learning.

Hadi SALARI, Mohammad Reza GHOTBI-RAVANDIR, Mohammad DASTANPOUR et al.

Abstract Introduction: One of the effective factors in the occurrence of musculoskeletal disorders is the mismatch between the mental workload on the person and his abilities and limitations. Therefore, this study aimed to investigate the effect of mental workload on the prevalence of musculoskeletal disorders in Bandar Abbas Production Company. Method: This cross-sectional descriptive-analytical study was conducted in 2019. The data collection tools included demographic information questionnaires, Nordic musculoskeletal disorders, and NASA- TLX mental workload. The participants were 172 people who were identified using Cochran's formula and simple random sampling. The collected data were analyzed by SPSS 25 software. Results: The results indicated that 76.74% of the subjects had musculoskeletal disorders. Most of disorders were reported in the low back (51.16%), knees (38.95%), and neck (23.84%). The mean score of mental workloads in Bandar Abbas Production Company in this study was high (66.67). Among the mental workload subscales, the effort subscale had the highest score (85.32) and the performance subscale had the lowest score (20.00). Statistical tests showed that there was a significant relationship between mental workload and the prevalence of musculoskeletal disorders. Conclusion: According to the findings of the study, there was a direct relationship between mental workload and the prevalence of musculoskeletal disorders. Therefore, measures should be taken to reduce the perceived mental and psychological load, such as reducing working hours, interrupting and resting between working, increasing the variety of working postures, and thus preventing the occurrence of musculoskeletal disorders.

Robert Zůvala, Kateřina Bucsuházy, Veronika Valentová et al.

Road accident occurrence is often the result of driving system malfunctions, and road safety improvements need to focus on all basic driving components—the vehicle, road infrastructure, and road users. Only focusing on one type of improvement does not necessarily lead to increased road safety. Instead, improved road safety requires comprehensive measures that consider all factors using in-depth accident analysis. The proposed measures, based on the findings from in-depth data that have general applicability, are necessary to determine whether data gained from in-depth studies adequately represent national statistics. This article aims to verify the representativeness of the Czech In-Depth Accident Study at a national level. The main contribution of this article lies in the use of a weighting method (specifically, a raking procedure) to generalise research results and render them applicable to a whole population. The obtained results could be beneficial at the national level, in the Czech Republic, and also on the supranational level. The applicability of this method on accident data is verified; thus, the method can be applied also in other countries or can be used to verify the applicability of conclusions from the Czech in-depth study also on a European or worldwide level.