Hasil untuk "Industrial safety. Industrial accident prevention"

Puyu Zeng, Zhaoxi Wang, Zhixu Duan et al.

Code generation and comprehension by Large Language Models (LLMs) have emerged as core drivers of industrial intelligence and decision optimization, finding widespread application in fields such as finance, automation, and aerospace. Although recent advancements have demonstrated the remarkable potential of LLMs in general code generation, existing benchmarks are mainly confined to single domains and languages. Consequently, they fail to effectively evaluate the generalization capabilities required for real-world industrial applications or to reflect the coding proficiency demanded by complex industrial scenarios. To bridge this gap, we introduce IndustryCode, the first comprehensive benchmark designed to span multiple industrial domains and programming languages. IndustryCode comprises 579 sub-problems derived from 125 primary industrial challenges, accompanied by rigorous problem descriptions and test cases. It covers a wide range of fields, including finance, automation, aerospace, and remote sensing-and incorporates diverse programming languages such as MATLAB, Python, C++, and Stata. In our evaluation, the top-performing model, Claude 4.5 Opus, achieved an overall accuracy of 68.1% on sub-problems and 42.5% main problems. The benchmark dataset and automated evaluation code will be made publicly available upon acceptance.

Aho Yapi, Pierre Latouche, Arnaud Guillin et al.

We propose a model-agnostic framework for short-term occupational accident forecasting that leverages safety inspections and models accident occurrences as binary time series. The approach generates daily predictions, which are then aggregated into weekly safety assessments for better decision making. To ensure the reliability and operational applicability of the forecasts, we apply a sliding-window cross-validation procedure specifically designed for time series data, combined with an evaluation based on aggregated period-level metrics. Several machine learning algorithms, including logistic regression, tree-based models, and neural networks, are trained and systematically compared within this framework. Across all tested algorithms, the proposed framework reliably identifies upcoming high-risk periods and delivers robust period-level performance, demonstrating that converting safety inspections into binary time series yields actionable, short-term risk signals. The proposed methodology converts routine safety inspection data into clear weekly and daily risk scores, detecting the periods when accidents are most likely to occur. Decision-makers can integrate these scores into their planning tools to classify inspection priorities, schedule targeted interventions, and funnel resources to the sites or shifts classified as highest risk, stepping in before incidents occur and getting the greatest return on safety investments.

Brian Lu, Dennis Pham, Ti-Chiun Chang et al.

We report the development of a knowledge representation and reasoning (KRR) system built on hybrid SHACL-SKOS ontologies for globally harmonized system (GHS) material Safety Data Sheets (SDS) to enhance chemical safety communication and regulatory compliance. SDS are comprehensive documents containing safety and handling information for chemical substances. Thus, they are an essential part of workplace safety and risk management. However, the vast number of Safety Data Sheets from multiple organizations, manufacturers, and suppliers that produce and distribute chemicals makes it challenging to centralize and access SDS documents through a single repository. To accomplish the underlying issues of data exchange related to chemical shipping and handling, we construct SDS related controlled vocabulary and conditions validated by SHACL, and knowledge systems of similar domains linked via SKOS. The resulting hybrid ontologies aim to provide standardized yet adaptable representations of SDS information, facilitating better data sharing, retrieval, and integration across various platforms. This paper outlines our SHACL-SKOS system architectural design and showcases our implementation for an industrial application streamlining the generation of a composite shipping cover sheet.

Enes Özeren, Alexander Ulbrich, Sascha Filimon et al.

A comprehensive understanding of traffic accidents is essential for improving city safety and informing policy decisions. In this study, we analyze traffic incidents in Munich to identify patterns and characteristics that distinguish different types of accidents. The dataset consists of both structured tabular features, such as location, time, and weather conditions, as well as unstructured free-text descriptions detailing the circumstances of each accident. Each incident is categorized into one of seven predefined classes. To assess the reliability of these labels, we apply NLP methods, including topic modeling and few-shot learning, which reveal inconsistencies in the labeling process. These findings highlight potential ambiguities in accident classification and motivate a refined predictive approach. Building on these insights, we develop a classification model that achieves high accuracy in assigning accidents to their respective categories. Our results demonstrate that textual descriptions contain the most informative features for classification, while the inclusion of tabular data provides only marginal improvements. These findings emphasize the critical role of free-text data in accident analysis and highlight the potential of transformer-based models in improving classification reliability.

Charity Owusu, Albert Ofori, Frank Adusei-Mensah et al.

Smokehouses play a vital role in several communities, while their environmental and health impacts remain largely unaddressed. Inside these confined spaces, the combination of intense heat, limited ventilation, and the use of firewood generates a complex mixture of hazardous air pollutants. While central to local economies, the health risks faced by workers in smokehouses are frequently overlooked. This study aimed to highlight these risks and to emphasize the urgent need for attention to these environments. Low-cost air quality monitors were deployed to monitor the levels of particulate matter (PM2.5), carbon monoxide, and ozone in 33 smokehouses. In addition, relative humidity and temperature were measured. The results revealed that PM2.5 concentrations ranged from 0.16 to 630.37 µg/m³ , with a mean concentration of 156.84 µg/m³ , and CO concentrations ranged from 2.37 parts per million (ppm) to 36.43 ppm, with a mean concentration of 17.29 ppm, all exceeding the World Health Organization's 24-hour guidelines. However, in the WHO guidelines, the ozone levels showed variability, ranging from 2.5 to 74.69 parts per billion (ppb). Temperature and relative humidity fluctuations were also significant, peaking at 46.29 °C and 81.59 %, respectively. This research spotlights the pressing need for enhanced air quality assessments in these environments and suggests innovative interventions that can ultimately protect public health and our fragile ecosystems.

Irfan Ullah, Ahmed Farid, Khaled Ksaibati

Intersections represent critical crash locations on road networks necessitating targeted safety interventions. This study employs a random parameters ordered logit (RPOL) model with heterogeneity in means to analyze injury severity contributing factors across 9108 Wyoming intersection crashes that occurred from 2007 to 2017. The analysis reveals that crashes on principal and minor arterial intersections are consistently associated with higher risks of severe/fatal injuries, while urban intersections exhibit less severe consequences, likely due to lower speeds and enhanced infrastructure. Adverse weather conditions, particularly snowy and icy road surfaces, increase the likelihood of property-damage-only (PDO) outcomes while reducing severe/fatal injuries. Temporal trends show a decline in crash severity over time, coinciding with advances in vehicle safety and policy improvements. Key behavioral factors, including left turn maneuvers and driver’s age heterogeneity, influence crash outcomes, whereas intersection sight distance (ISD) had no significant effect on crash severity underscoring data limitations requiring advanced analysis methods. This study’s findings prioritize the reconsideration of arterial intersection design, urban safety enhancements, and behavior-focused countermeasures for intersection safety.

Азаренко Е.И., Осадчая Л.И.

Jing Wu, Junru Ren, Ole Ravn et al.

The safety of robotics and automation technologies is a significant concern for stakeholders in Industry 5.0. Ensuring cost-effectiveness and inherent safety requires applying the defense-in-depth principle. This paper introduces a novel risk-informed design framework for functional safety, integrating function-centered hazard identification and risk assessment via fault tree analysis (FTA). Demonstrated in the design of a semi-automated agricultural vehicle, the framework begins with a function-centered hazard identification approach (F-CHIA) based on ISO 12100. It examined design intents, identified hazard zones, and conducted task and function identification. Foreseeable functional hazardous situations are analyzed, leading to functional requirements and the identification of relevant directives, regulations, and standards. The F-CHIA outputs inform the functional safety analysis, assessing the required performance level and deriving specific requirements for software, hardware, and human operators using FTA. The functional requirements derived from F-CHIA are more systematic than traditional methods and serve as effective inputs for functional safety analysis in human–robot collaboration applications. The proposed framework enables design teams to focus on enhancing factors that improve functional safety performance levels, resulting in a more thorough and effective safety design process.

F. Adetunji, A. Karukayil, P. Samant et al.

This paper addresses the challenges of vision-based manipulation for autonomous cutting and unpacking of transparent plastic bags in industrial setups, aligning with the Industry 4.0 paradigm. Industry 4.0, driven by data, connectivity, analytics, and robotics, promises enhanced accessibility and sustainability throughout the value chain. The integration of autonomous systems, including collaborative robots (cobots), into industrial processes is pivotal for efficiency and safety. The proposed solution employs advanced Machine Learning algorithms, particularly Convolutional Neural Networks (CNNs), to identify transparent plastic bags under varying lighting and background conditions. Tracking algorithms and depth sensing technologies are utilized for 3D spatial awareness during pick and placement. The system addresses challenges in grasping and manipulation, considering optimal points, compliance control with vacuum gripping technology, and real-time automation for safe interaction in dynamic environments. The system's successful testing and validation in the lab with the FRANKA robot arm, showcases its potential for widespread industrial applications, while demonstrating effectiveness in automating the unpacking and cutting of transparent plastic bags for an 8-stack bulk-loader based on specific requirements and rigorous testing.

Xiao Wang, Yutong Wang, Jing Yang et al.

As the concept of Industries 5.0 develops, industrial metaverses are expected to operate in parallel with the actual industrial processes to offer ``Human-Centric" Safe, Secure, Sustainable, Sensitive, Service, and Smartness ``6S" manufacturing solutions. Industrial metaverses not only visualize the process of productivity in a dynamic and evolutional way, but also provide an immersive laboratory experimental environment for optimizing and remodeling the process. Besides, the customized user needs that are hidden in social media data can be discovered by social computing technologies, which introduces an input channel for building the whole social manufacturing process including industrial metaverses. This makes the fusion of multi-source data cross Cyber-Physical-Social Systems (CPSS) the foundational and key challenge. This work firstly proposes a multi-source-data-fusion-driven operational architecture for industrial metaverses on the basis of conducting a comprehensive literature review on the state-of-the-art multi-source data fusion methods. The advantages and disadvantages of each type of method are analyzed by considering the fusion mechanisms and application scenarios. Especially, we combine the strengths of deep learning and knowledge graphs in scalability and parallel computation to enable our proposed framework the ability of prescriptive optimization and evolution. This integration can address the shortcomings of deep learning in terms of explainability and fact fabrication, as well as overcoming the incompleteness and the challenges of construction and maintenance inherent in knowledge graphs. The effectiveness of the proposed architecture is validated through a parallel weaving case study. In the end, we discuss the challenges and future directions of multi-source data fusion cross CPSS for industrial metaverses and social manufacturing in Industries 5.0.

Ahmed Gailani, Peter Taylor

Decarbonising the industrial sector is vital to reach net zero targets. The deployment of industrial decarbonisation technologies is expected to increase industrial electricity demand in many countries and this may require upgrades to the existing electricity network or new network investment. While the infrastructure requirements to support the introduction of new fuels and technologies in industry, such as hydrogen and carbon capture, utilisation and storage are often discussed, the need for investment to increase the capacity of the electricity network to meet increasing industrial electricity demands is often overlooked in the literature. This paper addresses this gap by quantifying the requirements for additional electricity network capacity to support the decarbonisation of industrial sectors across Great Britain (GB). The Net Zero Industrial Pathways model is used to predict the future electricity demand from industrial sites to 2050 which is then compared spatially to the available headroom across the distribution network in GB. The results show that network headroom is sufficient to meet extra capacity demands from industrial sites over the period to 2030 in nearly all GB regions and network scenarios. However, as electricity demand rises due to increased electrification across all sectors and industrial decarbonisation accelerates towards 2050, the network will need significant new capacity (71 GW + by 2050) particularly in the central, south, and north-west regions of England, and Wales. Without solving these network constraints, around 65% of industrial sites that are large point sources of emissions would be constrained in terms of electric capacity by 2040. These sites are responsible for 69% of industrial point source emissions.

Michael Wagner, Carmen Carlan

A system safety case is a compelling, comprehensible, and valid argument about the satisfaction of the safety goals of a given system operating in a given environment supported by convincing evidence. Since the publication of UL 4600 in 2020, safety cases have become a best practice for measuring, managing, and communicating the safety of autonomous vehicles (AVs). Although UL 4600 provides guidance on how to build the safety case for an AV, the complexity of AVs and their operating environments, the novelty of the used technology, the need for complying with various regulations and technical standards, and for addressing cybersecurity concerns and ethical considerations make the development of safety cases for AVs challenging. To this end, safety case frameworks have been proposed that bring strategies, argument templates, and other guidance together to support the development of a safety case. This paper introduces the Open Autonomy Safety Case Framework, developed over years of work with the autonomous vehicle industry, as a roadmap for how AVs can be deployed safely and responsibly.

Maryam Ahang, Todd Charter, Mostafa Abbasi et al.

Condition monitoring is essential for ensuring the safety, reliability, and efficiency of modern industrial systems. With the increasing complexity of industrial processes, artificial intelligence (AI) has emerged as a powerful tool for fault detection and diagnosis, attracting growing interest from both academia and industry. This paper provides a comprehensive overview of intelligent condition monitoring methods, with a particular emphasis on chemical plants and the widely used Tennessee Eastman Process (TEP) benchmark. State-of-the-art machine learning (ML) and deep learning (DL) algorithms are reviewed, highlighting their strengths, limitations, and applicability to industrial fault detection and diagnosis. Special attention is given to key challenges, including imbalanced and unlabeled data, and to strategies by which models can address these issues. Furthermore, comparative analyses of algorithm performance are presented to guide method selection in practical scenarios. This survey is intended to benefit both newcomers and experienced researchers by consolidating fundamental concepts, summarizing recent advances, and outlining open challenges and promising directions for intelligent condition monitoring in industrial plants.

Rima Hazra, Sayan Layek, Somnath Banerjee et al.

Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and complex objectives, making models vulnerable to generating harmful content. We propose Safety Arithmetic, a training-free framework enhancing LLM safety across different scenarios: Base models, Supervised fine-tuned models (SFT), and Edited models. Safety Arithmetic involves Harm Direction Removal to avoid harmful content and Safety Alignment to promote safe responses. Additionally, we present NoIntentEdit, a dataset highlighting edit instances that could compromise model safety if used unintentionally. Our experiments show that Safety Arithmetic significantly improves safety measures, reduces over-safety, and maintains model utility, outperforming existing methods in ensuring safe content generation.

Simon Liebl, Leah Lathrop, Ulrich Raithel et al.

As part of the Internet of Things, industrial devices are now also connected to cloud services. However, the connection to the Internet increases the risks for Industrial Control Systems. Therefore, a threat analysis is essential for these devices. In this paper, we examine Industrial Internet of Things devices, identify and rank different sources of threats and describe common threats and vulnerabilities. Finally, we recommend a procedure to carry out a threat analysis on these devices.

Christian W. Frey

Industrial production processes, especially in the pharmaceutical industry, are complex systems that require continuous monitoring to ensure efficiency, product quality, and safety. This paper presents a hybrid unsupervised learning strategy (HULS) for monitoring complex industrial processes. Addressing the limitations of traditional Self-Organizing Maps (SOMs), especially in scenarios with unbalanced data sets and highly correlated process variables, HULS combines existing unsupervised learning techniques to address these challenges. To evaluate the performance of the HULS concept, comparative experiments are performed based on a laboratory batch

Vadym Mashtalir , Oleksandr Huk , Igor Tolmachov et al.

З розвитком новітніх інформаційних технологій кіберпростір стає середовищем, у якому відбувається протиборство між суб’єктами міжнародних відносин у вигляді ведення кібервійн, а також інформаційних, мережецентричних, асиметричних, гібридних війн. З’являється тенденція використання стратегій асиметричних непрямих дій, заснованих на комбінації військових зусиль з політичними, економічними та інформаційно-психологічними методами впливу на супротивника для вирішення завдань, які раніше вирішувалися лише з використанням військової сили. В умовах цілеспрямованих інформаційно-технічних впливів і відсутності належних фахових знань про кіберпростір, розуміння цілей та характеру дій у ньому, а також динаміки змін означеного, виникла потреба розроблення методу прогнозування ступеню кібервпливу на гетерогенні інформаційні системи військового призначення. Основне завдання методу полягає у забезпеченні кібербезпеки держави за активного протистояння у кіберпросторі. Цей метод враховує сукупність факторів (загроз), що раніше не мали місця, а також еволюцію кібервпливів. Гетерогенні інформаційні системи є складними технічними системами та мають притаманні їм властивості, тому доцільно для їх опису застосовувати декомпозицію на окремі інформаційні системи. Метою статті є розроблення методу прогнозування ступеню кібервпливу на гетерогенні інформаційні системи військового призначення для забезпечення їх сталого функціонування в умовах кібервпливу. У статті застосовано аналітичний метод для розгляду останніх досліджень, публікацій та наукових джерел стосовно функціонування гетерогенних інформаційних систем військового призначення, цілочисельного програмування, максимального елементу та теорії оптимального розподілу ресурсів для прогнозування ступеню кібервпливу. Зазначений методологічний підхід дав змогу визначити набір засобів парирування зовнішніх впливів для кожного елементу гетерогенних інформаційних систем. Подано узагальнену структуру гетерогенних інформаційних систем, яка дозволяє формалізувати процес прогнозування ступеню кібервпливу. Розроблено метод прогнозування ступеню кібервпливу на гетерогенні інформаційні системи військового призначення та подано його формалізований математичний опис. Елементом наукової новизни є те що запропонований підхід базується на оптимальному розподілі засобів парирування зовнішніх впливів, які в свою чергу поділяються на види, за взаємопов’язаними елементами гетерогенних інформаційних систем. Сутність запропонованого підходу полягає у виборі для кожного з елементів системи та відповідного набору джерел кібервпливу, що діє на них з метою порушення сталого функціонування, оптимального розподілу типів засобів парирування зовнішніх впливів. Теоретична значущість дослідження полягає у тому, що на оcнові відомих математичних методів оптимального розподілу ресурсів під час синтезу складних систем, отримано новий підхід, що враховує еволюцію кібервпливів на гетерогенні інформаційні системи військового призначення. Практична цінність полягає у тому, що застосування зазначеного методу, є необхідним кроком для визначення придатності гетерогенних інформаційних систем військового призначення до виконання цільової функції, та дозволить на етапі створення гетерогенних інформаційних систем військового призначення визначити можливі уразливості.

H. Khayyam, B. Javadi, M. Jalili et al.

Fouad Oubari, Raphael Meunier, Rodrigue Décatoire et al.

Generative design is an increasingly important tool in the industrial world. It allows the designers and engineers to easily explore vast ranges of design options, providing a cheaper and faster alternative to the trial and failure approaches. Thanks to the flexibility they offer, Deep Generative Models are gaining popularity amongst Generative Design technologies. However, developing and evaluating these models can be challenging. The field lacks accessible benchmarks, in order to evaluate and compare objectively different Deep Generative Models architectures. Moreover, vanilla Deep Generative Models appear to be unable to accurately generate multi-components industrial systems that are controlled by latent design constraints. To address these challenges, we propose an industry-inspired use case that incorporates actual industrial system characteristics. This use case can be quickly generated and used as a benchmark. We propose a Meta-VAE capable of producing multi-component industrial systems and showcase its application on the proposed use case.

Sabrina Nurul Faiza, Kresna Febriyanto

Introduction: Noise is an unwelcome sound that disrupts workers. Noise is present in every workplace, including ship engine noise. Continuous noise exposure can result in health issues, including hearing loss. Noise can cause stress on traditional boat workers because being continuously exposed to noise causes an uncomfortable feeling in the work environment. This uncomfortable feeling can trigger stress on ferry boat workers. This study aims to determine the relationship between noise and work stress on ferry boat workers at the Pier of Kampung Baru Tengah, Balikpapan. Methods: This study used a quantitative approach with a cross-sectional research design with 44 respondents. The instruments used a Sound Level Meter to measure Noise Level and Dass 21 Questionnaire with an interview method to measure Job Stress. Results: As many as 35 respondents were exposed to noise caused by traditional boat engines, and more than 50% of workers did not experience work stress (normal). The results of this study indicated a relationship between noise and work stress in traditional boat workers. Conclusion: The direction of the association between noise and work stress was positive but low, meaning that, as noise levels rise, so does the risk of workplace stress.