Hasil untuk "Industrial safety. Industrial accident prevention"

Yen-Chia Hsu, Despoina Touska

This report describes a dataset for industrial smoke segmentation, published on a figshare repository (https://doi.org/10.21942/uva.31847188). The dataset is licensed under CC BY 4.0.

Liangtao Lin, Zhaomeng Zhu, Tianwei Zhang et al.

Standard Operating Procedures (SOPs) are essential for ensuring operational safety and consistency in industrial environments. However, retrieving and following these procedures presents unique challenges, such as rigid proprietary structures, condition-dependent relevance, and actionable execution requirement, which standard semantic-driven Retrieval-Augmented Generation (RAG) paradigms fail to address. Inspired by the Mixture-of-Experts (MoE) paradigm, we propose SOPRAG, a novel framework specifically designed to address the above pain points in SOP retrieval. SOPRAG replaces flat chunking with specialized Entity, Causal, and Flow graph experts to resolve industrial structural and logical complexities. To optimize and coordinate these experts, we propose a Procedure Card layer that prunes the search space to eliminate computational noise, and an LLM-Guided gating mechanism that dynamically weights these experts to align retrieval with operator intent. To address the scarcity of domain-specific data, we also introduce an automated, multi-agent workflow for benchmark construction. Extensive experiments across four industrial domains demonstrate that SOPRAG significantly outperforms strong lexical, dense, and graph-based RAG baselines in both retrieval accuracy and response utility, achieving perfect execution scores in real-world critical tasks.

Taekyung Kim, Aswin D. Menon, Akshunn Trivedi et al.

This paper revisits three backup-based safety filters -- Backup Control Barrier Functions (Backup CBF), Model Predictive Shielding (MPS), and gatekeeper -- through a unified comparative framework. Using a common safety-filter abstraction and shared notation, we make explicit both their common backup-policy structure and their key algorithmic differences. We compare the three methods through their filter-inactive sets, i.e., the states where the nominal policy is left unchanged. In particular, we show that MPS is a special case of gatekeeper, and we further relate gatekeeper to the interior of the Backup CBF inactive set within the implicit safe set. This unified view also highlights a key source of conservatism in backup-based safety filters: safety is often evaluated through the feasibility of a backup maneuver, rather than through the nominal policy's continued safe execution. The paper is intended as a compact tutorial and review that clarifies the theoretical connections and differences among these methods.

Aziida Nanyonga, Hassan Wasswa, Graham Wild

Aviation safety is paramount, demanding precise analysis of safety occurrences during different flight phases. This study employs Natural Language Processing (NLP) and Deep Learning models, including LSTM, CNN, Bidirectional LSTM (BLSTM), and simple Recurrent Neural Networks (sRNN), to classify flight phases in safety reports from the Australian Transport Safety Bureau (ATSB). The models exhibited high accuracy, precision, recall, and F1 scores, with LSTM achieving the highest performance of 87%, 88%, 87%, and 88%, respectively. This performance highlights their effectiveness in automating safety occurrence analysis. The integration of NLP and Deep Learning technologies promises transformative enhancements in aviation safety analysis, enabling targeted safety measures and streamlined report handling.

P. Vijaya Bharati, J. S. V. Siva Kumar, Sathish K Anumula et al.

Fourth Industrial Revolution has brought in a new era of smart manufacturing, wherein, application of Internet of Things , and data-driven methodologies is revolutionizing the conventional maintenance. With the help of real-time data from the IoT and machine learning algorithms, predictive maintenance allows industrial systems to predict failures and optimize machines life. This paper presents the synergy between the Internet of Things and predictive maintenance in industrial engineering with an emphasis on the technologies, methodologies, as well as data analytics techniques, that constitute the integration. A systematic collection, processing, and predictive modeling of data is discussed. The outcomes emphasize greater operational efficiency, decreased downtime, and cost-saving, which makes a good argument as to why predictive maintenance should be implemented in contemporary industries.

Sayaka Ogawa, Natsu Sasaki, Norito Kawakami et al.

Objective: This study aimed to develop a Japanese version and a shortened version of the Online Social Support Scale and test their reliability and validity. Method: A 40-item scale was developed with the permission of the original developer to measure online and other social support, depressive symptoms, and self-esteem. Study participants were recruited online using snowball sampling. Internal and test-retest reliability were tested; confirmatory factor analysis was used to test for structural validity, and correlation analysis was used to test for convergent validity. A follow-up survey was conducted 2 weeks later to examine the test-retest reliability of the scale. A shortened 12-item version was also developed and tested. Result: A total of 288 people participated in the survey, of whom 254 (88.2%) responded to the follow-up survey. The Cronbach’s α coefficient was 0.98 for the overall scale and ranged from 0.94-0.96 for the subscales. The intraclass correlation coefficient was 0.90 for the scale as a whole and ranged from 0.85–0.88 for the subscales. Confirmatory factor analysis confirmed a four-factor structure with an acceptable model fit. The scale showed a significant positive correlation with social support and a significant negative correlation with depressive symptoms but no significant correlation with self-esteem. The shortened version demonstrated similar reliability and validity. Conclusion: The Japanese version of the Online Social Support Scale showed adequate reliability and some validity, and the short version showed adequate reliability and validity, making them useful tools for measuring online social support in various contexts, such as peer support groups or remote work environments.

Josip Hoster, Aleksandar Sušić

Madapu Amarlingam, Abhishek Wani, Adarsh NL

Federated Learning (FL) is the most widely adopted collaborative learning approach for training decentralized Machine Learning (ML) models by exchanging learning between clients without sharing the data and compromising privacy. However, since great data similarity or homogeneity is taken for granted in all FL tasks, FL is still not specifically designed for the industrial setting. Rarely this is the case in industrial data because there are differences in machine type, firmware version, operational conditions, environmental factors, and hence, data distribution. Albeit its popularity, it has been observed that FL performance degrades if the clients have heterogeneous data distributions. Therefore, we propose a Lightweight Industrial Cohorted FL (LICFL) algorithm that uses model parameters for cohorting without any additional on-edge (clientlevel) computations and communications than standard FL and mitigates the shortcomings from data heterogeneity in industrial applications. Our approach enhances client-level model performance by allowing them to collaborate with similar clients and train more specialized or personalized models. Also, we propose an adaptive aggregation algorithm that extends the LICFL to Adaptive LICFL (ALICFL) for further improving the global model performance and speeding up the convergence. Through numerical experiments on real-time data, we demonstrate the efficacy of the proposed algorithms and compare the performance with existing approaches.

Aimira Baitieva, David Hurych, Victor Besnier et al.

Automating visual inspection in industrial production lines is essential for increasing product quality across various industries. Anomaly detection (AD) methods serve as robust tools for this purpose. However, existing public datasets primarily consist of images without anomalies, limiting the practical application of AD methods in production settings. To address this challenge, we present (1) the Valeo Anomaly Dataset (VAD), a novel real-world industrial dataset comprising 5000 images, including 2000 instances of challenging real defects across more than 20 subclasses. Acknowledging that traditional AD methods struggle with this dataset, we introduce (2) Segmentation-based Anomaly Detector (SegAD). First, SegAD leverages anomaly maps as well as segmentation maps to compute local statistics. Next, SegAD uses these statistics and an optional supervised classifier score as input features for a Boosted Random Forest (BRF) classifier, yielding the final anomaly score. Our SegAD achieves state-of-the-art performance on both VAD (+2.1% AUROC) and the VisA dataset (+0.4% AUROC). The code and the models are publicly available.

Rohit Konda, Jordan Prescott, Vikas Chandan et al.

The widespread use of industrial refrigeration systems across various sectors contribute significantly to global energy consumption, highlighting substantial opportunities for energy conservation through intelligent control design. As such, this work focuses on control algorithm design in industrial refrigeration that minimize operational costs and provide efficient heat extraction. By adopting tools from inventory control, we characterize the structure of these optimal control policies, exploring the impact of different energy cost-rate structures such as time-of-use (TOU) pricing and peak pricing. While classical threshold policies are optimal under TOU costs, introducing peak pricing challenges their optimality, emphasizing the need for carefully designed control strategies in the presence of significant peak costs. We provide theoretical findings and simulation studies on this phenomenon, offering insights for more efficient industrial refrigeration management.

Oleksii Zahorka , Serhii Polishchuk , Iryna Zahorka et al.

Під час створення або розвитку організації ключовим аспектом є визначення її потрібного складу, тобто сукупності елементів, здатних виконати визначені завдання з максимальною ефективністю за раціонального використання ресурсів. Проте функціонування організації здійснюється в умовах невизначеності. Це ускладнює обґрунтування складу її організаційної структури. Метою статті є розроблення методичних положень обґрунтування складу організаційної структури окресленого типу на основі принципів системного аналізу для виконання завдань за призначенням. Під час проведення дослідження застосовано: метод безпосереднього оцінювання – для визначення експертами ступеня взаємозв’язку згрупованих за визначеними ознаками завдань під час визначення необхідних типів підрозділів (елементів) організаційної структури; метод аналізу ієрархій – для оцінювання важливості завдань, які повинні виконуватися організацією; метод планування експерименту – для формування варіантів складу підрозділів-виконавців завдань; експертний метод ранжирування – для оцінювання важливості показників, що характеризують створення і функціонування організації; метод таксономії – для визначення раціонального варіанта складу організаційної структури. Застосування зазначених методів дало змогу забезпечити визначення складу організаційної структури відповідно до цілей діяльності організації та завдань, що мають виконуватися для їх досягнення, а також необхідних типів підрозділів (елементів) організаційної структури із врахуванням ступеня взаємозв’язку згрупованих завдань. Науковою новизною розроблених методичних положень є сумісне застосування методів планування експериментів і таксономії, що дає можливість визначити збалансований склад підрозділів за ефективністю і вартістю для виконання завдань організації. Особливістю розроблених методичних положень є комплексне застосування вказаних вище методів, що дасть змогу досягнути поставлену мету, яка визначає теоретичну значущість розроблених методичних положень. Розроблені у статті методичні положення можуть використовуватися органами державного і військового управління для обґрунтування збалансованого складу організаційних структур, що створюються або удосконалюються, за ефективністю і часом виконання завдань підрозділами та витратами на їх створення і застосування. Це визначає практичну значущість розроблених методичних положень. Застосування означених положень показано на прикладі.

Alessio Silvetti, Tiwana Varrecchia, Giorgia Chini et al.

In the Industry 4.0 scenario, human–robot collaboration (HRC) plays a key role in factories to reduce costs, increase production, and help aged and/or sick workers maintain their job. The approaches of the ISO 11228 series commonly used for biomechanical risk assessments cannot be applied in Industry 4.0, as they do not involve interactions between workers and HRC technologies. The use of wearable sensor networks and software for biomechanical risk assessments could help us develop a more reliable idea about the effectiveness of collaborative robots (coBots) in reducing the biomechanical load for workers. The aim of the present study was to investigate some biomechanical parameters with the 3D Static Strength Prediction Program (3DSSPP) software v.7.1.3, on workers executing a practical manual material-handling task, by comparing a dual-arm coBot-assisted scenario with a no-coBot scenario. In this study, we calculated the mean and the standard deviation (SD) values from eleven participants for some 3DSSPP parameters. We considered the following parameters: the percentage of maximum voluntary contraction (%MVC), the maximum allowed static exertion time (MaxST), the low-back spine compression forces at the L4/L5 level (L4Ort), and the strength percent capable value (SPC). The advantages of introducing the coBot, according to our statistics, concerned trunk flexion (SPC from 85.8% without coBot to 95.2%; %MVC from 63.5% without coBot to 43.4%; MaxST from 33.9 s without coBot to 86.2 s), left shoulder abdo-adduction (%MVC from 46.1% without coBot to 32.6%; MaxST from 32.7 s without coBot to 65 s), and right shoulder abdo-adduction (%MVC from 43.9% without coBot to 30.0%; MaxST from 37.2 s without coBot to 70.7 s) in Phase 1, and right shoulder humeral rotation (%MVC from 68.4% without coBot to 7.4%; MaxST from 873.0 s without coBot to 125.2 s), right shoulder abdo-adduction (%MVC from 31.0% without coBot to 18.3%; MaxST from 60.3 s without coBot to 183.6 s), and right wrist flexion/extension rotation (%MVC from 50.2% without coBot to 3.0%; MaxST from 58.8 s without coBot to 1200.0 s) in Phase 2. Moreover, Phase 3, which consisted of another manual handling task, would be removed by using a coBot. In summary, using a coBot in this industrial scenario would reduce the biomechanical risk for workers, particularly for the trunk, both shoulders, and the right wrist. Finally, the 3DSSPP software could be an easy, fast, and costless tool for biomechanical risk assessments in an Industry 4.0 scenario where ISO 11228 series cannot be applied; it could be used by occupational medicine physicians and health and safety technicians, and could also help employers to justify a long-term investment.

Alex de Voogt, Kayla Louteiro

Safety in General Aviation has been a continuous concern. About 12% of all airplane accidents in General Aviation involve nose-overs and nose-down events. A total of 134 accidents reported by the National Transportation Safety Board that include nose-overs and nose-downs were analyzed for their main causes. It was found that 35% of the defining events involved a loss of control on the ground while 58% of the total dataset involved tailwheel-type aircraft. A relatively high proportion of aircraft built before 1950 were found, which are also aircraft that have tailwheel-type landing gear, and thereby a higher propensity for ground loops and nose-overs. It is shown that the high accident rate in General Aviation, especially for accidents that did not result in a fatality, was, to an important extent, explained by tailwheel and older aircraft in the US General Aviation airplane fleet struggling with controlling the aircraft on the ground. Attention to this group of aircraft in future studies may help to more effectively address the relatively high accident rates in General Aviation.

Stephane Gille, Isabelle Clerc-Urmès

Test methods that use pushing forces to evaluate the maximal load capacities of carts in design standards require a flat, smooth and horizontal steel plate and thus do not take into account the real conditions of work. Resistive forces of a single wheel of a cart in a uniform rectilinear motion were measured using a unique test bench with five loads. Forty-four wheels were tested (varying diameters, treads and bearings) with one steel plate and four resilient floor coverings. Based on a linear mixed model, all the following results were significant (<i>p</i> < 0.05). Resistive forces were increased linearly with the load and depended on the characteristics of both the wheel and floor. These forces decreased as the diameter increased. They were important for wheels with sleeve bearings but decreased for cone ball bearings and precision ball bearings. Resistive forces depended on the material of the tread and were higher for solid rubber treads. In contrast, the hardness of the tread had little effect. Resistive forces strongly depended on the hardness of the base foam of resilient floor coverings: the softer the base foam, the higher the resistive forces. Test methods in design standards should be reviewed, using corrective forces based on these present results, to prevent musculoskeletal disorders.

Vuyiseka Langwana, Norman Khoza, Phoka Caiphus Rathebe et al.

Exposure to respirable crystalline silica dust is one of the most common and severe risks due to the associated health outcomes among workers and results in many occupational-related lung diseases, such as silicosis and lung cancer. The study aimed to determine knowledge, attitudes, and practices on occupation health and safety among mine workers exposed to crystalline silica dust in Lesotho. A descriptive retrospective cross-sectional study design was used in the study. A record review guide was used to retrieve secondary data from the Southern Africa Tuberculosis and Health Systems Support (SATBHSS) project, which were thereafter entered into STATA software, version 17 for descriptive and inferential analysis. The study participants were purposively selected. Most participants were between the ages of 31 to 40 years of age and there was a significant difference between the genders with 35 (9%) females and 350 (91%) males. The majority of the participants had a high school level of education (305, 79%). The knowledge was generally positive in the study with a knowledge score mean of 13.43 (standard deviation: 2.99). The miners agreed with most attitude statements except for A1 (25%), A2 (35%), A3 (18%), and A4 (31%). The practice of exposed mine workers in the study was influenced by working in a dolerite mine (<i>p</i> = 0.003), knowledge score (<i>p</i> ˂ 0.001), and having an attitude about health and safety rules at the mine (<i>p</i> ˂ 0.001; 95% CI: 0.92 to 0.79), while age was a protective factor in the study. The findings of this study highlighted positive knowledge, attitudes, and practices toward occupational health and safety among mine workers. However, more educational programs can be implemented to ensure all mine workers understand the importance of good knowledge, positive attitude, and appropriate practices towards occupational health and safety in their environment.

Yusuke Kato, Ryo Okumura, Tadahiro Taniguchi

The process of industrial box-packing, which involves the accurate placement of multiple objects, requires high-accuracy positioning and sequential actions. When a robot is tasked with placing an object at a specific location with high accuracy, it is important not only to have information about the location of the object to be placed, but also the posture of the object grasped by the robotic hand. Often, industrial box-packing requires the sequential placement of identically shaped objects into a single box. The robot's action should be determined by the same learned model. In factories, new kinds of products often appear and there is a need for a model that can easily adapt to them. Therefore, it should be easy to collect data to train the model. In this study, we designed a robotic system to automate real-world industrial tasks, employing a vision-based learning control model. We propose in-hand-view-sensitive Newtonian variational autoencoder (ihVS-NVAE), which employs an RGB camera to obtain in-hand postures of objects. We demonstrate that our model, trained for a single object-placement task, can handle sequential tasks without additional training. To evaluate efficacy of the proposed model, we employed a real robot to perform sequential industrial box-packing of multiple objects. Results showed that the proposed model achieved a 100% success rate in industrial box-packing tasks, thereby outperforming the state-of-the-art and conventional approaches, underscoring its superior effectiveness and potential in industrial tasks.

Hao Sun, Zhexin Zhang, Jiawen Deng et al.

With the rapid popularity of large language models such as ChatGPT and GPT-4, a growing amount of attention is paid to their safety concerns. These models may generate insulting and discriminatory content, reflect incorrect social values, and may be used for malicious purposes such as fraud and dissemination of misleading information. Evaluating and enhancing their safety is particularly essential for the wide application of large language models (LLMs). To further promote the safe deployment of LLMs, we develop a Chinese LLM safety assessment benchmark. Our benchmark explores the comprehensive safety performance of LLMs from two perspectives: 8 kinds of typical safety scenarios and 6 types of more challenging instruction attacks. Our benchmark is based on a straightforward process in which it provides the test prompts and evaluates the safety of the generated responses from the evaluated model. In evaluation, we utilize the LLM's strong evaluation ability and develop it as a safety evaluator by prompting. On top of this benchmark, we conduct safety assessments and analyze 15 LLMs including the OpenAI GPT series and other well-known Chinese LLMs, where we observe some interesting findings. For example, we find that instruction attacks are more likely to expose safety issues of all LLMs. Moreover, to promote the development and deployment of safe, responsible, and ethical AI, we publicly release SafetyPrompts including 100k augmented prompts and responses by LLMs.

Eric Wagner, David Heye, Martin Serror et al.

Industrial control systems increasingly rely on middlebox functionality such as intrusion detection or in-network processing. However, traditional end-to-end security protocols interfere with the necessary access to in-flight data. While recent work on middlebox-aware end-to-end security protocols for the traditional Internet promises to address the dilemma between end-to-end security guarantees and middleboxes, the current state-of-the-art lacks critical features for industrial communication. Most importantly, industrial settings require fine-grained access control for middleboxes to truly operate in a least-privilege mode. Likewise, advanced applications even require that middleboxes can inject specific messages (e.g., emergency shutdowns). Meanwhile, industrial scenarios often expose tight latency and bandwidth constraints not found in the traditional Internet. As the current state-of-the-art misses critical features, we propose Middlebox-aware DTLS (Madtls), a middlebox-aware end-to-end security protocol specifically tailored to the needs of industrial networks. Madtls provides bit-level read and write access control of middleboxes to communicated data with minimal bandwidth and processing overhead, even on constrained hardware.

Dries Van Leemput, Jeroen Hoebeke, Eli De Poorter

Industrial wireless sensor networks enable real-time data collection, analysis, and control by interconnecting diverse industrial devices. In these industrial settings, power outlets are not always available, and reliance on battery power can be impractical due to the need for frequent battery replacement or stringent safety regulations. Battery-less energy harvesters present a suitable alternative for powering these devices. However, these energy harvesters, equipped with supercapacitors instead of batteries, suffer from intermittent on-off behavior due to their limited energy storage capacity. As a result, they struggle with extended or frequent energy-consuming phases of multi-hop network formation, such as network joining and synchronization. To address these challenges, our work proposes three strategies for integrating battery-less energy harvesting devices into industrial multi-hop wireless sensor networks. In contrast to other works, our work prioritizes the mitigation of intermittency-related issues, rather than focusing solely on average energy consumption, as is typically the case with battery-powered devices. For each of the proposed strategies, we provide an in-depth discussion of their suitability based on several critical factors, including the type of energy source, storage capacity, device mobility, latency, and reliability.

Peter Knott, Georgia Csorba, Dustin Bennett et al.

Welding fume is generated during welding activities and is a known cancer-causing hazard for those working in the welding industry. Worker exposure has been shown to regularly exceed the applicable workplace exposure standard, and control measures are required to reduce worker exposure. The aim of this study is to compare the effectiveness of control measures to prevent welding fume exposure to workers. To achieve this aim, three common welding fume control measures (local exhaust ventilation (LEV), powered air purifying respirators (PAPRs) and on-gun extraction) were used during four different welding tasks. Compared to using no controls, LEV hood capture is likely to reduce welding fume concentrations in the breathing zone of a welder by up to a factor of 9. The use of on-gun LEV is likely to reduce welding fume concentrations in the breathing zone of a welder by up to a factor of 12. The 5th percentile effective protection factors of the PAPR for all sampled welding activities were considerably greater than the required minimum protection factor of 50 specified in AS/NZS 1715:2009 for powered air purifying respirators (PAPRs) with class PAPR-P3 particulate filters with any head covering.