Hasil untuk "Industrial safety. Industrial accident prevention"

Omer Mermer, Yanan Liu, Charles A. Jennissen et al.

Despite the agricultural sector’s consistently high injury rates, formal reporting is often limited, leading to sparse national datasets that hinder effective safety interventions. To address this, our study introduces a comprehensive framework leveraging advanced ensemble machine learning (ML) models to predict and interpret the severity of agricultural injuries. We use a unique, manually curated dataset of over 2400 agricultural incidents from AgInjuryNews, a public repository of news reports detailing incidents across the United States. We evaluated six ensemble models, including Gradient Boosting (GB), eXtreme Grading Boosting (XGB), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), Histogram-based Gradient Boosting Regression Trees (HistGBRT), and Random Forest (RF), for their accuracy in classifying injury outcomes as fatal or non-fatal. A key contribution of our work is the novel integration of explainable artificial intelligence (XAI), specifically SHapley Additive exPlanations (SHAP), to overcome the “black-box” nature of complex ensemble models. The models demonstrated strong predictive performance, with most achieving an accuracy of approximately 0.71 and an F1-score of 0.81. Through global SHAP analysis, we identified key factors influencing injury severity across the dataset, such as the presence of helmet use, victim age, and the type of injury agent. Additionally, our application of local SHAP analysis revealed how specific variables like location and the victim’s role can have varying impacts depending on the context of the incident. These findings provide actionable, context-aware insights for developing targeted policy and safety interventions for a range of stakeholders, from first responders to policymakers, offering a powerful tool for a more proactive approach to agricultural safety.

Zhuonan Wang, Zhenxuan Fan, Siwen Tan et al.

As industrial manufacturing scales, automating fine-grained product image analysis has become critical for quality control. However, existing approaches are hindered by limited dataset coverage and poor model generalization across diverse and complex anomaly patterns. To address these challenges, we introduce MAU-Set, a comprehensive dataset for Multi-type industrial Anomaly Understanding. It spans multiple industrial domains and features a hierarchical task structure, ranging from binary classification to complex reasoning. Alongside this dataset, we establish a rigorous evaluation protocol to facilitate fair and comprehensive model assessment. Building upon this foundation, we further present MAU-GPT, a domain-adapted multimodal large model specifically designed for industrial anomaly understanding. It incorporates a novel AMoE-LoRA mechanism that unifies anomaly-aware and generalist experts adaptation, enhancing both understanding and reasoning across diverse defect classes. Extensive experiments show that MAU-GPT consistently outperforms prior state-of-the-art methods across all domains, demonstrating strong potential for scalable and automated industrial inspection.

Aisyah Nur Jannah, Sara Moridpour, Richard Tay et al.

Kwangsu Moon, Kyung Woo Kim, Ji Dong Lee

Background: This study explored the applicability of the Trust Leading Indicator (TLI) and Proactive Leading Indicator (PLI), developed as part of the Vision Zero, a global campaign for the dissemination of prevention culture, in Korean industries. The relationship between these indicators and safety culture-related variables were compared, such as safety climate, safety behavior, risk perception, and accident experience. Methods: The study sample comprised 630 workers from 12 subcontractors affiliated with the Republic of Korea's large manufacturing plant. Correlations among the main variables were examined, including group differences in TLI and PLI based on subjective accident experience. Results: The TLI and PLI had significant positive correlations with the sub-factors of safety climate and safety behavior and negative correlations with risk perception, indicating their potential utility as extensions of existing safety culture indicators. A significant difference in TLI and PLI was observed across accident experience levels. Conclusion: Despite limitations, such as the predominance of male workers in the study owing to the nature of the industry and use of subjective accident experience rather than official industrial accident data, this study is significant as it explores the applicability of the two leading indicators of prevention culture in Korean industries, confirming the potential utility of these indicators across various cultural contexts and contributing to global efforts to disseminate a prevention culture.

Kristina Dundović

Seth Oppong

Efstathios Bouhouras, Grigorios Fountas, Socrates Basbas et al.

This paper presents a comparative analysis of pedestrian behavior and perceived safety among university students at two signalized intersections near the campus premises of the Aristotle University of Thessaloniki, Greece. Although both intersections include pedestrian crosswalks and traffic lights, one permits vehicle left turns during pedestrian phases via flashing yellow arrows, while the other restricts all vehicle movement. Two questionnaire-based surveys (<i>n</i>₁ = 304 and <i>n</i>₂ = 303) recorded demographic information, crossing behavior, perceived risk, and preferred safety interventions. Results indicate that the intersection permitting vehicle conflict is associated with significantly lower levels of perceived safety and higher instances of risk-taking, such as crossing “at any time”. Conversely, the vehicle-restricted intersection fosters greater compliance with pedestrian signals and a stronger sense of security. Key factors influencing crossing decisions included vehicle speed, signal duration, pedestrian group presence, and urgency. Respondents prioritized safety improvements such as pedestrian countdown timers, enhanced signage, and enforcement cameras. These findings underscore the critical role of signal phasing in shaping pedestrian behavior and safety perceptions. Evidence-based recommendations are offered to urban planners and policymakers to enhance pedestrian safety through targeted infrastructure upgrades and enforcement strategies.

Joseph Le Bihan, Thomas Lapi, José Halloy

This study proposes a new model based on a classic S-curve that describes deployment and stabilization at maximum capacity. In addition, the model extends to the post-growth plateau, where technological capacity is renewed according to the distribution of equipment lifespans. We obtain two qualitatively different results. In the case of "fast" deployment, characterized by a short deployment time in relation to the average equipment lifetime, production is subject to significant oscillations. In the case of "slow" deployment, production increases monotonically until it reaches a renewal plateau. These results are counterintuitively validated by two case studies: nuclear power plants as a fast deployment and smartphones as a slow deployment. These results are important for long-term industrial planning, as they enable us to anticipate future business cycles. Our study demonstrates that business cycles can originate endogenously from industrial dynamics of installation and renewal, contrasting with traditional views attributing fluctuations to exogenous macroeconomic factors. These endogenous cycles interact with broader trends, potentially being modulated, amplified, or attenuated by macroeconomic conditions. This dynamic of deployment and renewal is relevant for long-life infrastructure technologies, such as those supporting the renewable energy sector and has major policy implications for industry players.

Stefano Scanzio, Paolo Campagnale, Pietro Chiavassa et al.

QR codes are nowadays customarily used for embedding static data such as web hyperlinks or plain text. The sQRy technology (executable QR codes) permits to embed executable programs in QR codes, enabling people to interact with them even without an internet connection. In this work we present QRmap, a specific dialect that permits the inclusion of geographic maps in sQRy and supports interaction with the user to provide indications to reach the destination of interest. The QRmap technology facilitates navigation in large industrial plants where internet connectivity is absent, due to either environmental limitations or company policies. The proposed technology can have interesting applications in non-industrial contexts as well.

Guocong Zhai, Kun Xie, Di Yang et al.

Dwitya Harits Waskito, Ludfi Pratiwi Bowo, Siti Hidayanti Mutiara Kurnia et al.

Truck accidents are a prevalent global issue resulting in substantial economic losses and human lives. One of the principal contributing factors to these accidents is driver error. While analysing human error, it is important to thoroughly examine the truck’s condition, the drivers, external circumstances, the trucking company, and regulatory factors. Therefore, this study aimed to illustrate the application of HFACS (Human Factor Classification System) to examine the causal factors behind the unsafe behaviors of drivers and the resulting accident consequences. Bayesian Network (BN) analysis was adopted to discern the relationships between failure modes within the HFACS framework. The result showed that driver violations had the most significant influence on fatalities and multiple-vehicle accidents. Furthermore, the backward inference with BN showed that the mechanical system malfunction significantly impacts driver operating error. The result of this analysis is valuable for regulators and trucking companies striving to mitigate the occurrence of truck accidents proactively.

Md. Ripul Kabir, Mst. Taslima Khatun Toru, Golam Faruk Faruk

This study aimed to find the factors affecting the fruit vendor’s safety measures and sanitation facilities during COVID-19 in Bangladesh. A quantitative research design was used to conduct this study. Random sampling techniques were executed to collect data from 416 fruit vendors through a field survey. The study reveals that 87% of the fruit vendors took safety measures during COVID-19. Most of them had better sanitation facilities at home compared to their workplaces. Their safety measures and sanitation facilities were associated with socioeconomic backgrounds. Age, type of house, place of business, and receiving financial support influenced fruit vendors’ safety measures. Sanitation facilities at home were affected by their sex, schooling, types of houses, and working hours.  Types of houses, family income, and business duration impacted the workplace's sanitation facilities. Their socio-demographic and economic situations affected fruit vendors' safety measures and sanitation facilities during COVID-19. Fear of death and government market mechanisms also might have played a significant role in measuring the different steps against Coronavirus infection. Health and hygiene rules prescribed by the authorities should be followed strictly to avoid dire situations during the pandemic. Both government and non-government initiatives should be given the utmost priority to create sanitation awareness, whether about personal cleanliness or workplace hygiene and paired with financial support.

Qi Liu, Kai Zheng, Rui Huang et al.

Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users. Existing RS benchmark datasets primarily focus on the exposure space, where novel RS algorithms are trained and evaluated. However, when these algorithms transition to real world industrial RS, they face a critical challenge of handling unexposed items which are a significantly larger space than the exposed one. This discrepancy profoundly impacts their practical performance. Additionally, these algorithms often overlook the intricate interplay between multiple RS stages, resulting in suboptimal overall system performance. To address this issue, we introduce RecFlow, an industrial full flow recommendation dataset designed to bridge the gap between offline RS benchmarks and the real online environment. Unlike existing datasets, RecFlow includes samples not only from the exposure space but also unexposed items filtered at each stage of the RS funnel. Our dataset comprises 38M interactions from 42K users across nearly 9M items with additional 1.9B stage samples collected from 9.3M online requests over 37 days and spanning 6 stages. Leveraging the RecFlow dataset, we conduct courageous exploration experiments, showcasing its potential in designing new algorithms to enhance effectiveness by incorporating stage-specific samples. Some of these algorithms have already been deployed online, consistently yielding significant gains. We propose RecFlow as the first comprehensive benchmark dataset for the RS community, supporting research on designing algorithms at any stage, study of selection bias, debiased algorithms, multi-stage consistency and optimality, multi-task recommendation, and user behavior modeling. The RecFlow dataset, along with the corresponding source code, is available at https://github.com/RecFlow-ICLR/RecFlow.

Mazen Alamir, Raphaël Dion

In this paper, a new model-free anomaly detection framework is proposed for time-series induced by industrial dynamical systems.The framework lies in the category of conventional approaches which enable appealing features such as a learning with reduced amount of training data, a high potential for explainability as well as a compatibility with incremental learning mechanism to incorporate operator feedback after an alarm is raised and analyzed. Although these are crucial features towards acceptance of data-driven solutions by industry, they are rarely considered in the comparisons that generally almost exclusively focus on performance metrics. Moreover, the features engineering step involved in the proposed framework is inspired by the time-series being implicitly governed by physical laws as it is generally the case in industrial time-series. Two examples are given to assess the efficiency of the proposed approach.

M. Gundall, J. Schneider, H. D. Schotten et al.

The increasing demand for highly customized products, as well as flexible production lines, can be seen as trigger for the "fourth industrial revolution", referred to as "Industrie 4.0". Current systems usually rely on wire-line technologies to connect sensors and actuators. To enable a higher flexibility such as moving robots or drones, these connections need to be replaced by wireless technologies in the future. Furthermore, this facilitates the renewal of brownfield deployments to address Industrie 4.0 requirements. This paper proposes representative use cases, which have been examined in the German Tactile Internet 4.0 (TACNET 4.0) research project. In order to analyze these use cases, this paper identifies the main challenges and requirements of communication networks in Industrie 4.0 and discusses the applicability of 5th generation wireless communication systems (5G).

Zihan Liu, Ruinan Zeng, Dongxia Wang et al.

In industrial control systems, the generation and verification of Programmable Logic Controller (PLC) code are critical for ensuring operational efficiency and safety. While Large Language Models (LLMs) have made strides in automated code generation, they often fall short in providing correctness guarantees and specialized support for PLC programming. To address these challenges, this paper introduces Agents4PLC, a novel framework that not only automates PLC code generation but also includes code-level verification through an LLM-based multi-agent system. We first establish a comprehensive benchmark for verifiable PLC code generation area, transitioning from natural language requirements to human-written-verified formal specifications and reference PLC code. We further enhance our `agents' specifically for industrial control systems by incorporating Retrieval-Augmented Generation (RAG), advanced prompt engineering techniques, and Chain-of-Thought strategies. Evaluation against the benchmark demonstrates that Agents4PLC significantly outperforms previous methods, achieving superior results across a series of increasingly rigorous metrics. This research not only addresses the critical challenges in PLC programming but also highlights the potential of our framework to generate verifiable code applicable to real-world industrial applications.

Bian Shabri Putri Irwanto, Meirina Ernawati, Indriati Paskarini et al.

Introduction: Fires in the workplace can have consequences that adversely affect many parties, both for companies of the workers and the wider community, including institutions such as hospitals. In this research, hospitals are considered to be at high risk of causing fatalities in the event of a fire. The purpose of this research is to evaluate the prevention and control of fire in dr. R. Koesma Hospital Tuban based on the regulation of Minister of Health No.66 of 2016 about Occupational Health and Safety of Hospital. Method: This research is observational research. Data collection was done by interview and observation. The assessment of the evaluation of fire prevention and control is done by using a scoring formula made independently. Result: The evaluation is done on the identification of fire and explosion risk areas as well as on the mapping of high-risk areas of fire and explosion in dr. R. Koesma Hospital based on regulation of Minister of Health No.66 of 2016. The evaluation results on both aspects are 4% out of 6%. The evaluation result of the risk reduction of fire and explosion hazards shows a score of 15% out of 18%. The evaluation result of fire control is 22%. The evaluation result of the fire simulation shows a score of 38% out of 48%. Conclusion: This research concludes that the evaluation results of the fire prevention and control system in dr. R. Koesma Hospital based on regulation of Minister of Health No.66 of 2016 show a score of 83%.

Vincenzo Manfredi, Giuseppe Nicodemo, Angelo Masi

In the field of seismic risk assessment, the estimation of human casualties is an important task for medical and relief agencies to develop preparedness and emergency management actions. The process of calculating casualties involves several factors along with the associated uncertainties. Despite its complexity and the limited quality and availability of data, many studies have been devoted to this topic in recent decades, but additional effort is required to better analyze these studies by also comparing the results they provide. In the present paper, an extensive literature overview of the main models proposed to estimate casualties is reported. Further, the main factors involved in the available Casualty Estimation Models are also analyzed by analyzing loss scenarios related to two strong Italian earthquakes (1980 Irpinia–Basilicata and 2009 L’Aquila). Comparing estimated vs. collected data, it is found that, in addition to the damage level, both the building material and the occupancy rate at the time of the event significantly impact the estimation of human casualties. As for the occupancy rate, based on the data on the daily life of citizens collected by the Italian Institute of Statistics, the occupancy rate functions for Italian residential building stock are derived and discussed.

Mai Iwanaga, Mako Iida, Natsu Sasaki et al.

Objectives: Work-related subjective well-being (SWB) may be negatively affected by early-life adverse experiences, such as school bullying experience. This study aimed to identify the association between work-related SWB and school bullying experiences. Methods: A systematic review was conducted using five electronic databases to search for published observational studies from inception to May 5th, 2022. Eligibility criteria included the original papers in English, which measured school bullying experiences and work-related SWB (eg, satisfaction, engagement). Eight researchers independently conducted screening and a full-text review. We used the Risk of Bias Assessment tool for Non-randomized Studies to assess the certainty of the evidence. Narrative data were summarized. The study has been registered at UMIN-CTR (UMIN000040513). Results: A total of 6,842 studies were initially searched. We included two cross-sectional studies. Both studies were rated as high risk for bias in exposure measurements and incomplete outcome data. These studies showed conflicting results. One study reported that school bullying was negatively associated with job satisfaction among British lesbian, gay, or bisexual workers; on the other hand, another study reported that school bullying was positively associated with work engagement among Japanese workers. Conclusions: We found limited inconsistent evidence for the association between work-related SWB and school bullying experiences.

Kashif Ishaq, Fatima Khan

The possibility of block chain innovation revolutionizing business operations and interpersonal interactions in Industry 4.0 is becoming more widely acknowledged. Industry 4.0 and the Industrial Internet of Things (IoT) are among the new application fields. As a result, the purpose of this article is to investigate the block chain applications that are already being used in IoT and Industry 4.0. In particular, it looks at current research trends in various IoT applications, addressing problems, concerns, and potential future uses of integrating block chain technology. This article also includes a thorough discussion of the key elements of block chain databases, including Merkle trees, transaction management, sharding, long-term memory, and short-term memory. In order to do this, more than 46 pertinent primary research that have been published in reputable journals have been chosen for additional examination. The workflow of a block chain network utilizing IoT is also demonstrated, demonstrating how IoT devices communicate with one another and how they contribute to the network's overall operation. The taxonomy diagram below serves to illustrate the contribution.