Hasil untuk "Industrial safety. Industrial accident prevention"

Zheyuan Liu, Dongwhi Kim, Yixin Wan et al.

Multimodal large language models (MLLMs) are increasingly deployed as assistants that interact through text and images, making it crucial to evaluate contextual safety when risk depends on both the visual scene and the evolving dialogue. Existing contextual safety benchmarks are mostly single-turn and often miss how malicious intent can emerge gradually or how the same scene can support both benign and exploitative goals. We introduce the Multi-Turn Multimodal Contextual Safety Benchmark (MTMCS-Bench), a benchmark of realistic images and multi-turn conversations that evaluates contextual safety in MLLMs under two complementary settings, escalation-based risk and context-switch risk. MTMCS-Bench offers paired safe and unsafe dialogues with structured evaluation. It contains over 30 thousand multimodal (image+text) and unimodal (text-only) samples, with metrics that separately measure contextual intent recognition, safety-awareness on unsafe cases, and helpfulness on benign ones. Across eight open-source and seven proprietary MLLMs, we observe persistent trade-offs between contextual safety and utility, with models tending to either miss gradual risks or over-refuse benign dialogues. Finally, we evaluate five current guardrails and find that they mitigate some failures but do not fully resolve multi-turn contextual risks.

Wenwei Li, Ming Xu, Tianle Xia et al.

Industrial advertising question answering (QA) is a high-stakes task in which hallucinated content, particularly fabricated URLs, can lead to financial loss, compliance violations, and legal risk. Although Retrieval-Augmented Generation (RAG) is widely adopted, deploying it in production remains challenging because industrial knowledge is inherently relational, frequently updated, and insufficiently aligned with generation objectives. We propose a reinforced co-adaptation framework that jointly optimizes retrieval and generation through two components: (1) Graph-aware Retrieval (GraphRAG), which models entity-relation structure over a high-citation knowledge subgraph for multi-hop, domain-specific evidence selection; and (2) evidence-constrained reinforcement learning via Group Relative Policy Optimization (GRPO) with multi-dimensional rewards covering faithfulness, style compliance, safety, and URL validity. Experiments on an internal advertising QA dataset show consistent gains across expert-judged dimensions including accuracy, completeness, and safety, while reducing the hallucination rate by 72\%. A two-week online A/B test demonstrates a 28.6\% increase in like rate, a 46.2\% decrease in dislike rate, and a 92.7\% reduction in URL hallucination. The system has been running in production for over half a year and has served millions of QA interactions.

Anna Tozawa, Masao Tsuchiya

Objectives: This study examined the effects of an online group program based on acceptance and commitment therapy for young employees on employee well-being. Methods: Using a single-case A-B design, this study implemented a program that spanned three 90-min sessions among 24 employees of a Japanese company, who were up to 3 years after graduation from university or postgraduate studies. The baseline (times 1–5) phase was conducted across 15 days, followed by the intervention, which was conducted over 16 days. The intervention (times 6–10) phase was conducted over 35 days following session 1. Results: Fourteen participants met the inclusion criteria. A hierarchical Bayesian model indicated that the hypotheses were not supported in terms of the primary outcome of well-being and process outcome of psychological inflexibility of 10 employees because the credible interval included 0 (well-being: expected a posteriori estimation [EAP] 0.22; 95% credible interval, −0.31 to 0.81; Acceptance and Action Questionnaire-II: EAP −2.20; 95% credible interval, −5.60 to 1.31). Tau-U for well-being varied from −0.56 to 0.84 among the participants. Similarly, for the secondary outcomes of 13 employees, the hypotheses were not supported for work performance, work engagement, and stress reaction (World Health Organization Health and Work Performance Questionnaire: EAP −0.32; 95% credible interval, −1.22 to 0.57; Utrecht Work Engagement Scale-3: EAP −0.08; 95% credible interval, −0.47 to 0.34; stress reaction: EAP −0.49; 95% credible interval, −3.76 to 2.66). Conclusions: The online group program implemented in this study did not improve employee well-being. Trial registration: The study protocol was registered with the University Hospital Medical Information Network Clinical Trials Registry (ID: UMIN000042912).

Somayeh Mollaei, Mehdi Babaei, Behroz Khalili et al.

Background and objective This research aims to investiagte the challenges in the implementation of retrofitting projects in East Azerbaijan province in Iran, and propose solutions to enrich the construction project management.  Method This is a descriptive survey study. After identifying the challenges based on the opinions of 5 experts from the organization for development, renovation and equipping of schools (DRES) of Iran, a questionnaire was completed by 6 technical experts, 15 project supervisors and 23 contractors in East Azerbaijan province to determine the main issues that require attention for the successful implementation of retrofitting projects. Finally, a set of practical recommendations for each challenge was provided.  Results The most effective matter was inappropriate allocation of construction funds from the technical experts' point of view. In the contractors' opinion, delays in payment and conflicts in administrative cycles were the most significant challenges. Finally, the supervisors expressed that lack of skilled and experienced contractors was  the main challenging issue.The proposed solutions included the establishment of transparent budget allocation processes, the formation of groups for developing detailed specialized cost lists, the streamlining of project handover procedures, the improvement of workshop facilities and the implementation of robust project coordination frameworks.  Conclusion This study unveils the key challenges in building retrofitting projects in East Azerbaijan province, Iran, and offers practical solutions to enhance the implementation of these projects. The findings can be valuable for project managers, policymakers, and stakeholders involved in construction projects.

Yingyan Zeng, Ismini Lourentzou, Xinwei Deng et al.

Artificial intelligence (AI) systems have been increasingly adopted in the Manufacturing Industrial Internet (MII). Investigating and enabling the AI resilience is very important to alleviate profound impact of AI system failures in manufacturing and Industrial Internet of Things (IIoT) operations, leading to critical decision making. However, there is a wide knowledge gap in defining the resilience of AI systems and analyzing potential root causes and corresponding mitigation strategies. In this work, we propose a novel framework for investigating the resilience of AI performance over time under hazard factors in data quality, AI pipelines, and the cyber-physical layer. The proposed method can facilitate effective diagnosis and mitigation strategies to recover AI performance based on a multimodal multi-head self latent attention model. The merits of the proposed method are elaborated using an MII testbed of connected Aerosol Jet Printing (AJP) machines, fog nodes, and Cloud with inference tasks via AI pipelines.

Jeongwoo Park, Seabin Lee, Changmin Park et al.

The industrial insertion of flexible flat cables (FFCs) into receptacles presents a significant challenge owing to the need for submillimeter precision when handling the deformable cables. In manufacturing processes, FFC insertion with robotic manipulators often requires laborious human-guided trajectory generation. While Reinforcement Learning (RL) offers a solution to automate this task without modeling complex properties of FFCs, the nondeterminism caused by the deformability of FFCs requires significant efforts and time on training. Moreover, training directly in a real environment is dangerous as industrial robots move fast and possess no safety measure. We propose an RL algorithm for FFC insertion that leverages a foundation model-based real-to-sim approach to reduce the training time and eliminate the risk of physical damages to robots and surroundings. Training is done entirely in simulation, allowing for random exploration without the risk of physical damages. Sim-to-real transfer is achieved through semantic segmentation masks which leave only those visual features relevant to the insertion tasks such as the geometric and spatial information of the cables and receptacles. To enhance generality, we use a foundation model, Segment Anything Model 2 (SAM2). To eleminate human intervention, we employ a Vision-Language Model (VLM) to automate the initial prompting of SAM2 to find segmentation masks. In the experiments, our method exhibits zero-shot capabilities, which enable direct deployments to real environments without fine-tuning.

Dominic Parosh Yamarthi, Haripriya Raman, Shamsad Parvin

Road accidents significantly threaten public safety and require in-depth analysis for effective prevention and mitigation strategies. This paper focuses on predicting accidents through the examination of a comprehensive traffic dataset covering 49 states in the United States. The dataset integrates information from diverse sources, including transportation departments, law enforcement, and traffic sensors. This paper specifically emphasizes predicting the number of accidents, utilizing advanced machine learning models such as regression analysis and time series analysis. The inclusion of various factors, ranging from environmental conditions to human behavior and infrastructure, ensures a holistic understanding of the dynamics influencing road safety. Temporal and spatial analysis further allows for the identification of trends, seasonal variations, and high-risk areas. The implications of this research extend to proactive decision-making for policymakers and transportation authorities. By providing accurate predictions and quantifiable insights into expected accident rates under different conditions, the paper aims to empower authorities to allocate resources efficiently and implement targeted interventions. The goal is to contribute to the development of informed policies and interventions that enhance road safety, creating a safer environment for all road users. Keywords: Machine Learning, Random Forest, Accident Prediction, AutoML, LSTM.

Kuan Zou, Aixin Sun

Recommender systems have generated tremendous value for both users and businesses, drawing significant attention from academia and industry alike. However, due to practical constraints, academic research remains largely confined to offline dataset optimizations, lacking access to real user data and large-scale recommendation platforms. This limitation reduces practical relevance, slows technological progress, and hampers a full understanding of the key challenges in recommender systems. In this survey, we provide a systematic review of industrial recommender systems and contrast them with their academic counterparts. We highlight key differences in data scale, real-time requirements, and evaluation methodologies, and we summarize major real-world recommendation scenarios along with their associated challenges. We then examine how industry practitioners address these challenges in Transaction-Oriented Recommender Systems and Content-Oriented Recommender Systems, a new classification grounded in item characteristics and recommendation objectives. Finally, we outline promising research directions, including the often-overlooked role of user decision-making, the integration of economic and psychological theories, and concrete suggestions for advancing academic research. Our goal is to enhance academia's understanding of practical recommender systems, bridge the growing development gap, and foster stronger collaboration between industry and academia.

Antonella Scarano, Massimo Aria, Filomena Mauriello et al.

Windri Handayani, Anom Bowolaksono, Fatma Lestari et al.

Numerous hospital laboratories in Indonesia need to implement improved bio-risk management (BRM) systems. There are many potential biohazards in laboratory activities that can impact health and the environment, leading to laboratory incidents. To minimize the impact and occurrence of such incidents, it is necessary to evaluate the implementation of BRM in every hospital laboratory that uses biological agents. This study was conducted in eight COVID-19 reference hospitals in Indonesia in the regions of Sumatra, Kalimantan, and Java, which have committed to implementing BRM systems in their laboratory activities. This research employed a descriptive study design and quantitative methods, with the aim of analyzing and evaluating the implementation of BRM systems in laboratories by assessing the achievements and gap analysis obtained from each laboratory. This research utilized primary data in the form of checklist forms referencing ISO 35001:2019 for the laboratory BRM system. Then, the assessments were based on virtual interviews conducted by the researcher with laboratory personnel as the primary data. The evaluation conducted on gap analysis from the seven clauses in ISO 35001:2019 across all hospitals revealed large gaps, particularly in three clauses: leadership, support, and performance. However, the aspects concerning organization, improvement, and performance evaluation were relatively satisfactory. Hence, there is a need for further improvement in leadership, support, and performance evaluation clauses. Additionally, it is essential to highlight the importance of comprehensive performance assessment, including proactive audits and continuous enhancements to achieve optimal bio-risk management.

Alexandre Trilla, Ossee Yiboe, Nenad Mijatovic et al.

This paper describes the development of a causal diagnosis approach for troubleshooting an industrial environment on the basis of the technical language expressed in Return on Experience records. The proposed method leverages the vectorized linguistic knowledge contained in the distributed representation of a Large Language Model, and the causal associations entailed by the embedded failure modes and mechanisms of the industrial assets. The paper presents the elementary but essential concepts of the solution, which is conceived as a causality-aware retrieval augmented generation system, and illustrates them experimentally on a real-world Predictive Maintenance setting. Finally, it discusses avenues of improvement for the maturity of the utilized causal technology to meet the robustness challenges of increasingly complex scenarios in the industry.

Zhipeng Ma, Bo Nørregaard Jørgensen, Michelle Levesque et al.

Digitalization is challenging in heavy industrial sectors, and many pi-lot projects facing difficulties to be replicated and scaled. Case studies are strong pedagogical vehicles for learning and sharing experience & knowledge, but rarely available in the literature. Therefore, this paper conducts a survey to gather a diverse set of nine industry cases, which are subsequently subjected to analysis using the business model canvas (BMC). The cases are summarized and compared based on nine BMC components, and a Value of Business Model (VBM) evaluation index is proposed to assess the business potential of industrial digital solutions. The results show that the main partners are industry stakeholders, IT companies and academic institutes. Their key activities for digital solutions include big-data analysis, machine learning algorithms, digital twins, and internet of things developments. The value propositions of most cases are improving energy efficiency and enabling energy flexibility. Moreover, the technology readiness levels of six industrial digital solutions are under level 7, indicating that they need further validation in real-world environments. Building upon these insights, this paper proposes six recommendations for future industrial digital solution development: fostering cross-sector collaboration, prioritizing comprehensive testing and validation, extending value propositions, enhancing product adaptability, providing user-friendly platforms, and adopting transparent recommendations.

Karthik Muthineni, Alexander Artemenko, Josep Vidal et al.

The fifth generation (5G) mobile communication technology integrates communication, positioning, and mapping functionalities as an in-built feature. This has drawn significant attention from industries owing to the capability of replacing the traditional wireless technologies used in industries with 5G infrastructure that can be used for both connectivity and positioning. To this end, we identify the Automated Guided Vehicle (AGV) as a primary use case to benefit from the 5G functionalities. Given that there have been various works focusing on 5G positioning, it is necessary to analyze the existing works about their applicability with AGVs in industrial environments and provide insights to future research. In this paper, we present state of the art in 5G-based positioning, with a focus on key features, such as Millimeter Wave (mmWave) system, Massive Multiple Input Multiple Output (MIMO), Ultra-Dense Network (UDN), Device-to-Device (D2D) communication, and Reconfigurable Intelligent Surface (RIS). Moreover, we present the shortcomings in the current state of the art. Additionally, we propose enhanced techniques that can complement the accuracy of 5G-based positioning in controlled industrial environments.

Narelle Haworth, Amy Schramm, Divera Twisk

Sisay Ketema, Abayneh Melaku, Habtamu Demelash et al.

Occupational safety is a critical concern for disease prevention and control at healthcare facilities. Medical waste handlers, in particular, are those most exposed to occupational hazards among healthcare workers. Therefore, this cross-sectional study was conducted to evaluate safety practices and associated factors among healthcare waste handlers in four public hospitals, southwest Ethiopia from 15 March to 30 May 2022. The study included 203 healthcare waste handlers. The data were collected using an interviewer-administered questionnaire and observational checklists. The overall performance of occupational safety practices among healthcare waste handlers was 47.3% (95%CI; 40.3, 54.2). Waste handlers with an educational status of secondary and above (AOR 4.95; 95%CI 2.13, 11.50), good knowledge of infection prevention and safety practices (AOR 4.95; 95%CI 2.13, 11.50), training in infection prevention and safety practices (AOR 2.57; 95%CI 1.25, 5.29), and adequate access to safety materials (AOR 3.45; 95%CI 1.57, 7.60) had significantly better occupational safety practices than their counterparts. In general, medical waste handlers’ occupational safety practices were found to be inadequate. Waste handlers’ knowledge of safety measures and training, educational level, and availability of safety materials were predictors of safe occupational practices. Therefore, appropriate strategies and actions are needed to ensure the safe occupational practices of healthcare waste handlers.

Ainayya Rizky Savitri, Noeroel Widajati

Introduction: Work stress is the inability of a worker to face job demands, leading to discomfort while working. Work stress can be caused by many factors, among them work monotony, excessive workload, and individual characteristics. This study's aim was to analyze the strength of the relationship among individual characteristics, work monotony, and mental workload with work stress on the crane operators of Jamrud Terminal. Methods: This study used cross-sectional design. The population in this study was all crane operators in Jamrud Terminal as many as 28 people. Total sampling was applied as sampling technique. The independent variables in this study include individual characteristics (age and tenure), work monotony obtained from the questionnaire, mental workload which was appraised using NASA-TLX questionnaire, while the dependent variable was work stress assessed with DASS 42 questionnaire. Coefficient contingency and Spearman correlation test were applied to analyze collected data. Results: This study revealed 13 operators (46.4%) felt normal work stress and the other operators (53.6%) felt work stress ranging from light until very heavy. Contingency coefficient correlation test resulted in weak relationship among age and work stress and strong relationship among work monotony and work stress. Spearman correlation test revealed weak relationship among tenure and work stress and moderate relationship among mental workload and work stress. Conclusion: There were relationships among work monotony and mental workload with work stress on crane operators. The company is advised to give work music, variation on work, and arrange proper break time for crane operator.

Andrey Solano, Arne Sieverling, Robert Gieselmann et al.

We present Fast-dRRT*, a sampling-based multi-robot planner, for real-time industrial automation scenarios. Fast-dRRT* builds upon the discrete rapidly-exploring random tree (dRRT*) planner, and extends dRRT* by using pre-computed swept volumes for efficient collision detection, deadlock avoidance for partial multi-robot problems, and a simplified rewiring strategy. We evaluate Fast-dRRT* on five challenging multi-robot scenarios using two to four industrial robot arms from various manufacturers. The scenarios comprise situations involving deadlocks, narrow passages, and close proximity tasks. The results are compared against dRRT*, and show Fast-dRRT* to outperform dRRT* by up to 94% in terms of finding solutions within given time limits, while only sacrificing up to 35% on initial solution cost. Furthermore, Fast-dRRT* demonstrates resilience against noise in target configurations, and is able to solve challenging welding, and pick and place tasks with reduced computational time. This makes Fast-dRRT* a promising option for real-time motion planning in industrial automation.

Hossam Farag, Dejan Vukobratovic, Andrea Munari et al.

Enabling real-time communication in Industrial Internet of Things (IIoT) networks is crucial to support autonomous, self-organized and re-configurable industrial automation for Industry 4.0 and the forthcoming Industry 5.0. In this paper, we consider a SIC-assisted real-time IIoT network, in which sensor nodes generate reports according to an event-generation probability that is specific for the monitored phenomena. The reports are delivered over a block-fading channel to a common Access Point (AP) in slotted ALOHA fashion, which leverages the imbalances in the received powers among the contending users and applies successive interference cancellation (SIC) to decode user packets from the collisions. We provide an extensive analytical treatment of the setup, deriving the Age of Information (AoI), throughput and deadline violation probability, when the AP has access to both the perfect as well as the imperfect channel-state information. We show that adopting SIC improves all the performance parameters with respect to the standard slotted ALOHA, as well as to an age-dependent access method. The analytical results agree with the simulation based ones, demonstrating that investing in the SIC capability at the receiver enables this simple access method to support timely and efficient information delivery in IIoT networks.

Mohamed Essa, Tarek Sayed

Renyou Zhang, Huixing Meng, Jun Ge et al.

Oil tanker offloading is a human-related and high-risk task. A small operational error may trigger catastrophic accidents such as fire and explosion. It is recognised that more than 70% of industrial accidents are blamed for human errors, so preventing them is crucial. As human error is associated with a variety of Performance Shaping Factors (PSFs), it is meaningful to identify key PSFs for safe operations during oil tanker offloading process. However, some issues are obstacles to finding the crucial PSFs. The recording data of most PSFs are always incomplete and imperfect. Moreover, the standard for ranking PSFs should be rational. In addition, the performance of each PSF at the different stages is oil offloading is usually unstable and may change with time. As a result, this study aims to conduct a method that mainly relies on Grey Relational Analysis (GRA), the definition of “Risk” (combination of likelihood and impact), and Hierarchical Task Analysis (HTA) to find several significant PSFs to prevent human errors. GRA deals with the incomplete and imperfect data; the definition of “Risk” provides a rational basis for ranking PSFs; and HTA gives support for considering the PSFs’ changes at different stages of a task. The proposed approach is tested on a real engineering case of oil tanker offloading work at offshore terminal. The result indicates that the method can be applied to identify key PSFs, which in turn provides recommendations for human error prevention to ensure the safety both on board and at terminal.