Hasil untuk "Industrial hygiene. Industrial welfare"

Ana Rita Barata, Beatriz Ferreira, Patrícia Oliveira et al.

<b>Background:</b> Domestic refrigeration and egg handling are key factors in ensuring household food safety. Inadequate temperature control and poor hygiene in refrigerators can promote the survival and growth of foodborne pathogens. This study aimed to (i) characterize refrigerator temperature profiles and surface microbial contamination and (ii) screen eggs and egg-storage areas for the presence of <i>Salmonella</i> spp. and <i>Campylobacter</i> spp. <b>Methods:</b> Fifty domestic refrigerators were monitored twice in 2024 and 2025 in Porto, Portugal. The temperatures were continuously logged on the lowest shelf, which was swabbed for microbiological analysis. Surface hygiene was evaluated using total viable counts (TVC), <i>Enterobacteriaceae</i>, and <i>Escherichia coli</i> enumerated following ISO methods. Detection of pathogens <i>Listeria monocytogenes</i>, <i>Salmonella</i> spp., and <i>Campylobacter</i> spp. was performed using real-time PCR. Eggs (<i>n</i> = 92 in 2024; <i>n</i> = 88 in 2025), and domestic egg storage areas (total <i>n</i> = 76) were screened for <i>Salmonella</i> and <i>Campylobacter</i>. <b>Results:</b> The mean refrigerator temperatures were 6.0 ± 0.5 °C in 2024 and 6.1 ± 0.5 °C in 2025; 44% and 50% of the units, respectively, exceeded the recommended 6 °C threshold. In 2025, 31 (62%) and 33 (66%) refrigerators showed higher TVC and <i>Enterobacteriaceae</i> counts compared to 2024, whereas <i>E. coli</i> was only detected sporadically. <i>L. monocytogenes</i>, <i>Salmonella</i> spp., or <i>Campylobacter</i> spp. were not recovered from the refrigerator surfaces. Likewise, <i>Salmonella</i> and <i>Campylobacter</i> were not detected in any of the eggs or egg-storage sites. Indicator microorganism’s counts were not associated with the mean temperature. <b>Conclusions:</b> The absence of correlation between ΔT and Δ microbial counts suggests that behaviour-driven hygiene factors, rather than the relatively small year-to-year temperature differences observed, are more influential in determining household bioburden. Maintaining refrigerator temperatures ≤ 6 °C together with simple hygiene practices remains essential for reducing household food safety risks.

Wei Luo, Haiming Yao, Wenyong Yu

Industrial anomaly detection plays a crucial role in ensuring product quality control. Therefore, proposing an effective anomaly detection model is of great significance. While existing feature-reconstruction methods have demonstrated excellent performance, they face challenges with shortcut learning, which can lead to undesirable reconstruction of anomalous features. To address this concern, we present a novel feature-reconstruction model called the \textbf{T}emplate-based \textbf{F}eature \textbf{A}ggregation \textbf{Net}work (TFA-Net) for anomaly detection via template-based feature aggregation. Specifically, TFA-Net first extracts multiple hierarchical features from a pre-trained convolutional neural network for a fixed template image and an input image. Instead of directly reconstructing input features, TFA-Net aggregates them onto the template features, effectively filtering out anomalous features that exhibit low similarity to normal template features. Next, TFA-Net utilizes the template features that have already fused normal features in the input features to refine feature details and obtain the reconstructed feature map. Finally, the defective regions can be located by comparing the differences between the input and reconstructed features. Additionally, a random masking strategy for input features is employed to enhance the overall inspection performance of the model. Our template-based feature aggregation schema yields a nontrivial and meaningful feature reconstruction task. The simple, yet efficient, TFA-Net exhibits state-of-the-art detection performance on various real-world industrial datasets. Additionally, it fulfills the real-time demands of industrial scenarios, rendering it highly suitable for practical applications in the industry. Code is available at https://github.com/luow23/TFA-Net.

Yiliu He, Tianle Li, Binghao Ji et al.

Optimization modeling via mixed-integer linear programming (MILP) is fundamental to industrial planning and scheduling, yet translating natural-language requirements into solver-executable models and maintaining them under evolving business rules remains highly expertise-intensive. While large language models (LLMs) offer promising avenues for automation, existing methods often suffer from low data efficiency, limited solver-level validity, and poor scalability to industrial-scale problems. To address these challenges, we present EvoOpt-LLM, a unified LLM-based framework supporting the full lifecycle of industrial optimization modeling, including automated model construction, dynamic business-constraint injection, and end-to-end variable pruning. Built on a 7B-parameter LLM and adapted via parameter-efficient LoRA fine-tuning, EvoOpt-LLM achieves a generation rate of 91% and an executability rate of 65.9% with only 3,000 training samples, with critical performance gains emerging under 1,500 samples. The constraint injection module reliably augments existing MILP models while preserving original objectives, and the variable pruning module enhances computational efficiency, achieving an F1 score of ~0.56 on medium-sized LP models with only 400 samples. EvoOpt-LLM demonstrates a practical, data-efficient approach to industrial optimization modeling, reducing reliance on expert intervention while improving adaptability and solver efficiency.

Anwar Ahmed Khan, Indrakshi Dey

Efficient medium access control (MAC) is critical for enabling low-latency and reliable communication in industrial Machine-to-Machine (M2M) net-works, where timely data delivery is essential for seamless operation. The presence of multi-priority data in high-risk industrial environments further adds to the challenges. The development of tens of MAC schemes over the past decade often makes it a tough choice to deploy the most efficient solu-tion. Therefore, a comprehensive cross-comparison of major MAC protocols across a range of performance parameters appears necessary to gain deeper insights into their relative strengths and limitations. This paper presents a comparison of Contention window-based MAC scheme BoP-MAC with a fragmentation based, FROG-MAC; both protocols focus on reducing the delay for higher priority traffic, while taking a diverse approach. BoP-MAC assigns a differentiated back-off value to the multi-priority traffic, whereas FROG-MAC enables early transmission of higher-priority packets by fragmenting lower-priority traffic. Simulations were performed on Contiki by varying the number of nodes for two traffic priorities. It has been shown that when work-ing with multi-priority heterogenous data in the industrial environment, FROG-MAC results better both in terms of delay and throughput.

Peijian Zeng, Feiyan Pang, Zhanbo Wang et al.

Industrial Anomaly Detection (IAD) is critical for ensuring product quality by identifying defects. Traditional methods such as feature embedding and reconstruction-based approaches require large datasets and struggle with scalability. Existing vision-language models (VLMs) and Multimodal Large Language Models (MLLMs) address some limitations but rely on mask annotations, leading to high implementation costs and false positives. Additionally, industrial datasets like MVTec-AD and VisA suffer from severe class imbalance, with defect samples constituting only 23.8% and 11.1% of total data respectively. To address these challenges, we propose a reward function that dynamically prioritizes rare defect patterns during training to handle class imbalance. We also introduce a mask-free reasoning framework using Chain of Thought (CoT) and Group Relative Policy Optimization (GRPO) mechanisms, enabling anomaly detection directly from raw images without annotated masks. This approach generates interpretable step-by-step explanations for defect localization. Our method achieves state-of-the-art performance, outperforming prior approaches by 36% in accuracy on MVTec-AD and 16% on VisA. By eliminating mask dependency and reducing costs while providing explainable outputs, this work advances industrial anomaly detection and supports scalable quality control in manufacturing. Code to reproduce the experiment is available at https://github.com/LilaKen/LR-IAD.

Iva Kertusha, Gebremariem Assress, Onur Duman et al.

Web application testing is an essential practice to ensure the reliability, security, and performance of web systems in an increasingly digital world. This paper presents a systematic literature survey focusing on web testing methodologies, tools, and trends from 2014 to 2025. By analyzing 259 research papers, the survey identifies key trends, demographics, contributions, tools, challenges, and innovations in this domain. In addition, the survey analyzes the experimental setups adopted by the studies, including the number of participants involved and the outcomes of the experiments. Our results show that web testing research has been highly active, with ICST as the leading venue. Most studies focus on novel techniques, emphasizing automation in black-box testing. Selenium is the most widely used tool, while industrial adoption and human studies remain comparatively limited. The findings provide a detailed overview of trends, advancements, and challenges in web testing research, the evolution of automated testing methods, the role of artificial intelligence in test case generation, and gaps in current research. Special attention was given to the level of collaboration and engagement with the industry. A positive trend in using industrial systems is observed, though many tools lack open-source availability

Noel Portillo

The petrochemical industry faces significant technological, environmental, occupational safety, and financial challenges. Since its emergence in the 1920s, technologies that were once innovative have now become obsolete. However, factors such as the protection of trade secrets in industrial processes, limited budgets for research and development, doubts about the reliability of new technologies, and resistance to change from decision-makers have hindered the adoption of new approaches, such as the use of IoT devices. This paper addresses the challenges and opportunities presented by the research, development, and implementation of these technologies in the industry. It also analyzes the investment in research and development made by companies in the sector in recent years and provides a review of current research and implementations related to Industry 4.0.

Yan Chen, Cheng Liu

Accurate prediction of Remaining Useful Life (RUL) for complex industrial machinery is critical for the reliability and maintenance of mechatronic systems, but it is challenged by high-dimensional, noisy sensor data. We propose the Causal-Informed Data Pruning Framework (CIDPF), which pioneers the use of causal inference to identify sensor signals with robust causal relationships to RUL through PCMCI-based stability analysis, while a Gaussian Mixture Model (GMM) screens for anomalies. By training on only 10% of the pruned data, CIDPF fine-tunes pre-trained Large Language Models (LLMs) using parameter-efficient strategies, reducing training time by 90% compared to traditional approaches. Experiments on the N-CMAPSS dataset demonstrate that CIDPF achieves a 26% lower RMSE than existing methods and a 25% improvement over full-data baselines, showcasing superior accuracy and computational efficiency in industrial mechatronic systems. The framework's adaptability to multi-condition scenarios further underscores its practicality for industrial deployment.

Georg Rottenwalter, Marcel Tilly, Victor Owolabi

Machine learning is an essential tool for optimizing industrial quality control processes. However, the complexity of machine learning models often limits their practical applicability due to a lack of interpretability. Additionally, many industrial machines lack comprehensive sensor technology, making data acquisition incomplete and challenging. Explainable Artificial Intelligence offers a solution by providing insights into model decision-making and identifying the most relevant features for classification. In this paper, we investigate the impact of feature reduction using XAI techniques on the quality classification of injection-molded parts. We apply SHAP, Grad-CAM, and LIME to analyze feature importance in a Long Short-Term Memory model trained on real production data. By reducing the original 19 input features to 9 and 6, we evaluate the trade-off between model accuracy, inference speed, and interpretability. Our results show that reducing features can improve generalization while maintaining high classification performance, with an small increase in inference speed. This approach enhances the feasibility of AI-driven quality control, particularly for industrial settings with limited sensor capabilities, and paves the way for more efficient and interpretable machine learning applications in manufacturing.

Rizki Rahmawati, Mila Tejamaya

Introduction:In water treatment plants (WTP), chemicals play a crucial role. However, some of these chemicals are hazardous. This study aims to conduct a dermal risk assessment in the WTP of an ammonia and urea production facility. Methods: The study was performed in August 2023 and assessed dermal exposure risk for four hazardous chemicals: NaOCl (30%), HCl (60%), H2SO4 (98%), and NaOH (48%), utilizing the Tier 2 RISKOFDERM model. Intrinsic toxicity was evaluated using risk phrases and toxicity information. Potential dermal exposure rates (PERBODY and PERHANDS) were determined based on task group and exposure modifier, while actual dermal exposure rates (AERBODY and AERHANDS) were determined based on clothing type and activity time. Health risk was assessed using actual exposure scores and intrinsic toxicity levels, which were categorized into 10 different levels ranging from 1 to 10. Results: The risk phrases indicated that four chemicals possessed a high level of intrinsic toxicity in terms of local effect but no systemic effect. PERBODY and PERHANDS were high (NaOCl, HCl) and low (H2SO4, NaOH). The actual exposure scores were determined to be 1 (high) for NaOCl and HCI, 0.01 (low) for H2SO4, and 0.03 (medium) for NaOH. Health risk values were 8 for NaOCl and HCI, 5 for H2SO4, and 6 for NaOH. Conclusion: Health risks in NaOCl and HCl were assigned action priority (AP) 1, followed by NaOH at AP-2, and H2SO4 at AP-3. The study recommends the implementation of control measures encompassing engineering solutions, administration, and personal protective equipment.

Diego Vallarino

This paper examines the impact of fiscal incentives on industrial investment in Uruguay from 1974 to 2010. Using a mixed-method approach that combines econometric models with machine learning techniques, the study investigates both the short-term and long-term effects of fiscal benefits on industrial investment. The results confirm the significant role of fiscal incentives in driving long-term industrial growth, while also highlighting the importance of a stable macroeconomic environment, public investment, and access to credit. Machine learning models provide additional insights into nonlinear interactions between fiscal benefits and other macroeconomic factors, such as exchange rates, emphasizing the need for tailored fiscal policies. The findings have important policy implications, suggesting that fiscal incentives, when combined with broader economic reforms, can effectively promote industrial development in emerging economies.

Christoforos Vasilatos, Dunia J. Mahboobeh, Hithem Lamri et al.

Industrial Control Systems (ICS) are extensively used in critical infrastructures ensuring efficient, reliable, and continuous operations. However, their increasing connectivity and addition of advanced features make them vulnerable to cyber threats, potentially leading to severe disruptions in essential services. In this context, honeypots play a vital role by acting as decoy targets within ICS networks, or on the Internet, helping to detect, log, analyze, and develop mitigations for ICS-specific cyber threats. Deploying ICS honeypots, however, is challenging due to the necessity of accurately replicating industrial protocols and device characteristics, a crucial requirement for effectively mimicking the unique operational behavior of different industrial systems. Moreover, this challenge is compounded by the significant manual effort required in also mimicking the control logic the PLC would execute, in order to capture attacker traffic aiming to disrupt critical infrastructure operations. In this paper, we propose LLMPot, a novel approach for designing honeypots in ICS networks harnessing the potency of Large Language Models (LLMs). LLMPot aims to automate and optimize the creation of realistic honeypots with vendor-agnostic configurations, and for any control logic, aiming to eliminate the manual effort and specialized knowledge traditionally required in this domain. We conducted extensive experiments focusing on a wide array of parameters, demonstrating that our LLM-based approach can effectively create honeypot devices implementing different industrial protocols and diverse control logic.

Lei Ren, Haiteng Wang, Yuanjun Laili

Industrial Multivariate Time Series (MTS) is a critical view of the industrial field for people to understand the state of machines. However, due to data collection difficulty and privacy concerns, available data for building industrial intelligence and industrial large models is far from sufficient. Therefore, industrial time series data generation is of great importance. Existing research usually applies Generative Adversarial Networks (GANs) to generate MTS. However, GANs suffer from unstable training process due to the joint training of the generator and discriminator. This paper proposes a temporal-augmented conditional adaptive diffusion model, termed Diff-MTS, for MTS generation. It aims to better handle the complex temporal dependencies and dynamics of MTS data. Specifically, a conditional Adaptive Maximum-Mean Discrepancy (Ada-MMD) method has been proposed for the controlled generation of MTS, which does not require a classifier to control the generation. It improves the condition consistency of the diffusion model. Moreover, a Temporal Decomposition Reconstruction UNet (TDR-UNet) is established to capture complex temporal patterns and further improve the quality of the synthetic time series. Comprehensive experiments on the C-MAPSS and FEMTO datasets demonstrate that the proposed Diff-MTS performs substantially better in terms of diversity, fidelity, and utility compared with GAN-based methods. These results show that Diff-MTS facilitates the generation of industrial data, contributing to intelligent maintenance and the construction of industrial large models.

Quentin Raillard-Cazanove, Thibaut Knibiehly, Robin Girard

The decarbonisation of the energy system is crucial for achieving climate goals and is inherently linked to the decarbonisation of industry. Despite this, few studies explore the simultaneous impacts of decarbonising both sectors. This paper aims to examine how industrial decarbonisation in Europe affects the energy system and vice versa. To address this, an industry model incorporating key heavy industry sectors across six European countries is combined with an energy system model for electricity and hydrogen covering fifteen European regions, refered to as the EU-15, divided into eleven zones. The study evaluates various policy scenarios under different conditions.The results demonstrate that industrial decarbonisation leads to a significant increase in electricity and hydrogen demand. This additional demand for electricity is largely met through renewable energy sources, while hydrogen supply is predominantly addressed by blue hydrogen production when fossil fuels are authorized and the system lacks renewable energy. This increased demand results in higher prices with considerable regional disparities. Furthermore, the findings reveal that, regardless of the scenario, the electricity mix in the EU-15 remains predominantly renewable, exceeding 85%.A reduction in carbon taxes lowers the prices of electricity and hydrogen, but does not increase consumption, as the lower carbon tax makes the continued use of fossil fuels more attractive to industry. In scenarios that enforce a phase-out of fossil fuels, electricity prices rise, leading to a greater reliance on imports of low-carbon hydrogen and methanol. Results also suggest that domestic hydrogen production benefits from synergies between electrolytic hydrogen and blue hydrogen, helping to maintain competitive prices.

Chao Min, Guoquan Wen, Jiangru Yuan et al.

Industrial time-series, as a structural data responds to production process information, can be utilized to perform data-driven decision-making for effective monitoring of industrial production process. However, there are some challenges for time-series forecasting in industry, e.g., predicting few-shot caused by data shortage, and decision-confusing caused by unknown treatment policy. To cope with the problems, we propose a novel causal domain adaptation framework, Causal Domain Adaptation (CDA) forecaster to improve the performance on the interested domain with limited data (target). Firstly, we analyze the causality existing along with treatments, and thus ensure the shared causality over time. Subsequently, we propose an answer-based attention mechanism to achieve domain-invariant representation by the shared causality in both domains. Then, a novel domain-adaptation is built to model treatments and outcomes jointly training on source and target domain. The main insights are that our designed answer-based attention mechanism allows the target domain to leverage the existed causality in source time-series even with different treatments, and our forecaster can predict the counterfactual outcome of industrial time-series, meaning a guidance in production process. Compared with commonly baselines, our method on real-world and synthetic oilfield datasets demonstrates the effectiveness in across-domain prediction and the practicality in guiding production process

Nao Takeuchi-Storm, Lisbeth Truelstrup Hansen, Niels Ladefoged Nielsen et al.

<i>Listeria monocytogenes</i> is an ubiquitously occurring foodborne bacterial pathogen known to contaminate foods during the production processes. To assess the presence and persistence of <i>L. monocytogenes</i> in Danish ready-to-eat (RTE) food production companies in response to a Listeria awareness campaign, the production environment of selected companies were sampled in 2016 and in 2020. Whole genome sequencing (WGS) was performed to characterize the isolates (<i>n</i> = 50, plus 35 isolates obtained from the routine surveillance during 2016–2020), including investigation of the presence of virulence, persistence and resistance genes. The number of companies that tested positive by culture was 17/39 (43.6%) in 2016 and 11/34 (32.4%) in 2020, indicating a limited effect of the campaign. WGS analyses of the 85 isolates showed that the most common sequence types (STs) were ST8 and ST121. The single nucleotide polymorphism (SNP) analysis showed that isolates coming from the same company and belonging to the same ST exhibited <10 SNP differences regardless of the sampling year and whether the samples came from the environment or products, indicating the persistence of the specific STs. Several prevalent STs were found in clinical cases concurrently, including genetically similar isolates. This highlights the issue of persistent <i>L. monocytogenes</i> in the food production environment and the need for improved risk communication and mitigation strategies.

Gurjot Singh Bhatia, Yoann Corre, Marco Di Renzo

This paper presents an innovative method that can be used to produce deterministic channel models for 5G industrial internet-of-things (IIoT) scenarios. Ray-tracing (RT) channel emulation can capture many of the specific properties of a propagation scenario, which is incredibly beneficial when facing various industrial environments and deployment setups. But the environment's complexity, composed of many metallic objects of different sizes and shapes, pushes the RT tool to its limits. In particular, the scattering or diffusion phenomena can bring significant components. Thus, in this article, the Volcano RT channel simulation is tuned and benchmarked against field measurements found in the literature at two frequencies relevant to 5G industrial networks: 3.7 GHz (mid-band) and 28 GHz (millimeter-wave (mmWave) band), to produce calibrated ray-based channel model. Both specular and diffuse scattering contributions are calculated. Finally, the tuned RT data is compared to measured large-scale parameters, such as the power delay profile (PDP), the cumulative distribution function (CDF) of delay spreads (DSs), both in line-of-sight (LoS) and non-LoS (NLoS) situations and relevant IIoT channel properties are further explored.

Yunpeng Ma, Khalil Younis, Bestoun S. Ahmed et al.

Digital twins (DT) of industrial processes have become increasingly important. They aim to digitally represent the physical world to help evaluate, optimize, and predict physical processes and behaviors. Therefore, DT is a vital tool to improve production automation through digitalization and becomes more sophisticated due to rapidly evolving simulation and modeling capabilities, integration of IoT sensors with DT, and high-capacity cloud/edge computing infrastructure. However, the fidelity and reliability of DT software are essential to represent the physical world. This paper shows an automated and systematic test architecture for DT that correlates DT states with real-time sensor data from a production line in the forging industry. Our evaluation shows that the architecture can significantly accelerate the automatic DT testing process and improve its reliability. A systematic online DT testing method can significantly detect the performance shift and continuously improve the DT's fidelity. The snapshot creation methodology and testing agent architecture can be an inspiration and can be generally applicable to other industrial processes that use DT to generalize their automated testing.

Jérôme Rutinowski, Hazem Youssef, Sven Franke et al.

This contribution presents the TOMIE framework (Tracking Of Multiple Industrial Entities), a framework for the continuous tracking of industrial entities (e.g., pallets, crates, barrels) over a network of, in this example, six RGB cameras. This framework, makes use of multiple sensors, data pipelines and data annotation procedures, and is described in detail in this contribution. With the vision of a fully automated tracking system for industrial entities in mind, it enables researchers to efficiently capture high quality data in an industrial setting. Using this framework, an image dataset, the TOMIE dataset, is created, which at the same time is used to gauge the framework's validity. This dataset contains annotation files for 112,860 frames and 640,936 entity instances that are captured from a set of six cameras that perceive a large indoor space. This dataset out-scales comparable datasets by a factor of four and is made up of scenarios, drawn from industrial applications from the sector of warehousing. Three tracking algorithms, namely ByteTrack, Bot-Sort and SiamMOT are applied to this dataset, serving as a proof-of-concept and providing tracking results that are comparable to the state of the art.

Ivan Kraljevski, Yong Chul Ju, Dmitrij Ivanov et al.

Artificial intelligence experienced a technological breakthrough in science, industry, and everyday life in the recent few decades. The advancements can be credited to the ever-increasing availability and miniaturization of computational resources that resulted in exponential data growth. However, because of the insufficient amount of data in some cases, employing machine learning in solving complex tasks is not straightforward or even possible. As a result, machine learning with small data experiences rising importance in data science and application in several fields. The authors focus on interpreting the general term of "small data" and their engineering and industrial application role. They give a brief overview of the most important industrial applications of machine learning and small data. Small data is defined in terms of various characteristics compared to big data, and a machine learning formalism was introduced. Five critical challenges of machine learning with small data in industrial applications are presented: unlabeled data, imbalanced data, missing data, insufficient data, and rare events. Based on those definitions, an overview of the considerations in domain representation and data acquisition is given along with a taxonomy of machine learning approaches in the context of small data.