Accurate smoke detection in complex industrial environments, such as chemical plants, remains a significant challenge due to the inherently low contrast, transparency, and weak texture features of smoke, which often exhibits blurred boundaries and diverse spatial scales. To address these limitations, YOLOv8n-AM, an enhanced lightweight detection framework belonging to the YOLO (You Only Look Once) series, was developed by integrating advanced architectural components into the baseline YOLOv8n model. Specifically, the conventional Spatial Pyramid Pooling-Fast (SPPF) module was replaced with an Attention-based Intra-scale Feature Interaction (AIFI) Convolution Synergistic Feature Processing Module (SFPM), i.e., AIFC-SFPM, enabling more effective semantic feature representation and an improvement in detection accuracy. In parallel, the original convolutional module was optimized using a Multi-Scale Downsampling (MSDown) module, which reduces model redundancy and computational overhead, increasing the detection speed. Experimental evaluations demonstrate that the YOLOv8n-AM model achieves a 1.7% improvement in mean Average Precision (mAP), accompanied by a 9.1% reduction in Giga Floating-point Operations Per Second (GFLOPs) and a 15.4% decrease in parameter count when compared to the original YOLOv8n framework. These improvements collectively underscore the model’s suitability for real-time deployment in resource-constrained industrial settings where rapid and reliable smoke detection is critical. The proposed architecture thus provides a computationally efficient and high-precision solution for safety-critical visual monitoring applications.

Click fraud is a deceptive malicious strategy that relies on repetitive mimicking of human clicking on online advertisements, without actual intention to complete a purchase. This fraud can result in significant financial loses for both advertising companies and marketers, and at the same time destroying their public images. Nevertheless, detection of these illegitimate clicks is very challenging as they closely resemble to authentic human engagement. This study examines the utilization of artificial intelligence approaches to detect deceptive clicks, by identifying subtle correlations between the timing of the clicks, taking into account their geographical or network sources and linked application sources as indicators to separate legitimate from malicious activity. This study highlights the application of recurrent neural networks (RNNs) for this task, keeping in mind that the process of selection and tuning of the model's hyperparameters plays a vital role in the performance. An adapted implementation of crayfish optimization algorithm (COA) was consequently proposed in this paper, and used to optimize RNN models to enhance their general performance. The developed framework was evaluated utilizing actual operational datasets and yielded encouraging outcomes.

The internal translucent color light box serves as both a display and behavioral guidance tool in exhibitions. However, its functionality can be compromised by variations in light intensity, temperature, humidity, bolt fastening integrity, and door lock status. Conventional Internet of Things (IoT)-based systems, while effective, often involve the installation of expensive sensors, control units, and network infrastructure within each light box. Given the large number of light boxes typically used in exhibitions, the high cost and slow response time of such systems remain significant limitations. This study proposes a novel approach utilizing a Peripheral Component Interconnect (PCI) bus structure to form a network of interconnected light boxes. By sequentially collecting voltage and current data from photosensitive resistors across adjacent groups of four light boxes, faults can be rapidly identified through a hierarchical comparison method. This method enables precise fault localization with minimal cost and at significantly reduced time. Simulations and physical prototypes were developed using Multisim to model the changes in light intensity during the fault detection process. Experimental results demonstrate the system's ability to accurately pinpoint malfunctioning light boxes when light levels fall below 1000 lx. The detection accuracy reaches 100% under these conditions. Notably, the proposed system requires no complex control processing, and offers an over 90% reduction in detection time and cost compared to traditional manual inspections and IoT-based fault detection systems. This approach presents a highly cost-effective and efficient solution for exhibition light box fault localization, facilitating maintenance by enabling visual identification of malfunctioning units.

This study investigates the optimization of wrench time to improve maintenance efficiency and reliability within a chemical processing plant. Wrench time, defined as the proportion of time spent directly performing maintenance tasks, was quantified through random observations of maintenance technicians. The findings revealed an average wrench time of 28% across the site, with variations between individual crew groups ranging from 20% to 35% and craft-specific wrench times varying from 13.3% to 45.5%. Several inefficiencies were identified, including prolonged wait times for equipment isolation, safety clearance, job planning, and parts procurement. Key contributing factors to these inefficiencies were found to include poor coordination between maintenance and production, insufficient work prioritization, inadequate adherence to schedules, a high volume of emergency tasks, and the absence of essential tools such as bills of materials (BOMs), equipment data, and troubleshooting checklists. To address these challenges, a range of improvement initiatives were implemented. These included enhancing coordination between maintenance and production by refining process steps, introducing additional planning tools for effective work prioritization, providing job aids, developing generic troubleshooting checklists, leveraging Industrial Internet of Things (IIoT) technologies, and establishing metrics to monitor progress. Early indications suggest that these initiatives have led to a reduction in maintenance backlog and gradual improvements in overall equipment effectiveness (OEE). It is anticipated that these changes will result in increased wrench time, enhanced maintenance quality and reliability, reduced downtime, and lower operational costs. For maintenance managers and engineers, the findings offer actionable insights into optimizing workflows and resource allocation, thereby contributing to the improvement of operational efficiency and reliability.

This study evaluates the potential of nitrogen and hydrogen as alternative working fluids in air conditioning systems to improve thermal comfort and optimize energy efficiency, using computational fluid dynamics (CFD) simulations. A controlled indoor environment measuring 6 m $\times$ 4.5 m $\times$ 3 m was simulated, with nitrogen and hydrogen tested at inlet velocities of 0.7 m/s, 0.8 m/s, 0.9 m/s, 1.0 m/s, and 1.1 m/s, and an inlet temperature fixed at 293 K (20℃). The analysis focused on the impact of these gases on room and outlet temperatures to assess airflow distribution, heat transfer, and thermal comfort compared to traditional air-based systems. Results indicated that nitrogen improved airflow uniformity and facilitated heat transfer but exhibited limitations in effectively reducing room temperature due to its thermal properties. In contrast, hydrogen demonstrated stable outlet temperatures across all velocities, benefiting from its higher thermal conductivity; however, room temperatures showed significant variation, particularly at higher inlet velocities. Temperature prediction errors in the CFD model ranged from 0.003% to 2.78%, suggesting high accuracy yet underscoring the need for refinement in simulation methods. The findings highlight the promise of nitrogen and hydrogen in optimizing air conditioning system performance but emphasize the necessity for further investigation into the practical implications, specifically regarding operational safety, energy efficiency, and environmental impacts.