Safety Accidents Research Articles

Lightweight Safety Activity Recognition Algorithm for Railway Field Personnel Based on Portable Cards

In recent years, railway construction has been plagued by frequent safety accidents, with workers’ safety during the construction process remaining a major concern. To mitigate this issue, intelligent monitoring of railway workers’ activity has been proposed as a means of improving the safety coefficient of construction. Human activity recognition (HAR) based on wearable devices holds significant application value in areas such as health monitoring, motion analysis, and intelligent assistance. Recently, convolutional neural networks (CNNs) have gained extensive adoption and demonstrated outstanding performance in HAR. However, current HAR research still faces some challenges, including problems with establishing spatial–temporal dependencies and addressing the demand for lightweight models. To address the above issues, we propose a lightweight dual-stream convolution model (LDSC) based on deformable convolution and hierarchical segmentation. The model adaptively captures significant variations in sensor readings over time from portable cards of railway personnel through a temporal stream and learns the interactive information among sensor channels over a spatial stream. LDSC consists of three lightweight convolutional modules that combine deep convolution and point convolution to reduce model parameters, thus meeting the demand for a lightweight model. Experiments and ablation studies are conducted on three available datasets (UCI-HAR, UniMiB-SHAR, and WISDM) to evaluate the proposed model. The experimental results indicate that our model outperforms existing state-of-the-art methods in terms of recognition accuracy, validating the effectiveness and feasibility of LDSC. In addition, theoretical analysis and ablation experiments demonstrate that the proposed LDSC embodies lightweight characteristics.

Study on erosion and residual strength of tee in high pressure manifold

ABSTRACT The complex fluid and solid particles inside the throttled pressure well manifold will cause a certain degree of erosion and wear on the inner wall, which will accumulate to form erosion defects and make the wall thickness thin, which may eventually lead to the failure of the tee due to irreversible damage, triggering serious safety accidents. In order to avoid the occurrence of such safety accidents, in-service training must be non-destructive testing to ensure the safe operation of the manifold. Therefore, for the tee of the throttle manifold, an erosion simulation model was established to carry out the study on the erosion and wear law of the tee with different displacements and sand ratios and analyze the erosion parts of the tee under different working conditions; and based on the erosion-prone parts of the tee, a residual strength simulation model of the tee with defects was established to carry out the influence of the depth of the defects and the internal pressure on the residual strength of the tee. The analyzed results can provide a theoretical basis for the nondestructive testing location and replacement timing of the tee.

IMU Sensor-Based Worker Behavior Recognition and Construction of a Cyber-Physical System Environment.

According to South Korea's Ministry of Employment and Labor, approximately 25,000 construction workers suffered from various injuries between 2015 and 2019. Additionally, about 500 fatalities occur annually, and multiple studies are being conducted to prevent these accidents and quickly identify their occurrence to secure the golden time for the injured. Recently, AI-based video analysis systems for detecting safety accidents have been introduced. However, these systems are limited to areas where CCTV is installed, and in locations like construction sites, numerous blind spots exist due to the limitations of CCTV coverage. To address this issue, there is active research on the use of MEMS (micro-electromechanical systems) sensors to detect abnormal conditions in workers. In particular, methods such as using accelerometers and gyroscopes within MEMS sensors to acquire data based on workers' angles, utilizing three-axis accelerometers and barometric pressure sensors to improve the accuracy of fall detection systems, and measuring the wearer's gait using the x-, y-, and z-axis data from accelerometers and gyroscopes are being studied. However, most methods involve use of MEMS sensors embedded in smartphones, typically attaching the sensors to one or two specific body parts. Therefore, in this study, we developed a novel miniaturized IMU (inertial measurement unit) sensor that can be simultaneously attached to multiple body parts of construction workers (head, body, hands, and legs). The sensor integrates accelerometers, gyroscopes, and barometric pressure sensors to measure various worker movements in real time (e.g., walking, jumping, standing, and working at heights). Additionally, incorporating PPG (photoplethysmography), body temperature, and acoustic sensors, enables the comprehensive observation of both physiological signals and environmental changes. The collected sensor data are preprocessed using Kalman and extended Kalman filters, among others, and an algorithm was proposed to evaluate workers' safety status and update health-related data in real time. Experimental results demonstrated that the proposed IMU sensor can classify work activities with over 90% accuracy even at a low sampling rate of 15 Hz. Furthermore, by integrating internal filtering, communication modules, and server connectivity within an application, we established a cyber-physical system (CPS), enabling real-time monitoring and immediate alert transmission to safety managers. Through this approach, we verified improved performance in terms of miniaturization, measurement accuracy, and server integration compared to existing commercial sensors.

Modeling and Evaluation of Attention Mechanism Neural Network Based on Industrial Time Series Data

Chemical process control systems are complex, and modeling the controlled object is the first task in automatic control and optimal design. Most chemical process modeling experiments require test signals to be applied to the process, which may lead to production interruptions or cause safety accidents. Therefore, this paper proposes an improved transformer model based on a self-attention mechanism for modeling industrial processes. Then, an evaluation mechanism based on root mean square error (RMSE) and Kullback–Leibler divergence (KLD) metrics is designed to obtain more appropriate model parameters. The Variational Auto-Encoder (VAE) network is used to compute the associated KLD. Finally, a real nonlinear dynamic process in the petrochemical industry is modeled and evaluated using the proposed methodology to predict the time series data of the process. This study demonstrates the validity of the proposed transformer model and illustrates the versatility of using an integrated modeling, evaluation, and prediction scheme for nonlinear dynamic processes in process industries. The scheme is of great importance for the field of industrial soft measurements as well as for deep learning-based time series prediction. In addition, the issue of a suitable time domain for the prediction is discussed.

Mechanism and Control Strategies of Lithium-Ion Battery Safety: A Review.

Lithium-ion batteries (LIBs) are extensively used everywhere today due to their prominent advantages. However, the safety issues of LIBs such as fire and explosion have been a serious concern. It is important to focus on the root causes of safety accidents in LIBs and the mechanisms of their development. This will enable the reasonable control of battery risk factors and the minimization of the probability of safety accidents. Especially, the chemical crosstalk between two electrodes and the internal short circuit (ISC) generated by various triggers are the main reasons for the abnormal rise in temperature, which eventually leads to thermal runaway (TR) and safety accidents. Herein, this review paper concentrates on the advances of the mechanism of TR in two main paths: chemical crosstalk and ISC. It analyses the origin of each type of path, illustrates the evolution of TR, and then outlines the progress of safety control strategies in recent years. Moreover, the review offers a forward-looking perspective on the evolution of safety technologies. This work aims to enhance the battery community's comprehension of TR behavior in LIBs by categorizing and examining the pathways induced by TR. This work will contribute to the effective reduction of safety accidents of LIBs.

Machine vision model for drip leakage detection of pipeline.

The prevailing trend in industrial equipment development is integration, with pipelines as the lifeline connecting system components. Given the often harsh conditions of these industrial equipment pipelines, leakage is a common occurrence that can disrupt normal operations and, in severe cases, lead to safety accidents. Early detection of even minor drips at the onset of leakage can enable timely maintenance measures, preventing more significant leaks and halting the escalation of pipeline failures. In light of this, our study investigates a method for monitoring pipe drips in industrial equipment using machine vision technology. We propose a machine vision model specifically designed for pipe drip detection, aiming to facilitate monitoring of pipe system drips. The system designed to collect the image of the droplet side cross-section with a Charge charge-coupled device (CCD) industrial camera, is aided by the computer image processing system used to analyze and process the collected images. Image enhancement technology is applied to improve the visibility of the image and image filtering technology is applied to remove the noise of the image. With the help of image segmentation technology, target droplet identification and division are achieved. Morphological reconstruction and region-filling techniques are used to remove the noise caused by shooting in the side cross-section image, such as hollow, reflection, and irregular droplet edge, to upgrade the quality of the solution droplet edge. The mathematical model is established for boundary position points extracted from the droplet side cross-section image. Then, the fitting droplet image is drawn. The droplet volume is obtained by calculating the volume of the rotating body. The two-dimensional image of the target droplet is obtained dynamically through the camera capture technology. The droplet boundary extraction algorithm is proposed, and the three-dimensional model of the target droplet is established, so the volume calculation problem of the droplet is solved, which provides a way of thinking for drip leakage detection of the pipeline.

Occupational Health and Safety in Beekeeping: An Analysis of Bayburt and the Upper Çoruh Valley

Beekeeping is an agricultural activity closely intertwined with nature and involves various occupational risk factors. This study examines stationary and migratory beekeepers' occupational health and safety risks in the Bayburt and Upper Çoruh Valley regions. The research evaluates the chemical, physical, biological, and ergonomic risks beekeepers face and analyses their potential adverse effects on beekeepers’ health and public health. It is noted that the use of antibiotics and pesticides poses a risk of residue in honey, potentially affecting the food chain and leading to occupational diseases. Using the Fine-Kinney risk analysis method, evaluations were conducted in 13 apiaries, identifying 17 risks: 5 ergonomic, 4 physical, 6 chemical, and 2 biological. Among these risks, heavy lifting and repetitive movements were prominent in terms of ergonomic risks, pesticide and antibiotic use in terms of chemical risks, apiary site safety and traffic accidents in terms of physical risks, and bee stings and wild animal attacks in terms of biological risks. The study emphasises the need to enhance occupational health and safety measures in the beekeeping sector and to adopt more modern production methods.

The Effect of Cycling Participants’Awareness of Safety Accidents on their Ability to respond to First Aid: Focusing on Recreational Athletes and Hobbyists

The Effect of Cycling Participants’Awareness of Safety Accidents on their Ability to respond to First Aid: Focusing on Recreational Athletes and Hobbyists

요양병원간호사가 경험한 환자안전사고, 환자안전문화 및 안전간호활동에 대한 연구

This study aimed to analyze patient safety accidents experienced by nurses in long-term care hospitals, and to understand the relationships between these accidents, patient safety culture, and safety nursing activities. A survey was conducted from November 1 to November 30, 2023, involving 234 nurses who had been engaged in nursing duties for more than 6 months at five different long-term care hospitals. The collected data were analyzed using SPSS 29.0 software, employing the chi-square, the t-test, ANOVA, and the Pearson correlation test. The results revealed that 73.5% of participants had experienced a patient safety accident in the past year, with 3.5% of these accidents remaining unreported. The most frequently encountered accident was falls, predominantly occurring in inpatient wards. The accident stage most commonly identified was near misses, and the most common post-accident response was intensive monitoring. Nurses with more experience in terms of age, nursing career, and tenure in long-term care facilities, as well as those involved in accreditation evaluations, reported a higher incidence of patient safety accidents. Nurses with access to patient safety guidelines had higher scores for patient safety culture and safety nursing activities, and those who completed patient safety training had higher scores for patient safety culture. However, no significant relationship was found between the experience of patient safety accidents and both patient safety culture and safety nursing activities. Based on these findings, it is recommended to implement differentiated patient safety training according to nursing experience and to utilize guidelines based on patient safety regulations.

유전자 편집 생물체(Genome-Edited Products)의 규제체계의 개선과 정책수렴에 관한 연구: 국제기준 조화의 정책적 접근

This study examines the policy approach to improve the regulatory system of Korea for genetically edited organisms and foods using new technologies and to harmonize international standards. To this end, the policy approach was discussed focusing on the regulatory measures of GMOs based on the regulatory systems of major countries and the policy convergence theory. The analysis results showed that there could be significant differences when applying ex post facto regulations such as GMO labeling, traceability, crop registration, and license renewal. In particular, the regulatory system for genetically modified foods and foods using new technologies is inadequate due to intermittent food safety accidents in the food safety regulatory science field in Korea. In addition, it was confirmed that domestic regulations are not consistent with international standards and are facing problems such as trade barriers. As a result, important policy implications were derived for improving the regulatory system of Korea for genetically edited organisms and foods using new technologies, including restoring and increasing consumer trust, reorganizing the regulatory system and ensuring consistency with international standards, fostering experts in the field of regulatory science, and strengthening research capacity.

Formation and Prevention of Natural Gas Hydrates

Natural gas hydrate is formed under certain temperatures and pressures, which makes it an unavailable clean energy source. However, in industrial production, clogging occurring due to hydrate generation can cause a series of safety accidents and economic losses. In order to solve the hazards of natural gas hydrates in drilling, this paper reviews the formation conditions of natural gas hydrates and the prevention and control measures. In order to inhibit the formation of hydrates, the use of traditional well control measures and the addition of thermodynamic inhibitors have high costs, large dosages, an unfriendly environment, etc. The new type of kinetic inhibitor has a strong effect and low dosage and is considered to be the most promising chemical treatment for hydrate prevention and control in the industry. However, kinetic inhibitors are greatly affected by environmental factors, and compounding them with thermodynamic inhibitors and their synergistic effect can greatly reduce the dosage of thermodynamic inhibitors and improve inhibition performance. It is an important direction for laboratory research and has shown good results in field applications.

Improved Entropy-Based Condition Monitoring for Pressure Pipeline Through Acoustic Denoising.

During long-term operation in complex environments, the pressure pipeline systems are prone to damage and faults, and serious safety accidents may occur without real-time condition monitoring. Moreover, in traditional non-contact monitoring approaches, acoustic signals are widely employed for condition monitoring for pressure pipelines, which are easily contaminated by background noise and provide unsatisfactory accuracy. As a tool for quantifying uncertainty and complexity, signal entropy is applied to detect abnormal conditions. Based on the characteristics of entropy and acoustic signals, an improved entropy-based condition monitoring method is proposed for pressure pipelines through acoustic denoising. Specifically, this improved entropy-based noise reduction model is proposed to reduce the noise of monitoring acoustic signals through adversarial training. Based on the denoising of acoustic signals, an abnormal sound detection method is proposed to realize condition monitoring for pressure pipelines. In addition, the experimental platform is built to test the effectiveness and reliability of the proposed method. The results indicate that the quality of signal denoising can reach over 3 dB, while the accuracy of condition monitoring is about 92% for different conditions. Finally, the superiority of the proposed method is verified by comparing it with other methods.

Lightweight Research on Fatigue Driving Face Detection Based on YOLOv8

Introduction: With the rapid development of society, motor vehicles have become one of the main means of transportation. However, as the number of motor vehicles continues to increase, traffic safety accidents also continue to appear, bringing serious threats to people's lives, and property safety. Fatigue driving is one of the important causes of traffic safety accidents. Method: To address this problem, a target detection algorithm called VA-YOLO is designed to improve the speed and accuracy of facial recognition for fatigue checking. The algorithm employs a lightweight backbone network, VanillaNet, instead of the traditional backbone network, which reduces the computational and parametric quantities of the model. The SE attention mechanism is also introduced to enhance the model's attention to the target features, which further improves the accuracy of target detection. Finally, in terms of the bounding box regression loss function, the SIoU loss function is used to reduce the error. Result: The experimental results show that, compared toYolov8n, the VA-YOLO algorithm improves the accuracy by 1.3% while the number of parameters decreases by 30%. Conclusion: This shows that the VA-YOLO algorithm has a significant advantage in realizing the balance between the number of parameters and accuracy, which is important for improving the speed and accuracy of fatigue driving detection.

Rapid diagnosis of power battery faults in new energy vehicles based on improved boosting algorithm and big data

In recent years, the new energy vehicle industry has developed rapidly. A fast diagnostic method based on Boosting and big data is proposed to address the low accuracy and efficiency of fault diagnosis in new energy vehicle power batteries. Boosting is a machine learning technique that combines multiple weak learners into a strong learner. Big data refers to large-scale, complex datasets that exceed traditional data processing capabilities. Firstly, analyze and preprocess the big data uploaded by the battery. Subsequently, the importance of indicators in the data was analyzed using the Random Forest algorithm (RF). Finally, three improved Boosting algorithms were proposed, namely Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting Tree (XGBoost), and Gradient Boosting Decision Tree (CatBoost). The experimental results indicate that the LightGBM model effectively detects anomalies in battery big data. The accuracy values of XGBoost, CatBoost, and LightGBM are 97.84%, 98.57%, and 99.16%, respectively. The recall rates of XGBoost, CatBoost, and LightGBM models are all 1. The F1 values of GBoost, CatBoost, and LightGBM are 0.873, 0.983, and 0.985, respectively. The power battery is the core component of new energy vehicles, and its safety performance directly affects the operational safety of the vehicle. Timely identification and diagnosis of battery faults can effectively reduce potential accidents such as battery overheating and short circuits. Research can achieve real-time monitoring and timely reminders of potential faults. By early detection of issues such as battery overheating and voltage imbalance, this method can effectively reduce the risk of serious safety accidents and improve the overall operational reliability of new energy vehicles during driving.

Scalable Hierarchical‐Colored Passive Cooling Metapaint for Outdoor Facility

ABSTRACTThe temperature of metal‐based facilities rises significantly under high outdoor solar irradiation, leading to serious safety accidents. The application of active cooling technology poses challenges due to its high energy consumption, especially in complex outdoor environments. Passive cooling devices with high solar reflection and thermal emission can continuously cool objects under sunlight. However, the white or silvery passive cooling devices do not meet the need for aesthetics and specific demands. Here, we present a hierarchical metapaint for outdoor facilities that simultaneously achieve vibrant color and passive cooling ability. The top layer selectively absorbs visible wavelengths to display desired colors, while the underlayer boosts the reflection of near‐to‐short wavelength infrared (NSWIR) light to prevent solar heating. The metapaint‐coated metal is resistant to high and low temperatures, acidic and alkaline environments, and simulated seawater. It also has satisfactory anti‐fouling properties. When compared to metal coated without commercial paint, the hierarchical passive cooling paint (metapaint) coated metal can cool up to 9.7°C and 17.1°C. The metapaint has excellent passive cooling performance, attributed to its broad‐spectrum selective regulation function. Our work offers a simple, inexpensive, and scalable approach to reduce cooling energy usage and promote a low‐carbon lifestyle. image

An evaluation method for electromagnetic compatibility risks caused by the intelligent transformation of oil and gas field stations

Abstract With the development of the intelligentization of the petroleum and chemical industry, the application of wireless communication technology and a large number of communication devices in the construction of smart oil and gas fields may cause harmful interference to important electronic and electrical equipment within the oil and gas fields, leading to shutdowns or other serious safety accidents. This paper mainly studies the analysis and evaluation methods of electromagnetic safety risks that may arise after the deep integration of new generation information technology and oil and gas field engineering, so as to quickly analyse and locate the electromagnetic safety risks and risk levels that may arise in the process of building wireless communication networks in the oil and gas field areas. It provides guidance for the intelligent upgrade of oil and gas field projects and accelerates the construction of 5G communication networks in the petroleum and chemical industry.

How the Content of Interprofessional Safety Management Education Can Be Structured Through the Perception of Nursing Home Practitioners: A Mixed Methods Design.

This study aimed to assess perceptions of safety management, with a particular focus on interprofessional influences, to determine priorities for safety management training needs and to explore target areas for strengthening the capacity of nursing home practitioners. A mixed methods design was used. A qualitative-driven mixed methods design was employed in two phases. In Phase 1, as a core component for integrating supplementary components, an inductive content analysis was performed to investigate perceptions of safety management and specific aspects of care related to it through semi-structured interviews with nursing home practitioners. In Phase 2, a descriptive survey was conducted using items derived from the interviews conducted in the initial stage. The aim was to explore the educational needs of practitioners concerning safety management elements practised in nursing homes. In the study, through qualitative interviews, practitioners' perceptions of interprofessional safety management were derived into 5 themes and 22 subthemes. Based on this, the results of a descriptive survey derived priorities through a paired t-test, importance-performance analysis, Borich's needs assessment model and the Locus for Focus model for safety management items performed by nursing home practitioners. Results from both phases of the study showed that practitioners recognise the importance of sharing the causes of safety accidents and that there is a high need for training on falls, dehydration, and hypoglycaemia management. Nurses, care workers, physical therapists, and social workers employed in nursing homes took part in this study by participating in interviews and surveys.

Research on Arc Fault Detection Based on Conditional Batch Normalization Convolutional Neural Network with Cost-Sensitive Multi-Feature Extraction.

An arc fault is a potential hazard in power systems, capable of causing serious safety accidents such as fires. Therefore, the timely detection of arc faults and implementation of circuit-breaking measures are crucial for ensuring safety, preventing fires, and maintaining the stable operation of power systems. Although existing studies have made progress in improving the accuracy of their detection, most methods have not proposed effective solutions that address the cost-sensitive problem of feature selection. Thus, a multi-feature method is proposed by combining time-domain, frequency-domain, energy, and spatial features, which are integrated into a CBN (conditional batch normalization) convolutional neural network for detection. The experimental results show that the proposed method outperforms traditional models in terms of its accuracy and misjudgment rate while maintaining a lower computational cost, demonstrating its superior detection performance. This provides an effective improvement for arc fault detection.

Fault Diagnosis of Lithium-Ion Batteries Based on the Historical Trajectory of Remaining Discharge Capacity

In recent years, the number of safety accidents in new-energy electric vehicles due to lithium-ion battery failures has been increasing, and the lithium-ion battery fault diagnosis technology is particularly important to ensure the safe operation of electric vehicles. This paper proposes a method for lithium-ion battery fault diagnosis based on the historical trajectory of lithium-ion battery remaining discharge capacity in medium and long time scales. The method first utilizes the sparrow search algorithm (SSA) to identify the parameters of the second-order equivalent circuit model of the lithium-ion battery, and then estimates the state of charge (SOC) of the lithium-ion battery using the extended Kalman filter (EKF). The remaining discharge capacity is estimated according to the SOC, and finally the feature vectors are used to diagnose the faults using box plots on the medium and long time scales. Experimental results verify that the root mean squared error (RSME) and mean absolute error (MAE) of the proposed SOC estimation method are 0.0049 and 0.0034, respectively. This method can accurately identify the faulty single cell in a battery pack with low-capacity single cells and promptly detect any abnormalities in the single cell when a micro-short circuit fault occurs.

An integrated industrial risk assessment methodology for accident safety, chronic health, and chemical exposure

An integrated industrial risk assessment methodology for accident safety, chronic health, and chemical exposure