International Journal of Reliability and Safety (10 papers in press)

Regular Issues

• Pre-chamber spark ignition: a reliability analysis of pre-chamber valve functions  
  by Faraz Akbar, Sarah Zaki 
  Abstract: A pre-chamber ignition allows spark-ignition engines to operate in lean air-fuel settings. It improves fuel efficiency and reduces emissions. In this study, a reliability analysis of a single GE Jenbacher J620 natural gas engine was done. It was operational on continuous load in the power generation sector in Karachi, Pakistan. A bathtub curve of the GE J620 pre-chamber gas valve (PCV) was generated. The three-year industrial data comprised PCV failures that occurred between two overhauls. During infant mortality, the curve revealed 7 failures during 1000 hours. This decreased to a failure for the next two cycles of thousand hours each. There was a 40% decrease in reliability after 1500 hours. Exponential distribution revealed that the mean time-to-failure (MTTF) was 545.5 hours. This study was the first of its kind in the facility. Previously, much time was lost in breakdown maintenance. Thus, it helped to increase the systems reliability.
  Keywords: bathtub curve; exponential distribution; failure rate; fuel injection; gas engine; pre-chamber combustion; pre-chamber spark ignition; pre-chamber valve; probability density function; reliability.
  
  
• Seismic safety evaluation of dam using cloud model  
  by Alabhya Sharma, Shiv Dayal Bharti, Mahendra Kumar Shrimali, Tushar Kanti Datta 
  Abstract: For the preliminary estimate of the seismic safety of the dam, expert opinions are often relied upon. However, expert opinions, when expressed linguistically, are associated with uncertainty and fuzziness. To address this inadequacy, cloud models have been utilized in numerous studies. In the present investigation, a cloud model is employed to predict the seismic safety of a concrete gravity dam. Experts evaluate seismic safety factors of dams, focusing on seismic damage potential, hazard, and structural strength. Each factor has key sub-indicators rated on a five-point scale. Through qualitative-to-quantitative conversion, cloud points are generated for analysis. The coefficient of variation method identifies sub-indicator influences on each factor. Comparing these cloud models to standard ones visually depicts dam safety. Illustrated with Koyna dam, this approach reveals its seismic safety below normal range, showcasing the effectiveness of the three indicators in assessing dam safety.
  Keywords: cloud model; dam seismic safety assessment; Koyna dam; correlation coefficient method; risk assessment.
  DOI: 10.1504/IJRS.2025.10069925
   
  
• Testing scenario generation and selection for autonomous vehicles using an integrated approach based on real-world accident data  
  by Guozheng Song, Xiaopeng Li 
  Abstract: The safety and reliability of Autonomous Vehicles (AVs) is a core concern, which should be validated before application. The critical testing scenarios extracted from historical accidents of AVs can help achieve the efficient safety and reliability testing of AVs. This paper presents an integrated approach that combines a data-driven method with a Bayesian Network (BN). The information including states, states' occurrence likelihoods and quantitative relationships of variables related to scenarios are learned from an AV accident database of California Department of Motor Vehicles (DMV), which is applied to establish a BN. Then the scenarios are generated and assessed with the BN and a severity matrix. The testing scenarios are selected based on their weighted consequence severity and risk. In this way, this work achieved critical testing scenarios for the automated driving systems (ADSs) and perception systems (PSs) of AVs based on the AV accident database.
  Keywords: autonomous vehicle; Bayesian network; testing scenario generation and selection.
  DOI: 10.1504/IJRS.2024.10070893
   
  
• Fatigue in the Indonesian palm oil industry: a critical review  
  by Taufiq Ihsan, Vioni Derosya 
  Abstract: The palm oil industry in Indonesia is a major contributor to global oil and fat production, employing millions of workers. Despite its vast workforce, there is a significant lack of information regarding worker fatigue. This review highlights critical fatigue-related issues in Indonesian palm oil plantations. We conducted a comprehensive literature review, gathering publications addressing fatigue risk factors, short-term and long-term health and safety consequences, and various fatigue mitigation strategies. Working in oil palm plantations exposes individuals to multiple fatigue-inducing factors. These factors not only lead to immediate effects like reduced cognitive function and accidents but also contribute to chronic illnesses. It is crucial to evaluate the effectiveness of existing legislation and industry practices while optimizing working, living, and sleeping conditions. Considering the current workplace conditions, a thorough assessment of potential preventive measures, including fatigue prediction tools and personalized fatigue management systems, is recommended.
  Keywords: mitigation strategies; palm oil; risk factors; worker fatigue.
  DOI: 10.1504/IJRS.2025.10072246
   
  
• Improving the accuracy of drowning detection based on improved YOLOv5  
  by Kaikai Wang, Ruiliang Yang, Libin Yang 
  Abstract: Drowning stands as a primary cause of unintentional deaths globally. This paper presents an improved YOLOv5 algorithm tailored for drowning detection, aiming to effectively mitigate drowning incidents. The improved YOLOv5 incorporates the Ghost-CBAM-C3 (GCC) module, which comprises Ghost-bottleneck modules and the CBAM module, and the learning rate decay of Cosine Annealing. To gauge the algorithm's efficacy, four self-made datasets were curated utilizing a DJI mini3pro drone over both swimming pools and natural water bodies. Experimental findings underscore the heightened performance of the improved YOLOv5 over the original YOLOv5s. This enhancement manifests in a precision boost from 92.8% to 97.1 %, and the values for mean average precision (mAP@0.5), weights, and the frames-per-second (FPS) are 93.2, 14.1, and 23.70, respectively, affirming its applicability in real-time scenarios. Furthermore, results indicate superior performance of the swimming pool dataset compared to those from natural water bodies.
  Keywords: drowning detection; improved YOLOv5; self-made datasets; CBAM; safety; drone; LabelImg software; k-means; SPPF; Ghost module.
  DOI: 10.1504/IJRS.2024.10072350
   
  
• Examining the antecedents of deep safety compliance and surface safety compliance: an expanding of technology acceptance model  
  by Ho Y. Hiep, Nguyen Ngoc Hien 
  Abstract: This study examines the antecedents of deep safety compliance and surface safety compliance among garment and footwear workers in Vietnam. The study expands on the technology acceptance model by incorporating social cognitive theory to investigate the influence of participative management and co-worker support on perceived usefulness, perceived ease of use and self-efficacy, ultimately impacting deep safety compliance and surface safety compliance. Data from a survey of 549 workers in five garment and footwear enterprises in Vietnam was analysed using partial least squares structural equation modelling. Findings revealed that both participative management and co-worker support significantly enhance perceived usefulness, perceived ease of use of safety procedures and worker self-efficacy. These perceptions, in turn, positively influence deep safety compliance and negatively impact surface safety compliance. This research adds a novel finding to the technology acceptance model by demonstrating the significant influence of participative management and co-worker support on safety compliance, expanding its applicability in the safety domain. Other literature contributions and practical implications for enhancing workplace safety are also discussed.
  Keywords: deep safety compliance; surface safety compliance; self-efficacy; participative management; co-worker support.
  DOI: 10.1504/IJRS.2025.10072657
   
  
• Coupling of risk factors in emergency processes for oil storage system fires based on the Bayesian network and N-K model  
  by Changfeng Yuan, Xing Sun, Lulu Niu, Yating Tong, Qing Zhang 
  Abstract: Frequent secondary accidents caused by emergency treatment of oil storage system fires (OSSF) show that risk factors and their interactions in emergency processes can lead to recurrence of accidents. To quantitatively evaluate coupling effects of risk factors on accident development, a novel risk coupling effect analysis (RCEA) method based on the Bayesian network (BN) and N-K model is proposed. Based on a statistical analysis of 252 typical accidents, risk coupling types caused by different factors are defined. Risk coupling value is calculated using the N-K model. A RCAE model based on the BN and N-K model is constructed. The model is used to analyze the coupling effect of risk factors, including: coupling degree variation characteristics, sensitivity and joint adjustment measures of risk factors. Some risk management suggestions are proposed. This study presents a new research idea and measurement method for evaluating risk coupling effect in emergency processes for OSSF.
  Keywords: oil storage system fire; risk factor; Bayesian network; N-K model; coupling effect.
  DOI: 10.1504/IJRS.2025.10072752
   
  
• Estimation of conditional stress strength reliability using ranked set sampling: exponential case  
  by M. Architha, Parmeshwar Pandit 
  Abstract: This study focuses on estimating the conditional stress strength reliability of a system using ranked set sampling when stress and strength variables follow independent exponential distributions. Two estimation methods are used; namely maximum likelihood estimation (MLE) and bootstrap estimation. The asymptotic confidence interval is constructed based on a maximum likelihood estimator and the Boot p confidence interval is constructed. A simulation study is carried out to determine the mean square error (MSE) and length of the confidence interval. This study uses MSE and the length of the confidence interval to compare the estimator based on ranked set sampling to that based on simple random sampling in the context of exponential distribution.
  Keywords: exponential distribution; simple random sampling; ranked set sampling; stress-strength model; conditional stress-strength model; maximum likelihood estimator; bootstrap estimation; confidence interval.
  DOI: 10.1504/IJRS.2024.10072886
   
  
• Construction fatigue prediction model based on improved random forest algorithm  
  by Fuhai Wu 
  Abstract: Construction workers are prone to construction fatigue in high-intensity working environments, and failure to receive effective rest may result in casualties and property damage. The study uses deep learning algorithms to construct an intelligent fatigue prediction model aimed at accurately assessing the fatigue status of construction workers. The study takes smartphones to collect basic data and inputs it into an improved random forest algorithm for fatigue feature recognition. Then, an intelligent construction fatigue recognition model is established based on the improved random forest algorithm. The research model had an accuracy rate of 94.7% in recognizing different human movements, and an accuracy rate of 91% in predicting construction fatigue. The designed method accurately predicts the complete exhaustion, fatigue, concentration, and excitement states of workers, and its predictive ability is superior to other prediction models. The research model can effectively assist construction managers in accurately detecting workers' fatigue status and taking timely intervention measures to reduce safety accidents.
  Keywords: RF; PCA; PSO; fatigue; construction.
  DOI: 10.1504/IJRS.2025.10072988
   
  
• Power grid fault diagnosis technology based on improved deep Q-network model  
  by Qiang Wang, Hongyan Song 
  Abstract: As the increasing complexity of the power system, the difficulty of fault diagnosis in the power grid is also increasing. In response to the issue of continuously decreasing fault diagnosis accuracy, a power grid fault diagnosis model based on an improved deep Q-network model is raised. This model enhances its information integration capability by constructing a fault parameter recognition model and introducing alarm information for text processing. By identifying power grid fault parameters and processing alarm information, the efficiency and accuracy of fault diagnosis can be improved. The experimental results show that the model shows significant performance improvement in multiple state dimensions, and is significantly better than the traditional algorithm in single fault diagnosis and multi-fault diagnosis scenarios. The results show that the proposed method has significant advantages in the accuracy of fault prediction, processing efficiency and antinoise ability, which verifies the validity and practicability of applying this model in complex power systems. It also emphasises the importance of combining reinforcement learning with unstructured data to further promote the development of smart grid technology.
  Keywords: DQN; alarm information; power grid; reinforcement learning; fault diagnosis.
  DOI: 10.1504/IJRS.2025.10072989