Top Read Articles

    Published in last 1 year |  In last 2 years |  In last 3 years |  All
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Comparative study of inherent safety, behavior-based safety, process safety and functional safety based on safety management paradigm shift
    TONG Ruipeng, WANG Lulu, XU Surui, WANG Zhihao, LIAN Fangfei
    China Safety Science Journal    2025, 35 (1): 7-15.   DOI: 10.16265/j.cnki.issn1003-3033.2025.01.1045
    Abstract672)   HTML9)    PDF(pc) (10704KB)(65)       Save

    To clarify the essential characteristics and differences between inherent safety, behavior-based safety, process safety, and functional safety and to promote a virtuous cycle of high-quality development and high-level safety, this study employed literature review and comparative analysis methods to explore their basic connotations and evolution processes, interrelationships, realistic challenges, and development paths based on the safety management paradigm shift. The results indicate that inherent safety is an idealized form of safety. Behavior-based safety is an interdisciplinary field that involves the theories and methods of safety science and behavioral science. Process safety protects humans, machines, and the environment through systematic approaches from a full life cycle perspective. Functional safety aims at preventing unacceptable risks caused by functional failures of systems. The four types of safety, led by inherent safety, involve a gradual progression from concepts to practice. These types of safety share a unified internal structure encompassing the elements of humans, machines, environment and management. The current representative standards cover various industry sectors and focus on accident prevention. In the future, the synergistic effect of the four in safety governance should be fully utilized. By using artificial intelligence technology to empower the new engine of safety production, the four should be continuously improved in specific practices tailored to local conditions.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    China Safety Science Journal    2025, 35 (8): 272-272.  
    Abstract661)   HTML0)    PDF(pc) (2008KB)(0)       Save
    Related Articles | Metrics | Comments0
    Research review and progress of coal mine gas explosion risk assessment
    LI Min, WANG Dan, HE Shan, SHI Shiliang, WANG Deming, LU Yi
    China Safety Science Journal    2025, 35 (2): 127-136.   DOI: 10.16265/j.cnki.issn1003-3033.2025.02.0963
    Abstract607)   HTML4)    PDF(pc) (4007KB)(18)       Save

    Gas explosion disaster is the most serious coal mine accidents. In order to summarize the research progress of gas explosion risk assessment, firstly, the risk factors of gas explosion were identified. Then the shortcomings of existing risk assessment methods were analyzed, and the following conclusions were drawn by sorting out relevant literature. The analysis shows that there are subjective problems in identification method and evaluation method of coal mine gas explosion risk sources. There are also some problems with risk factors, such as the uncertainty of gas source and change, the unknown ignition source, the uncertainty of ventilation and air control. The application of objective weighting method and evaluation method based on mathematical theory can improve the accuracy of weighting and evaluation results, but the computational complexity limits its wide application. Although the application of computer models has made the assessment of coal mine gas explosion risk more accurate, it is necessary to solve the problem of expanding the integration of data collection and deep learning. Based on the current research status and existing problems, the future risk assessment of coal mine gas explosion can develop in the direction of multi-source data fusion technology, deeply mining precursory warning information, establishing intelligent models of disaster information based on information depth perception and data mining, and realizing dynamic risk assessment of coal mine gas explosion.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    A review of research for civil aviation safety resilience
    YUAN Leping, ZHENG Ying, GU Zekun, GAO Yuyu
    China Safety Science Journal    2025, 35 (2): 1-9.   DOI: 10.16265/j.cnki.issn1003-3033.2025.02.0661
    Abstract545)   HTML4)    PDF(pc) (1521KB)(29)       Save

    In order to systematically review the research and development status of safety resilience in the field of civil aviation at home and abroad, and deepen the research on safety resilience in the field of civil aviation, firstly, the concept of aviation safety resilience was explored by reviewing policy documents, standards and research literature related to air transport systems in recent years. Then the research and application of safety resilience in civil aviation airport, air traffic control, flight operation and other fields were discussed. Finally, the existing problems were analyzed and corresponding suggestions and prospects are put forward. The results show that the safety management of civil aviation has formed a relatively perfect system, and the safety resilience covers all stages of safety management before, during and after, but it still cannot meet the needs of perfect connection and integration with the existing safety management system. Current studies focus more on the resilience of airports and route networks. In terms flight operation, more measures are taken to improve safety resilience based on the actual flight operation. The basic research on aviation resilience assessment is relatively lacking, and the research on aviation personnel resilience at operational level is far from enough. In the future, relevant research should be carried out around the individual operation resilience, enrich the basic research of resilience assessment, further deepen the research and form a relatively stable discipline system, pay attention to the connection between safety resilience and safety management system, and assess individual operation resilience from the perspective of safety.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Exploration and practice of a new training mode for safety engineering degree postgraduates
    HU Juan, WANG Kai, TONG Ruipeng, ZHOU Aitao
    China Safety Science Journal    2025, 35 (1): 1-6.   DOI: 10.16265/j.cnki.issn1003-3033.2025.01.1037
    Abstract517)   HTML11)    PDF(pc) (1880KB)(51)       Save

    Cultivating professional master's students is essential to addressing the shortage of high-level applied talents. To meet the industry demand for safety engineering professionals, this study analyzes challenges in China's training processes based on domestic and international practices. It introduces the "professional group + action learning method" model, alongside reforms in curriculum, teaching methods, training bases, faculty, and evaluation standards, using China University of Mining and Technology-Beijing as a case study. Data from the 2023 cohort validate the model's effectiveness in improving graduate quality, enhancing competencies, and addressing traditional education shortcomings, proving its feasibility and reference value.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Failure causes of emergency response in oil and gas pipeline accidents and social network analysis
    GONG Yunhua, ZHANG Zhe
    China Safety Science Journal    2025, 35 (1): 209-215.   DOI: 10.16265/j.cnki.issn1003-3033.2025.01.1536
    Abstract472)   HTML2)    PDF(pc) (2984KB)(11)       Save

    To avoid worsening the consequences of oil and gas pipeline accidents due to emergency failures, the causes of emergency failure in 27 accidents at home and abroad were analyzed using the HFACS model. Based on the results of grounded theory (GT) statistical coding analysis, a classification model of failure causes of emergency response in oil and gas pipeline accidents was proposed. SNA was used to develop the relationship network of the causes of emergency failures in oil and gas pipeline accidents. The core-periphery, centrality, and association direction index analyses were used to identify core factors and factors with high association and strong mediating roles in the classification model of the causes of emergency failures in oil and gas pipeline accidents. The results indicated that the classification model of emergency failure causes in oil and gas pipeline accidents was divided into five levels: government and emergency department factors, operator organizational factors, operator unsafe supervision, preconditions for unsafe behavior of on-site personnel, and unsafe behavior of on-site personnel. The emergency failure causes were further divided into 16 bottom-level factors, among which there were 9 core factors: inadequate safety supervision by government and emergency departments, ineffective emergency rescue, regulations defects, insufficient supervision by pipeline operators, technical environment, and skill errors. Skill errors, regulations or procedure defects, technical environment, and insufficient supervision by operators were highly associated factors. Moreover, pipeline operators' regulation defects, procedure defects, technical environment, insufficient supervision, improper resource management, and decision-making errors were strong mediating factors.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Human reliability analysis of emergency behaviors for hazardous chemical accidents in chemical industry parks
    WANG Dongdong, YANG Angbin, WANG Zhihao, ZHAO Jingrong, DONG Guoyu, TONG Ruipeng
    China Safety Science Journal    2025, 35 (2): 21-27.   DOI: 10.16265/j.cnki.issn1003-3033.2025.02.1078
    Abstract457)   HTML7)    PDF(pc) (3177KB)(28)       Save

    To explore human error in complex emergency rescue scenarios for hazardous chemical accidents in chemical industry parks and improve human reliability in emergency rescue actions, a comprehensive analysis method was established to quantitatively evaluate the human reliability of emergency rescue for hazardous chemical accidents. Firstly, based on the laws, regulations and standards related to the emergency rescue of hazardous chemical accidents, 20 emergency behaviors in chemical industry parks were summarized and extracted. Secondly, cognitive reliability and error analysis method(CREAM) was introduced to determine the probability of human error. Analytic hierarchy process(AHP) and entropy weight method were combined to quantify the severity of errors in emergency behaviors. Finally, from the perspectives of possibility and severity, the weak aspects of emergency behaviors in chemical industry parks were explored, and the strategies for enhancing emergency rescue capabilities in chemical industry parks were discussed. The practical application of the method was verified with the example of N chemical industry park. The results show that 20 emergency behaviors were divided into 3 clusters. There are 4 emergency behaviors identified that needed to be prioritized for improvement in the petrochemical zone: risk assessment, fire-fighting, initial disposal of enterprises and rescue of people in distress. For these emergency behaviors, it was proposed that N chemical industry park should focus on optimizing the accident information transmission mechanism, improving decision-making and command effectiveness, and strengthening rapid response and disaster identification capabilities, so as to provide countermeasures and suggestions for improving its emergency rescue capability.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Research on aircraft control system fault risk assessment based on hybrid probability models
    SHI Tongyu, GAO Yi, WANG Yantao
    China Safety Science Journal    2025, 35 (2): 10-20.   DOI: 10.16265/j.cnki.issn1003-3033.2025.02.0601
    Abstract455)   HTML3)    PDF(pc) (3453KB)(14)       Save

    To address the flight safety risks posed by faults in aircraft control systems, a composite framework for fault risk assessment based on IRPN was proposed. This framework comprehensively considered four key risk factors: fault probability, severity, detectability, and risk damping. First, system fault modes were deduced bidirectionally using FMECA-FTA method. Second, human and environmental factors were incorporated, and a Bayesian network approach was employed to construct a hybrid probability model for calculating fault probabilities. Third, fault severity was categorized into three evaluation parameters, which were comprehensively assessed using the Analytic Hierarchy Process and Fuzzy Comprehensive Evaluation methods. Next, utilizing resources such as pilot quick reference manuals and aircraft type design manuals, a criterion-based reasoning method was applied to establish detectability scoring criteria, allowing for a more scientific evaluation of fault mode detectability levels. Finally, the FRAM was introduced to define risk damping coefficients, characterizing the propagation of risk during the evolution of fault risks. The computational validation was carried out with the case of jamming failure mode of aircraft flap seam wing actuation system. The research results show that its IRPN assessment result is 158, which is in perfect agreement with the actual operation. The validity and accuracy of the failure composite risk index calculated by the IRPN composite risk assessment framework are confirmed by the failure mode example simulation and the real verification of unsafe events.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Empirical analysis of construction engineering safety impact network influenced by five-party responsible entities
    CHEN Dawei, YANG Zhe, YU Rui, CAO Weiqiang
    China Safety Science Journal    2025, 35 (4): 1-8.   DOI: 10.16265/j.cnki.issn1003-3033.2025.04.1638
    Abstract426)   HTML2)    PDF(pc) (2249KB)(17)       Save

    In order to effectively prevent construction safety accidents, a safety responsibility network model of the five responsible parties was developed based on complex network topology characteristics to reveal the nonlinear coupling mechanism of their safety responsibilities, supported by accident case studies. First, relevant regulations, standards, and literature were analyzed to extract safety responsibility checklists for each party, and a responsibility matrix was constructed. Subsequently, Neo4j software was utilized to visualize the network diagram illustrating the safety influence relationships among the five parties in construction projects. Finally, topological metrics were applied to explore the interdependencies between the parties across multiple dimensions. The results indicate that the construction client plays a central and dominant role in project safety, with particularly significant influence on the contractor. The contractor's impact is primarily concentrated within its organizational boundaries, and its responsibility implementation is susceptible to external influences from other parties. The survey and design units indirectly affect other parties through the construction client. The supervision unit maintains systemic balance and regulation through monitoring and feedback mechanisms. The identification of critical decision-making nodes and passive response factors provides network topology-based evidence for differentiated management of responsible parties.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Risk assessment of biological sample transport by UAVs based on Bayesian networks
    LIU Qing, SHEN Tian
    China Safety Science Journal    2025, 35 (1): 16-24.   DOI: 10.16265/j.cnki.issn1003-3033.2025.01.0441
    Abstract419)   HTML7)    PDF(pc) (3180KB)(31)       Save

    To quantify the transportation risks associated with biological samples using UAVs, this study first identified 32 risk factors across five dimensions-human, machine, environment, management, and hazard-based on national standards and relevant literature. A BN for risk assessment was constructed using Netica software, with prior probabilities determined through expert knowledge and fuzzy set quantitative analysis. The proposed risk assessment model was then used for bidirectional reasoning and scenario analysis. A case study of a UAV company in Shenzhen was presented to evaluate the transportation risks of biological samples and identify key influencing factors. The results indicate that the risk probability of biological sample transportation, as calculated through forward reasoning, is approximately 2.203×10-5. The primary risk factors are related to hazardous materials, followed by equipment and facility-related issues. The core risk factors influencing biological sample transportation include the size, quantity and weight of hazardous material packages, the temperature control effectiveness of specialized cold chain logistics boxes, the integrity of emergency response plans, emergency handling capabilities, safety management and education, and the presence of obstacles.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Mechanism of risk perception on safety cognition of construction workers in underground caverns
    JIANG Xin, LI Fengbiao, PENG Jiayu, JIAN Li, JIN Lianghai
    China Safety Science Journal    2025, 35 (3): 1-9.   DOI: 10.16265/j.cnki.issn1003-3033.2025.03.1121
    Abstract383)   HTML1)    PDF(pc) (1948KB)(14)       Save

    In order to improve the safety cognition level of underground caverns construction workers, safety requirement and safety capability were introduced as mediating variables, and occupational burnout was used as a moderating variable to construct a moderated chain mediation model. A structured questionnaire was designed using 5 scales: risk perception, safety requirement, safety capability, occupational burnout and safety cognition. A questionnaire survey and data analysis were conducted on 312 underground caverns construction workers, and SPSS 26.0 and AMOS 26.0 software were used to test the mediating effect and moderating effect.The results show that risk perception directly and positively affects the safety cognition of underground cavern construction workers, while occupational burnout plays a negative moderating role between the two. Risk perception also affects the safety cognition of construction workers through the independent mediating effect of safety requirement and safety capability, as well as through the chain mediating effect of safety requirement and safety capability. Therefore, motivating and improving the risk perception, safety requirement and safety capability of construction workers, while reducing their occupational burnout, can effectively improve their safety cognition level.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Mining truck driver fatigue driving detection based on improved YOLOv8
    GU Qinghua, YIN Shutan, WANG Dan, LI Xuexian, YIN Huimin
    China Safety Science Journal    2025, 35 (1): 60-66.   DOI: 10.16265/j.cnki.issn1003-3033.2025.01.0147
    Abstract382)   HTML2)    PDF(pc) (12457KB)(34)       Save

    To address the high rates of missed detections and false alarms, as well as the poor robustness in fatigue driving detection for open-pit mine truck drivers, a fatigue driving detection model for mine truck drivers (EBS-YOLO) based on the improved YOLOv8 is constructed to enhance the overall performance of fatigue detection. Firstly, YOLOv8 was used as the basic model for fatigue detection, and a small target detection layer was added to enhance the model's attention to small targets. Secondly, the bottleneck attention module (BAM) was used to improve the model performance to extract small target features, especially eye features. Finally, all cross-stage aggregation modules (C2f) in the backbone network were replaced with efficient multi-scale attention (EMA) modules, thereby effectively reducing model parameters and computational overhead to meet the requirements of a lightweight model. The results showed that the improved YOLOv8 model had a great detection effect with the accuracy, recall rate, and average detection accuracy reaching 93.6%, 93.9%, and 96.5%, respectively, and the memory size of the model was only 4.9 MB. Compared with the YOLOv8 model, the improved model can quickly and accurately identify the fatigue state of mining truck drivers, meet real-time requirements, and effectively prevent fatigue-driving accidents.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Exploration and practice of collaborative training for safety discipline talents between universities and institutions: from integration of science and education to integration of industry and education
    TONG Ruipeng, WANG Leyao, HAN Jixiang, ZHANG-JIANG Bonan, KANG Rongxue, AN Yu
    China Safety Science Journal    2025, 35 (7): 1-7.   DOI: 10.16265/j.cnki.issn1003-3033.2025.07.1357
    Abstract363)   HTML0)    PDF(pc) (6248KB)(0)       Save

    To cultivate talents with both theoretical innovation and practical abilities in safety science and engineering discipline of universities, this paper explored the educational practice of safety discipline from the integration of science and education to the integration of production and education. First, the integration concepts of science and education and integration of production and education were analyzed under the new Degree Law, establishing the connotation requirements and an educational framework for science-industry-education synergy. Utilizing macro, meso, and micro perspectives, this study constructed robust educational systems, management mechanisms and training programs. Examples from School of Emergency Management and Safety Engineering of China University of Mining and Technology-Beijing and National Academy of Safety Science and Engineering illustrated the effective cultivation of talent seeds, the creation of nurturing environments, and the achievement of substantial educational outcomes. Results indicate that this collaborative model significantly enhances the comprehensive development of safety professionals and improves the overall quality of education in the safety discipline.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    System fault evolution process based on quantum thought description
    CUI Tiejun, LI Shasha, DENG Wenhao
    China Safety Science Journal    2025, 35 (5): 1-7.   DOI: 10.16265/j.cnki.issn1003-3033.2024.05.0671
    Abstract351)   HTML0)    PDF(pc) (3234KB)(11)       Save

    In order to study the SFEP and its characteristics, a method for describing SFEP using quantum concepts is proposed. The relationship between SFEP and event function states was discussed. The principle of describing SFEP by quantum thought was studied. The mathematical model of quantum description of SFEP was constructed. The measurement collapse of SFEP quantum states was realized, and the failure mode and its probability were finally determined. The results indicate that SFEP has diversity and uncertainty, event quantum state superposition, measurement collapse, bipolar state, which is the basis of studying SFEP through quantum thought. SFEP can be decomposed into multiple layers, with distinct objects and quantum state superposition modes in each layer. The SFEP quantum states are derived from the superposition of the quantum states of objects at each layer, which is composed of the polynomial product of the probability amplitude of the objects in each layer. The restriction conditions for the formation of the probability amplitude of quantum states of each layer are given. Each dimension of the SFEP quantum state vector is a fault state. The measurement of the factor phase value makes the SFEP quantum state collapse, and the possible failure mode and occurrence probability are obtained.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    China Safety Science Journal    2025, 35 (10): 247-247.  
    Abstract348)   HTML0)    PDF(pc) (2383KB)(0)       Save
    Related Articles | Metrics | Comments0
    Cognitive test of construction safety education effect based on VR technology
    DING Chao, ZHANG Xiangke, WANG Kun, SONG Ziwei, GUO Xiaowen
    China Safety Science Journal    2025, 35 (1): 84-93.   DOI: 10.16265/j.cnki.issn1003-3033.2025.01.0181
    Abstract341)   HTML1)    PDF(pc) (5706KB)(17)       Save

    In order to make up for the deficiency of VR technology in safety education theory support and practical effect tests, the relevant influencing factors affecting the effect of engineering safety education were taken as the entry point. SEM was used to establish an analytical framework for the influencing factors of safety education and the cognitive experiments were carried out to test the effect. The results show that the frequency of education, the mode of education, individual initiative, fun and comfort are the main factors affecting the effectiveness of construction safety education. The hybrid mode of "VR + lecture" is the most effective educational method at present, but the use of VR technology still requires personnel assistance. The optimal frequency of education is recommended to be less than 30 days. The main factors of fun, comfort are significantly positively correlated with educational effect, but comfort is more important in the application of construction safety education with VR technology.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Visual behavior for construction site hazard identification under different cognitive loads
    DENG Hongze, KONG Yuanyuan, XU Sheng
    China Safety Science Journal    2025, 35 (1): 40-49.   DOI: 10.16265/j.cnki.issn1003-3033.2025.01.0685
    Abstract340)   HTML2)    PDF(pc) (8899KB)(14)       Save

    In order to explore the effect of cognitive load on workers' hazard identification behavior, a cognitive experiment based on eye-tracking technology for construction site hazard identification was designed firstly. In this experiment, a N-digit task was introduced to increase the cognitive load. Secondly, the gaze and glance data were collected to analyze the static attention allocation, and the scanning path was processed to extract the dynamic transfer characteristics of attention. Finally, three parameters of variance review probability (RP), transition probability (TP) and switching probability (SP) were selected as the quantitative parameter values to classify the scanning patterns of hazard identification, which explored the influence of cognitive load on hidden hazard identification from the perspective of visual behavior performance. The results show that the level of cognitive load negatively affects hazard identification performance. The subjects with high cognitive load show longer first fixation time, fewer fixation counts and saccade counts, and there is no significant difference in fixation percentage and mean fixation duration. Additionally, based on the attention characteristics, three scanning patterns are identified: sequential inspection, repeated comparison and random discovery. With the improvement of cognitive load level, subjects will pay more attention to identifying single hazard but neglect others during sequential inspection, and reduce the attention in the hazard area but still keep the fixation point quickly and frequently switching during repeated comparison, while the number and time of inspection of hazard areas are reducing simultaneously during random discovery.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Work safety solution for China's chemical (hazardous chemicals) enterprise
    WANG Haoshui
    China Safety Science Journal    2025, 35 (5): 16-22.   DOI: 10.16265/j.cnki.issn1003-3033.2025.05.0097
    Abstract317)   HTML0)    PDF(pc) (1938KB)(6)       Save

    In order to improve the work safety management level of China's chemical (hazardous chemicals) industry, firstly, the formation of chemical process safety management was expounded, including the traditional management method and the proposal of process safety concept. Then, the characteristics and specific content of the elements of the chemical process management elements system in China were analyzed, including 8 modules and 20 elements. Finally, a systematic solution was proposed, that was, four-element solution with safety leadership, management barrier (responsibility, equipment, management and capability), and safety culture as the primary-level elements. The results show that core elements of four-element solution are the concept, safety leadership, management barrier (responsibility, equipment, management, capability) and safety culture. Among them, safety leadership is the most critical element, leading the concept into practice, responsibility division, equipment upgrading, management system construction, capability improvement and culture cultivation. Other elements together constitute the skeleton of work safety management, and realize systematization. Businesses can help prevent accidents and improve the overall safety level of the industry by taking the lead and promoting the implementation of various elements through participation of all staff.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Emergency rescue equipment support capability assessment model
    ZHENG Xuezhao, DONG Beibei, TONG Xin, WANG Yishuo
    China Safety Science Journal    2025, 35 (1): 194-201.   DOI: 10.16265/j.cnki.issn1003-3033.2025.01.0742
    Abstract314)   HTML1)    PDF(pc) (6759KB)(12)       Save

    To ensure that the equipment support system of professional emergency rescue teams could meet the requirements of rescue tasks and gradually adapt to complex and variable disaster risks, a text mining method was applied to analyze the factors influencing the equipment support capacity of emergency rescue. Based on technical personnel support capability, equipment resource support capability, equipment and facility support capability, information resource support capability and management system support capability, an assessment index system for emergency rescue equipment support capacity was developed. To reduce the impact of fuzziness, randomness, and subjective-objective bias on assessment results, a combined weighting method was adopted to determine the weights of each assessment index. A comprehensive assessment method was established using the matter-element extension model and the integrated cloud model. Professional emergency rescue team A was selected as an example for application to verify the scientific validity and effectiveness of the model. The results show that the index system comprehensively and accurately reflects the overall level of emergency rescue equipment support capability of professional teams. The assessment model reasonably and effectively assesses the capability level and identifies weaknesses in the current equipment support system, providing improvement points and theoretical support for the development of the team's equipment support system.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Unsafe behavior recognition model of high climbing workers based on vision
    ZHANG Zehui, ZHANG Qianlong, XU Xiaobin, ZHAO Zuguo, WANG Haiquan, LI Hao
    China Safety Science Journal    2025, 35 (2): 144-151.   DOI: 10.16265/j.cnki.issn1003-3033.2025.02.0278
    Abstract312)   HTML0)    PDF(pc) (7997KB)(17)       Save

    In order to accurately identify unsafe behaviors during the climbing process of high-altitude workers, this paper proposed an unsafe behavior recognizing method for high climbing workers based on vision, which included the human pose estimation and the one-dimensional convolutional unsafe behavior recognition models. Quantized autoencoder was used to structurally model human key points in human pose estimation, enabling the detection of human key point coordinates. Combining with safety behavior knowledge in high climbing operations, the unsafe behavior recognition model was constructed based on one-dimensional convolutional neural network model, and it was validated by industrial data experiments. Experimental results show that the accuracy of this method is 93.91% and 90.34% on unobstructed and partially obstructed datasets, respectively. Moreover, compared with support vector machines (SVM) and K-nearest neighbor (KNN), this method has stronger generalization capability.

    Table and Figures | Reference | Related Articles | Metrics | Comments0