Loading...

Table of Content

    28 March 2026, Volume 36 Issue 3
    Safety Science Theories and Methods
    Influence mechanism of career resilience on safety performance of civil aviation pilots
    WU Fan, LAI Mimi, LI Mingyang
    2026, 36(3):  1-8.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0771
    Asbtract ( 157 )   HTML ( 1)   PDF (4018KB) ( 1 )  
    Figures and Tables | References | Related Articles | Metrics

    To enhance the safety performance of civil aviation pilots, this study constructs a three-dimensional analytical framework for career resilience based on affect, behavior, and cognition(ABC). Integrating machine learning with fsQCA, it empirically analyzes 229 questionnaire responses from Chinese civil aviation pilots. Building upon the measurement of antecedent variable importance weights using the random forest algorithm, the fsQCA method is further applied to decipher the impact mechanisms of different condition configurations on safety performance.The results indicated that no single factor constitutes a necessary condition for either high or non-high safety performance; however, learning willingness and cooperation consciousness play key roles in driving civil aviation pilots to achieve high safety performance. Five configurational paths leading to high safety performance are identified and categorized into three patterns: “emotionally empowered-behaviorally oriented,” “resilient collaboration-behaviorally dominant,” and “efficiency driven-intrinsically motivated.” In contrast, two configurational paths leading to non-high safety performance are classified as “behavior-atrophy” and “affection-deficiency” types. Furthermore, substitution relationships exist among conditional variables in the five configurations for high safety performance.

    Analysis and construction of core competencies for fire engineering professionals in new era based on OBE
    LI Xiaobin, LIU Yixiang, LI Sicheng, QI Jialin, WANG Xingqi, WEI Lei
    2026, 36(3):  9-16.  doi:10.16265/j.cnki.issn1003-3033.2026.03.1546
    Asbtract ( 70 )   HTML ( 1)   PDF (3206KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To address the new demands for professionals in the fire protection industry and improve the quality of talent development, this study adopted the OBE framework. It drew on interviews with industry organizations, practitioners, graduates, and educators, along with an analysis of relevant laws, regulations, and standards. The curriculum systems of 29 domestic and international universities offering fire engineering programs were compared, and the competency requirements for talent in the context of fire protection and artificial intelligence integration were examined. The study identifies key job roles and core competencies in fire engineering, defines corresponding educational objectives and graduation outcomes, and maps their interrelationships. Furthermore, it proposes a curriculum system and knowledge structure suited to the evolving needs of the industry, designates eight core courses such as Fire Combustion Science, and develops new engineering-oriented fire protection courses that respond to emerging safety challenges and integrate artificial intelligence. Finally, it is suggested that fire engineering majors in different universities should leverage their respective institutional and disciplinary strengths to develop distinctive features, serve the industry, and foster mutual support.

    Experimental study on similarity perception and visual cognitive performance of nuclear power plant interfaces
    WU Xiaoli, HE Yuqi, LIU Xiao, HUANG Yongqiang, ZHANG Xuegang, LI Yiqun
    2026, 36(3):  17-24.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0569
    Asbtract ( 47 )   HTML ( 0)   PDF (7620KB) ( 1 )  
    Figures and Tables | References | Related Articles | Metrics

    To prevent interface similarity-induced errors in nuclear power plants, this study investigated the impact of interface similarity on cognitive performance and identified the optimal similarity range using semantic differential scale and scenario-based experiments. Firstly, a multi-dimensional perceptual feature system for interface similarity was developed through literature review, and 10 key similarity variables applicable to industrial control scenarios were identified. Secondly, a normalized equation for estimating the overall perceived similarity of nuclear power interfaces was established using semantic differential questionnaire survey and multiple linear regression analysis. Finally, typical interfaces from nuclear procedure tasks and alarm handling tasks were selected as experimental materials. Interface samples with varying levels of similarity were constructed based on three feature dimensions: color, layout structure, and complexity. Subjective questionnaires and scenario-based task experiments were conducted to measure and analyze the optimal range of similarity. The results indicate that interface similarity has a significant impact on operators' cognitive responses. with color, layout, and complexity as core dimensions. Cognitive performance is optimal when the interface similarity falls within the "generally similar" range (4-6).

    An experimental study on DCS operators' keyboard input under sway conditions
    YI Cannan, XIAO Nan, ZHAO Caijun, HU Hong, GAO Xu, KANG Yinjuan
    2026, 36(3):  25-32.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0780
    Asbtract ( 46 )   HTML ( 1)   PDF (4913KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to explore the effects of sway on keyboard input of operators in DCS and to reduce human errors, an experimental study was conducted under four sway conditions—static, low, moderate, and high. Operators' performance in numeric, alphabetic, and alphanumeric input tasks, as well as their subjective ratings, were measured. Statistical analyses were employed to examine the effects of sway and to compare performance differences across input types. The results show that sway has a significant main effect on keyboard input performance. Compared with the static, low, and moderate sway conditions, the input time and number of corrections for alphabetic and alphanumeric entries significantly increase under the high-sway condition, whereas the accuracy of numeric and alphanumeric inputs significantly decrease. Significant differences are also found among the three input types: numeric input achieves the highest accuracy and shortest completion time, while alphabetic input requires the longest time. Sway also significantly affects subjective evaluations. Under the high-sway condition, perceived input difficulty, physical discomfort, visual discomfort, and workload ratings are all significantly higher. Under low and moderate sway conditions, input performance and perceived difficulty are largely consistent with the static condition, whereas under moderate sway, the perceived difficulty and workload for alphabetic input are significantly higher than those under low and static conditions. Under high sway, overall input performance markedly declines, accompanied by pronounced increases in difficulty, discomfort, and workload.

    Safety management dilemma under AI anxiety: human-AI trust and system transparency mechanism
    NIU Lixia, LI Bo, LI Guo
    2026, 36(3):  33-40.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0299
    Asbtract ( 64 )   HTML ( 1)   PDF (1844KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To address employee' AI anxiety arising from increased system complexity and heightened information uncertainty in the application of AI to corporate safety management and decision-making, a mechanism model of "AI anxiety-human-AI trust-human-AI collaborative decision quality" was developed based on UMT. It introduced system transparency as a boundary condition to explain how employees appraised and coped with AI-related threats in contexts such as risk warnings and algorithmic black boxes. A questionnaire survey was conducted with a sample of 523 employees from AI-adopting enterprises. Confirmatory factor analysis(CFA) and structural equation modeling were employed to test the measurement model, path relationships, and moderating effects, while controlling for variables such as gender, age, education, job type, and AI usage frequency. The results show that AI anxiety reduces the quality of human-AI collaborative decision-making. Human-AI trust partially mediates the relationship between AI anxiety and collaborative decision-making quality. System transparency positively moderates the effect of human-AI trust on collaborative decision-making quality, such that higher transparency facilitates the translation of trust into higher-quality collaboration.

    Pilot mental workload assessment based on single-electrode EEG signals
    JIANG Hao, ZHANG Chao, LUO Xueying, PENG Xing
    2026, 36(3):  41-48.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0442
    Asbtract ( 57 )   HTML ( 1)   PDF (2501KB) ( 1 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to overcome the limitations of traditional multi-electrode electroencephalography technology in flight applications and effectively assess the mental workload of pilots, 43 pilots were recruited in this study to conduct simulated flight experiments. Each participant was required to perform flight tasks at three different mental workload levels (low, medium, and high) using a Cessna 172R simulator. The low workload task involved a standard five-leg takeoff and landing route, while the medium and high workload tasks were variations of the low workload task, with the addition of one and three malfunctions, respectively. Heart rate signals, EEG signals (collected from the Frontal Pole(FP) 1 electrode), and National Aeronautics and Space Administration-Task Load Index(NASA-TLX) scale data were recorded. The results show that as mental workload increased, both NASA-TLX scale scores and heart rate exhibited an upward trend. The power values in the Alpha and Beta bands significantly increased as mental workload levels increased. A threshold based on the percentage increase in EEG power was established. When the power increase exceeded the threshold, it was classified as medium or high mental workload, triggering an alert. The findings suggest that single-electrode EEG signals based on the FP1 electrode can effectively assess the mental workload levels of pilots.

    Study on dissemination and academic influence of 24Model
    LU Yuxuan, YANG Chun, HAN Meng, YUAN Chenhui, ZHAO Jinkun, XIE Xuecai
    2026, 36(3):  49-57.  doi:10.16265/j.cnki.issn1003-3033.2026.03.1165
    Asbtract ( 62 )   HTML ( 0)   PDF (3788KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    The 24Model, as an original and systematic accident causation theory in China, has been widely applied in the field of safety science since 2005. However, a comprehensive review of its theoretical development and application trends is still lacking. A systematic search and stratified screening were conducted based on the preferred reporting items for systematic reviews and meta-analyses (PRISMA) framework. A scoping review approach was employed to perform structured coding and data extraction from the 357 screened Chinese- and English-language publications. Subsequently, data analyses, including cross-tabulation analysis and chi-square tests, were carried out. The results indicate that research on the 24Model has shown a sustained growth trend and has begun to disseminate globally. Its application domains have expanded from the coal mining industry to complex system industries such as the chemical sector. In addition, application paradigms have evolved from qualitative analysis to quantitative modeling, from post-accident analysis to proactive prevention, and from traditional analytical approaches to digital and intelligent technologies. The systematic model has been further developed and refined in the fifth and sixth editions, providing a new theoretical framework for safety analysis in complex systems. This study suggests that future research on the 24Model may continue to focus on deepening its systematic theoretical foundations, innovating preventive applications, and integrating digital and intelligent technologies.

    Cascading failure evolution model of safety risks in UAV logistics distribution based on complex network
    QIU Pei, LUO Fan, MA Cheng
    2026, 36(3):  58-65.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0477
    Asbtract ( 61 )   HTML ( 1)   PDF (6249KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To enhance the safety risk management level of UAV logistics distribution, a cascading failure evolution model for UAV logistics distribution safety risks was constructed based on complex network theory. Through simulated evolution experiments, the risk evolution characteristics in specific scenarios of UAV logistics distribution were revealed. By analyzing 63 interview transcripts, safety risk factors and their interrelationships were identified, and the credibility of these findings was verified by comparing them with relevant literature analysis results. The safety risk factors were categorized into five types: personnel, machinery, materials, methods, and environment. A directed weighted complex network with 69 nodes and 469 edges was then constructed. Using the Gephi platform, the overall topological structure characteristics of the complex network were calculated and analyzed, confirming the necessity of dynamic risk evolution analysis. The importance levels of nodes in the complex network were classified as high, medium, and general, and the development stages were classified as latent, diffusion, and occurrence, which laid the foundation for the construction of the dynamic cascading failure evolution model. Risk propagation probability and risk load redistribution rules were defined to quantitatively characterize risk evolution. A Python program was designed to conduct simulation evolution experiments. Key experimental groups were defined, and the evolution network of UAV logistics distribution safety risks was constructed. The simulated evolution results were analyzed from dimensions such as key evolution nodes and key evolution paths. The results show that in the evolution network, nodes s15, s17, and s18 in the machinery category are the most important, and the key evolution paths starting from this category of factors are the most abundant. The loss of control of nodes s54 and s57 in the environment category is the primary cause of control failure in the machinery category nodes. Therefore, strategies should be formulated to focus on controlling factors in the environment and machinery categories, such as immature external supervision and equipment signal issues, to achieve forward shifting of safety risk control.

    Safety Technology and Engineering
    A large model for analyzing power production safety accidents integrating LLM, RAG and KG
    JIN Lianghai, ZHANG Qian, XU Tongxin, CHEN Yun, PENG Zhongwen
    2026, 36(3):  66-73.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0874
    Asbtract ( 66 )   HTML ( 1)   PDF (5653KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to address the inherent limitations of traditional analysis methods—such as insufficient integration of professional knowledge and weak interpretability of causal reasoning—when dealing with the complex characteristics of multi-factor nonlinear interactions in power systems, a large model for power production safety accident analysis was proposed that integrates LLM, RAG, and KG. A framework with four core modules was built: knowledge retrieval, knowledge reasoning, answer generation, and performance evaluation. RAG technology was used to accurately retrieve relevant knowledge from professional texts, and KG was leveraged for structured reasoning on accident entities and relationships to make up for retrieval blind spots. Finally, LLM was employed to generate professional and interpretable answers for accident causal analysis. The study comprehensively evaluated the system through subjective expert scoring and objective metrics like ROUGE and BLEU, and results show that in the scenario of power production safety accident analysis, the knowledge enhancement technology of RAG and KG provides universal performance improvement for basic models with a certain parameter scale—it helps models accurately capture professional correlations such as equipment fault transmission chains and enhances the quality of accident cause mining and result evolution reasoning. Large models including DeepSeek-R1 and Qwen2.5-72B significantly improved in the accuracy of parsing professional terms and organizing multi-factor correlations under this mode, among which DeepSeek-R1 achieved a comprehensive score of 4.05, better meeting the precision requirements of the field; meanwhile, there is a model capability threshold for the enhancement effect: after enhancement, Qwen2.5-72B can efficiently parse complex logics like cross-regional power grid fault linkage, balances performance and deployment costs, and is suitable for enterprises' practical needs, while smaller models such as Qwen2.5-14B, due to limited basic reasoning capabilities, fail to process professional information effectively after introducing external knowledge, leading to performance degradation and inability to meet professional requirements.

    Analysis and research on collision restitution coefficient of rocking rigid body based on kinetic energy conversion of discrete elements
    DENG Tongfa, ZHOU Tong, SHEN Botan, MAO Qiuyu
    2026, 36(3):  74-80.  doi:10.16265/j.cnki.issn1003-3033.2026.03.1829
    Asbtract ( 32 )   HTML ( 0)   PDF (6215KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to solve the problem that the classical model of rocking rigid body has a large error and cannot solve the collision restitution coefficient of heterogeneous and irregular rigid bodies, realize more accurate dynamic response prediction, design, safety evaluation and vibration control of rocking structure, based on the energy conversion analysis of mass element, the heterogeneous and irregular rigid bodies were discretized and the kinetic energy conversion analysis of discrete elements was carried out. The collision process of rigid body was divided into three stages. In the first stage, the residual kinetic energy of each discrete unit of rigid body was calculated after the vertical kinetic energy was dissipated. In the second stage, the residual kinetic energy of each discrete element of the rigid body was calculated after the kinetic energy had been dissipated in the direction of the rotation corner after the collision. In the third stage, the residual kinetic energy of each discrete element was converted and calculated under the action of internal force, and the collision recovery coefficient of the whole process was solved. With the help of the Digital Image Correlation (DIC) measurement system, the swing response test was carried out and the method was verified. The results show that the relative error between the collision recovery coefficient of a homogeneous rectangular rigid body obtained by this method and the experimental value is less than 3%, far less than the relative error between the classical model of a rocking rigid body and the experimental value. The relative error between the calculated collision recovery coefficients of heterogeneous and irregular rigid bodies and the experimental values is less than 5%. By this method, the dynamic response of a rocking structure after impact can be predicted more accurately, and a more reasonable structural design and safety evaluation can be provided.

    Prediction of slope instability in open-pit mine waste dumps based on GA-BP neural network
    XIE Zunxian, MA Haohao, JIANG Song, WU Xiaoyun
    2026, 36(3):  81-88.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0427
    Asbtract ( 51 )   HTML ( 1)   PDF (4751KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To improve the prediction accuracy and reliability of slope instability in mine waste dumps, a hybrid GA-BP model was developed by integrating an improved GA with a BP neural network. The model employed GA to globally optimize the initial weights and thresholds of the BP network, and incorporated the Levenberg-Marquardt (LM) algorithm to enhance convergence speed. Ten key parameters—including bench slope angle, geotechnical internal stress, bench height, surface displacement, and pore water pressure—were selected as inputs, with the slope safety factor as the output. Training and validation was performed using 150 field case datasets. The results show that GA-BP model reduces the mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) by 46.9%, 25.4%, and 5.38%, respectively, compared to the conventional BP model. Predictions are closer to the safety threshold (Fs = 1.2), indicating enhanced sensitivity and stability. Pearson correlation analysis confirms strong relationships between surface and internal displacement (0.98) and between pore water pressure and rainfall (0.75), supporting the rationality of the input indicators. The study demonstrates that GA-BP model effectively overcomes local optima and gradient vanishing issues in BP networks, providing a reliable tool for intelligent slope stability assessment.

    Safety distance warning for forklift driving obstacles based on improved YOLOv12
    ZHOU Cheng, DAI Wenjie, WAN Shuhao, JU Likai
    2026, 36(3):  89-97.  doi:10.16265/j.cnki.issn1003-3033.2026.03.1262
    Asbtract ( 49 )   HTML ( 1)   PDF (14971KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to solve the problems of high equipment price and large quantity demand in the existing forklift driving obstacle safety early warning distance measurement, a forklift driving obstacle safety distance early warning model based on image information was proposed. Firstly, based on deep learning technology, Squeeze-and-Excitation(SE) networks channel attention mechanism is introduced, and methods such as replacing the Intersection over Union(IoU) localization loss function with the Adaptive Threshold Focal Loss (ATFL)function are employed to improve the YOLOv12 algorithm for identifying obstacle targets in forklift travel. Secondly, on the basis of the improved YOLOv12 algorithm, the Kalman filter was introduced to improve the motion prediction model. And the distance detection method considering the camera pitch angle was used to accurately obtain the actual distance between different types of targets and the driving fork workshop. Thirdly, the kinematic process of forklift braking and forklift obstacle avoidance was analyzed, and the classification criteria of safe braking distance warning level and safety obstacle avoidance distance warning level were established, respectively. Finally, experiments were carried out to verify the feasibility of the safety warning distance of forklift driving obstacles based on image information. The results show that the real-time distance warning model can accurately identify obstacle targets in real-time and precisely determine the distance to obstacles within the permissible error range, enabling risk-level warning for obstacles during forklift operation.

    Quantitative study on suppression of LNG evaporation and heating vapor by high expansion foam
    YANG Jie, ZHENG Zhizhong, LI Linfeng, LI Yuxing, LIU Yanbin, YANG Guanghui
    2026, 36(3):  98-103.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0142
    Asbtract ( 34 )   HTML ( 1)   PDF (6224KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to effectively reduce the vaporization rate of LNG, three parameters were proposed and weight factors were introduced. Through Taguchi experiments, the quantitative research was conducted on the foaming ratio and stability of high-pressure foams, the amount of LNG leakage, and the height of foam coverage, to investigate their effects on suppressing LNG evaporation and vapor diffusion. The results show that foams with high foaming ratio and good stability are more conducive to reducing the initial volume fraction of vapor, while foams with poor stability are more conducive to vapor diffusion; the leakage volume has a significant impact on the initial volume fraction of vapor, while the foam coverage has a relatively smaller impact on the later volume fraction of vapor accumulation; the foam height has a minor impact on the initial volume fraction of vapor, but has a significant impact on the ease of vapor diffusion; the foam performance and coverage height at different spatial points have different effects on the speed of the decrease in vapor volume fraction; the leakage volume and foam coverage height have different effects on the speed of the decrease in vapor volume fraction 10 minutes after the cessation of adding foam.

    An image-text multimodal intelligent identification method for construction safety hazards in hydropower engineering
    NIE Benwu, CHEN Shu, CHEN Yun, TIAN Xueqi, CAO Kunyu, LI Zhi
    2026, 36(3):  104-112.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0881
    Asbtract ( 46 )   HTML ( 0)   PDF (5011KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To address the problems of incomplete unimodal feature representation and low image-text fusion efficiency in construction safety hazard identification for hydropower projects, an intelligent image-text multimodal intelligent identification method was proposed. First, 12 categories of construction safety hazards were defined according to hydropower construction characteristics, and an image-text multimodal dataset was established. Second, bidirectional encoder representations from transformers (BERT) model and vision transformer (ViT) model were employed to extract hazard text and image features respectively. GFN was then introduced to dynamically adjust the contribution of image and text features and capture cross-modal correlated feature information, while a multi-layer perceptron was used to improve classification accuracy. Comparative experiments were conducted to verify the model's accuracy and reliability. The results show the method optimizes the contribution of multimodal features by enhancing identification stability. The multimodal hazard identification accuracy reaches 84.99%, representing an improvement of 1.73% over the text-based model and 12.24% over the image-based model.. The proposed approach outperforms existing benchmark models in hazard classification and improves the robustness of intelligent hazard identification.

    Applications and challenges of fiber optic sensors in lithium-ion battery safety monitoring
    FU Ju, SHI Jiaji, MA Xingyang, XIE Wenna, XIE Song
    2026, 36(3):  113-120.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0239
    Asbtract ( 49 )   HTML ( 1)   PDF (1742KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To address the inability of existing battery management systems in acquiring internal temperature gradients, structural strain, and gas generation signals in lithium-ion cells, which result in inadequate safety monitoring and early-warning capability against thermal runaway, a systematic review of fiber optic sensors for lithium-ion battery safety monitoring and the challenges they face was provided. First, key safety-related monitoring parameters, including temperature, strain, gas evolution, and electrolyte state, were identified. Second, the principles and characteristics of representative sensing technologies, such as Fiber Bragg Gratings(FBG), Tilted Fiber Bragg Gratings(TFBG), Fiber Optic Evanescent Wave Sensing(FOEW), and Distributed Optic Fiber Sensing(DOFS), were reviewed. Third, the research progress in in-situ temperature and strain monitoring, electrolyte state evaluation, gas detection, and thermal runaway risk identification for each technology was summarized. Finally, major challenges in practical application, including integration compatibility, multi-parameter cross-sensitivity, long-term stability, and cost, were discussed. The survey reveals that fiber-optic sensing enables multi-point, millisecond-scale temperature monitoring with ±0.1 ℃ accuracy, strain mapping at ±0.1 με resolution, in-situ gas detection at 0.12% precision, and electrolyte refractive-index tracking down to 10-3. Feeding these multi-parameter, in-situ, real-time data into advanced algorithms can significantly enhance early-warning capability for lithium-ion battery thermal runaway.

    Linking landslide deformation to triggering factors via isotonic constraints of displacement measurements
    YE Xiao, SHEN Linxuan, YU Yiqiang, ZHAN Wei, ZHU Honghu
    2026, 36(3):  121-129.  doi:10.16265/j.cnki.issn1003-3033.2026.03.1209
    Asbtract ( 153 )   HTML ( 0)   PDF (7521KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To accurately identify landslide deformation characteristics and triggering factors from monitoring data containing excessive noise, this study proposed a noise-reduction method for displacement monitoring data based on isotonic regression. It further established correlation rules linking deformation in different subzones to multi-level hydrometeorological conditions, incorporating time-lag effects. Using the Zhakoushi landslide in Fengjie County, Chongqing as a case study, displacement monitoring data before and after isotonic regression processing were comparatively analyzed to preliminarily investigate deformation patterns at different locations. The time delays between displacement at each monitoring station and rainfall and elevation of reservoir water level were calculated, enabling the extraction of association rules between deformation in these subzones and hydrometeorological factors, thus clarifying long-term deformation characteristics and its triggering mechanism of the landslide. The results demonstrate that the isotonic regression algorithm effectively removes non-physical noise while preserving intrinsic deformation information, considerably enhancing data quality. The landslide movements exhibit significant spatial heterogeneity, with the front part experiencing the most extensive deformation controlled jointly by reservoir drawdown and rainfall, followed by the rear part influenced by topography-enhanced rainfall recharge. The synergistic effect of rapid drawdown of reservoir water (>0.5 m/d) and intense rainfall (>30 mm/d), which generate an outward-directed seepage force and reduce matrix suction, is the primary triggering mechanism for the landslide.

    Unified kinematic modeling theory of water bomb wheel structure of rescue robot
    SHANG Zuen, YANG Peng, MENG Jiyang, LIU Qian, YU Xisheng
    2026, 36(3):  130-143.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0308
    Asbtract ( 38 )   HTML ( 1)   PDF (10713KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To enhance the obstacle-crossing and terrain adaptability of mobile rescue robots in complex environments such as unstructured scenerios and mine disaster roadways, a variable-diameter wheel based on the waterbomb-origami principle was designed. Addressing the limitation of exisiting modeling approaches for waterbomb wheel structures, which rely on a single basic unit, a unified modeling theory was proposed that incorporates square, rectangular and parallelogram units as fundamental elements. By establishing multi-coordinate kinematic models for the wheel axle layer, wheel support layer, and wheel connection layer, and systematically deriving the corresponding constraint equations, a unified description and parametric analysis of the folding and deployment process of waterbomb wheels with different unit configurations was achieved. The variation trends and effective ranges of key state variables during folding and deployment were studied in detail, and deploy ability tests were conducted on prototype robot models fabricated via multi-material 3D printing. The results show that the kinematic modeling method is applicable to waterbomb wheel structures composed of different basic unit types. The maximum deployed diameter obtained from testing is 124.35 mm, with a 2.5% deviation from the design value, and the deployment ratio reaches 2.015. During testing, it was observed that the fold and deployment process of the actual structure closely matches the kinematic model, demonstrating the strong applicability and accuracy of the proposed modeling theory.

    Prediction method of support load in coal mining face based on MTAM-LSTM
    ZHANG Jie, YANG Ke, FAN Chaochen
    2026, 36(3):  144-152.  doi:10.16265/j.cnki.issn1003-3033.2026.03.1821
    Asbtract ( 40 )   HTML ( 0)   PDF (10942KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to effectively predict hydraulic support loads and evaluate the operational status of supports, a hydraulic support load prediction model based on MTAM-LSTM was proposed. The CEEMDAN algorithm was employed to decompose the load data of supports and extract intrinsic mode functions. Redundant components in the intrinsic mode functions were eliminated according to K-L divergence criterion, thereby forming the input sequence for load prediction. An MTAM was constructed to capture the variation characteristics of hydraulic support loads. Static attention generated attention weights for feature information of data, while dynamic attention optimized the focus on different sequence features. Residual learning was introduced to maintain the integrity of feature signals. LSTM networks were then utilized to establish deep dependencies between feature information and hydraulic support loads, enabling advanced prediction of support load data. Field data from the 402102 working face of a rockburst-prone coal mine in Shaanxi were used for empirical validation. RMSE, R2, and MAE were used as evaluation metrics for comparison among different models. The results show that the RMSE and MAE of the MTAM-LSTM model are significantly lower than those of the comparison models, with RMSE reduced by 0.16-0.45 and MAE reduced by 0.16-0.45, while the coefficient of determination R2 reaches 0.91 under different scenarios, thereby validating the prediction accuracy and generalization capability of MTAM-LSTM model.

    Experimental study on influence of ultrasonic stimulation on kinetic characteristics of gas diffusion in coal
    ZHANG Xiaoying, LIN Haifei, YAN Min, WANG Ruizhe, QIU Yue, ZHOU Xing
    2026, 36(3):  153-161.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0456
    Asbtract ( 31 )   HTML ( 0)   PDF (2329KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To further investigate the effect of ultrasonic stimulation on gas diffusion in coal, this study utilized an ultrasonic stimulation test system for gas-bearing coal to analyze variations in gas diffusion under different ultrasonic conditions. Based on the Langmuir-like model, Quasi-first-order kinetic model, and gas dynamic diffusion model, the influence of ultrasonic stimulation on the kinetic characteristics of gas diffusion was systematically examined. Results demonstrate that increased ultrasonic power, elevated frequency, or prolonged stimulation time significantly enhance gas diffusion. Specifically, when ultrasonic power increases from 250 W to 1 000 W, gas diffusion rises from 0.689 mL/g to 0.981 mL/g, with the diffusion rate increasing from 5.92% to 10.69%. Similarly, gas diffusion escalates from 0.739 mL/g at 20 kHz to 1.074 mL/g at 40 kHz, elevating the diffusion rate from 6.36% to 9.65%. Extending stimulation time from 30 min to 120 min boosts gas diffusion from 0.833 mL/g to 1.100 mL/g, increasing the diffusion rate from 8.50% to 12.65%. The gas dynamic diffusion model exhibits the strongest fit for describing gas diffusion behavior under ultrasonic stimulation, followed by the Langmuir-like and Quasi-first-order kinetic models. Both the initial gas diffusion coefficient D0 and its attenuation coefficient β demonstrate identical trends under ultrasonic stimulation, showing exponential positive correlations with ultrasonic power, frequency, and stimulation time. Ultrasonic stimulation enhances the kinetic characteristics of gas diffusion in coal by improving pore connectivity through mechanical vibration and pore-cleaning effects.

    Study on dual-stage exothermic characteristics and critical spontaneous combustion temperature of silicon sludge
    TAO Rundong, BAO Zhiming, HU Cheng, XU Xiaonan, HAO Tianzi, LI Jingjing
    2026, 36(3):  162-170.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0415
    Asbtract ( 48 )   HTML ( 1)   PDF (12621KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To address the frequent spontaneous combustion accidents of photovoltaic silicon sludge, a multi-experimental approach was employed to reveal its dual-stage exothermic characteristics and critical spontaneous combustion size. An isothermal microcalorimeter was used to analyze the heat release sources of silicon sludge under a low-temperature environment of 30 ℃, and to investigate the effects of pH and particle size on heat release characteristics. Simultaneous thermal analysis was applied to investigate the thermal behavior of silicon sludge during the programmed temperature rise process of 40-1 300 ℃, and the flynn-wall-ozawa method was adopted to determine the activation energy of the oxidation stage, revealing the high-temperature reaction mechanism. Based on metal basket self-heating tests and Frank-Kamenetskii theory, the critical spontaneous combustion temperature and critical size of silicon sludge under different ambient temperatures and sample states were calculated. Targeted safety control suggestions for the safe storage and transportation of photovoltaic silicon sludge were proposed. The results show that in the low-temperature stage (30 ℃), the heat release of silicon sludge is dominated by silicon-water and silicon-alkali reactions. The alkaline environment and small particle size can increase the maximum heat release power to 837.5 μW, significantly enhancing the heat accumulation risk. In the high-temperature stage (>405 ℃), the silicon-oxygen oxidation reaction becomes the main heat release source, and the oxidation activation energy decreases from 177 kJ/mol to 141 kJ/mol, with the reaction transitions from interfacial chemical control to diffusion control. The critical spontaneous combustion size of dried silicon sludge, alkali-containing silicon sludge, and silicon sludge with small particle size is significantly reduced, and for every 10 ℃ increase in ambient temperature, the critical spontaneous combustion size decreases multiplicatively. The minimum critical stacking size is 2.2 m at 60 ℃.

    Public Safety and Emergency Management
    Research on multi-objective optimization of forest fire station site selection based on improved NSGA-II
    LI Hua, CHEN Xin, YI Peng, WU Lizhou
    2026, 36(3):  171-177.  doi:10.16265/j.cnki.issn1003-3033.2026.03.1051
    Asbtract ( 31 )   HTML ( 1)   PDF (8376KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to enhance the emergency response capability of the firefighting and rescue teams and the overall efficiency of the forest and grassland fire prevention and control layout, an optimization method for the site selection of forest and grassland fire stations based on hybrid fire prevention emergency roads was proposed. By combining the eight-direction tilt point algorithm with digital elevation model data, a hybrid fire emergency road network was constructed to enhance the fire brigade's early prevention and emergency response capabilities. Subsequently, the location allocation model of the improved NSGA-II was adopted to optimize the site selection of the fire station, ensuring the rational allocation of resources and expanding the coverage. The results show that the coverage rate of the hybrid fire prevention emergency road in the overall area is 96.91%, and the coverage rate in the high-risk area is 93.51%, which improves the ability of the rescue team to deal with complex terrains. The optimized layout of the fire stations has a coefficient of variation of 0.26, ensuring the inspection and response capabilities of the teams. The overall demand satisfaction rate is 0.86, ensuring that the key areas are fully protected. The optimization model proposed in this study can provide a theoretical basis for the layout of forest and grassland fire prevention and control, improve the utilization rate of rescue resources, and promote the precise development of forest fire management.

    Evacuation path numerical simulation for occupants in single-story building fires
    ZHANG Xiaolei
    2026, 36(3):  178-185.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0548
    Asbtract ( 69 )   HTML ( 0)   PDF (8522KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To address the low efficiency and safety of personnel evacuation in fire scenarios amid China's accelerating urbanisation and the increasing number of densely populated venues, a single-story building fire evacuation model based on the A* algorithm was developed. A grid-based model was introduced and combined with the PSO algorithm to comprehensively account for multiple complex factors influencing the evacuation process, including smoke concentration, high-temperature environments, hazardous gas dispersion, and personnel density. Based on the single-story building fire evacuation model, multivariate functional relationships were used to quantify the influence coefficients of various factors on personnel movement velocity, thereby achieving a precise description of the evacuation process. During numerical simulation experiments, the performance of the original and improved A* algorithms was compared across scenarios with varying occupant numbers within the building. The results indicate that compared to the traditional A* algorithm, the improved model reduces evacuation time by 20.9% and path length by 3.27%. It can effectively prevent evacuation paths from falling into local optima and avoid occupants entering dead ends.

    Emergency evacuation bus scheduling for toxic gas leakage scenarios
    LIU Yuanyuan, TAN Zefeng, HAN Shuang, XU Mengting
    2026, 36(3):  186-193.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0113
    Asbtract ( 29 )   HTML ( 0)   PDF (3819KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To improve the efficiency of large-scale personnel evacuation and reduce casualties after toxic gas leakage accidents, a CFD model and wind direction statistical probability were adopted to simulate the spatiotemporal distribution of toxic gas concentrations. Combined with the facilities and personnel conditions of evacuation sites, a dynamic comprehensive risk measurement method for evacuation sites was proposed. First, based on the differences in dynamic comprehensive risks of evacuation sites, a multi-trip emergency evacuation bus scheduling model with splitable evacuation demand was constructed, with the objectives of minimizing evacuation time and total risk expectation. Then, the augmented weighted Chebyshev method was used to convert the multi-objective model into a single-objective model, and a genetic algorithm integrated with adaptive large neighborhood search was designed for solution, in which destruction and repair operators were adopted to improve the search capability of the algorithm. Finally, the rationality of the model and the effectiveness of the algorithm were verified through numerical example analysis.The results show that the emergency evacuation bus scheduling model with the objectives of minimizing evacuation time and total evacuation risk expectation can generate scheduling schemes that prioritize the evacuation of personnel from high-risk evacuation sites, thereby improving evacuation efficiency and reducing the total risk expectation. Compared with the expected total evacuation risk, evacuation time is more sensitive to changes in the latest time window of evacuation sites, and the number of required buses decreases with the extension of the evacuation time window. In comparison with the traditional genetic algorithm, the genetic algorithm integrated with adaptive large neighborhood search can reduce the objective functions by 4.46% and 2.44%, respectively.

    Study on hazard characteristics and onset time of hazard escalation of leakage fires in diesel road tankers
    WANG Jiyun, WANG Zichao, ZONG Ruowen, LIU Xuanya
    2026, 36(3):  194-202.  doi:10.16265/j.cnki.issn1003-3033.2026.03.1528
    Asbtract ( 37 )   HTML ( 1)   PDF (10941KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to prevent and control the fire hazard of a road tanker coupling with diesel leaking and burning, small-scale experiments were first conducted using a 5 L tank filled with 1.65 L of 0# diesel fuel. The diesel was released from the tank bottom and burned, and the temporal evolution of the fuel temperature, tank pressure, thermal radiation, and flame morphology was investigated. Subsequently, numerical simulations of tank thermal exposure were conducted. The results show that once the temperature of leaking diesel reaches 227.8 ℃, the diesel fuel leaking to the external environment will boil and burn. This leads to a sudden escalation of fire hazard, i.e., a sudden increase in the tank pressure, the thermal radiation and flame size. The onset time of hazard escalation increases exponentially with filling level. When the filling level rises from 33% to 80%, the onset time increases by an average factor of 2.32 across different thermal boundary conditions. Flame offset relative to the tank reduces the thermal load on the tank, thereby lowering the diesel temperature-rise rate and increasing the onset time. Moreover, the rising rate of the onset time grows with the flame offset degree. The increase in the onset time provides more available safe egress time (ASET). Thus, ASET increases as both the filling level and the flame offset degree increase.

    Optimization model of forest fire spread based on cellular automata
    QIN Weihao, LIU Quanyi, AI Hongzhou, LIU Jihao, ZHU Pei
    2026, 36(3):  203-211.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0362
    Asbtract ( 62 )   HTML ( 0)   PDF (9125KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To investigate the spread characteristics of forest fires under complex topography and multi-factor coupling conditions, this study develops an optimized forest fire spread model that integrates terrain-slope correction, wind-field effects, and vegetation indices. First, Gaussian filtering was applied to correct the digital elevation model (DEM) to reduce noise, and terrain slope and aspect were derived from the refined DEM. Subsequently, the enhanced vegetation index (EVI) was introduced to improve the forest fire spread prediction model, enhancing prediction accuracy in areas with dense vegetation cover. By combining the model with CA, the predicted fire spread can be visualized. Finally, the predicted fire variable values were compared with the observed data from Muli Tibetan Autonomous County to verify the scientific validity and effectiveness of the model. The results indicate that the model is highly sensitive to vegetation changes in low EVI value ranges, with an effect size of 0.870, suggesting that the introduction of EVI improves fire prediction accuracy in areas with high vegetation cover. The improved fire spread model achieved an area prediction error rate and perimeter error rate of 29.40% and 5.79%, respectively, which are lower than the pre-improvement values of 44.27% and 16.99%. The Kappa coefficient of the improved model is 0.8238, which is closer to 1 compared to the pre-improvement model.

    Optimization of camouflage strategies and Nash equilibrium solution in traffic supervision based on game theory
    DENG Kailong, XU Ting, CHEN Yixin, LIU Wenyu, LAI Xinhe, ZHANG Zhishun
    2026, 36(3):  212-220.  doi:10.16265/j.cnki.issn1003-3033.2026.03.1452
    Asbtract ( 40 )   HTML ( 1)   PDF (5905KB) ( 1 )  
    Figures and Tables | References | Related Articles | Metrics

    Aiming at the problem of traffic offenders evading law enforcement by prejudging regulatory measures, this study explored the interference mechanism of compliance camouflage strategies on the reconnaissance behavior of traffic offenders, to improve the anti-reconnaissance efficiency of traffic management. Based on the dynamic game theory of incomplete information, a sequential decision-making model between managers (government/enterprise) and offenders during the reconnaissance stage was constructed. The signal distortion mechanism was used to quantify the interference effects of four camouflage strategies (honest performance, camouflage government style, camouflage enterprise style, random interference) on the Bayesian belief updating of offenders, and the optimal strategy combination was solved using the refined Bayesian Nash equilibrium. An empirical study was conducted based on the road network of Xi'an High-tech Zone. The results show that differentiated equilibrium conditions exist in four typical scenarios. The government core area strategy increases the post-reconnaissance compliance probability by 82.3%. The enterprise park strategy induces a 40.3% rise in surface reconnaissance behavior. The suburban combination strategy reduces the violation rate by 41.7%. And the transportation hub area maintains a dynamic compliance index of 0.87±0.03. The spatio-temporal evolution demonstrats that the camouflage strategy delayed the convergence period of offenders' beliefs by 42%, drove an exponential decay of the violation rate by 73.7% within 30 days, and achieved an input-output ratio of 194%. This study indicates that, within legal frameworks such as warnings and indications, dynamic camouflage strategies can reverse information disadvantage by interfering with offenders' cognitive decision-making, thereby constructing a "cognitive-spatial-economic" collaborative governance paradigm and promoting the transformation of traffic supervision toward active intervention.

    Disaster Prevention and Mitigation Technology and Engineering
    Meso response mechanism of diorite under loading and unloading conditions
    AN Xuexu, HU Zhiping, WANG Zhenlin, TIAN An'an, ZHANG Yonghui
    2026, 36(3):  221-228.  doi:10.16265/j.cnki.issn1003-3033.2026.03.1000
    Asbtract ( 30 )   HTML ( 0)   PDF (13195KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to explore the microscopic response characteristics of hard rock under the loading and unloading stress paths, the diorite numerical model under 20 MPa confining pressure was carried out by using the PFC3D program. Then, the numerical simulation results were compared with the laboratory test results to verify the reliability of the numerical simulation scheme. On this basis, the change characteristics of micro particle velocity, contact force and tensile shear micro-crack along the axial and radial direction of the model during loading and unloading were studied. The results show that in the pre-peak stage, driven by synergistic effects of terminal energy input and lateral confinement, particle axial velocity exhibits higher values at the ends and lower values in the central region, while radial velocity increases linearly from interior to exterior. Contact normal forces demonstrate enhanced distribution characteristics along both axial (ends > center) and radial (periphery > core) directions, with sustained growth during loading. Tensile cracks dominate damage initiation, concentrating radially near unloading surfaces while distributing uniformly axially. In the post-peak stage, an abrupt reduction of lateral confinement triggers a dramatic particle velocity surge. Disintegration of force chains precipitates rapid decay in contact normal and shear forces. Accelerated propagation of tensile-shear micro-cracks occurs at the mesoscopic level, particularly with shear cracks concentrating and coalescing along double-shear planes, directly precipitating macroscopic bearing-capacity collapse.

    Occupational Health
    Evaluation of employee's psychological stress status using LSTM with attention mechanism
    CAO Haiqing, YAO Zhiying, LYU Shuran, YAO Cuiyou
    2026, 36(3):  229-237.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0432
    Asbtract ( 37 )   HTML ( 1)   PDF (4945KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To safeguard employees' psychological health and improve the accuracy and interpretability of psychological stress evaluation methods, taking multimodal physiological time-series data as the research object, a LSTM with AM(LSTMA) method was proposed to accurately evaluate employees' psychological stress states in the paper. Firstly, using the multimodal physiological time-series data (Blood Volume Pulse (BVP), Electrocardiogram (ECG), Electrodermal Activity (EDA), Electromyogram (EMG), Respiration (RESP), Body Temperature (TEMP), and three-axis Acceleration (ACC)) from the WESAD dataset were adopted as the research carrier, the gating memory mechanism of the modal-specific LSTM modules was utilized to accurately capture cross-time-step temporal dependency features, effectively retain key physiological features strongly associated with psychological states, and filter out short-term random noise, thereby ensuring that the physiological feature data could truly characterize the dynamic evolution of employees' psychological states. Secondly, after feature fusion, the attention mechanism was introduced to adaptively assign attention weight coefficients based on the feature importance of physiological data across different modalities and time steps, enhancing key features and micro-response features sensitive to psychological stress states while suppressing the interference of redundant information. Finally, the accurate evaluation of psychological stress states was accomplished through a fully connected neural network. Experimental results show that the LSTMA method achieves an evaluation accuracy of 94.56% for the four-classification task (neutral, stress, pleasure, and meditation) of psychological stress states. After Leave-One-Out Cross-Validation (LOOCV), the accuracy is improved to 98.08%. Ablation experiments verify the synergistic enhancement effect of the modal-specific LSTM and the attention mechanism, and model interpretability analysis further confirms the scientificity and rationality of LSTMA.

    Muscle fatigue characteristics of mine rescue personnel during pull-down dynamometer training
    MENG Yunchen, YU Liuhuan, YANG Sanjun, YE Maosheng, WU Fang, CHEN Qiangsheng
    2026, 36(3):  238-246.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0375
    Asbtract ( 39 )   HTML ( 0)   PDF (8482KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    This study analyzes the muscular fatigue characteristics of mine emergency rescue personnel during pull-down dynamometer training, aiming to provide scientific support for enhancing the safety and efficiency of mine emergency rescue training. Forty team members from the Datong National Mine Emergency Rescue Team were selected as participants. sEMG technology was used to record changes in muscle activation, muscle contribution rates, root mean square(RMS) amplitude, and MF under standardized pull-down dynamometer training conditions. The results indicate that the triceps and latissimus dorsi are the primary force-generating muscles, while the erector spinae plays a critical role in movement restoration and trunk stabilization. As the number of repetitions increases, the triceps brachii begins to appear fatigue in the second half of training. To maintain the training, the latissimus dorsi and erector spinae show enhanced compensatory activation, and the lower segment of the erector spinae exhibits a higher activation level while showing significant fatigue characteristics. This compensation pattern driven by triceps fatigue is the key inducement for increased lumbar load and elevated injury risk in rescue personnel. It is suggested that the strength endurance of triceps brachii and the stability control and anti-fatigue ability of core muscles should be strengthened in training.

    Study on particulate matter blocking performance of firefighter protective suits
    YANG Xinyu, SONG Yuhan, ZHAO Jiaxuan, LIU Xiaoyong
    2026, 36(3):  247-254.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0733
    Asbtract ( 39 )   HTML ( 0)   PDF (3933KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    To quantitatively evaluate the particle matter barrier performance of different firefighter protective clothing, a test platform was established using a high-precision environmental chamber and a particle generation device. Aerosol mixtures of sodium chloride, dioctyl sebacate and titanium dioxide particles were released to simulate a smoke-filled fire environment. The inward leakage rate was calculated based on the particle matter concentration distribution inside and outside the garments, allowing a quantitative assessment of the particle matter barrier performance of 4 types of protective clothing. The results demonstrate that firefighting garments and emergency-rescue suits provide inadequate protection for the upper and lower extremities. The light-duty chemical protective coverall exhibits the best overall performance, with an average total inward leakage rate of 4.69%, representing a 92.4% reduction compared to the control group. It demonstrates excellent protective capability. However, all four types of protective clothing are ineffective at blocking small particles with diameters of 0.3-1.0 μm.

    Intelligent Safety Technology
    Driver cognitive state recognition in autonomous driving takeover decision making
    SHAO Shuyu, LI Yanping, HAN Jiaqi
    2026, 36(3):  255-263.  doi:10.16265/j.cnki.issn1003-3033.2026.03.0912
    Asbtract ( 49 )   HTML ( 1)   PDF (5187KB) ( 0 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to address the issue of human-machine collaboration failure in the takeover decision-making of autonomous driving and achieve precise recognition of the driver's cognitive state, this paper simulates three typical scenarios, night high-speed curves, mobile phone distracted driving, and combined scenarios of strong light and heavy rain, collecting and analyzing the dynamic interaction data of driving behavior and eye movement features construct a dynamic weight allocation(DWA)distribution feature fusion framework for multimodal perception and cognition collaboration, constructed DWA-RF model, and explore the dynamic mechanism of the driver's cognitive state and takeover decision-making behavior in complex environments. The results show that the distracted state significantly prolongs the takeover time. In scenes of strong light and heavy rain, the superimposition of distraction and environmental pressure leads to a sharp reduction in the range of scanning. Fatigue causes an increase in lane departure distance, accompanied by a reduction in pupil diameter and abnormal scanning behavior. The cognitive state classification accuracy of DWA-RF constructed in this paper has reached 93.6%, verifying the effectiveness of this model in identifying the driver's cognitive state for autonomous driving takeover decisions.