Development Of Law Research Articles

Study on the influence of temperature on the damage evolution of hot dry rock in the development of geothermal resources

In order to more accurately understand the rock mechanics properties of hot dry rock (HDR) reservoirs under high-temperature conditions and further guide the drilling and construction of HDR wells, conducting research on rock damage evolution under high-temperature conditions plays a guiding role in the efficient development of geothermal resources. To reveal the evolution law of fracture damage of HDR under temperature influence, taking marble as an example, the thermo-mechanical damage and failure mechanism under the conditions of 30 °C, 60 °C, 90 °C, 120 °C and 150 °C were studied using a rock high-temperature rheometer and an acoustic emission (AE) testing system. The numerical simulation results were compared with the indoor experimental results by combining the particulate flow program Particle Flow Code 3D (PFC3D) to verify the effectiveness of the simulation analysis model of thermo-coupled particulate flow at the micro scale. The results show that under high temperature, the marble three-axis compression failure passes through the compaction and elastic deformation stage, plastic deformation stage, ductile failure stage and instability failure stage, and the peak strength and elastic modulus of the marble decrease with the increase of temperature, and the acoustic emission b-value of the sample can judge the damage evolution process of the marble. At the micro scale, high temperature accelerates the force chain transmission between particles, the contact force between marble particles gradually decreases during the heating process, and the number of particle bonding failures increases steadily; the bearing capacity and elastic modulus attenuation of the rock are the result of microcrack evolution, and the force chain void zone and particle displacement field inside the sample are consistent with its macroscopic failure form. The development of microcracks in marble under different test loading conditions is different, and with the increase of test temperature, the total number of cracks inside the sample increases, but the proportion of shear cracks decreases, the activity of particle displacement increases, and the “plastic extension” characteristic of marble becomes more significant. The thermal damage evolution of marble was quantitatively analyzed based on the elastic modulus method and the peak stress method, and the damage evolution law of marble under different temperatures was obtained.

Adsorption mechanism of Cd2+ on solid waste–based PRB composite filler and pore structure dynamic evolution laws

In this study, a composite granular filler (CGF) was prepared primarily using steel slag, fly ash, and desulphurization gypsum to remedy the default of expensive, passivation, and ease of failure for the traditional permeable reactive barrier (PRB). The adsorption characteristics of the CGF on Cd2+ were investigated by the static adsorption, and the strength loss and scatter ratio were clarified with an immersion test. Dynamic adsorption and visualization modeling were used to determine the primary factors influencing adsorption and the evolution laws of material corrosion and pore clogging. Various characterization methods were used to research the adsorption mechanism. The results showed that the CGF fit with the pseudo-second-order kinetic model and Langmuir model, and the optimal adsorption capacity reached 8.64 mg/g; the minimum ratio of scatter and strength loss were 4.95% and 6.16%, respectively. The pump speed greatly influenced the breakthrough curves. The maximum dynamic adsorption capacity reached 1.81 mg/g, and the Thomas model described the adsorption behavior well. After adsorption, the porosity increased by 7.79%, and clogging in the middle of the column was not serious. The connected pores still accounted for 99.48%, and the pore network model (PNM) maintained excellent connectivity. Hydration products generated in the CGF ensured strength and durability, and they also benefited the adsorption of Cd2+ through ion exchange, co-precipitation, and surface adsorption. This research provides a new solid-waste resource utilization method for heavy metal removal in groundwater and a theoretical basis for the long-term purification of PRB with good potential for application and economic benefits.

Investigation on Cryogenic Cavitation Characteristics of an Inducer Considering Thermodynamic Effects

An inducer is a key component in a cryogenic pump to improve its cavitation performance. The thermodynamic effects of the cryogenic medium make the cryogenic cavitation flow extremely complicated. For this reason, it is crucial to investigate the cryogenic cavitation flow of the inducer which is equipped upstream of the cryogenic pump. In this paper, the isothermal cavitation model is modified based on the law of heat conduction, and the cryogenic cavitation model of the inducer is developed by considering thermodynamic effects. The turbulence model is also modified to account for the compressibility of cryogenic cavitation flow. The methods of numerical calculations are performed to investigate the influence of thermodynamic effects on cryogenic cavitation of the inducer. The law of the spatio-temporal evolution of cryogen cavitation in the inducer is clarified. The initial position, development and collapse phenomenon of cavitation are obtained. The relationship between the generation and collapse of the cavitation and the work capacity of the inducer’s blade, the relationship between thermodynamic effects and the influence of the inducer’s blade tip leakage vortex and thermodynamic on cryogenic cavitation of the inducer are revealed.

Exploration of the behavior and evolution features of beam-column joints with T-stub using the structural strain energy method

Based on the structural strain energy method, the work behavior of four T-stub connection joints under cyclic loading is analyzed to visualize their working behavior and failure evolution. The experimental strain data are modeled as generalized strain energy density (GSED) to characterize the structural stress state and the corresponding characteristic parameters, and the Mann-Kendall (M-K) criterion is formulated to determine the performance characteristic points (P and Q) of the joint Mj-Ej curves and to derive the starting point of structural continuity damage. Then, by analyzing the parameters of the joint working state (strain, deformation, joint energy dissipation, connection stiffness, bolt force and pry force), the trends of the joint stressing state curves before and after the critical loading are reflected. Finally, the feature point data interpolation (EDI) method is introduced to effectively expand the joint test data, visualize the change process of the strain/stress field, and deeply reveal the mechanical response mechanism and evolutionary degradation law behind it. The contribution of the above work is to quantitatively identify the P and Q characteristic points in the changing trend of the joint working state, to reveal the mechanical mechanism and the failure degradation law from the perspective of energy evolution, and to visualize the mutation of the field data before and after the P/Q using the EDI method, which is a generalized method that can be applied to the other progressive failure structures.

Applying network-free renormalization and clustering algorithms to reveal the crack evolution laws of laterally loaded composite T-joints

Delamination or crack are standard failure patterns of composite T-joints. Most existing studies focus on pull-off loaded composite T-joint cracking but little focus on adverse conditions such as lateral loading. The mainstream composite T-joint research predicts the macroscale failure based on the composite’s microscale/mesoscale crack starting and evolution. However, the cracking process is within the microscale, mesoscale, and macroscale, making detecting its starting based on phenomena complicated. This work attempts to directly model the macroscale deformation distribution from a thermodynamic perspective to reveal the cracking/failure evolution of a laterally loaded composite T-joint. Firstly, we conducted eight laterally loaded composite T-joint tests with different molding processes. Then, network-free renormalization was applied to construct Matrices (Modes) and Hamiltonians (Characteristic parameters) that can characterize their cracking evolution process. Further, a clustering algorithm was applied to reveal the cracking starting points (phase transition loads) embedded in the macroscale deformation distribution. We can verify its rationality by comparing the composite T-joints localized and systematic phase transition loads based on Wilson’s phase transition theory. In summary, this work applies network-free renormalization and clustering algorithms from a thermodynamic perspective to reveal the cracking starting point embedded in the macroscale deformation distribution of the laterally loaded composite T-joints.

Damage evolution in layered rock masses of a mining floor under the influence of fluid–structure coupling

AbstractCurrent research on rock damage in mining floors primarily focuses on the seepage‐stress coupling effect, overlooking the fact that rock masses in coal measure strata are predominantly layered. To address this gap, cyclic loading and unloading triaxial tests were conducted. Additionally, theoretical analysis, mathematical statistics, and other methods were used to investigate the damage evolution law of layered rock masses in coal measures. This investigation was carried out under the coupled effects of a specific stress path, characterized by ‘stress concentration‐stress unloading‐stress recovery’, and a high confined water seepage field. The results show that the compression modulus increases with the increase in confining pressure and osmotic pressure, but its increasing trend gradually slows down. Within a certain range, increasing the confining pressure and osmotic pressure helps to close rock fractures and increase stiffness.

Fracture modeling of CNT/epoxy nanocomposites based on phase-field method using multiscale strategy

The computational modeling of fracture, particularly in structures with complex crack topologies, remains challenging due to significant computational costs, especially in simulating two- and three-dimensional brittle fracture. This study presents an efficient phase-field model to address these challenges. By leveraging the user (UMAT) subroutine in ABAQUS and establishing an analogy between the phase-field evolution law and the heat transfer equation, the method efficiently tackles complex fracture problems. The model is verified through analysis of typical 2D and 3D fracture benchmarks with different failure modes, demonstrating accuracy and efficiency compared to experimental and numerical data. Additionally, the model is applied to explore brittle fracture in carbon nanotubes (CNTs)/epoxy nanocomposites, revealing insights into the impact of CNT weight fraction on fracture phenomena prediction. The incorporated CNTs in the matrix are considered uniformly dispersed and randomly oriented. Overall, the developed model and computational implementation show promise for meeting the requirements of structural-level engineering practices.

Multiaxial ratcheting-fatigue evaluation of pressurized elbow pipe under strong cyclic loading using damage-coupled cyclic plasticity model

Continuous damage mechanics (CDM) is based on the theories of continuous medium mechanics and continuous medium thermodynamics, which considers damage is an irreversible dissipative process within the materials, and employs the field-theoretic approach of image-only science to study the internal macroscopic damage evolution law of the materials and its influence on the deterioration of the macroscopic mechanical properties of the materials. Hence, within the framework of CDM, a damage-coupled cyclic plasticity constitutive model is proposed based on combined isotropic and Chen-Jiao-Kim (CJK) kinematic hardening rule for evaluating the ratcheting-fatigue behavior of 90° elbow pipes under strong cyclic loading in this paper. Stress return mapping and numerical solution procedures of the proposed model are formulated based on the backward finite difference method. Formulation of the consistent tangent operator is presented for the Finite Element implementation of the plasticity model in ABAQUS UMAT. The FE analysis of non-pressurized and pressurized elbow pipes under cyclic displacement-controlled loading is respectively performed using the implemented constitutive model. The results reveal that the predicted results of the damage-coupled cyclic plasticity constitutive model are better than combined isotropic-kinematic hardening model, and well consistent with the experimental data.

Energy evolution and damage model of sandstone under seepage-creep-disturbance loading

The geological environment of deep coal seam is complex, and the failure mechanism of coal seam under the action of seepage pressure and disturbance stress is unclear, which restricts the development of deep ground engineering. In this study, triaxial compression test of sandstone under seepage-creep-disturbance loading (SCD) was carried out to analyze the characteristics of disturbance deformation, creep rate and permeability. The focus was on the energy evolution law of sandstone under SCD, and the damage creep model was constructed based on the energy proportion. The results show that the creep increment of sandstone under disturbed load was significantly higher than that under undisturbed load, and the stress level can promote the expansion and development of microcracks, in which the creep increment under high stress level showed a jump increase. The total energy and elastic energy of sandstone showed a step change with time. The damage factor under disturbance load was defined in the form of energy dissipation ratio, and the corresponding coupling damage factor was determined by considering the seepage factor and creep factor, which can reflect the coupled damage deformation of sandstone under SCD. Based on fractional order theory, a nonlinear damage creep model describing sandstone deformation under SCD was established by connecting the acceleration element in series with the Nishihara model and introducing the coupling damage factor. This study can provide research ideas for water inrush of coal seam rock mass.

Tribological behavior of graphene/h-BN vdW heterostructures: the role of defects at the BN layer

Molecular dynamics simulations and first principles calculations were performed to study the tribological behavior of graphene/h-BN (G/h-BN) heterostructures with vacancy and Stone–Wales (SW) defect under uniform normal load, revealing the mechanism of the effect of defect types on friction, and discussing the coupling effect of temperature and interfacial defects on the tribological behavior of G/h-BN heterostructures. Under the normal force of 0.2 nN/atom, the friction force of the four systems is 0.0057, 0.0096, 0.0077, and 0.26 nN, respectively. The friction force of SW defect heterostructure is 45 times that of perfect interface heterostructure. The influence of defect type on friction force is SW > SV > DV. By observing the dynamic change of the Z-direction coordinate position of the sliding layer atoms, the slip potential energy curves and the evolution law of the moiré pattern, the relationship between the structural morphology and the energy change of different defective heterostructures and the frictional behavior was investigated comprehensively and intuitively for the first time. From the perspective of atomic strain, the deformation of heterostructures at the atomic level was quantified. The results showed that at 300 K and 0 K, the maximum strain of atoms in the sliding layer was 11.25% and 9.85%, respectively. The thermal perturbation mainly occurs in the out-of-plane direction, which in turn affects the friction. Through density functional theory, it is found that under uniform load, it is difficult to form bonds between the graphene sliding layer and the substrate layer when the defects are in the h-BN substrate layer, which has less influence on the friction of the system, thus making the defective heterostructures also remainsuperlubricity state. These results provide a new understanding of the interfacial friction of G/h-BN defective heterostructure.

Energy hub management for integrated energy systems: A multi-objective optimization control strategy based on distributed output and energy conversion characteristics

To improve the comprehensive utilization efficiency of energy, a multi-objective optimization control strategy applied to the energy hub (EH) within the system is proposed to address the electrical and thermal load distribution of the integrated energy system (IES) and the low-carbon economic operation. First, a model of the electrical and thermal energy outputs is established based on the characteristics of the IES network and the multidimensional “load parameter” evolution law. Moreover, a distributed control strategy is proposed that utilizes the information interaction between neighboring EHs to accurately share the electrical and thermal loads, which reduces the communication burden of the system while avoiding overloads. Furthermore, to coordinate the optimal operation of the devices within the hub, based on the energy conversion characteristics of the EH, a multi-objective optimization model is proposed that considers low-carbon and economic aspects to realize efficient energy use. Simulation results show that the proposed strategy effectively improves the robustness of the system while realizing proportional load distribution and low-carbon economic operation. Under the same load, when focusing on system economics, the operating cost is 2.182/¥ lower than when focusing on low-carbon systems, but carbon emission is 1.6753/kg CO2 higher.

Study on the Fracture Extension Pattern of Shale Reservoir Fracturing under the Influence of Mineral Content.

This study aimed to investigate the effect of the microstructure of shale on fracture initiation and extension during hydraulic fracturing. The Longmaxi Formation shale reservoir in the Sichuan Basin was considered as the research object; its structure was modeled from a microscopic perspective, and a zero-thickness cohesive unit was embedded within the solid unit. Numerical simulations were performed to study the effect of mineral content on the microextension of the hydraulic fracture, extension behavior, and evolution law of shale. The results showed that changes in the mineral content resulted in changes in the forces between molecules within the minerals, which, in turn, affected the shale's brittleness. The percentages of brittle mineral content in the Long I, II, and III reservoir sections are 60.37, 47.60, and 53.56%, respectively. The fracture initiation pressures of the three reservoirs were 29.22, 31.42, and 30.22 MPa, respectively, and a linear correlation was found between the fracture initiation pressures and the brittle mineral contents of the reservoir sections. An increase in the reservoirs' percentage of brittle mineral content facilitated the fracture initiation, with a corresponding gradual decrease in the resistance to fracture initiation. The pore pressures of the fractures in the three reservoirs after fracture initiation were 0.90, 1.18, and 1.00 MPa, respectively. The larger the percentage of brittle minerals was, the lower was the fracture pore pressure. The greater the length, number, area, and width of the cracks were, the more likely they were to form longer and wider cracks. Hence, reservoirs with a high percentage of brittle minerals should be prioritized as the target formations for hydraulic fracturing operations. The results of this study reveal how the mineral content affects the extension of microscopic hydraulic fractures in shale reservoirs. As such, this work can provide a theoretical basis for rationally selecting a hydraulic fracturing operation layer in shale gas reservoirs.

Evolution and deposition patterns of turbidity currents under complex vegetation canopies

Understanding the flow-vegetation-sediment feedback mechanism is critical for ecological restoration of gently sloped landscapes. Numerous simulation or laboratory experiments on turbidity currents over vegetation have revealed the important roles of vegetation canopy morphology and structure in this feedback mechanism. However, there is still a lack of analysis on the related physical processes. This study investigated the evolutionary characteristics and sediment transport and deposition patterns of turbidity currents with different sediment size distribution in vegetation patches of different canopy morphologies through lock-exchange experiments. The roles of vegetation leaf morphology and canopy structure were explored by varying the leaf morphology and vegetation density with turbidity currents prepared using sediment samples configured with different particle sizes, which are more compatible with natural conditions. The kinetic characteristics and sediment distribution of the turbidity currents over vegetation were simultaneously analyzed, providing a new perspective for updating the methodology in laboratory experiments. The major findings of this study can be summarized as follows: 1) the general spatiotemporal evolution law of turbidity currents is applicable to complex vegetation canopy morphology; 2) canopy structure dominated by leaf morphology is an important influencing factor that needs to be taken into account in the research on vegetation resistance; and 3) the correlation between turbidity current momentum and suspended sediment transport decreases under complex conditions, and coarse-grained suspended sediment tend to limit the movement of turbidity currents and major deposition distance of the sediment. These findings can provide theoretical support for conservation of floodplain soil and water and restoration of watershed ecology.

Public Opinion Evolution Law and Sentiment Analysis of Campus Online Public Opinion Events

Public Opinion Evolution Law and Sentiment Analysis of Campus Online Public Opinion Events

Study on Catastrophic Evolution Law of Water and Mud Inrush in Water-Rich Fault Fracture Zone of Deep Buried Tunnel

Study on Catastrophic Evolution Law of Water and Mud Inrush in Water-Rich Fault Fracture Zone of Deep Buried Tunnel

Study on pore structure evolution and water damage of asphalt mixture under cyclic loading

For a long time, the water damage issues of asphalt mixture pavements have been highly regarded by engineers. However, the existing research is difficult to accurately describe the fatigue damage process of asphalt mixture under hydrodynamic pressure environments. In order to reveal the influence of water damage on the asphalt mixture structure and its mechanism, this study combined low-field NMR technology to investigate the evolution law of asphalt mixture pore structure under cyclic loading with different parameters. The erosion effect of the coupled loading-dynamic water environment on asphalt mixtures and their failure mechanisms are analyzed. The results show that the initial damage dominated by harmful pores and major-harm pores provides space for water migration and storage, and improves the sensitivity of asphalt mixture to water damage. Under the action of repeated cycles of stress increase-decrease, the irreversible hydrodynamic extrusion-cracking and friction-stripping deformations in the asphalt matrix increase. The micro-cracks inside the materials continue to expand and the pores are interconnected. To comprehensively consider the influence of initial porosity, maximum cyclic stress and the number of cycles, the cumulative damage model of the material is optimized based on the mechanism of pore structure evolution, and obtained more accurate porosity prediction results. This study can provide scientific reference and guidance for solving the problem of asphalt pavement disease and durability design.

Evolution and prediction of rural ecological environment quality in eastern coastal area of China

Introduction: Rural ecological environment construction, as a pivotal component of the rural revitalization strategy and ecological civilization construction strategy, plays an indispensable role in promoting sustainable agricultural development and safeguarding ecological security. An accurate assessment and prediction of Rural Ecological Environment Quality (REEQ) serves as the theoretical basis to achieving these goals, and provide scientific guidance for future rural ecological environment construction and planning. The field of regional ecology, proposed in the mid-20th century, represents an emerging interdisciplinary domain that integrates ecology, geography, and economics. It plays a pivotal role in addressing large-scale ecological challenges and fostering social sustainability. As global urbanization continues to advance, urban ecological environments undergo significant transformations under the pressures of intense human activities. Scholars have increasingly focused on the essence, evolutionary patterns, and causal mechanisms shaping urban ecological environment quality. Consequently, ecological environment assessments have evolved from singular pollution evaluations to comprehensive ecological appraisals. However, coastal rural area with complex geographical conditions and fragile ecological environments are often neglected and marginalized. Currently, there are few specialized evaluation systems for REEQ, making it difficult to accurately reveal the evolution pattern of rural ecological environment. This weakens its guidance on practical rural ecological environment governance and restoration.Methods: The Pressure-State-Response (PSR) model can simplify the identification process of driving factors for REEQ, reflect the feedback mechanism between indicators, and is conducive to scientific and accurate evaluation of REEQ. Therefore, we constructed an evaluation index system for REEQ based on the PSR. We measured REEQ in the eastern coastal area of China, analyzed its spatiotemporal characteristics and development trends, and used the obstacle degree model to identify obstacle factors. It is beneficial for rural areas to grasp the evolution laws of REEQ, provide theoretical basis for the formulation of sustainable development policies, and provide scientific policy recommendations.Results: Our findings indicate that: 1) From 2000 to 2020, REEQ in the eastern coastal area of China has continuously improved, with the index value increasing from 0.454 to 0.525, a total growth of 15.64%. The number of high-level REEQ areas increased from 0 to 29, showing a positive development trend. 2) High-density areas of REEQ in the eastern coastal area of China are concentrated in the northern parts of Guangdong and Zhejiang provinces. The center of REEQ has shifted from the southwest to the northeast. 3) The obstacle degrees of various criteria layers in REEQ are relatively stable, with the response subsystem being the highest, followed by the state and pressure subsystems. Forest coverage, per capita grain production, effective irrigation rate of farmland, afforestation area in the current year, per capita disposable income of rural residents, and per capita mechanical power of farmers are the main obstacle indicators. 4) From 2020 to 2035, REEQ in the eastern coastal area of China will continue to improve. The standard deviation ellipse will move towards the northwest, the center will shift from the southwest to the northeast, the rotation angle will slowly decrease, showing a northwestward trend.

Study on Fracture Evolution and Water-Conducting Fracture Zone Height beneath the Sandstone Fissure Confined Aquifer

Studying the evolution law of overlying rock fissures and predicting the development height of water-conducting fissure zones is the key to preventing roof water damage, protecting mine water resources, and realizing the safe and sustainable development of the mine. To study the overburden fracture evolution law of coal mining under aquifer conditions, the 1402 working face of Longwangzhuang Mine in Shaanmian Coalfield serves as the engineering background based on the Fractal Theory and similar simulation technology; this paper analyzes the fracture evolution of overburden rock and the development law of Water-Conducting Fracture Zone (WCFZ) during the advancing of working face, and further puts forward a model for the location discrimination of overburden fracture based on plate theory. The results indicate that post-mining, overburden rock failure assumes a trapezoidal shape, and fractures around the cutting hole and the side of the working face fully develop, while those in the middle of the goaf tend to compact. The distribution of the fracture network of mining strata at different advancing distances has good self-similarity, and the fractal dimension of the fracture network of overlying rock can be divided into three stages: ascending dimension, decreasing dimension, and stable phase. The II 1 coal seam fracture does not spread to the Sandstone Fissure Confined Aquifer. These findings provide strategic guidance for protecting mine aquifer water resources, preventing and controlling roof water inrush, and ensuring safe and sustainable production within the study area.

Experimental study on creep-fatigue damage of hot central plant recycling asphalt mixture containing high RAP

The objective of this study is to delve into the nonlinear damage evolution mechanism of hot central plant recycling asphalt mixture under the influence of creep-fatigue interaction. A predictive model for lifespan, considering the interaction of temperature and load, was developed. Dynamic creep tests were conducted at different temperatures to assess the creep effect of the asphalt mixture under actual road temperature conditions. The investigation began by acknowledging the material's viscoelastic properties, thereby deriving the loss compliance value - a key indicator of temperature effects - using an equivalent conversion factor and a viscoelastic mechanics model. This allowed for the incorporation of creep behavior into the load system. Furthermore, to analyze the nonlinear damage mechanism and fatigue prediction mechanism, direct tensile fatigue tests were performed at different temperatures and different stress levels. The fatigue damage evolution law of hot central plant recycling asphalt mixture containing high RAP considering the creep effect was revealed, and the fatigue life evaluation method under the combined action of temperature and stress level was proposed. The results show that the fitting degree of the time-temperature conversion equation and the viscoelastic mechanics model to the test data is more than 0.9, and the derived loss compliance value better captures the creep effect. Based on the nonlinear creep-fatigue damage model, the damage law of high-RAP hot central plant recycling asphalt mixture was identified. The optimized fatigue life prediction model fully considers the combined effect of temperature and stress level and analyzes the influence parameters of the real state of pavement fatigue. The prediction accuracy is within the requirements of engineering applications. The model's predictive accuracy meets the criteria for engineering applications, enhancing the multifaceted damage coupling analysis approach for hot central plant recycling asphalt mixture and predict the service life of recycled pavements under complex conditions, establishing a groundwork for the prediction and assessment of long-lasting recycled pavements.

Micro-expression recognition based on a novel GCN-transformer cooperation model for IoT-eHealth

If a person is truly healthy, his/her well-being encompasses both physical and psychological health. However, the existing IoT-eHealth system typically focus only on monitoring the user’s physical data through various sensors, neglecting their mental state. To enhance the intelligence level of IoT-eHealth system and enable it to have the psychological monitoring ability, a novel collaborative model based on Graph Convolutional Network (GCN) and Transformer is designed for Micro-Expression (ME) recognition in this paper. Firstly, facial information within each frame is transformed into a Spatial Topological Relationship Graph (STRG) by using facial landmarks detection and psychological relationship of local patches. Then, in order to automatically aggregate the key information on facial patches that contribute to ME recognition from the structured graph data, a Hierarchical Adaptive Graph Pooling (HAGP) module is designed for obtaining discriminative frame-level feature based on GCN utilizing graph structure and vertex global dependencies. Finally, in order to model the long-term dependencies among frames and capture the key frame-level features that are beneficial for ME recognition, a Temporal Sensitive Self-Attention (TSSA) mechanism is designed, and a novel Temporal Sensitive Transformer (TST) encoder is constructed based on TSSA to explore the evolution law of facial patterns and obtain discriminative video-level features that are helpful for ME recognition. In the comparative experiments of standard dataset verification and practical dataset testing, designed collaborative model is superior to other methods and can achieve the highest recognition accuracy, which almost can meet the application requirements of IoT-eHealth system.