In reality, the structure of most graphs could be noisy, i.e., including some noisy edges or ignoring some edges that exist between nodes in practice. To solve these challenges, a novel differentiable similarity module (DSM), which boosted node representations by digging implict association between nodes to improve the accuracy of node classification, was presented. Basic representation of each target node was learnt by DSM using an ordinary graph neural network (GNN), similar node sets were selected in terms of node representation similarity and the basic representation of the similar nodes was integrated to boost the target node’s representation. Mathematically, DSM is differentiable, so it is possible to combine DSM as plug-in with arbitrary GNNs and train them in an end-to-end fashion. DSM enables to exploit the implicit edges between nodes and make the learned representations more robust and discriminative. Experiments were conducted on several public node classification datasets. Results demonstrated that with GNNs equipped with DSM, the classification accuracy can be significantly improved, for example, GAT-DSM outperformed GAT by significant margins of 2.9% on Cora and 3.5% on Citeseer.

Aiming at the limitation that static knowledge graph representation learning methods cannot model time, a temporal graph representation learning method based on relational aggregation was designed to describe and reason about the temporal information of dynamic knowledge graphs from the demand of practical applications. Different from the discrete snapshot temporal neural networks, temporal information was treated as a link property among entities. A time-aware relational graph attention encoder was used to learn entity representations of temporal knowledge graphs, while the neighborhood relations and time stamps of central nodes were incorporated into the graph structure, and then different weights were assigned to aggregate temporal knowledge efficiently. Results of running on public datasets showed that, compared with traditional temporal graph encoder frameworks, the attention aggregation network had a strong competitive advantage in the performance of both the complementation and alignment tasks, especially for highly time-sensitive entities, reflecting the superiority and strong robustness of the algorithm.

A news recommendation method based on Transformer and knowledge graph was proposed to increase the auxiliary information and improve the prediction accuracy. The self-attention mechanism was used to obtain the connection between news words and news entities in order to combine news semantic information and entity information. The additive attention mechanism was employed to capture the influence of words and entities on news representation. Transformer was introduced to pick up the correlation information between clicked news of user and capture the change of user interest over time by considering the time-series characteristics of user preference for news. High-order structural information in knowledge graphs was used to fuse adjacent entities of the candidate news and enhance the integrity of the information contained in the candidate news embedding vector. The comparison experiments with five typical recommendation methods on two versions of the MIND news dataset show that the introduction of attention mechanism, Transformer and knowledge graph can improve the performance of the algorithm on news recommendation.

The segmentation model construction and training based on single source data may lead to insufficient segmentation accuracy due to the defects of various imaging methods in medical images. Aiming at this problem, a medical image segmentation method based on multi-source information fusion was proposed. The FFDM and DBT data sources in the breast tumour microcalcification cluster lesion were used as examples to verify the effectiveness of the proposed method. The Yolov4 region candidate network was used to screen the suspicious regions of the FFDM data. DBT image was preprocessed by using the suspicious region information. The preprocessed DBT image was used as the input of the improved U-Net model to achieve lesion segmentation. Finally, through the fusion strategy of fault segmentation results based on sequential similarity discrimination, the multi-slice results in DBT were combined to complete the final lesion segmentation. True positive rate of 98.52%, false positive rate of 10.45% and accuracy of 94.07% were obtained from the FFDM and DBT data of 20 patients by using this method. Results show that the medical image segmentation method based on multi-source information fusion can effectively utilize the advantages of multi-source data, and achieve the rapid and accurate segmentation of lesions. The method can provide a novel solution for intelligent medical image diagnosis and treatment.

A refrigerant-based battery thermal management system with compact structure and high heat efficiency was proposed in order to solve the heat dissipation problem of high specific energy and superior energy density power battery. The coupling model of air-conditioning and battery thermal management was constructed by AMESim based on the whole vehicle system. The temperature drop and temperature uniformity of the single cell and battery module, the system’s COP and exergy efficiency were analyzed from the point of view of system temperature response characteristics and system energy consumption. Results show that the refrigerant-based system has a fast temperature response characteristic. The battery can be quickly cooled, and a better temperature uniformity under high temperature and high speed steady state and dynamic conditions can be achieved. The energy analysis was conducted for a stable working condition, and a higher system energy efficiency ratio with a COP of 4.19 was obtained. The exergy efficiency of system was 46.17%, and there’s the promotion space of system exergy efficiency.

The surrounding fictitious soil pile model was proposed to simulate the interaction between pile and pile soil plug, and the vertical dynamic model of the pile and cement soil plug was built, considering the strong cohesiveness between the pile and inner cement soil. The analytical solution in the frequency domain and the semi-analysis in the time domain of dynamic response of pile top under simple harmonic excitation were derived by impedance function transfer method. The reliability of the solution was verified by comparing with that of 3D finite element model. A parameter study was conducted to investigate the influence of cement soil parameters on the dynamic characteristics at pile top. Laboratory tests on cement soil and field tests were performed to investigate the influence of inner cement soil on low-strain test curves of pile, and the key parameters in the model were fitted and inverted based on the measured curves. Results show that the reflection signal from the pile tip becomes weaker and the integrated velocity of the pile becomes smaller with the increase of the height of cement soil plug. However, the reflection signal from the pile tip becomes weaker and the integrated velocity of the pile becomes bigger slightly with the increase of the modulus of the cement soil plug. The size of fictitious soil pile obtained by inversion keeps stable but the damping coefficient shows big difference with that from empirical formula. The measured curves show a good agreement with calculated curves, which indicates that the proposed theoretical model can well simulate the dynamic interaction between piles and inner cement soil.

The calcareous sand reinforced in this experiment was obtained from an island in the South China Sea. The shear strength characteristics of microbially induced carbonate precipitation (MICP) cemented calcareous sand were studied using ring shear tests. The influences of bacterial concentration, immersion time of bacterial solution, cementation solution concentration, treated time, vertical stress and seawater environment were considered. Results show that MICP can effectively improve the shear strength of calcareous sand. When the cementation solution concentration was 0.5 mol/L, the shear strength of the treated samples reached the maximum values, which was about three times of that of the untreated samples, showing a remarkable strain softening phenomenon. Increasing the concentration of the bacteria solution, soaking time, concentration of the reinforcement solution and strengthening time can improve the reinforcement effect, reduce the ratio of residual strength to peak strength, and make the strain softening phenomenon more and more obvious. Although seawater has an inhibitory effect on the reinforcement process of MICP, the application of MICP in this environment can effectively improve the shear strength of calcareous sandy foundation.

The loading state of integrated cutter holder system was analyzed by combining numerical simulation with experimental research, in order to improve the bearing performance of integrated cutter holder system. Combined with the automatic assembly process of cutters, the linkage relationship between each structural parameter in integrated cutter holder system and the influence of different structural parameters on its bearing performance were studied. The structural parameters significantly affecting the bearing performance of integrated cutter holder system were optimized based on the weight matrix method of orthogonal test. Results showed that the influence degree of each test factor on the bearing performance of integrated cutter holder system in descending order was as follows: the neck fillet radius of rotating block, the width of rotating block, the vertical distance between cutter shaft and rotating block shaft. The optimal scheme for comprehensive performance of integrated cutter holder system was obtained as follows: the width of rotating block was 107.5 mm, the neck fillet radius of rotating block was 60.0 mm, and the vertical distance between cutter shaft and rotating block shaft was 97.5 mm. Compared with the original scheme of integrated cutter holder system, the overall maximum deformation was reduced by 11.31%, the maximum stress of end cap was reduced by 34.07%, and the maximum stress of rotating block was reduced by 41.01%.

An improved algorithm MR²-YOLOV5 based on YOLOv5 was proposed aiming at the problem that the traditional target detection algorithm did not consider the diversity of the target shape scale in the actual sorting scene and could not obtain the rotation angle information. Precise rotation angle detection was completed by adding angle prediction branches and introducing angle classification method of ring smooth label (CSL). The target detection layer was added to improve the detection ability of different scales of the model. Transformer attention mechanism was used at the end of the backbone network to give different weights to each channel and strengthen feature extraction. The feature graphs of different levels extracted from the backbone network were input into the BiFPN network structure to conduct multi-scale feature fusion. The experimental results showed that the mean average precision (mAP) of MR²-YOLOV5 on the self-made data set was 90.56%, which was 5.36% higher than that of YOLOv5s with only angle prediction branch. Categories and rotation angles can be recognized for objects such as occlusion, transparent and deformation. The detection time of single frame is 0.02-0.03 s, which meets the performance requirements of target detection algorithm for sorting scenes.

A trajectory planning method based on improved particle swarm optimization (PSO) algorithm was proposed in order to improve the working efficiency of tunnel boring machine (TBM) disc cutter changing robot and reduce the motion jerk in the process of tool changing. The kinematics of the redundant joint robot was analyzed by using the position and pose separation method and the joint variable minimization strategy. The target trajectory was mapped from Cartesian space to joint space by using the inverse solution. The jerk continuous joint trajectory was constructed by using 5-degree NURBS curve for each joint. The objective function was constructed by the time jerk optimization, and the optimal time series was solved by using the improved PSO algorithm so as to complete the trajectory optimization. The trajectory planning of specific disc cutter change task was conducted, and the optimal trajectory of each joint was obtained. The optimization results show that the proposed trajectory planning method can provide an ideal trajectory for each joint of the tool changing robot and has strong trajectory tracking ability. The 5th NURBS interpolation method and the improved PSO optimization algorithm were used to ensure the shortest time and minimum impact of the trajectory, and improve the efficiency and stability of the operation.

10% Na₂SO₄ with mass fraction solution was used to carry out indoor corrosion tests under different osmotic pressures and different lengths of concrete samples, in order to simulate the corrosion damage and degradation of concrete under seawater environment. Combined with micro indentation test, CT scanning test and SEM test, the corrosion damage and micromechanical properties of concrete under the action of high osmotic pressure sulfate coupling corrosion were studied. Experimental results show that osmotic pressure accelerates ion migration and mainly promotes chemical erosion. The higher the osmotic pressure, the faster the chemical damage rate of concrete, the deeper the erosion depth; the cementation of aggregate and mortar is the weak point which is easy to be eroded and destroyed; the hydration products are easy to form in the internal pores of concrete, and more short column gypsum crystals and more fine needle ettringite crystals are formed under higher osmotic pressure.

A load simulation technology for ground test system of wind turbine drive chain was proposed. The ground drive chain test system of wind turbines were discussed, and the inertiamoment of impeller under the drag test was calculated. Three main non-torque five-degree-of-freedom loading structural schemes were summarized, i.e., symmetrical loading scheme, radial eccentric loading scheme and parallel six hydraulic cylinders loading scheme. The loading principles of the schemes were discussed, and the load solving equations of the three schemes were constructed. A 100 kW wind turbine drive chain test system loading experimental bench was designed and constructed based on the principle of symmetrical loading scheme in order to further simulate the six-degree-of-freedom load of the wind turbine. The load was accurately reproduced, the feasibility and the rationality of the non-torque five-degree-of-freedom loading technology was verified, and combined with the wind torque load simulation technology, a complete simulation of the wind turbine's six-degree-of-freedom load was achieved.

A graph contrastive learning framework based on negative-sample-free loss and adaptive augmentation was proposed to address the problems of random enhancement of the input graph and the need to construct losses using negative samples in graph contrastive learning methods. In the framework, the centrality of the node degree in the input graph was used to generate two views by adaptive enhancement, which avoided the deletion of important nodes and edges by random enhancement and thus improved the robustness of the framework . The embedding matrix of the two views was obtained using the same weight encoder network without specifying. A cross-correlation-based loss function which did not rely on non-symmetric neural network architectures was used to guide the framework learning. Negative samples were not required in this loss function, avoiding that negative samples became more challenging to define in the case of graphs and that negative samples increased the computational and storage burden of constructing losses. Results showed that the proposed framework outperformed many baseline methods in terms of classification accuracy in the node classification experiments on three citation datasets.

In order to evaluate the power system’s ability to cope with various uncertain factors, a novel concept named power system flexible operation region (PSFOR) was proposed by taking the source and load fluctuation of the system as the research object, which can be used to assess the maximum range of uncertainties that can be accepted by power grid under a certain level of flexible operation. The boundary and the application scope of the PSFOR were expounded on this basis, then an optimization model including source-load fluctuation ranges as well as operating economy was constructed. The extreme scenario method (ESM) and C&CG-based robust optimization (CRO) algorithm were put forward to solve the above model. Simulations on 6-bus system and IEEE RTS 39-bus system verified the effectiveness of the proposed methods. Then the average value and the standard deviation were used as evaluation indexes of FOR to analyze the influence of various flexible resources on PSFOR. Results show that the PSFOR can effectively reflect the operation state and the uncertainty range that can be accepted, and further provide theoretical guidance for the planning and dispatching of power grid.

The expressions of the test hypergravity potential generated by the earth gravity and the centrifugal hypergravity, the static fluid pressure and the buoyancy of an object in fluid were derived in the rotational non-inertial frame by considering the residual angle of the suspended basket in order to characterize the motion law of object in fluid under the centrifugal hypergravity environment. The motion equation of a rigid object in static fluid in centrifugal model test was established based on Newton’s second law, and its numerical solution program was compiled and verified. The numerical analysis results of sphere motion in fluid show that the residual angle of the suspended basket can be ignored under high centrifugal acceleration. The equipotential surface of test hypergravity is a rotating paraboloid with the centrifuge spindle as the axis. The influence of earth gravity on the equipotential surface is gradually reduced with the increase of centrifugal acceleration. The shape of the equipotential surface tends to be a cylindrical surface. The buoyancy is centripetal and non-uniform, and the influence of the Coriolis force cannot be ignored when the object moves in fluid.

A high-order mutual information maximization and pseudo-label guided deep clustering model, HMIPDC, was proposed to solve the problem that the existing clustering methods cannot fully explore the topological structure and node relationships of the graph, and cannot benefit from inaccurate labels predicted by the model. The high-order mutual information maximization strategy was adopted to maximize the mutual information among the global representation of the graph, node representation, and node attribute information. Low-dimensional representations of nodes were extracted more reasonably through a self-attention mechanism combined with multi-hop proximity matrices. A deep divergence-based clustering loss function (DDC) was used to iteratively optimize the clustering objective while high confidence predicted labels were utilized to supervise the learning of low-dimensional representations. Experimental results of clustering tasks, experimental time analysis and clustering visualization analysis on four benchmark datasets show that the clustering performance of HMIPDC is always better than that of most deep clustering methods. The effectiveness and the stability of the model were also verified by ablation study and parameter sensitivity analysis.

In order to study the mechanical response characteristics of shield tunnels under fault dislocation, an analytical model of the longitudinal mechanical response of shield tunnels under cross-active fault conditions was proposed by introducing the Vlasov two-parameter foundation model and considering the influence of horizontal friction. Taking the normal fault dislocation condition as a case study, the rationality of the analytical model was verified by model test and numerical simulation, and the main factors affecting the longitudinal mechanical response of the structure were further discussed. A three-dimensional numerical model considering the plastic deformation of the annular joints was established to analyze the influence of plastic deformation of the annular joint on the longitudinal force and deformation of the tunnel structure. Results show that the longitudinal mechanical response characteristics of the tunnel calculated by the analytical model are consistent with those obtained by the model test and numerical calculation. When the vertical shear stiffness of the foundation is not considered, the longitudinal bending moment of the tunnel calculated is too large. Compared with the shallow tunnel in soil conditions, the deep-buried tunnel in rock stratum has a more obvious restriction on tunnel deformation and leads to the excessive longitudinal internal force of the structure. The vertical distance between the tunnel and the fault, the width of the fault fracture zone, and the effective rate of the longitudinal bending stiffness of the structure all significantly influence the maximum longitudinal internal force of the tunnel. When considering the plastic deformation of the annular joint, the obvious plastic deformation of the shield tunnel annular joint has occurred under 20 cm fault dislocation, which severely affects the operation safety of the shield tunnel.

In order to reveal the spatiotemporal relationship between urban multi-dimensional features and bike-sharing parking demand and their associated scales, combined with multi-source data in Shanghai, a multiscale geographically and temporally weighted regression model constrained by riding distance (RD-MGTWR) was constructed to explore the spatiotemporal heterogeneity patterns of the impact of built environment and regional economic attributes on parking demand. The model comparison analysis shows that the MGTWR model exhibits better explanatory power and reliability than the geographically and temporally weighted regression model (GTWR), and the introduction of riding distance further improves the robustness of the MGTWR model. Results show that the scale of the positive impact of socioeconomic attributes on parking demand is global, while the negative impact of location conditions presents local heterogeneity, and is most significant in the inner ring central area during the commuter morning peak. In addition, bus station density, metro station density and shopping service facility density with micro-spatial or temporal scales have positive and negative effects on parking demand. The findings of the scale effect of influencing factors can help guide parking facility zoning development and bike sharing time-sharing scheduling.

The day-ahead bidding method of wind farms participation in the energy market and frequency regulation (FR) market was proposed in order to solve the problem that large-scale wind power integration on power system can increase the FR demand of the power system. The revenue mechanisms of wind farms in the energy market and FR market were analyzed. The frequency regulation performance index (FRPI) was considered in the FR market revenue, and the evaluation method of FRPI was proposed. The bidding strategy of wind farms participating in the energy and FR (E&FR) markets was analyzed. The wind power probability density prediction model KELM-PSO-KDE was established by using the kernel extreme learning machine (KELM) and the kernel density estimation (KDE). An optimization model for the wind farm participating in the E&FR markets was established with the goal of maximizing the wind farm revenue based on the probability density prediction results of wind power. The ant lion optimizer (ALO) algorithm was used to solve the optimization model in order to obtain the day-ahead optimal bidding power for the wind farm participating in the E&FR markets. The simulation results based on the actual wind farm data show that the bidding strategy for wind farms in the E&FR markets can help wind farms to obtain more revenue, and help the power system to relieve the FR pressure. The bidding strategy has more advantages and universality.