Traditional and new geotechnical engineering problems such as compressed air energy storage, intercepting water with compressed air, carbon dioxide sequestration and oil and gas underground reserve project are all involving air-water two-phase flow and stress coupling problems. For this engineering reality, based on the weak coupling theory of gas-water two-phase seepage and stress in unsaturated soil, a air-water two-phase percolation-stress coupling calculation program based on coupled TOUGH2 and FLAC3D was developed. The calculation program can simulate real air-water two phase flow, and can investigate the gas-water interaction of seepage process. The calculation program considers the direct interaction between gas-water two-phase seepage and soil skeleton deformation, reflects the process of porosity, permeability, capillary pressure and the change of soil physical and mechanical parameters, and achieve a more perfect gas-water two-phase seepage-stress coupling analysis. Furthermore, by comparing with classical drainage test and model test, it is verified that the program can accurately simulate the gas-water two-phase flow-stress interaction.

In order to promote the transformation of industrial cyber security defense mode from static passive defense to active defense, and alleviate the contradiction between the serious shortage of security experts and the sharp increase of cyber security demands, a cyber security active defense system framework of digital twin system was built from the perspective of bionics, and then five kinds of key technologies focusing on active defense were proposed based on the digital twin security brain (DTSB), including security data interaction and systems collaborative defense based on cloud-edge collaboration, cyber security active defense model of parallel digital twin system, situation awareness of parallel digital twin systems based on digital twin security brain, active defense and control technical framework for digital twin system based on immune system, and anti-attack intelligent recognition of digital twin system based on artificial intelligence. A case study of a digital twin workshop was given to demonstrate the successful application of digital twin cyber security in smart manufacturing.

The research progress of direct air capture CO₂ adsorbents was reviewed. The advantages and disadvantages of alkali/alkaline metal based adsorbents, metal organic framework adsorbents, amine loaded adsorbents and moisture swing adsorbents were compared. Meanwhile, the properties of adsorbents from the aspects of adsorption capacity and amine efficiency, kinetics and supporters, regeneration mode and energy consumption, thermal stability and resistance to degradation were evaluated. Additionally, the related engineering demonstration projects and economic evaluation were briefly discussed. Finally, the problems existing in the current research were summarized, and the future research direction was prospected.

An adaptive control strategy based on the general nonlinear relative motion equation was proposed by considering the uncertainty of the spacecraft rendezvous model. A parameterization via adaptive neural networks was implemented for the linear and nonlinear uncertainties in the complex nonlinear system caused by the external disturbances and the orbital parameters of the target spacecraft. Both the backstepping technique and the Lyapunov method were utilized to achieve the control targets and guarantee the asymptotic stability of the resulting closed-loop system. An auxiliary control system was proposed to analyze the effect of input constraints in order to explore the adaptive control design of the spacecraft relative motion in the presence of both model uncertainty and input constraints. The adaptive control strategy proposed for relative motion ensured the stability of the closed-loop system, as well as the uniform ultimate boundedness of the adaptive estimation of the unknown parameters. The effectiveness of the proposed method was verified by the numerical results via the analysis and comparison of different cases.

An underwater image enhancement algorithm was proposed based on generative adversarial networks (GAN) and improved convolutional neural networks (CNN) in order to solve the problems of haze blurring and color distortion of underwater image. Generative adversarial network was used to synthesize underwater images to effectively expand the paired underwater data set. The underwater image was decomposed by multi-scale wavelet transform without losing the feature resolution. Then, combined with CNN, the compact learning method was used to extract features from multi-scale images, and skip connection was used to prevent gradient dispersion. Finally, the fog blur effect of the underwater image was resolved. In order to improve the color correction ability of the model and overcome the problem of color distortion of underwater images, the correlation between different channels of color images was learned by using the style cost function. Experimental results show that, in subjective visual and objective indicators, the proposed algorithm is superior to the contrast algorithm in comprehensive performance and robustness.

A multi-objective particle swarm optimization algorithm with multi-role and multi-strategy (MOPSO_RS) was proposed, in view of the immature convergence and poor diversity of particle swarm optimization in solving complex multi-objective problems. According to index-based role, the particles with different performances were assigned for different roles. A multi-strategy parameter adjustment method and global optimal particle selection method were proposed to help the population carry out various search mechanisms. Different learning parameters enabled particles with different performances to obtain different search strategies so as to adjust the exploration and exploitation capabilities of the particles. Different global optimal particles made particles search different regions to improve the search efficiency of the population. To avoid the algorithm from falling into the local optimal, a mutation operator with Gaussian function was introduced to make particles mutate toward different global optimal particles and increase accuracy of the algorithm. The experiment results indicate that MOPSO_RS has better convergence and diversity than other improved multi-objective optimization algorithms, and verifies the effectiveness of the proposed strategy.

A new knowledge-enhanced graph convolutional neural network (KEGCN) classification model was proposed aiming at the problem of text classification. In the KEGCN model, firstly a text graph containing word nodes, document nodes, and external entity nodes was constructed on the entire text set. Different similarity calculation methods were used between different types of nodes. After the text graph was constructed, it was input into the two-layer graph convolutional network to learn the representation of the node and classified. The KEGCN model introduced external knowledge to compose the graph, and captured the long-distance discontinuous global semantic information, and was the first work to introduce knowledge information into the graph convolution network for classification tasks. Text classification experiments were conducted on four large-scale real data sets, 20NG, OHSUMED, R52 and R8, and results showed that the classification accuracy of the KEGCN network model was better than that of all baseline models. Results show that integrating knowledge information into the graph convolutional neural network is conducive to learning more accurate text representations and improving the accuracy of text classification.

An intelligent inversion system based on support vector machine (SVM) was established, and creep tests of soft soil were conducted in laboratory under the background of a large foundation pit project of Taihu tunnel. An innovative analysis method was proposed by combining the intelligent inversion and creep tests. The basic physical and mechanical parameters and creep parameters of relevant soil layers were determined combined with the monitoring data. The feasibility of the method in long-term stability analysis and deformation prediction of soft soil foundation pit under overloading was verified by analyzing the deformation at the site of soft soil foundation pit under overloading. The method was applied to the optimization design under overloading of Taihu tunnel, and good results were obtained.

A method for perception and recognizing the deflection angle of robot spline assembly based on parameter optimization was proposed, aiming at the problem of low assembly success rate due to the deflection angle of the shaft hole during the spline assembly process. According to the characteristics of spline assembly, the force sensor was used to collect the force/torque signal during the spline assembly process, an extreme learning machine (ELM) based on the hybrid whale optimization algorithm (HWOA) was used to identify the force signal of deflection angle and construct a deflection angle experience library. Combined with the support vector data description (SVDD) algorithm the perception of undefined deflection angle and self-updating of deflection angle experience library were realized, and the perception and recognition of deflection angle to guide the robot to complete the spline assembly task was achieved. The experimental results show that the proposed method has a success rate of 98.8% for sensing undefined deflection angles and 98.12% for recognizing known deflection angles, and can effectively guide the spline assembly.

A fire detection algorithm based on improved GhostNet-FCOS was proposed in view of the low detection accuracy and high complexity of existing fire detection algorithms. The algorithm was based on FCOS with reduced channel dimensions, and GhostNet was selected as the feature extraction network to implement a lightweight fire detection algorithm. Dynamic convolution was introduced to optimize the basic modules of the backbone without increasing width and depth, resulting in improved feature extraction ability for variable flames. A spatial attention module was introduced into the backbone network in order to optimize the expression of network spatial features. The definition of positive and negative samples and the regression loss function were improved to optimize the network’s attention to different areas in the ground truth box during the training process. The experimental results in self-built fire dataset and public dataset show that the algorithm has advantages in detection accuracy and model complexity. The detection accuracy of the algorithm in the self-built fire dataset was 90.9%, the amount of parameter was 4.58×10⁶, and the floating point operation was 31.45×10⁹.

A cooperative control algorithm of multi-intersection variable-direction lanes based on multi-agent reinforcement learning was proposed to alleviate the congestion of multi-intersection, in order to solve the problem that traditional variable-direction lane control method can't adapt to the complex traffic flow problem under multiple intersections scenarios. In this method, the deep multi-agent reinforcement learning (QMIX ) algorithm was improved. The global reward under variable-direction lane scenarios was composed of basic reward and performance reward, which improved the decision-making accuracy of lane turn control in congestion scenarios. The priority experience playback algorithm was introduced to improve the utilization efficiency of the transfer sequence in the experience playback pool and accelerate the algorithm convergence. Experimental results show that the algorithm has better performance than other control methods in case of queue length, delay times and waiting times, which can effectively coordinate the policy switch of the variable-direction lanes and improve the road network capacity in the multi-intersection scenarios.

In order to collaboratively and optimally control the key elements of the technical interface of the railway bridge-tunnel in the arduous mountainous area, the tradeoff optimization model of the key elements for the technical interface was established, which was combined the multi-attribute utility function and the "three-one" elements transformation structure. Firstly, the relationships among quality, schedule, cost and safety were analyzed and quantified by functional forms. The "three-one" elements transformation structure was employed to determine the "main attachment" dimensions, and the tradeoff optimization function of the key elements for the technical interface of the railway bridge-tunnel in the arduous mountainous area was established. Then based on the mechanism that the technical interface to the key elements, the decision preference coefficients of the tradeoff optimization function were determined by ANP, the achievement scalarizing functions preference inspired co-evolutionary algorithm (ASF-PICEA-g) was used to obtain the optimal solution of the tradeoff optimization model, and find the optimal solution of each key element under the optimal solution of the whole model. Finally, both the rationality of the tradeoff optimization function and the effectiveness of the ASF-PICEA-g were verified by constructing the tradeoff optimization function of the technical interface between the Zangmu Bridge and the Allah Tunnel and carrying out the optimization analysis.

The research works of Chinese font style transfer were classified according to different stages of research development. The traditional methods were briefly reviewed and the deep learning-based methods were combed and analyzed. The commonly used open data sets and evaluation criteria were introduced. The future research trends were expected from four aspects, which were to improve the generation quality, enhance personalized differences, reduce the number of training samples, and learn calligraphy font style.

A distributed swarm control strategy based on graph convolutional imitation learning was proposed to deal with the cooperative control of robot swarms under restricted communication conditions. The strategy aimed to improve swarm robustness and enhance the success rate of avoiding swarm splitting based on achieving intra-swarm obstacle avoidance and velocity consistency. A quantitative evaluation index of swarm robustness based on entropy evaluation was proposed to establish the connection between the balanced distribution of node and link importance and cluster robustness. The importance-correlated graph convolutional networks were proposed to realize feature extraction and weighted aggregation of non-Euclidean data under restricted communication conditions. A centralized expert strategy was designed to improve swarm robustness, and the graph convolutional imitation learning method was adopted. Furthermore, a distributed swarm cooperative control strategy was obtained by imitating the centralized expert strategy. Simulation experiments demonstrate that the resulting distributed strategy achieves control effects close to those of the centralized expert strategy based on restricted communication conditions.

A dehazing algorithm combined with atmospheric scattering model based on generative adversarial network was proposed in order to improve the performance of image dehazing. The algorithm was improved base on pix2pix GAN. Firstly, the generator is improved to a double decoder structure. The double decoder generates the fog-free image and the transmittance image, separately, then the fog-free image and the transmittance image are combined to restore the fog image by the atmospheric scattering model. The purpose is to improve the quality of decomposition. Secondly, in the Markov discriminator structure, the reverse learning mechanism is used to replace the random cropping mechanism, which aims to reduce the probability of inaccurate judgment caused by the random cropping algorithm. Finally, the haze loss function is added to the original loss function to improve the quality of image translation. The ablation experiments and contrast experiments were applied on STOS and NYU datasets. Experimental results showed that the proposed method was better than the original algorithm pix2pix GAN in terms of PSNR and SSIM, and both were better than the existing dehazing algorithms. The restored images have the advantages of high-resolution, low noise and rich texture.

At present, there is no public dataset suitable for the research work of material entity relationship extraction technology in the field of materials. Aiming at the above problem, the construction method of aluminum-silicon alloy entity relationship extraction dataset was proposed through the literature of high-silicon aluminum alloy spray deposition. The construction standards of the aluminum-silicon alloy entity relationship extraction dataset were formulated under the guidance of experts in the material field, and the collected data were marked with entities and relationships according to the construction standards. After the annotation was completed, the aluminum-silicon alloy entity relationship extraction dataset was generated through data preprocessing. Experiments were conducted through the entity-relationship joint extraction model to verify that the dataset can be applied to entity-relationship extraction tasks. Compared with the public dataset, the semantics and grammar of the sentence in the material dataset were more complicated, and there were more long sentences, which led to a slightly worse performance of the entity relationship joint extraction model on the material dataset. Therefore, a self-attention mechanism was added to the entity relationship joint extraction model, which increased the overall F1 value by about 5.8%. The method of constructing the dataset is universal, and the material dataset can be constructed by the construction method.

Digital twin and manufacturing simulation integrated platform (DTMSIP) architecture for reconfigurable manufacturing system (RMS) was proposed, aiming at the application problem of digital twin on RMS. DTMSIP was highly adapted to RMS’s dynamic reconfiguration and can be used for simulation analysis in RMS configuration design. Digital twin mapping for RMS was modeled. By defining twinning entity (TE), heterogeneous multi-source data integration in RMS shop-floor was realized and digital twin mapping for machine tools and configuration was established. The application procedure of digital twin-based RMS reconfiguration was proposed. DTMSIP served the purpose of assisting RMS reconfiguration through iteration of cyber physical fusion and iteration of configuration simulation. In order to validate the proposed method, Unreal Engine 4 (UE4) was adopted to implement DTMSIP software for a modular RMS. Current configuration and four planned configurations were input to DTMSIP software for simulation. Quantitative and comprehensive analysis was performed on the configurations taking into consideration cost of reconfiguration, cycle time and line balance, contributing to accelerate RMS reconfiguration design processes.

An efficient network vehicle recognition algorithm combined with attention mechanism was proposed in order to solve the problem that the existing vehicle type recognition algorithm does not adequately describe the vehicle type characteristics. The depth, width and resolution of the network were balanced by the compound scaling method in the efficient network, and the depth separable convolution was integrated into the basic feature extraction module in order to improve the accuracy of the model. The residual attention mechanism of two channels was added to pay attention to the key information in the picture, and the feature map with richer semantic information was obtained. A separate softmax classifier was added at the end of the network, and the label smoothing regularization was used to deal with the loss function in order to reduce the problem of model over-fitting. Experiments on BIT-Vehicles data set showed that the average classification precision of the proposed method was 96.83%, which was 1.11% higher than that of the original model, and was better than the existing improved algorithms of DCNN and Faster-CNN and 7.16% higher than Faster R-CNN.

A task allocation method for Internet of vehicles spatial crowdsourcing with privacy protection was proposed under the blockchain architecture in order to solve the problem that centralized spatial crowdsourcing server in the traditional spatial crowdsourcing of Internet of vehicles was untrusted and vulnerable to malicious attacks, which posed a great threat to users’ privacy. A distributed and trusted spatial crowdsourcing system of Internet of vehicles was designed based on the blockchain technology. The multi-key homomorphic encryption algorithm was adopted to distribute tasks, which supported task allocation of location ciphertext data of different vehicle users (keys). Then the possibility of privacy disclosure of vehicle users was reduced. The experimental results show that the proposed method can effectively protect users’ privacy information, reduce the computing overhead of task allocation by 34.3% compared with the existing methods, and improve the efficiency of task allocation.

The model experiment on influence of buried fault dislocation on shield tunnel was conducted based on the longitudinal equivalent continuous model for shield tunnels in order to analyze the mechanical properties of shield tunnel structure and stratum failure mode under buried fault dislocation. The relationship between the longitudinal mechanical properties of the structure, the opening of circumferential joint and the fault dislocation was analyzed. The rationality of the model experiment result was verified by numerical simulation. The experimental and numerical results show that the longitudinal stress of tunnel structure changes obviously under buried fault dislocation, and the influence range of fault dislocation on the tunnel structure is within 60 m. The circumferential joints near the projection plane at the top of the fault obviously produce tensile deformation, and the circumferential joints are more likely to produce tensile deformation under normal fault dislocation. The longitudinal tunnel structure under normal fault dislocation is in eccentric tension state, and the longitudinal tunnel structure under reverse fault dislocation is in eccentric compression state. Shearing deformation occurs obviously in the strata under normal fault dislocation, and the propagation law of inverted triangular shearing deformation appears. The surface ground transverse cracks develop significantly. The shearing deformation of strata is relatively weak under reverse fault dislocation.