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.

A thorough analysis and cross-comparison of recent relevant works was provided, outlining a closed-loop process for EEG data analysis based on deep learning. EEG data were introduced, and the application of deep learning in three key stages: preprocessing, feature extraction, and model generalization was unfolded. The research ideas and solutions provided by deep learning algorithms in the respective stages were delineated, including the challenges and issues encountered at each stage. The main contributions and limitations of different algorithms were comprehensively summarized. The challenges faced and future directions of deep learning technology in handling EEG data at each stage were discussed.

The researches on data security management and privacy protection technologies at home and abroad were analyzed and summarized aiming at current problems in blockchain security, such as unreasonable data management mode, unreliable data sharing scheme, smart contract vulnerabilities not easily fixed and incomplete privacy protection of multiple types of data. Various security problems and reasonable solutions in current blockchain systems were outlined from four aspects: data storage security, data privacy security, data access security and data sharing security. The challenges and future research directions of data security in blockchain were discussed. Some reference for the future work of researchers was provided in the field of blockchain security.

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.

Most of the compound fault diagnosis methods regard the compound fault as a new single fault type, ignoring the interaction of internal single faults, and the fault analysis is vague in granularity and poor in interpretation. An improved Transformer-based compound fault decoupling diagnosis method was proposed for industrial environments with very little compound fault data. The diagnosis process included pre-processing, feature extraction and fault decoupling. With introducing the decoder of the Transformer, the cross-attention mechanism enables each single fault label to adaptively in the extracted feature layer focus on the discriminative feature region corresponding to the fault feature and predicts the output probability to achieve compound fault decoupling. Compound fault tests were designed to verify the effectiveness of the method compared with the advanced algorithms. The results showed that the proposed method had high diagnostic accuracy with a small number of single fault training samples and a very small number of compound fault training samples. The compound fault diagnosis accuracy reached 88.29% when the training set contained only 5 compound fault samples. Thus the new method has a significant advantage over other methods.

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.

A multi-agent reinforcement learning algorithm based on priority experience replay and decomposed reward function was proposed in multi-agent pursuit and evasion games. Firstly, multi-agent twin delayed deep deterministic policygradient algorithm (MATD3) algorithm based on multi-agent deep deterministic policy gradient algorithm (MADDPG) and twin delayed deep deterministic policy gradient algorithm (TD3) was proposed. Secondly, the priority experience replay was proposed to determine the priority of experience and sample the experience with high reward, aiming at the problem that the reward function is almost sparse in the multi-agent pursuit and evasion problem. In addition, a decomposed reward function was designed to divide multi-agent rewards into individual rewards and joint rewards to maximize the global and local rewards. Finally, a simulation experiment was designed based on DEPER-MATD3. Comparison with other algorithms showed that DEPER-MATD3 algorithm solved the over-estimation problem, and the time consumption was improved compared with MATD3 algorithm. In the decomposed reward function environment, the global mean rewards of the pursuers were improved, and the pursuers had a greater probability of chasing the evader.

For the poor real-time detection capability of the current object detection model in the production environment of electronic components, GhostNet was used to replace the backbone network of YOLOv5. And for the existence of small objects and objects with large scale changes on the surface defects of electronic components, a coordinate attention module was added to the YOLOv5 backbone network, which enhanced the sensory field while avoiding the consumption of large computational resources. The coordinate information was embedded into the channel attention to improve the object localization of the model. The feature pyramid networks (FPN) structure in the YOLOv5 feature fusion module was replaced with a weighted bi-directional feature pyramid network structure, to enhance the fusion capability of multi-scale weighted features. Experimental results on the self-made defective electronic component dataset showed that the improved GCB-YOLOv5 model achieved an average accuracy of 93% and an average detection time of 33.2 ms, which improved the average accuracy by 15.0% and the average time by 7 ms compared with the original YOLOv5 model. And the improved model can meet the requirements of both accuracy and speed of electronic component surface defect detection.

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 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.

An indoor positioning method of unmanned aerial vehicle (UAV) based on improved multi-state constraint Kalman filter (MSCKF) was proposed aiming at the problem that the indoor positioning of UAV is prone to drift. A high robustness and low delay detection method was proposed under the framework of MSCKF. The pose of UAV was calculated with the help of the known positions of the mark points in world coordinate system. Then inertial measurement unit (IMU) data and monocular vision data fusion and UAV pose correction were realized. The proposed positioning method was tested. The simulation results show that the positioning error of the proposed method was within 0.266 m, and the positioning accuracy was improved by more than 54.6% compared to OpenVins and LARVIO.

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.

Ensuring that the flue gas in the furnace stays within the temperature range of no less than 850 ℃ for at least 2 s contributes to the steady municipal solid waste (MSW) incineration, and the reduction of secondary pollution. However, at present, it is difficult to quantitatively calculate and predict the residence time of flue gas in the high temperature area by only using the thermocouple for qualitative evaluation. Based on the thermodynamic calculation, correlation analysis of practical operation parameters, and a variety of machine learning algorithms (backpropagation neural network, recurrent neural network, and random forest regression), the residence time of flue gas in high-temperature areas (>850 ℃) was calculated, correlation analysis of key operation parameters was conducted, and the prediction model of residence time was constructed, aiming at a typical MSW circulating fluidized bed boiler in China. Results revealed that 10 key operating parameters, e.g. section temperature of the furnace, temperature and pressure of primary air and secondary air, etc., had a strong correlation and predictability with the high-temperature flue gas residence time. Moreover, the model of the recurrent neural network was relatively optimal, with a higher fitting degree and accuracy. Specifically, the mean square error (MSE) was 0.11626, and the average absolute error between the predicted value and real value was 1.174%. Research enabled the prediction of flue gas temperature variation in high-temperature areas, helped optimize the MSW incineration, and contributed to the advanced control of pollutant emission reduction.

There has been a trend of intelligent development using artificial intelligence technology in order to improve the efficiency of software development. It is important to understand program semantics to support intelligent development. A series of research work on program representation learning has emerged to solve the problem. Program representation learning can automatically learn useful features from programs and represent the features as low-dimensional dense vectors in order to efficiently extract program semantic and apply it to corresponding downstream tasks. A comprehensive review to categorize and analyze existing research work of program representation learning was provided. The mainstream models for program representation learning were introduced, including the frameworks based on graph structure and token sequence. Then the applications of program representation learning technology in defect detection, defect localization, code completion and other tasks were described. The common toolsets and benchmarks for program representation learning were summarized. The challenges for program representation learning in the future were analyzed.

The improved YOLOv5 object detection algorithm was used to detect the facial region of the driver and a multi-feature fusion fatigue state detection method was established aiming at the problem that existing fatigue state detection method cannot be applied to drivers under the epidemic prevention and control. The image tag data including the situation of wearing a mask and the situation without wearing a mask were established according to the characteristics of bus driving. The detection accuracy of eyes, mouth and face regions was improved by increasing the feature sampling times of YOLOv5 model. The BiFPN network structure was used to retain multi-scale feature information, which makes the prediction network more sensitive to targets of different sizes and improves the detection ability of the overall model. A parameter compensation mechanism was proposed combined with face keypoint algorithm in order to improve the accuracy of blink and yawn frame number. A variety of fatigue parameters were fused and normalized to conduct fatigue classification. The results of the public dataset NTHU and the self-made dataset show that the proposed method can recognize the blink and yawn of drivers both with and without masks, and can accurately judge the fatigue state of drivers.

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.

The design technique of the digitally controlled active clamp flyback (ACF) converter based on adaptive dead time control (ADTC) was proposed in order to improve conversion efficiency of the converter. The zero voltage switching (ZVS) information for two primary switches was detected by the secondary-side sampling, then the dead time was controlled adaptively, and the ZVS for switches was achieved. The withstand voltage requirements of sampling device were reduced by the secondary-side sampling. The system design was verified on a 45 W (20 V/2.25 A) prototype of a CoolMOS-based ACF converter, and a field-programmable gate array (FPGA) was used to achieve digital control. Measured results showed that the converter could operate normally at 300 kHz, the dead time was controlled adaptively under 155 V DC voltage input and different loads conditions, and the ZVS for primary switches was achieved. The highest and the lowest efficiency of the system were 97.48% and 92.86 % respectively.

An improved method for the blockchain Kademlia network based on small world theory was proposed aiming at the issue of sacrificing security to improve scalability in the current research of the blockchain Kademlia network. The idea of the small world theory was followed, and a probability formula for replacing expansion nodes was proposed. The probability was inversely proportional to the distance between nodes. The number of node replacements and additional nodes could be flexibly adjusted according to actual conditions. The theoretical analysis and experimental verification demonstrate that the network transformed by this method can reach a stable state. The experimental results showed that the transmission hierarchy required for broadcasting transaction messages throughout the network was reduced by 15.0% to 30.8% and the rate of locating nodes was increased. The level of network structure was reduced and network security was enhanced compared to other optimization algorithms that modify the network structure.

Most of existing structural image super-resolution reconstruction algorithms can only solve a specific single type of structural image super-resolution problem. A structural image super-resolution network based on improved Transformer (TransSRNet) was proposed. The network used the self-attention mechanism of Transformer mine a wide range of global information in spatial sequences. A spatial attention unit was built by using the hourglass block structure. The mapping relationship between the low-resolution space and the high-resolution space in the local area was concerned. The structured information in the image mapping process was extracted. The channel attention module was used to fuse the features of the self-attention module and the spatial attention module. The TransSRNet was evaluated on highly-structured CelebA, Helen, TCGA-ESCA and TCGA-COAD datasets. Results of evaluation showed that the TransSRNet model had a better overall performance compared with the super-resolution algorithms. With a upscale factor of 8, the PSNR of the face dataset and the medical image dataset could reach 28.726 and 26.392 dB respectively, and the SSIM could reach 0.844 and 0.881 respectively.

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.