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.

An improved active disturbance rejection impedance control strategy was proposed, in order to improve the accuracy and flexibility of robot assembly operations. In this strategy, the new expected force was generated by the active disturbance rejection controller to adjust the position of the robot's end tool coordinate system, and achieve the accurate force tracking. The environmental information was observed by the disturbance observer and the expected force of the control system was compensated to improve the adaptability of the control system to environmental parameters. The impedance model was introduced to improve the disturbance observer, which increased the response speed of the observer and improved the precision of force tracking. The experimental results of precision peg-in-hole assembly based on 6-DOF robot showed that the impedance control based on active disturbance rejection control (ADRC) could complete the assembly with less contact force error to traditional impedance control, and the force average error of the impedance control based on improved ADRC was reduced by 12.0% to 28.2% compared with that before the improvement.

A comprehensive evaluation and categorization of blockchain-based mobile crowdsensing (MCS) data processing was conducted, in order to address the wide participation of users, the flexible mobility of collection devices, and the complexity of communication environment in mobile crowdsensing data processing. Firstly, the developments of MCS and blockchain were reviewed, and the challenges of MCS data processing and the characteristics of blockchain were introduced. Secondly, a blockchain-based mobile crowdsensing architecture (BMCA) was designed to achieve decentralized data management, data security assurance, precise data quality evaluation, and enhanced credibility of incentives. Then, existing data processing techniques were sorted from privacy-preserving, data quality evaluation, and incentive mechanism. Finally, the current problems and challenges in resource consumption control, precise data analysis, full-cycle and differentiated privacy-preserving, and integrated mode application of blockchain-based MCS data processing research were discussed, and the potential future research direction was pointed out.

A new type of robot collision detection algorithm was proposed for the security problem that collision may occur when conventional industrial robots operate in an unknown environment. The convolution torque observer was designed. The robot collision detection was realized by real-time observation of the deviation between the joint output torque and the dynamic estimation torque. The static LuGre model was used to compensate the joint friction in order to avoid the interference of joint friction of the robot in different poses and motion states on robot collision detection. By monitoring the motion of actual industrial robots, more accurate static LuGre model parameters were identified. The collision detection algorithm does not need acceleration information, avoiding the calculation error caused by the secondary derivation of the position feedback information. The joint torque was acquired based on the current information of the joint servo drive. It is not necessary to install a special force/torque sensor. Therefore, in the case of conventional industrial robots without additional configuration, just collect the robot joint drive motor current and position information to achieve collision detection. The effectiveness of the collision detection algorithm is verified by human-robot interaction experiments.

A time-aware combination (TAC) method for temporal knowledge graph completion was proposed aiming at the problem that the existing temporal knowledge graph embedding methods only consider the relationship of temporal information or encode independent temporal vectors and the completion performance of these methods is not high enough. The effectiveness of temporal information on knowledge graph completion methods was analyzed by modeling dimensional features. Different learning methods have different effects on the representation learning ability after considering the embedding of temporal information through the embedding method of combining the embedded and independent temporal information. Long short-term memory (LSTM) network was utilized to encode temporal information, learn more accurate temporal dimension features and help to improve the performance of temporal graph. Experiments on ICEWS14, ICEWS05-15 and GDELT datasets verified the effectiveness of the time-aware combination method. The related research performance metrics were compared. Results show that the proposed method performs better in link prediction.

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.

The problems existing in aspect-based sentiment analysis include: a singular approach to syntactic dependency parsing, incomplete extraction and utilization of grammatical information; limited use of external knowledge bases, which failed to provide sufficient background knowledge and information for judging sentiment; and an excess of introduced knowledge, leading to biased conclusions. A new aspect-based sentiment analysis model was proposed, and two different syntactic parsing methods were utilized to construct two types of syntactic dependency graphs for sentences. Emotional dependency graphs were built based on external emotional knowledge, incorporating conceptual knowledge graphs to enhance aspect terms in sentences, constructing visible matrices corresponding to the sentences enhanced through conceptual knowledge graphs. A dual-channel graph convolutional neural network was employed to process the dependency graphs, the emotional dependency graphs and the visible matrices, integrating the dependency graphs with the emotional dependency graphs to perform semantic and syntactic dual interactions on specific aspect feature representations. Experimental results showed that the proposed model significantly outperformed the mainstream models in terms of accuracy and macro F1 score on multiple datasets.

A simple method for estimating model parameters that only uses the available information in the manufacturer datasheet was proposed aiming at the problem that the parameter values of the simplified solar cell engineering model in the existing literature were not suitable for current PV modules. The parameter b was obtained by fitting the open-circuit voltage data corresponding to different irradiance at 25 ℃. The parameters a and c were treated equal to the temperature coefficients of the short-circuit current and the open-circuit voltage, respectively. The value of parameter b for PV modules produced by different manufacturers is different, while it can take the same value for the same manufacturer’s different type of PV modules. The electrical output characteristics of PV modules were dynamically simulated by integrating the improved solar cell engineering model, the cell temperature model in piecewise function form and the solar irradiance model considering the installation conditions of the PV module. The angle change has little effect on the maximum output power when the module inclination angle is less than the optimal one. The angle change has a great influence on the maximum output power when the inclination angle is greater than the optimum one, and the influence degree increases with the increase of the angle.

The backgrounds are cluttered, the spot sizes of apple leaf disease are varying in complex environments, and the existing models have the problems of multiple parameters and a large amount of calculation. Thus, an apple leaf disease recognition network, ConvNext network based on attention and multiscale feature fusion (MA-ConvNext), was proposed. A multiscale spatial reconstruction and channel reconstruction block (MSCB) and a feature extraction block with triplet attention fusion (TAFB) were utilized to effectively extract the features at different scales and enhance the focus on leaf disease spots. Additionally, a stepwise relational knowledge distillation method was employed to fuse the "teacher" network (MA-ConvNext) with an "intermediate" network (DenseNet121) to guide the training of the "student" network (EfficientNet-B0) and achieve the model lightweighting. Experimental results showed that MA-ConvNext achieved a recognition accuracy of 99.38%, improving by 3.98 percentage points, 7.55 percentage points and 4.27 percentage points compared to ResNet50, MobileNet-V3, and EfficientNet-V2 networks, respectively. After the stepwise relational knowledge distillation, the recognition accuracy further improved by 1.76 percentage points, with a smaller network size and parameters of 1.56×10⁷ and 5.29×10⁶. respectively. The proposed method offers new insights and technical support for the precise detection of pests and diseases in agriculture.

A Poisson noise image denoising method based on Bayesian probability model was proposed. An image denoising model was constructed based on Bayesian maximum a posteriori probability model and with combination of Poisson probability distribution. Considering that Markov random fields cannot represent complex natural images effectively, a higher-order Markov fields of experts was introduced as a prior regular term of the model to represent the probability distribution of the image. The quadratic penalty function was used to optimize the denoising model and restore clear images. The proposed method was compared with other denoising algorithms; the denoising effect was evaluated objectively by using two evaluation indexes: peak signal-to-noise ratio and structural similarity. The experimental results show that, compared with the traditional denoising methods, the peak signal-to-noise ratio of this method increased by at least 0.18 dB, and the denoising performance is significantly better than that of other methods. Thus, the details of the image can be retained better by using this mothed.

An assessment method for social engineering threat based on attribute attack graph and Bayesian network was proposed, aiming at the problem that social engineering threats in social networks were difficult to evaluate quantitatively. The semantics of vulnerability and attack node in social engineering were defined, and the corresponding method for calculating available probability of vulnerability was proposed, according to the process of social engineering attack in social network. Phishing attacks and cross-station identity cloning attacks were simulated by analyzing the attack patterns of social engineering in social network. Social engineering attack maps were constructed based on the attribute attack graph generation algorithm. Bayesian network model was applied to assess quantitatively the social engineering threats caused by each attack path, and the privacy threat risk value of personal account in social network was obtained. Experiments on the Facebook dataset verified the effectiveness of the proposed method.

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.

Aiming at the coordination problem of active front steering (AFS) and direct yaw moment control (DYC) in vehicle handling and stability control, an optimal phase plane method for stable region partition was proposed. In order to realize the integrated control of handling and stability on lateral and longitudinal dynamic system, a coordination criterion considering tire force characteristics was established based on the proposed method . Firstly, the side slip angle of front and rear tires and the difference between them were used as the characterization of vehicle lateral stability. Combined with the lateral force characteristics of the tires, the lateral state of the vehicle was divided into stable, critically stable and unstable regions. Thereby the coordination criterion between AFS and DYC was established. Secondly, considering the problem of obtaining the state variables when the control algorithm was oriented to practical applications, a state observer based on the super-twisting algorithm was established to estimate the vehicle front and rear wheel slip angle. Finally, the AFS and DYC higher-order sliding mode controller based on the adaptive super-twisting algorithm was designed to eliminate the chattering phenomenon and avoided frequent switching of the controllers during the process of stability control. Experimental results showed that the proposed coordination criteria and control method had positive effect on the coordination of AFS and DYC and obtained great effect on the control of handling and stability.

The dynamic damping expression of rheological soil was derived based on the time-dependent modulus, and the continuum model of the pile-soil periodic structure was constructed. The energy band structure and band gap of the pile-soil periodic system were calculated by using the multiple scattering method. The band gap characteristics and parameter influence of shear wave in rheological soil pile foundation were analyzed through an example. Results showed that the damping ratio of rheological soil changed non-monotonously with frequency. The amplitude of damping ratio was determined by the initial and final modulus ratio, and the change rate of damping ratio with frequency was determined by the relaxation time. The rheological properties of the soil lead to a higher frequency of band gaps in the actual engineering of row pile foundations than the theoretical value, and the bandwidth decreases, weakening the vibration isolation effect of row piles. Eliminating the rheological properties of the soil around the piles will be conducive to the vibration isolation effect of row piles.

Two typical cases including the stiff system of ordinary differential equations ROBER problem and the steady-state mixture fraction equation in jet flame were selected in order to efficiently embed the complex physicochemical information of turbulent combustion into physics-informed neural networks (PINNs). The potential of PINNs in solving combustion chemical differential equations was explored. Results show that the PINNs model can correctly capture the evolution of the zero-dimensional stiff reaction system. PINNs solution accorded well with the conventional numerical solution for steady jet flame. The selection of residual points was particularly important for solving complex differential equations in the field of combustion and chemistry, which should be considered based on the specific configuration in detail.

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 novel method based on machine learning algorithms was proposed to realize the quality prediction and the process parameter optimization, in order to reuse the process information and the inspection information of machining parts effectively. A model-based definition (MBD) model which was integrated with process information and inspection information was treated as input. Process and inspection parameter extraction based on the MBD model was developed and the corresponding structured data set was established through the secondary development of three-dimensional modeling software. Several classifiers in machine learning were used to construct the quality prediction model based on process parameters and quality classification labels. Combining the information gain algorithm, after sorting all process parameters, the process parameter that had the greatest impact on quality was selected. Quality prediction and process parameter optimization tool set was developed to realize the optimization of the selected parameter by using the gradient boost decision tree algorithm. The validity and the reliability of the proposed method were verified by the milling experiment data provided by an aviation company. Results show that the proposed method can realize the quality prediction and process parameter optimization of machining parts effectively.

The accurate thermal model of the typical forced air cooling system was proposed based on the theory of heat conduction, fluid heat transfer and fluid mechanics in order to improve the design efficiency of thermal design. A simplified thermal model was proposed based on the accurate thermal model. The forced air cooling system can be quickly and accurately designed by the simplified thermal model. The simplified thermal model with the advantages of small calculation amount and high design efficiency was applied to the thermal design of 380 V/50 kVar SiC-MOSFET static var generator (SVG). The surface temperature rise error of the SVG heatsink designed by the simplified model was 4.1 ℃ (full load condition), which meeted the requirements of engineering design.

An intelligent determination method was presented for the operating parameters of hard rock tunnel boring machine (TBM) based on extreme gradient boosting (XGBoost) prediction model in order to realize the homogeneity of the tunnel constructions. The field operation index (FOI) was defined as the characteristic parameter of the surrounding rock types in order to replace field penetration index (FPI), and the XGBoost based prediction model was established to realize the accurate prediction of FOI value. The expert model was established to associate the FOI value and the specific TBM operation parameters selected by excellent drivers. Then the intelligent determination of the TBM operation parameters can be accomplished. The experiments on practical engineering data show that the operation parameter can be estimated by the proposed parameters determination system. The experimental results indicated that the mean relative error of thrust speed and cutterhead rotational speed decreased by 8.84 % and 7.97 % compared with the conventional system.