Army Infantry College of PLA

Blockchain is a data structure of data blocks arranged in chronological order. It is featured by decentralization, trustworthiness, data sharing, security, etc. It has been widely used in digital currency, smart contract, credit encryption and other fields. With the development of the Internet technology, online education, a novel education mode, has been greatly popularized. However, this education mode still faces many problems in course credibility, credit and certificate certification, stu-dent privacy, and course sharing. Through literature review and case analysis, this paper discusses the basic technical principles and application features of blockchain technology, and proposes a solution to the problems of online educa-tion based on blockchain technology. The blockchain technology can store learn-ing records in a trusted, distributed manner, provide credible digital certificates, realize learning resource sharing with smart contract, and protect intellectual property through data encryption. The research shows that the integration of blockchain technology is a promising trend in the development of online educa-tion.

Clay brick masonry unit (CBMU) walls are widely used in building structures, and its damage and protection under explosion loads have been a matter of concern in the field of engineering protection. In this paper, a series of full-scale experiments of the response characteristics of 24 cm CMBU walls unreinforced and reinforced with polyurea elastomer subjected to blast loading were carried out. Through setting 5.0 kg TNT charges at different stand-off distances, the damage characteristics of masonry walls at different scaled distances were obtained. The reinforcement effect of different polyurea coating thicknesses and methods on the blast resistance performance of masonry walls under single and repeated loads were also explored. Five failure grades were summarized according to the dynamic response features of masonry walls. Based on the stress wave propagation pattern in multi-media composite structures, the internal stress distribution of masonry walls were analyzed, and the division basis of the masonry walls’ failure grades was then quantified. Combined with Scanning Electron Microscope(SEM) images, the deformation characteristics of soft and hard segments of polyurea and effects of detonation products on microstructures were revealed respectively, which provides an important reference for the design and application of polyurea in the blast resistance of clay brick masonry walls.

A novel tracking algorithm is proposed by the integration of the adaptive current statistical (CS) model and the modified strong tracking (ST) square‐root cubature Kalman filter (SCKF) for the manoeuvring aircraft tracking problem. Firstly, the acceleration recursion equation and the acceleration mean input estimation are combined in order to realise the adaptive adjustment of the CS model. Then, the introduced position of the fading factor is relocated from the orthogonality principle and a new formula is put forward. Additionally, the strong manoeuver detection function is established to adjust the manoeuvring frequency of the CS model. The simulation results show that the proposed algorithm possesses better tracking accuracy than the multiple‐fading‐factor SCKF based on the CS model, the SCKF‐ST filter based on the modified CS model and the interacting‐multiple‐model (IMM)‐SCKF. Moreover, the proposed algorithm decreases the runtime by 40% compared with the IMM‐SCKF.

Object detection models based on convolutional neural networks (CNN) have achieved state-of-the-art performance by heavily rely on large-scale training samples. They are insufficient when used in specific applications, such as the detection of military objects, as in these instances, a large number of samples is hard to obtain. In order to solve this problem, this paper proposes the use of Gabor-CNN for object detection based on a small number of samples. First of all, a feature extraction convolution kernel library composed of multi-shape Gabor and color Gabor is constructed, and the optimal Gabor convolution kernel group is obtained by means of training and screening, which is convolved with the input image to obtain feature information of objects with strong auxiliary function. Then, the k-means clustering algorithm is adopted to construct several different sizes of anchor boxes, which improves the quality of the regional proposals. We call this regional proposal process the Gabor-assisted Region Proposal Network (Gabor-assisted RPN). Finally, the Deeply-Utilized Feature Pyramid Network (DU-FPN) method is proposed to strengthen the feature expression of objects in the image. A bottom-up and a top-down feature pyramid is constructed in ResNet-50 and feature information of objects is deeply utilized through the transverse connection and integration of features at various scales. Experimental results show that the method proposed in this paper achieves better results than the state-of-art contrast models on data sets with small samples in terms of accuracy and recall rate, and thus has a strong application prospect.

In order to study the effect pattern of hydrophobic silica aerogel on aerogel foam concrete (AFC), this work successfully prepared silica aerogel foam concrete (AFC) and investigated the influence of the silica aerogel (SA) particle size and content on the properties of AFCs in detail. The microstructure shows that the SAs are inlaid in the foam concrete matrix, forming a physical combination between the two components. Due to the hydrophobic property of SA, its incorporation into AFCs significantly alters the physical and chemical properties of the material. Notably, the primary impact lies in the remarkable antifoaming effect imparted by hydrophobic SA, a phenomenon regulated by both the content and particle size of SA. Furthermore, the introduction of SA imparts hydrophobic characteristics to the prepared AFCs, with enhanced hydrophobicity observed at higher SA content and smaller particle sizes. The study outcomes reveal that the density, compressive strength, and thermal conductivity of AFCs are influenced by the defoaming effect of SA. Specifically, a decrease in particle size of SA correlates with increased density and compressive strength in AFCs, primarily attributed to the defoaming effect of SA influencing the pore structure of the material. Simultaneously, the thermal conductivity of AFCs falls within the range of 59.0–83.5 mW/m/K, a metric affected by both the SA content and the concurrent defoaming effect. By investigating the influences of silica aerogel particle size and content, this work contributes some novel insights into optimizing the comprehensive performance of AFCs, which is conducive to the development of aerogel composites.

Because the dual-mass MEMS gyroscope's output is greatly influenced by temperature, which can lead to errors that cannot be ignored. To solve this problem, a novel compensation method is proposed: a parallel processing algorithm, which integrates the Permutation entropy (PE), Local Characteristic-scale Decomposition (LCD) and Adaptive network-based fuzzy inference system (ANFIS). Firstly, LCD is used to decompose the output which contains temperature noises and drifts into a trend component and several intrinsic scale components (ISC), according to autocorrelation and complexity, three different categories will be obtained by PE: pure noise output, mixed output, and drift output. The different processes are as follows, the noise output is discarded, the mixed output is filtered by SG (Savitzky-Golay filter), then dual ANFIS is applied. Since the drift output completely reflects the temperature characteristics, the degree of non-linearity is high, the ANFIS with complex rules is used for processing. And the mixed output is composed of intermediate layer modes, containing a relatively small amount of temperature characteristics, simple rule ANFIS is adopted for processing. Finally, the signal is reconstructed. After that, the temperature error experiment is carried out, the result shows the method can effectively eliminate the error and compensate for the drift, it has a fast convergence speed and good effect, and has the advantage of good compensation efficiency.

In order to further study the blast mitigation performance of polyurea and to investigate the protection mechanism and damage characteristics of polyurea-protected structures under contact explosion loads, based on earlier work, this paper investigated the response and energy absorption performance of polyurea under various frequency loads. Qtech T26 blast mitigation polyurea (T26 polyurea) was adopted to protect the reinforced concrete (RC) slab and damage analysis of the post-explosion specimens was carried out at micro and macro levels. The response and energy absorption capacity of the material towards different frequency loads were investigated by dynamic mechanical analysis (DMA). Protective performance of T26 polyurea on RC slab was examined with a 10 kg TNT contact explosion test. Scanning electron microscopy (SEM) was employed to analyze the microscopic fracture morphology of the typical areas of the coating after the explosion. The chemical structure changes of the blast-face coating before and after the explosion were compared by Fourier transform infrared spectroscopy (FTIR). The results show that the glass transition region of T26 polyurea is −40 °C to 10 °C, which is a large temperature range, and the microphase separation of T26 polyurea is low. It is significantly influenced by the ambient temperature and loading frequency. The energy absorption of T26 polyurea is realized through the interaction between the hard and soft segments. When the frequency is between 102 Hz and 106 Hz, the loss factor of T26 polyurea is between 0.20 and 0.31, which exhibits a good energy dissipation performance. In the contact explosion of 10 kg TNT, the fragmentation rate of the coated specimen decreased significantly compared with that of the unprotected specimen, realizing the zero fragmentation protection effect on the back-blast face. The maximum deformation area and the main energy absorption area of T26 polyurea under contact explosion is the ring area outside the longitudinal deformation area. The chemical structure of T26 polyurea changed significantly after the explosion; typically the N-H bonds, etc., were broken and the percentage of hydrogen bonding was reduced. T26 polyurea has realized the protection effect of zero fragmentation of large-equivalent contact explosion, which has a high application value for blast mitigation and blast-fragmentation prevention in actual engineering.

In this paper, we study the static discrete berth allocation problems (BAPs) for large-scale time-critical marine-loading scenarios. The objective is to allocate the vessels to different types of berths so that all the vessels can be loaded within the minimum time under the tidal condition. The BAP is formalized as a min–max problem. This problem is rather complex as the vessels and berths are quite numerous in the large-scale marine-loading problem. We analyze this problem from a novel perspective, and find out that this problem has the characteristic of partially separable. Therefore, the iterative variable grouping genetic algorithm (IVGGA) is designed to search the near-optimal berth allocation plans. The vessels and berths are divided into subgroups, and the genetic algorithm (GA) is applied to generate the near-optimal berth allocation plans in each subgroup. To achieve the balance of loading tasks among subgroups, we propose reallocating some vessels among subgroups according to the berth allocation plans in subgroups. To guarantee the convergency of the algorithm, an iterative vessel reallocation policy is devised considering the loading tasks of different types of berths. We demonstrate the proposed algorithm in dealing with large-scale BAPs through numerical experiments. According to the results, we find that the proposed algorithm would have good performance when the number of vessels in each subgroup are kept in medium scale. Compared with the original GA, our algorithm shows the effectiveness of the iterative variable grouping strategy. The performance of our algorithm is almost not changed as the number of vessels and berths increases. The proposed algorithm could obtain efficient berth allocation plans for the large-scale marine-loading problem.

In this work, we prepared heat-treated aramid pulp/silica aerogel composites (AP/aerogels) and investigated in detail the feasibility of improving thermal stability and thermal insulation via tailored heat treatment. The microstructure and FTIR spectra reveal that AP/aerogels are formed by a physical combination of the silica aerogel matrix and aramid pulps. When the heat treatment temperature increases, the density slightly decreases and then increases to the maximum due to the significant volume shrinkage. The pyrolysis of aramid pulp and the collapse of silica skeletons occur during heat treatment; nevertheless, the typical structures of AP/aerogels do not change significantly. It is also found that both the hydrophobicity and the thermal insulation decrease with the increasing heat treatment temperature. We note that when the heat treatment is at 600 °C, the AP/aerogel still maintains a low density of 0.19 g/cm3 and a contact angle of 138.5°. The thermal conductivity is as low as 26.11 mW/m/K, measured using the transient hot wire method. Furthermore, the heat-treated AP/aerogels can avoid heat shock and possible thermal hazards during practical thermal insulation applications. The onset temperatures of the thermal decomposition of AP/aerogels increase from 298.8 °C for an untreated one to 414.7 °C for one treated at 600 °C, indicating that the thermal stability of AP/aerogels is improved significantly. This work provides a practical engineering approach to expand the thermal insulation applications of silica aerogel composites.

Vectors are a key type of geospatial data, and their discretization, which involves solving the problem of generating a discrete line, is particularly important. In this study, we propose a method for constructing a discrete line mathematical model for a triangular grid based on a “weak duality” hexagonal grid, to overcome the drawbacks of existing discrete line generation algorithms for a triangular grid. First, a weak duality relationship between triangular and hexagonal grids is explored. Second, an equivalent triangular grid model is established based on the hexagonal grid, using this weak duality relationship. Third, the two-dimensional discrete line model is solved by transforming it into a one-dimensional optimal wandering path model. Finally, we design and implement the dimensionality reduction generation algorithm for a discrete line in a triangular grid. The results of our comparative experiment indicate that the proposed algorithm has a computation speed that is approximately 10 times that of similar existing algorithms; in addition, it has better fitting effectiveness. Our proposed algorithm has broad applications, and it can be used for real-time grid transformation of vector data, discrete global grid system (DGGS), and other similar applications.

Giant magnetostrictive actuators (GMA) are widely used in the field of servo valves, but the displacement of GMA is limited, which renders meeting the requirements of large flow direct-drive electro-hydraulic servo valves (DDV) difficult. In order to solve these problems, this study proposes a double-row bow-type micro-displacement amplifier (DBMA), used to increase output displacement of GMA to meet the requirements. This study, by static analysis, analyzes the force of a flexure hinge based on theoretical mechanics and material mechanics, derives the stiffness matrix of the flexure hinge by the influence coefficient method, establishes the pseudo-rigid model, and derives the amplification ratio of a DBMA. Also, by kinetic analysis, using Castigliano's second theorem, a formula of equivalent stiffness and natural frequency of DBMA were derived and the influences of different parameters on them were analyzed, respectively. After that, we analyzed the amplifier using finite element method (FEM) simulation software and verified the model by manufacturing a prototype and building a test system. Theoretical calculations and experimental results showed that the amplification ratio of the DBMA fluctuated between 15.43 and 16.25. The natural frequency was about 305 Hz to 314 Hz and the response bandwidth was up to 300 Hz. The error among the theoretical, simulated, and experimental values was within 8%, supporting the accuracy of the model.

It is a challenge for existing artificial intelligence algorithms to deal with incomplete information of computer tactical wargames in military research, and one effective method is to take advantage of game replays based on data mining or supervised learning. However, the open source datasets of wargame replays are extremely rare, which obstruct the development of research on computer wargames. In this paper, a data set of wargame replays is opened for predicting algorithm on the condition of incomplete information, to be specific, we propose the dataset processing method for deep learning and an network model for enemy locations predicting. We first introduce the criteria and methods of data preprocessing, parsing and feature extraction, then the training set and test set for deep learning are predefined. Furthermore, we have designed a newly specific network model for enemy locations predicting, including multi-head input, multi-head output, CNN and GRU layers to deal with the multi-agent and long-term memory problems. The experimental results demonstrate that our method achieves good performance of 84.9% on top-50 accuracy. Finally, we open source the data set and methods on https://github.com/daman043/AAGWS-Wargame-master.

In the research on firepower strike optimization of intelligent battlefield multi-weapon platform, in order to improve the overall strike effectiveness of weapons, it is necessary to establish a weapon target allocation model to obtain real-time and accurate strike plans, and obtain strike-related strike parameters through data model comparison. To this end, this article first introduces the concept, classification and basic mathematical model of the WTA problem, and sorts out the progress of the weapon-target assignment (WTA) problem at home and abroad. For the analysis of the WTA problem, you can use the genetic algorithm "survival of the fittest, survival of the fittest" mechanism, the particle swarm algorithm iterative process is simple and fast, and the ant colony algorithm has clear goals and strong scalability, etc. to obtain a precise strike plan to solve the problem of low real-time firepower strikes, The problem of low accuracy, finally pointed out the lack of horizontal comparison between the current WTA problem and the intelligent optimization algorithm research, and clarified the next development direction from the three perspectives of the feasibility, effectiveness and scalability of the WTA problem.

A novel fusion algorithm is proposed based on Improved Adaptive Wavelet Threshold De-noising (IAWTD), C-means Support Vector Machine (CSVM) and Ensemble Empirical Mode Decomposition (EEMD) method to eliminate the humidity drift of MEMS gyroscope. Firstly, the IAWTD method is employed to decrease the humidity drift component in MEMS gyroscope output signal. Then, the humidity drift compensation model is established: the input elements are the relative humidity, the change rate of relative humidity and the humidity drift, and the output is the compensated MEMS gyroscope output signal by EEMD method. In order to verify the compensation effect of the fusion algorithm, the gyroscope outputs are collected and analyzed with the relative humidity ranged from 40% to 90% based on the temperature varying from 20°C to 60°C. The results show that the IAWTD-CSVM-EEMD method significantly reduces the influence of relative humidity drift on the gyroscope output, according to the quantitative analysis of Allan variance, the quantization noise of the gyroscope output decreases by 87.78%, 96.37%, 97.77%, 99.17% and 92.62% respectively under the relative humidity ranging from 40% to 90%, as the temperature rose from 20 °C to 60 °C at intervals of 10 °C. In addition, the bias stability decreases by 96.9%, 99.41%, 99.1%, 99.46%, and 99.78% respectively and the angle random walk decreases by 88.16%, 96.54%, 98.16%, 94.43%, and 92.05% respectively at different temperatures. It is worth mentioning that, to further verify the applicability of the fusion algorithm, a group of comparative experiments are added to consider the influence of temperature changes on the gyroscope output under different relative humidity. The experimental results show that the quantization noise, bias stability and angle random walk of the MEMS gyroscope are significantly reduced compared with the original output after processing by IAWTD-CSVM-EEMD. Therefore, the method proposed in this paper is beneficial to reduce the humidity drift in the MEMS gyroscope output.

In this study, a unique mechanical exfoliation route, liquid-electric effect, is applied to prepare few-layer black phosphorene using black phosphorus powders through liquid pulsed discharge.

The premise of analyzing and researching robot technology is to establish a proper mathematical model and then to solve it with kinematics. In this study, a self-developed humanoid hydraulically driven dual-arm robot is taken as the research object, and the DH (Denavit–Hartenberg) parameter method and the rotational exponential formula (POE) are used to solve the kinematics of the robot. The calculation results are verified by simulation. The advantages and disadvantages of the two methods are analyzed. The differences between the two methods are compared. It lays a foundation for other scholars to choose mathematical models when analyzing the mechanism in the future.

Animal pose estimation (APE) boosts the understanding of animal behaviors. Recent vision-based APE has attracted extensive attention due to the advantages of contactless and sensorless applications. One of the main challenges in APE is the lack of high-quality keypoint annotations for different animal species since manually annotating the animal keypoints is very expensive and time-consuming. Existing works alleviate this problem by synthesizing APE data and generating pseudo-labels for unlabeled animal images. However, feature representations learned from synthetic images could not be directly transferred to real-world scenarios, and the generated pseudo-labels are usually noisy, which limits the model’s performance. To address the above challenge, we propose a novel cross-domain vision transformer for APE to Transfer Human pose estimation to Animal pose estimation, termed THANet, as humans share skeleton similarities with some animals. Inspired by the success of ViTPose in HPE, we design a unified vision transformer encoder to extract universal features for both animals and humans followed by two task-specific decoders. We further introduce a simple but effective cross-domain discriminator to bridge the domain gaps between the human pose and the animal pose. We evaluated the proposed THANet on the AP-10K and Animal-Pose benchmarks, and the extensive experiments show that our method achieves a promising performance. Specifically, the proposed vision transformer and cross-domain method significantly improve the model’s accuracy and generalization ability for APE.

Introduction: The volume conduction effect and high dimensional characteristics triggered by the excessive number of channels of EEG cap-acquired signals in BCI systems can increase the difficulty of classifying EEG signals and the lead time of signal acquisition. We aim to combine transfer learning to decode EEG signals in the few-channel case, improve the classification performance of the motor imagery BCI system across subject cases, reduce the cost of signal acquisition performed by the BCI system, and improve the usefulness of the system. Methods: Dataset2a from BCI CompetitionIV(2008) was used as Dataset1, and our team's self-collected dataset was used as Dataset2. Dataset1 acquired EEG signals from 9 subjects using a 22-channel device with a sampling frequency of 250 Hz. Dataset2 acquired EEG signals from 10 healthy subjects (8 males and 2 females; age distribution between 21-30 years old; mean age 25 years old) using an 8-channel system with a sampling frequency of 1000 Hz. We introduced EA in the data preprocessing process to reduce the signal differences between subjects and proposed VFB-RCSP in combination with RCSP and FBCSP to optimize the effect of feature extraction. Results: Experiments were conducted on Dataset1 with EEG data containing only 8 channels and achieved an accuracy of 78.01 and a kappa coefficient of 0.54. The accuracy exceeded most of the other methods proposed in recent years, even though the number of channels used was significantly reduced. On Dataset 2, an accuracy of 59.77 and a Kappa coefficient of 0.34 were achieved, which is a significant improvement compared to other poorly improved classical protocols. Discussion: Our work effectively improves the classification of few-channel EEG data. It overcomes the dependence of existing algorithms on the number of channels, the number of samples, and the frequency band, which is significant for reducing the complexity of BCI models and improving the user-friendliness of BCI systems.

A mechanical model for the strength prediction of composite ceramics (CC) with nano-interface and micro-interface is presented based on nano-interface damage mechanism and micro-interface damage mechanism. Firstly, on the basis of composite microstructure, micro-domain whose main component is regularly arranging eutectic crystal is built. Moreover, nano-cell is brought into eutectic crystal which is comprised of parallel inclusions, nano-interfaces, matrix and effective medium. Secondly, the stress field of micro-domain is deduced based on interaction direct derivative. Thirdly, three failure mechanisms of micro-domain including the fracture of eutectic crystal based on the damage of nano-interface, the slipping and cracking of micro-interface among eutectic crystals are taken into account. Finally, the strength model of the composite ceramic is obtained by using random distribution of the micro-domain, and several factors that may decrease the strength of the composite ceramic are analyzed. The results indicate that inclusion size, volume fraction and micro-interface cracking size are the three primary factors decreasing the strength of composite, while the shapes of inclusion and structure of domain have little influence on the strength of composite. The comparison with experimental data shows that the model is effective in the explanation of the failure mechanism of composite ceramic with nano-interface and micro-interface.

The performance of piezoelectric actuator ceramics under strong electric field(20 kV/cm) and variable temperature (30~150℃) were tested on a piezoelectric ceramic thermo-electro-mechanical multi-field loading test bench. The variation of hysteresis loop, strain loop, free capacitor and dielectric loss tangent with temperature was analyzed. A mathematical model of displacement characteristics of ceramic materials considering temperature effect is established, and the accuracy of the model is verified. The results show that the hysteresis loops become slender with the increasing of temperature, while the residual polarization, maximum polarization and coercive field decrease. The effect of the temperature on the residual polarization and coercive field is stronger than that on maximum polarization. The strain loop presents a typical butterfly curve, and the negative strain decreases gradually to 0.12% with the increasing of temperature. In the unipolar electric field, the residual polarization varies slightly with the increasing of temperature, and the maximum polarization increases about 40%. The piezoelectric constant of the material increases linearly. The free capacitor and dielectric loss tangent increases continuously. The higher the temperature, the greater the increase.