Top Read Articles

    Published in last 1 year |  In last 2 years |  In last 3 years |  All
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Research on efficiency prediction method of reciprocating air compressor based on digital twin technology
    YU Jian-ping, HU Shuang, LIU Xing-wang, TIAN You-wen, QIU Hong-wei, AKOTO Emmauel
    Journal of Lanzhou University of Technology    2024, 50 (1): 48-52.  
    Abstract180)      PDF(pc) (2613KB)(280)       Save
    The method for compressor efficiency prediction and parameter optimization by establishing the reciprocating air compressor digital twin model has the advantage of flexibility, low cost, and good versatility. However, the traditional twin model based on the BP neural network (BPNN) has lots of shortcomings, such as longer training time to establish a module, easily falling into the local optimal solution, and difficulty in achieving the global optimal solution. To solve these problems, a novel digital twin model based on the CIWOA-BPNN algorithm is put forward to determine the key indexes by the principal component analysis method, in which a CIWOA algorithm is introduced to improve the BPNN’s performance. The results show that the new CIWOA-BPNN twin model effectively avoids falling the local optimal problem. The relative error of CIWOA-BPNN is less than 0.6%, and the coefficient of determination is 0.997 75, which greatly improves the prediction accuracy compared with the traditional model.
    Reference | Related Articles | Metrics
    Research on configuration optimization design method of hybrid electric vehicle
    ZHAO Si-li-gen, WANG Jing-yuan, ZHANG Xiao-ming
    Journal of Lanzhou University of Technology    2024, 50 (1): 60-67.  
    Abstract172)      PDF(pc) (3271KB)(231)       Save
    According to the relationship between the structural characteristics and dynamic characteristics of planetary gear vehicle, a theoretical design method of power system configuration of hybrid electric vehicle was proposed. Firstly, all the connections in the configuration are divided into three categories, and the matrix representation is used to represent these connections to reflect the system dynamics and the physical structure of the configuration. Subsequently, a matrix representation method for automatic configuration design is proposed. The speed equation is obtained through matrix operation, and consequently, various configurations of automobile double planetary gear structures are obtained. Finally, the effectiveness of this approach is validated through simulation. Results indicate that with the support of the matrix representation method, the optimal configuration can be selected automatically by computer, which avoids manual calculation and comparison, thereby conserving significant effort and time.
    Reference | Related Articles | Metrics
    Effect of ultrasonic treatment on microstructure and properties of degradable Zn-0.5Sr alloy
    LIU Jian-jun, ZHANG Peng-tao, ZHAO Zhi-xin, ZHANG Jiao, LI Qing-lin, DING Yu-tian
    Journal of Lanzhou University of Technology    2024, 50 (1): 1-9.  
    Abstract172)      PDF(pc) (6577KB)(340)       Save
    The effects of different ultrasonic power (0,300,600,900 W) on the microstructure and corrosion properties of Zn-0.5Sr alloy were studied. The results show that the SrZn 13 phase in the as-cast Zn-0.5Sr alloy changes from coarse polygon to fine block after ultrasonic treatment.Compared with the untreated alloy, the electrochemicalcorrosion rate of the alloy increases from 2.078±0.141 mm/a to 5.747±0.390 mm/a when the ultrasonic power is 600 W.The immersion corrosion rates of Zn-0.5Sr alloy after 15 and 30 days are0.090±0.002 1、0.074±0.001 9 mm/a, respectively, which are 1.88 times and 1.95 times higher than that of the untreated alloy.
    Reference | Related Articles | Metrics
    Fault diagnosis for chemical process based on an improved LSTM neural network
    DU Xian-jun, QIU Xiao-yu
    Journal of Lanzhou University of Technology    2023, 49 (6): 72-79.  
    Abstract172)      PDF(pc) (2999KB)(109)       Save
    According to the characteristics of data nonlinearity, high dimension, and dynamic time sequence in modern chemical processes, traditional methods have low accuracy for fault diagnosis. Therefore, a fault diagnosis method based on improved long short-term memory (LSTM) neural network is designed in this paper. First, the collected fault data were input into a convolutional neural network (CNN) to extract the features and reduce the dimension of the data. Secondly, the processed data was input into the improved LSTM network for deep feature extraction. Finally, the extracted deep feature information was input into the attention mechanism for feature “focusing” to realize feature fusion, and then input into the softmax classifier to realize fault classification. Simulation results on the Tennessee-Eastman (TE) dataset demonstrate that the proposed method is better than recurrent neural network (RNN), gated recurrent unit (GRU), CNN, and deep auto-encoder network (DAEN) in fault classification accuracy and diagnose speed, which has certain advantages in the application of the practical chemical process.
    Reference | Related Articles | Metrics
    Organizational structure and mechanical properties of Al 2O 3 interfacially modified unidirectional fiber C/C composites
    JIA Jian-gang, NIU Chao, ZHANG Zhen, FU Fang-xing, PAN Zi-kang
    Journal of Lanzhou University of Technology    2023, 49 (6): 1-8.  
    Abstract164)      PDF(pc) (5784KB)(143)       Save
    In order to alleviate the brittleness of C/C composites, the unidirectional carbon fiber preform was treated with Boehm sol, and the Al 2O 3 coating was prepared on the fiber surface. The preform was densified by self-made thermal gradient chemical vapor infiltration (TG-CVI) deposition equipment to obtain a dense C/C composite. The bonding strength of the interface and the graphitization degree of the matrix carbon were further adjusted by high-temperature heat treatment.The density of the composite material was tested by drainage method, while tensile properties were assessed with the universal material testing machine. The sample was treated with the visualization of graphene texture (VGT). The microstructure, interfacial, and cross-sectional morphologies of the composite were studied using polarizing microscope (PLM), scanning electron microscope (SEM), and X-ray diffraction (XRD) to analyze phase composition. The results showed that the C/C composites coated with Al 2O 3 coating transform into rough layer (RL) texture in the late deposition stage. After high-temperature heat treatment, the graphitization degree of the carbon matrixis increased. As a result of this, the fracture mechanism of the C/C compositeis significantly changed. The elongation is improved from the initial brittle fracture of the composite to the quasi-ductility. The peak stress of the C f(Al2O3)/C-3 sample reached 77.3 MPa, and the elongation reached 15%.
    Reference | Related Articles | Metrics
    Microstructure and properties of TiNbVMo-(Zr, Cr) refractory high entropy alloys for nuclear application
    LI Ji-jing, HU Shi-wen, LIU De-xue
    Journal of Lanzhou University of Technology    2024, 50 (2): 1-8.  
    Abstract162)      PDF(pc) (6063KB)(223)       Save
    Three novel ductile and single-phase BCC structurerefractory high-entropy alloys (RHEAs)Ti 40Nb 25V 15Mo 5Zr 15 ,Ti 40Nb 30V 20Mo 5Zr 5 andTi 40Nb 30V 20Mo 5Cr 5were developed, and the alloy, exhibit good strength and toughness at room temperature,the alloy Ti 40Nb 25V 15Mo 5Zr 15has a maximum tensile strength of 1 037 MPa. With the decrease of Zr content, the fracture elongation of Ti 40Nb 30V 20Mo 5Zr 5increases from 8.94% to 13.96%.A single layer of corrosion diffusion is only formedafter a static lead-bismuth saturated oxygen corrosion testto Ti 40Nb 30V 20Mo 5Cr 5at 450 ℃ for 100, 300, and 700 h.The thickness of the corrosion layer dno't change significantly with time.
    Reference | Related Articles | Metrics
    Microstructure and properties of AlCoCrFeNi 2.1 high entropy alloy modified by deformation heat treatment
    WANG Peng-hui, ZHANG Xiao-bo
    Journal of Lanzhou University of Technology    2024, 50 (4): 1-5.  
    Abstract158)      PDF(pc) (2366KB)(186)       Save
    High-entropy alloys have become a focal point in the field of materials in recent years due to their combination of high strength, toughness, high-temperature mechanical properties, oxidation resistance, and corrosion resistance. Eutectic high-entropy alloys combine the advantages of eutectic alloys and high-entropy alloys, making it possible to cast large-scale components. The mechanical properties of the alloy are regulated by cold rolling and annealing, and the changes inmicrostructure organization and mechanical properties of the eutectic high-entropy alloy after annealing at different temperatures are investigated by XRD, SEM, EDS, and tensile testing machine. The results showed that the tensile strength of the alloy is abnormally improved after 30% cold rolling, while the elongation plummeted. After annealing at temperatures of 800 ℃, 900 ℃, and1 000 ℃ after 30% cold rolling, the organization gradually changes from partial recrystallisation to complete recrystallisation, accompanied by slight grain growth. After annealing at 800 ℃, there are deformed large grains and recrystallised small grains, and a variety of reinforcement mechanisms work in a coordinated way to make the tensile strength and elongation to 1 272 MPa and 12.39%, respectively.
    Reference | Related Articles | Metrics
    Study on mechanical properties and durability of fiber-geopolymer concrete
    GONG Jin-fang, REN Yong-xiang
    Journal of Lanzhou University of Technology    2024, 50 (2): 24-30.  
    Abstract131)      PDF(pc) (2696KB)(118)       Save
    In order to improve the mechanical properties and durability of geopolymer concrete, experimental studies were conducted on the effects of incorporating polypropylene fibers of varying lengths and dosages on the mechanical properties, frost resistance, chloride ion corrosion resistance, and crack resistance of geopolymer concrete. Furthermore, based on SEM experiments, the mechanism of action of polypropylene fibers was further elucidated from a microscopic perspective. The research results indicated that the addition of polypropylene fibers can improve both the mechanical properties and durability of geopolymer concrete. Specifically, when the fiber content is 0%-0.6%, the improvement effect of geopolymer concrete becomes more pronounced with the increase of fiber content. However, when the dosage exceeds 0.6%, both the mechanical properties and durability begin to decline. SEM analysis further indicated that polypropylene fibers can improve the integrity and compactness of the matrix, thereby significantly improving the mechanical properties and durability of geopolymer concrete. Ultimately, the optimal dosage of polypropylene fibers is recommended to be 0.6% with a length of 12 mm.
    Reference | Related Articles | Metrics
    Microstructure and properties of H13 steel treated by laser hardening and nitriding
    CAO Chi, LUO Wei-dong, CHEN Zhi-lin, LUO Li-ping, CHEN Xian-wu
    Journal of Lanzhou University of Technology    2024, 50 (1): 10-18.  
    Abstract131)      PDF(pc) (10421KB)(83)       Save
    H13 steel surface was modified by laser quenching/plasma nitriding compound treatment method, so as to improve the performance of its surface. The influence process and mechanism of plasma nitriding, laser quenching, and the laser quenching/plasma nitriding compound treatment on the microstructure, mechanical properties, and friction and wear properties of H13 steel were studied by X-ray diffraction, optical observation, scanning electron observation, energy spectrum analysis technology, microhardness and nano testing, and high-frequency reciprocating wear test, respectively.The results showed:that the compound treatment process can significantly improve the comprehensive performance of the modified layer. Compared with single nitriding treatment, the hardness of effective case depth of the compound treatmentmodified layer increased from 1 180 HV and 80 μm to 1 360 HV and 550 μm, respectively. and the friction coefficient and wear rate decreased from 0.68 and 5.78×10 -8 mm 3·N -1·m -1 to 0.59 and 1.35×10 -8 mm 3·N -1·m -1, respectively. The hardness and wear resistance of the specimen are significantly increased, and the average coefficient of friction is significantly reduced.
    Reference | Related Articles | Metrics
    Effect of calcium chloride hexahydrate-based phase change material on energy storage and thermal insulation performance of rock wool insulation board
    YANG Xiao-tian, WANG Cai-long, LIU Jun-yan, GAO Hui, HE Cheng-jun
    Journal of Lanzhou University of Technology    2024, 50 (1): 27-34.  
    Abstract127)      PDF(pc) (4185KB)(219)       Save
    Using rock wool board as carrier, the self-developed calcium chloride hexahydrate-based phase change energy storage material was uniformly infiltrated into rock wool board to prepare rock wool/calcium chloride hexahydrate-based phase change insulation wall board. The influence of calcium chloride hexahydrate-based phase change material on the energy storage and thermal insulation capacity of rock wool board was studied, and its mechanical strength was tested. The test results showed that the maximum adsorption capacity of rock wool board on calcium chloride hexahydrate-based phase change material is 30 wt.%, and maximum specific heat capacity is 0.700 1 MJ/(m 3·K). Although the composite plate show a large thermal conductivity of 0.089 1 W/(m·K) under this adsorption capacity, the corresponding thermal diffusion is the smallest of 0.127 3 mm 2/s. Thermal temperature test showed that the maximum indoor temperature drop by 3.4 ℃ under this adsorption capacity, which indicates that thermal conductivity is not the only factor affecting the thermal insulation performance of rock wool board, and it is more reasonableto evaluate thermal insulation performance by using thermal diffusivity.SEM showed that calcium chloride hexahydrate-based phase change material is adhered to rock wool fibers and form a stable spatial grid structure,which effectively improve the compressive strength of rock wool board.
    Reference | Related Articles | Metrics
    Crack propagation in GH4151 alloy during hot deformation
    LIU Jian-jun, WEI Bao-lin, JIA Zhi, DING Yu-tian
    Journal of Lanzhou University of Technology    2023, 49 (6): 28-32.  
    Abstract122)      PDF(pc) (2919KB)(152)       Save
    GH4151 alloy is a new type of nickel-base superalloy that is difficult to deform and can be used above 800 ℃. Due to the high alloying degree and large grain size of as-cast GH4151, it is easy to crack during hot deformation and can not be deformed such as cogging. The hot deformation behavior of GH4151 alloy at different temperatures and strain rates was investigated by the Gleeble-3500 thermal simulator. Electron backscatter diffraction (EBSD) and scanning electron microscopy (SEM) were used to characterize the typical crack area, and the effects of grain orientation, recrystallization, low energy grain boundary, and solid solution phase on the crack propagation were analyzed. The results showed that the grains with 〈101〉 orientation can effectively hinder crack propagation compared with the grains of 〈001〉 and 〈111〉. The formation of recrystallized grains reduces the stress in the alloy, thereby reducing the crack growth rate. Low-energy grain boundaries have stronger resistance to crack propagation than random grain boundaries, and the greater the number of low-energy grain boundaries at the trifurcate grain boundary, the stronger the resistance effect. The crack propagation is promoted by the formation of a solid solution phase with brittle characteristics.
    Reference | Related Articles | Metrics
    Wavelet ridge extraction based on improved Carazy Climber algorithm
    ZHAO Li-jie, LI Wen-wen, LIU Jin, JIN Dong-li
    Journal of Lanzhou University of Technology    2024, 50 (1): 132-138.  
    Abstract121)      PDF(pc) (4298KB)(75)       Save
    For the problems of time-consuming and low efficiency of extracting multiple wavelet ridges using the traditional Crazy Climber algorithm, an improved Crazy Climber algorithm in simulating normalizing cooling was proposed. The continuous wavelet transform is applied to the response of the structural vibration. In the time-frequency plane composed of the wavelet coefficients amplitudes, the wavelet ridge points are tracked by the simulating normalizing cooling algorithm to make each random point gather on the ridge line, eliminating the operation time. Through the numerical simulation of single-degree of freedom and multi-degree of freedom system, the computational efficiency and recognition accuracy of the proposed algorithm are compared with that of the traditional Crazy Climber algorithm, and the advantages of the proposed algorithm are demonstrated.
    Reference | Related Articles | Metrics
    Image dehazing algorithm based on multi-scale residual and attention mechanism
    CHEN Hui, NIU Li-li, FU Hui, ZHANG Tian-you, XI Lei
    Journal of Lanzhou University of Technology    2024, 50 (2): 69-76.  
    Abstract121)      PDF(pc) (4568KB)(110)       Save
    The presence of fog severely reduces the image quality and hinders further image processing as well as the corresponding feature information extraction. An end-to-end image defogging algorithm based on a multi-scale hole residual block and multi-scale attention mechanism is proposed to address the problems of inadequate feature extraction of existing defogging algorithms. First, the shallow features of the fog map were extracted by three small-scale convolution kernels, which can obtain a large receptive field and reduce the number of parameters. Then, it was input into a plurality of network modules composed of a multi-scale residual hole convolution feature extraction module and multi-scale attention mechanism module in series, in which the multi-scale hole convolution residual feature extraction module could extract the fog map features of different receptive fields and fuse the features of different dimensions to effectively solve the problem of single feature scale, while the multi-scale attention mechanism module reasonably allocated the weights of different features and suppressed irrelevant redundant information. Finally, the fog features in the fog map were filtered to obtain the feature map of the defogging map, followed by restoring the fog-free image using convolution operation. By testing on the sots test set, better visual effects are obtained compared with other classical methods, and the performance on PSNR and SSIM is also better than other classical methods.
    Reference | Related Articles | Metrics
    Molecular dynamics simulation of the deposition process of cold sprayed Fe 0.5CrMnAlCu mixed metal coating
    WEN Jie, WANG Zhao-qin, MA Deng-pan, YUAN Yu-dong, FENG Li
    Journal of Lanzhou University of Technology    2024, 50 (3): 1-8.  
    Abstract120)      PDF(pc) (7406KB)(104)       Save
    The molecular dynamics method was used to simulate the minimum deposition temperature of different metal powders in the process of low pressure cold spraying. The calculation results showed that Mn particles can be effectively deposited at 600 K, Fe particles need a spraying temperature of 700 K and above, and Cr particles need 1 100 K and above to be deposited effectively. Al and Cu particles can be effectively deposited in the temperature range of 500~800 K, and the maximum flattening rate of the two particles exceeds 0.6. When the powders of different metal elements are mixed and deposited at 700 K, due to the interaction and tamping effect of different powder particles during the deposition process, even if the Cr particles do not reach the deposition conditions, the Cr particles are also deposited in the coating like other element particles.
    Reference | Related Articles | Metrics
    Research on the effect of inter-stage flow channel on the cavitation characteristics of tandem high speed centrifugal pump
    WANG Xiao-hui, ZHANG Kai, SONG Xin, HOU Chang-liang, LI Ke-jian
    Journal of Lanzhou University of Technology    2024, 50 (1): 53-59.  
    Abstract115)      PDF(pc) (5787KB)(119)       Save
    In order to analyze the influence of transition flow channels of different shapes on the cavitation characteristics of a tandem high-speed centrifugal pump, the second stage of a certain type of series high-speed centrifugal pump was taken as the research object. Based on the Zwart-Gerber-Belamri cavitation model in ANSYS Fluent, RNG k-ε two-equation turbulence model is used to compare and analyze the pressurization value, blade cavitation area, and cavitation volume in the flow channel under different cavitation numbers of annular and spiral transition channels under the same working conditions. The results show that the pressure increase value of the Secondary pump of the spiral transition channel is increased by about 8.5% in the flow range of 32 000~64 000 L/h, and the efficiency is improved by about 3%~6% under the large flow condition ( qV>52 000 L/h). When the secondary impeller is completely cavitated, the cavitation area on the back of the secondary impeller blade in the spiral transition channel and the cavitation volume in the channel decreases to a certain extent compared with the annular transition channel. Consequently, it can be seen that the helical transition flow channel inhibits the generation of cavitation bubbles in the impeller blade and improves the anti-cavitation performance of the secondary impeller.
    Reference | Related Articles | Metrics
    Parameter optimization design of gear transmission system in wind turbine based on genetic algorithm
    WANG Bao-min, YAN Rui-xiang, FANG Wen-bo, ZHAO Rui-ping, LIU Hong-qin
    Journal of Lanzhou University of Technology    2024, 50 (2): 31-35.  
    Abstract114)      PDF(pc) (670KB)(159)       Save
    The gearbox is an important component of the wind turbine generation system. However, its large volume and high weight pose significant constraints on the development of wind turbine. Taking the 1.5 MW wind turbine as the research object, a mathematical model is established for the lightweight optimization of the gear transmission system, and the genetic algorithm is used to solve the optimization. The optimization results show that the genetic algorithm is practicable and effective, with a reduction of 4.59% in the volume of the optimization gear transmission system, which consequently to the diminution of both the volume and the total mass of the gearbox system. The feasibility of the optimization results is verified by the transmission efficiency of the planetary gear transmission system. The paper provides a new approach to the lightweight design of gear transmission systems in wind turbines.
    Reference | Related Articles | Metrics
    Corrosion deterioration behavior of reinforced concrete based on Weibull distribution in salt spray environment
    WANG Yan-peng, WANG Zi-jian, WANG Li-juan, LIU Ji-lin, FENG Qiong, ZHANG Yun-sheng
    Journal of Lanzhou University of Technology    2023, 49 (6): 9-15.  
    Abstract113)      PDF(pc) (3741KB)(148)       Save
    In view of the serious issue of reinforced concrete deterioration under the atmospheric environment of the western region, the corrosion characteristics of reinforced concrete under salt spray dry-wet accelerating corrosion experiment were investigated by electrochemical and concrete damage degree tests. Based on Weibull distribution function, the deterioration model of reinforced concrete in salt spray environment was established, and the competitive failure analysis was carried out. The results showed that under the environment of salt spray dry-wet cycles, both the protective layer of reinforced concrete and the internal reinforcement exhibit a trend of initial strengtheningand then following subsequent deterioration in corrosion resistance. Weibull distribution function can effectively describe the deterioration process of reinforced concrete under salt spray dry-wet environment. In the early stage of salt spray dry-wet cycles, the damage degree of concrete is more sensitive than the corrosion current density, while in the later stage, the corrosion current density becomes the dominant factor for the deterioration of reinforced concrete.
    Reference | Related Articles | Metrics
    Reliability research of wind turbine based on PAC-FSEM method
    ZHENG Yu-qiao, LANG Qi-fa, SHI Cheng-long, LIU Yu-hang, LIU Yan-jie
    Journal of Lanzhou University of Technology    2024, 50 (1): 35-40.  
    Abstract112)      PDF(pc) (1195KB)(193)       Save
    Based on the relevant operating data from a wind farm in Northwest China, the reliability of wind turbines is studied. Considering the correlation and redundancy among operating data, Principal Component Analysis (PCA) method was used to reduce dimensionality, and some key reliability indicators were selected. Subsequently, a reliability evaluation model is constructed utilizing fuzzy theory in conjunction with the selected key indicators from operational data. A subset of wind turbine operating data is selected for model verification. The research results show that the PCA method extracts the principal component with a cumulative variance contribution rate of 87.585%, which can comprehensively express the reliability information of wind turbines. In the evaluation of a single reliability index, the availability of B02 is as high as 98%, but its total power generation is the lowest. Conversely, the availability of A04 is the lowest in the available area yet relatively higher power generation, indicating potential discrepancies when assessing reliability based on single reliability index. All indicators of A05 and B03 are high, the actual operation state of which is good, and the power generation is high, indicating that their comprehensive reliability is higher, which is consistent with the research results. Therefore, the fuzzy theoretical evaluation model (FSEM) of wind turbine reliability established based on PCA and fuzzy theory is in line with the actual operating state and has guiding significance for quantitatively evaluating the reliability of wind turbines.
    Reference | Related Articles | Metrics
    Numerical simulation and experimental research on fracture toughness of T300/69 laminated considering 90° sub-layup
    WEI Yao-bing, WANG Xue-xue, JIN Yi-fan, LIU Jian-hui, LANG Shan-shan
    Journal of Lanzhou University of Technology    2023, 49 (6): 33-40.  
    Abstract111)      PDF(pc) (4131KB)(163)       Save
    A modified fracture toughness calculation method is proposed in this research to address the shortcoming that the existing fracture toughness calculation model for composite laminates ignores the effects of 90° sub-layers and fiber debonding on fracture toughness. First, in the study of fracture toughness of orthotropic anisotropic fiber-reinforced composites, an extended finite element method is used to simulate the crack expansion process of T300/69 fiber-reinforced composite laminate with the help of ABAQUS finite element software to analyze the effect of 90° sub-layers on the overall fracture toughness of the laminate. Next, the fracture toughness model considering the effect of fiber debonding combined with energy release rate was established considering the effect of 90° sub-layers. Finally, the fracture toughness of T300/69 composite laminate under different paving methods is studied by compact tensile experiments using displacement-load data to verify the accuracy of the model. The results show that the fracture toughness obtained from the model proposed in this paper exhibits minimal disparities from the experimental results, thereby rending it more representative of the real-world applications. The proposed model holds significant practical implications for practical engineering.
    Reference | Related Articles | Metrics
    A generation method of malicious domain name training data based on generating adversarial network
    LIU Wei-shan, MA Xu-qi, WANG Hang, WU Zi-yan
    Journal of Lanzhou University of Technology    2023, 49 (6): 100-106.  
    Abstract109)      PDF(pc) (2595KB)(107)       Save
    Domain generation algorithm(DGA) is widely used by cyber attackers to generate a large number of random domain names to evade detection at present. While the existing DGA domain name detection can not effectively detect unknown malicious domains, because these models are all trained and constructed on publicly available datasets. In this paper, an autoencoder(AE) is first trained using real domain names, and then it is combined with the generative adversarial network(GAN) to construct a new DGA domain name generating model. Experiment results show that the sequences generated by this model are similar to the Alexa domain names in terms of length and character distribution, and it also can effectively reduce the performance of the DGA domain name classifier based on a long short-term memory (LSTM) network. These generated sequences enrich the malicious domain name dataset, which can significantly improve the performance of existing DGA domain name detectors with further utilization.
    Reference | Related Articles | Metrics