A modulation recognition algorithm based on a hybrid attention prototype network is proposed to address the modulation recognition problem of communication signals with very few labeled samples. Integrating the ideas of meta learning and metric learning, the signal is mapped to a new feature metric space through a feature extraction module within the prototype network framework, and the modulation style of the query signal is determined by comparing the distances between various prototypes and the query signal in this space. A feature extraction module was designed based on the temporal characteristics of the communication signal IQ component, which is cascaded by a convolutional neural network and a long and short term memory network. The convolutional attention mechanism was introduced to enhance the weight of key features; Adopting an Episode based training strategy, the algorithm can be generalized to new signal recognition tasks. The simulation results show that the proposed algorithm has an average recognition rate of 85.68% when there are only 5 labeled samples (5-way 5-shot) for each type of signal.
{"title":"Modulation recognition algorithm based on mixed attention prototype network","authors":"Yi Pang, Hua Xu, Lei Jiang, Yunhao Shi, Xiang Peng","doi":"10.1051/jnwpu/20224061375","DOIUrl":"https://doi.org/10.1051/jnwpu/20224061375","url":null,"abstract":"针对极少量带标签样本条件下的通信信号调制识别难题, 提出一种基于混合注意力原型网络的调制识别算法。综合元学习和度量学习的思想, 在原型网络框架下通过特征提取模块将信号映射至一个新的特征度量空间, 并通过比较该空间内各类原型与查询信号之间的距离确定查询信号调制样式。根据通信信号IQ分量的时序特点设计了由卷积神经网络和长短时记忆网络级联的特征提取模块, 并引入卷积注意力机制提升关键特征的权重; 采用基于Episode的训练策略, 使算法可泛化到新的信号识别任务中。仿真结果表明, 所提算法在每类信号只有5个带标签样本(5-way 5-shot)时平均识别率可达85.68%。","PeriodicalId":39691,"journal":{"name":"西北工业大学学报","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45835984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-01DOI: 10.1051/jnwpu/20224061250
Ning Xie, Dengkai Chen, Yao Zhou, Xian Zhang
In order to reduce the probability of human error in the cockpit of a civil aircraft, based on the SHEL model, this paper classifies performance shaping factors (PSF) that affect the human factor reliability of the human-machine interface. Then it constructs the relevant PSF system and uses the interpretation structure model to establish the corresponding adjacency matrix. When a multi-level recursive structure is obtained, the Noisy-OR model is introduced to construct the Bayesian network, thus establishing the new human-machine interface evaluation method. Real cases are used to verify the effectiveness of the method thus established through causal inference with the Bayesian network. The evaluation method for the reliability of a set of human factors this paper proposes provides a new approach to evaluating the human-machine interface in the cockpit of a civil aircraft.
{"title":"A method for evaluating human-machine interface in civil aircraft cockpit based on human factor reliability","authors":"Ning Xie, Dengkai Chen, Yao Zhou, Xian Zhang","doi":"10.1051/jnwpu/20224061250","DOIUrl":"https://doi.org/10.1051/jnwpu/20224061250","url":null,"abstract":"In order to reduce the probability of human error in the cockpit of a civil aircraft, based on the SHEL model, this paper classifies performance shaping factors (PSF) that affect the human factor reliability of the human-machine interface. Then it constructs the relevant PSF system and uses the interpretation structure model to establish the corresponding adjacency matrix. When a multi-level recursive structure is obtained, the Noisy-OR model is introduced to construct the Bayesian network, thus establishing the new human-machine interface evaluation method. Real cases are used to verify the effectiveness of the method thus established through causal inference with the Bayesian network. The evaluation method for the reliability of a set of human factors this paper proposes provides a new approach to evaluating the human-machine interface in the cockpit of a civil aircraft.","PeriodicalId":39691,"journal":{"name":"西北工业大学学报","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49245698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Polishing force is a key parameter that affects the quality and efficiency of the flexible polishing surface of the centenary wheel, and the normal displacement of the centenary wheel and the workpiece is a direct factor affecting the polishing force. Therefore, establishing a relationship model between the two is very important and necessary. A surface abrasive particle distribution function was established based on the structural characteristics of the hundred leaf wheel; Based on the elastic-plastic contact theory, the expression of polishing force and workpiece deformation under the action of a single abrasive particle is obtained, and a relationship model between polishing force and normal displacement is established based on the distribution function of abrasive particles on the surface of the wheel; Verify the established relationship model through simulation and experiments. The results indicate that the relationship model can better reflect the corresponding relationship between polishing force and normal displacement in the flexible polishing process.
{"title":"Research on the contact model between the polishing force and normal displacement in the flexible polishing using ABFW","authors":"Junfeng Zhang, Yaoyao Shi, Xiaojun Lin, Xiaojun Wu","doi":"10.1051/jnwpu/20224061335","DOIUrl":"https://doi.org/10.1051/jnwpu/20224061335","url":null,"abstract":"抛光力是影响百页轮柔性抛光表面质量和效率的关键参数, 而百页轮和工件的法向位移是影响抛光力的直接因素, 因此建立二者的关系模型十分重要和必要。根据百页轮结构特性建立了其表面磨粒分布函数; 基于弹塑性接触理论得到单颗磨粒作用时抛光力和工件变形量的表达式, 并根据百页轮表面磨粒分布函数建立了抛光力和法向位移的关系模型; 通过仿真和实验对所建立关系模型进行验证。结果表明: 该关系模型可较好地体现柔性抛光过程中抛光力和法向位移的对应关系。","PeriodicalId":39691,"journal":{"name":"西北工业大学学报","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45481518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vanishing point detection is an important component of vision based autonomous navigation for unmanned vehicles. Due to the lack of clear road lines and complex background interference in unstructured scenes, existing detection methods generally have the drawbacks of low accuracy and long calculation time. Therefore, a vanishing point detection method combining stereo vision is proposed based on the characteristics of unstructured roads. Using binocular stereo vision technology to obtain disparity maps of road images, and using breadth first algorithm to quickly estimate the background area of the road image; Design a four sided five scale Gabor filter bank to estimate the pixel response amplitude, and reduce detection errors through amplitude correction; Design a series of voting point selection strategies based on the background area to eliminate interference in the background area and improve algorithm accuracy; Adopting a strategy of dynamically adjusting the range of candidate points to reduce the search range of vanishing points, thereby improving algorithm efficiency; We have designed an angle first voting function that treats candidate points that obtain the maximum number of votes in the voting space as vanishing points. The results show that the improved method has good robustness in complex background interference scenarios, and has significant improvements in detection speed and accuracy.
{"title":"Research on vanishing point detection of unstructured road scene combined with stereo vision","authors":"Xing Chen, Wenhai Zhang, L. Yang, Xunjia Zheng","doi":"10.1051/jnwpu/20224061431","DOIUrl":"https://doi.org/10.1051/jnwpu/20224061431","url":null,"abstract":"消失点检测是基于视觉的无人车辆自主导航的重要组成部分。由于非结构化场景存在缺乏清晰的道路线和复杂的背景干扰等问题, 现有检测方法普遍存在精度低、计算时间长的缺点。因此, 针对非结构化道路特点, 提出了一种结合立体视觉的消失点检测方法。采用双目立体视觉技术获得道路图像的视差图, 使用广度优先算法快速估计出道路图像的背景区域; 设计四方向五尺度的Gabor滤波器组估计像素响应幅值, 并通过幅值校正减少检测误差; 结合背景区域设计一系列投票点选择策略, 来剔除背景区域的干扰, 提高算法精度; 采用动态调整候选点范围策略, 减少消失点的搜索范围, 从而提高算法效率; 设计了一种角度优先投票函数, 将在投票空间中获得最大票数的候选点视为消失点。结果表明, 改进的方法在复杂背景干扰的场景下具有较好的鲁棒性, 在检测速度和检测精度上都有显著提升。","PeriodicalId":39691,"journal":{"name":"西北工业大学学报","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49635595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-01DOI: 10.1051/jnwpu/20224061212
Junchao Liu, Luyi Li
The importance analysis of a structural system with distribution parameter uncertainty can identify key parameters that significantly affect its output performance, thus providing importance guidance for its design and optimization. However, the traditional importance analysis method requires the three-loop Monte Carlo sampling to estimate the importance measurement index of a distribution parameter with such output characteristic values as mean and variance, whose computational cost is too large. To solve this problem, two efficient cubature formula methods based on the surrogate sampling probability density function (SSPDF) for the importance analysis of distribution parameters are proposed: ①the double-loop cubature formula based on the surrogate sampling probability density function (S-DLCF); ②the single-loop cubature formula based on the surrogate sampling probability density function (S-SLCF). The two methods use cubature formulas to efficiently compute the nested mean and variance in the importance measurement index of a distribution parameter, thus solving the problem that the computational effort of propagating parameter uncertainty to output characteristic values depends on parameter dimensionality because of SSPDF. The S-DLCF makes full use of the efficiency and accuracy of the cubature formula to estimate output statistical moments; the S-SLCF simplifies the integral to calculate output moments by expanding the dimensionality of the distribution parameter. The numerical and engineering examples verify the efficiency and accuracy of the two methods for the importance analysis of distribution parameters.
{"title":"Efficient importance analysis methods for structures with distribution parameter uncertainty based on cubature formula","authors":"Junchao Liu, Luyi Li","doi":"10.1051/jnwpu/20224061212","DOIUrl":"https://doi.org/10.1051/jnwpu/20224061212","url":null,"abstract":"The importance analysis of a structural system with distribution parameter uncertainty can identify key parameters that significantly affect its output performance, thus providing importance guidance for its design and optimization. However, the traditional importance analysis method requires the three-loop Monte Carlo sampling to estimate the importance measurement index of a distribution parameter with such output characteristic values as mean and variance, whose computational cost is too large. To solve this problem, two efficient cubature formula methods based on the surrogate sampling probability density function (SSPDF) for the importance analysis of distribution parameters are proposed: ①the double-loop cubature formula based on the surrogate sampling probability density function (S-DLCF); ②the single-loop cubature formula based on the surrogate sampling probability density function (S-SLCF). The two methods use cubature formulas to efficiently compute the nested mean and variance in the importance measurement index of a distribution parameter, thus solving the problem that the computational effort of propagating parameter uncertainty to output characteristic values depends on parameter dimensionality because of SSPDF. The S-DLCF makes full use of the efficiency and accuracy of the cubature formula to estimate output statistical moments; the S-SLCF simplifies the integral to calculate output moments by expanding the dimensionality of the distribution parameter. The numerical and engineering examples verify the efficiency and accuracy of the two methods for the importance analysis of distribution parameters.","PeriodicalId":39691,"journal":{"name":"西北工业大学学报","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49584557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurately obtaining the vibration environment of aircraft structures and onboard equipment is crucial. Traditional vibration environment prediction methods have low accuracy and may lead to issues of over or under testing in later vibration environment tests. An innovative vibration environment prediction method based on Extended Operating Condition Transfer Path Analysis (OPAX) was proposed. A vibration environment prediction model was constructed using measured data, and then the model was used to predict the vibration environment under new operating conditions. In the laboratory environment, a vibration testing system for a typical equipment compartment of a certain type of aircraft was built, and a vibration environment prediction model for airborne equipment was built based on the OPAX method, and its prediction accuracy was verified. Comparing the expected results with the experimental results, it was found that: ① the error between the predicted root mean square value of the model under new operating conditions and the root mean square value of the experimental test remained within 20%; ② Within the expected frequency range, the expected change trend of the model under new operating conditions is basically consistent with experimental testing, with significant differences at individual frequencies. Based on the predicted results under new working conditions, this vibration environment prediction method based on OPAX has high prediction accuracy, requires less data to build the model, is convenient to build, and has operability and practical engineering value.
In the context of the integration of smart grids and new energy generation, the widespread use of power electronic interface devices will introduce additional DC bias to the system. Therefore, the DC bias suppression ability of the grid voltage information acquisition algorithm has become crucial. The second-order generalized integrator phase-locked loop (SOGI-PLL) is widely used in the synchronization and extraction of power grid information, which can effectively suppress the impact of frequency fluctuations and phase jumps on the accuracy of power grid state estimation. However, its adaptive frequency feedback loop is very sensitive to DC bias contained in the power grid while achieving harmonic suppression. A cascaded SOGI-PLL (FFCD-SOGI-PLL) with fixed frequency feedback is proposed to address this issue. The cascaded structure is used to input the nominal frequency of the fixed power grid, achieving signal DC component filtering and enhancing harmonic suppression performance. Provide stability analysis and parameter design methods through small signal models. The experimental results show that when the power grid voltage contains DC components, harmonics, and voltage drops, the designed FFCD-SOGI-PLL can quickly and stably accurately estimate the voltage state information of the power grid.
{"title":"State estimation of power grid under smart grid integration based on FFCD-SOGI-PLL","authors":"Xiangyu Zhou, Zhen Zhang, Ruiqing Ma, Chun-Yi Wu, Yong-man Lu, Kang Xiangli, Danqing Wang","doi":"10.1051/jnwpu/20224061343","DOIUrl":"https://doi.org/10.1051/jnwpu/20224061343","url":null,"abstract":"在智能电网与新能源发电融合背景下, 电力电子接口装置的大量使用将给系统引入额外的直流偏置。因此, 电网电压信息获取算法的直流偏置抑制能力变得至关重要。二阶广义积分器锁相环(SOGI-PLL)广泛应用于电网信息的同步与提取, 可以有效抑制频率波动和相位跳变对电网状态估计精度的影响, 但其自适应频率反馈环节在实现谐波抑制的同时, 对于电网中含有的直流偏置非常敏感。针对这一问题, 提出了一种固定频率反馈的级联SOGI-PLL(FFCD-SOGI-PLL), 使用级联结构输入固定电网标称频率, 实现信号直流分量滤除, 增强了谐波抑制性能。通过小信号模型给出其稳定性分析和参数设计方法。实验结果表明, 在电网电压含有直流分量、谐波以及电网电压跌落时, 设计的FFCD-SOGI-PLL可以快速稳定地对电网电压状态信息进行精确估计。","PeriodicalId":39691,"journal":{"name":"西北工业大学学报","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45391404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D flip-flop is the basis of timing logic circuit, and SEMU phenomenon tends to be serious with the integrated circuit process size shrinking to nanometer scale. The anti-SEU ability based on DICE structure for D flip-flop cannot meet the requirements of aerospace engineering. Based on the SEU reinforcement technology of D flip-flop under nano-technology and the SEU mechanism of DICE structure, a layout-level anti-SEU flip-flop design method based on DICE circuit structure is proposed considering the circuit performance, area, power consumption and other resource costs. And then a D flip-flop with SEU resistance is designed by commercial 65 nm process, and the designed flip-flop area is 1.8 times that of commercial structure flip-flop. The function and and radiation simulation results indicate that the establishment time and transmission delay of the flip-flop are equivalent to those of the commercial one, and no SEU occurs under the Ge ion bombardment with the LET threshold of approximately 37 MeV·cm2/mg. The performance of the flip-flop circuit and the ability to resist single particle soft error are excellent. In the anti-radiation ASIC design, the area, wiring resources and timing overhead caused by the reinforcement of the D flip-flop circuit are greatly saved.
{"title":"Single event upset reinforcement technology of DICE flip-flop based on layout design","authors":"Xiaoling Lai, Jian Zhang, Ting Ju, Qi Zhu, Yangming Guo","doi":"10.1051/jnwpu/20224061305","DOIUrl":"https://doi.org/10.1051/jnwpu/20224061305","url":null,"abstract":"D flip-flop is the basis of timing logic circuit, and SEMU phenomenon tends to be serious with the integrated circuit process size shrinking to nanometer scale. The anti-SEU ability based on DICE structure for D flip-flop cannot meet the requirements of aerospace engineering. Based on the SEU reinforcement technology of D flip-flop under nano-technology and the SEU mechanism of DICE structure, a layout-level anti-SEU flip-flop design method based on DICE circuit structure is proposed considering the circuit performance, area, power consumption and other resource costs. And then a D flip-flop with SEU resistance is designed by commercial 65 nm process, and the designed flip-flop area is 1.8 times that of commercial structure flip-flop. The function and and radiation simulation results indicate that the establishment time and transmission delay of the flip-flop are equivalent to those of the commercial one, and no SEU occurs under the Ge ion bombardment with the LET threshold of approximately 37 MeV·cm2/mg. The performance of the flip-flop circuit and the ability to resist single particle soft error are excellent. In the anti-radiation ASIC design, the area, wiring resources and timing overhead caused by the reinforcement of the D flip-flop circuit are greatly saved.","PeriodicalId":39691,"journal":{"name":"西北工业大学学报","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44462710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-01DOI: 10.1051/jnwpu/20224061233
Yifei Wang, J. Dang, Chuang Huang, Haiyu Xu, Z. Zuo
To study the influence of attack angle on ventilated supercavitating flow, a numerical model is established to simulate the supercavitation flow by using the inhomogeneous multiphase flow model and the SST k-ω turbulence model. And then, the model is verified and validated by comparing with the experimental results. The effect of attack angle on the profile of ventilated supercavity was numerically investigated over high Froude number. Results show that the attack angle causes the linear deviation of the ventilated supercavity axis, the deviation angle is in direct proportion to the attack angle, the deviation direction is opposite to the lift of the cavitator, and the deformation of the supercavity contour increases along the flow direction. The attack angle changes the gas flow structure inside the ventilated supercavity, causing the different deformation of the upper profile and lower profile. Under the condition of positive attack angle, the deformation of the lower profile of the supercavity generated by the disk cavitator is significantly greater than that of the upper profile.
{"title":"Influence of attack angle on ventilated supercavitating flow at high Froude number condition","authors":"Yifei Wang, J. Dang, Chuang Huang, Haiyu Xu, Z. Zuo","doi":"10.1051/jnwpu/20224061233","DOIUrl":"https://doi.org/10.1051/jnwpu/20224061233","url":null,"abstract":"To study the influence of attack angle on ventilated supercavitating flow, a numerical model is established to simulate the supercavitation flow by using the inhomogeneous multiphase flow model and the SST k-ω turbulence model. And then, the model is verified and validated by comparing with the experimental results. The effect of attack angle on the profile of ventilated supercavity was numerically investigated over high Froude number. Results show that the attack angle causes the linear deviation of the ventilated supercavity axis, the deviation angle is in direct proportion to the attack angle, the deviation direction is opposite to the lift of the cavitator, and the deformation of the supercavity contour increases along the flow direction. The attack angle changes the gas flow structure inside the ventilated supercavity, causing the different deformation of the upper profile and lower profile. Under the condition of positive attack angle, the deformation of the lower profile of the supercavity generated by the disk cavitator is significantly greater than that of the upper profile.","PeriodicalId":39691,"journal":{"name":"西北工业大学学报","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43322903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：