Cross iteration often exists in the computational process of the simulation models, especially for control models. There is a credibility defect tracing problem in the validation of models with cross iteration. In ord...Cross iteration often exists in the computational process of the simulation models, especially for control models. There is a credibility defect tracing problem in the validation of models with cross iteration. In order to resolve this problem, after the problem formulation, a validation theorem on the cross iteration is proposed, and the proof of the theorem is given under the cross iteration circumstance. Meanwhile, applying the proposed theorem, the credibility calculation algorithm is provided, and the solvent of the defect tracing is explained. Further, based on the validation theorem on the cross iteration, a validation method for simulation models with the cross iteration is proposed, which is illustrated by a flowchart step by step. Finally, a validation example of a sixdegree of freedom (DOF) flight vehicle model is provided, and the validation process is performed by using the validation method. The result analysis shows that the method is effective to obtain the credibility of the model and accomplish the defect tracing of the validation.展开更多
A method for fast 1-fold cross validation is proposed for the regularized extreme learning machine （RELM）. The computational time of fast l-fold cross validation increases as the fold number decreases, which is oppo...A method for fast 1-fold cross validation is proposed for the regularized extreme learning machine （RELM）. The computational time of fast l-fold cross validation increases as the fold number decreases, which is opposite to that of naive 1-fold cross validation. As opposed to naive l-fold cross validation, fast l-fold cross validation takes the advantage in terms of computational time, especially for the large fold number such as l 〉 20. To corroborate the efficacy and feasibility of fast l-fold cross validation, experiments on five benchmark regression data sets are evaluated.展开更多
Distribution-based degradation models （or graphical approach in some literature） occur in a wide range of applications. However, few of existing methods have taken the validation of the built model into consideratio...Distribution-based degradation models （or graphical approach in some literature） occur in a wide range of applications. However, few of existing methods have taken the validation of the built model into consideration. A validation methodology for distribution-based models is proposed in this paper. Since the model can be expressed as consisting of assumptions of model structures and embedded model parameters, the proposed methodology carries out the validation from these two aspects. By using appropriate statistical techniques, the rationality of degradation distributions, suitability of fitted models and validity of degradation models are validated respectively. A new statistical technique based on control limits is also proposed, which can be implemented in the validation of degradation models＇ validity. The case study on degradation modeling of an actual accelerometer shows that the proposed methodology is an effective solution to the validation problem of distribution-based de qradation models.展开更多
It is well known that the incorrect results will be given using either the electric or magnetic field integral equation to calculate the radar cross section (RCS) of a closed body at the interior resonance. In this pa...It is well known that the incorrect results will be given using either the electric or magnetic field integral equation to calculate the radar cross section (RCS) of a closed body at the interior resonance. In this paper, an effective iterative technique is used to correct the calculated surface current density from the electric field integral equation. The radar cross section is computed for an infinite conducting circular cylinder at the interior resonance, and the obtained results are in good agreement with the analytical results. The backscattering cross section of an infinite triangular cylinder in the vicinity of a resonant frequency is also calculated. It is shown that the presence method is efficient and accurate.展开更多
Based on a Pade approximation, a wide-angle parabolic equation method is introduced for computing the multiobject radar cross section （RCS） for the first time. The method is a paraxial version of the scalar wave equ...Based on a Pade approximation, a wide-angle parabolic equation method is introduced for computing the multiobject radar cross section （RCS） for the first time. The method is a paraxial version of the scalar wave equation, which solves the field by marching them along the paraxial direction. Numerical results show that a single wide-angle parabofic equation run can compute multi-object RCS efficiently for angles up to 45 ° . The method provides anew and efficient numerical method for computation electromagnetics.展开更多
传统CNN算法在花生荚果外观识别任务中存在内存密集型和计算密集型问题,以及其在资源受限的边缘终端上部署困难,基于此,该研究提出了一种高效的花生荚果识别模型——PPINET(peanut pod identification network),以适应嵌入式设备的资源...传统CNN算法在花生荚果外观识别任务中存在内存密集型和计算密集型问题,以及其在资源受限的边缘终端上部署困难,基于此,该研究提出了一种高效的花生荚果识别模型——PPINET(peanut pod identification network),以适应嵌入式设备的资源限制需求。该模型通过结合深度可分离卷积和倒残差结构显著降低参数量和计算量,同时保留特征提取能力,并引入MQA(multi-query attention)模块增强关键特征提取,并利用TuNAS(easy-to-tune and scalable implementation of efficient neural architecture search with weight sharing)策略优化模型结构,使其在资源受限设备上表现优异。此外,采用ResNet(residual neural network)进行知识蒸馏配合三折交叉验证训练提升精度,最终量化为RKNN格式并在瑞芯微RK3588上实现NPU加速部署。PPINET模型尺寸仅为1.85 MB,参数量为0.49 M,浮点运算数为0.30G。PPINET在花生荚果分类中表现优异,准确率达98.65%,在RK3588上推理速度达321 fps。该模型具备较高的识别准确率和快速的识别速度,能够实现花生荚果的实时精准检测。展开更多
交叉熵法可显著加速电网可靠性评估,但往往聚焦于独立随机变量,若将其拓展至相关性变量可进一步提升加速性能。为有效获取相关性变量的重要抽样密度函数以实现其重要抽样,针对相关性建模中广泛使用的核密度估计模型(kernel density esti...交叉熵法可显著加速电网可靠性评估,但往往聚焦于独立随机变量,若将其拓展至相关性变量可进一步提升加速性能。为有效获取相关性变量的重要抽样密度函数以实现其重要抽样,针对相关性建模中广泛使用的核密度估计模型(kernel density estimation,KDE)开展了交叉熵优化研究。因KDE模型不属于指数分布家族,传统交叉熵优化难以实施,故利用复合抽样算法特点提出了新颖的直接交叉熵优化方法,推导出KDE模型最优权重参数的解析表达式。因权重参数数量级较小,直接优化易导致准确性退化,故基于子集模拟思想进一步提出间接交叉熵优化方法,将较小的权重参数优化转换成较大的条件概率优化,提升了优化准确性。通过MRTS79和MRTS96可靠性测试系统的评估分析,验证了所提方法在含相关性变量电网可靠性评估中的高效加速性能。展开更多
基金supported by the National Natural Science Foundation of China(61374164)
文摘Cross iteration often exists in the computational process of the simulation models, especially for control models. There is a credibility defect tracing problem in the validation of models with cross iteration. In order to resolve this problem, after the problem formulation, a validation theorem on the cross iteration is proposed, and the proof of the theorem is given under the cross iteration circumstance. Meanwhile, applying the proposed theorem, the credibility calculation algorithm is provided, and the solvent of the defect tracing is explained. Further, based on the validation theorem on the cross iteration, a validation method for simulation models with the cross iteration is proposed, which is illustrated by a flowchart step by step. Finally, a validation example of a sixdegree of freedom (DOF) flight vehicle model is provided, and the validation process is performed by using the validation method. The result analysis shows that the method is effective to obtain the credibility of the model and accomplish the defect tracing of the validation.
基金supported by the National Natural Science Foundation of China(51006052)the NUST Outstanding Scholar Supporting Program
文摘A method for fast 1-fold cross validation is proposed for the regularized extreme learning machine （RELM）. The computational time of fast l-fold cross validation increases as the fold number decreases, which is opposite to that of naive 1-fold cross validation. As opposed to naive l-fold cross validation, fast l-fold cross validation takes the advantage in terms of computational time, especially for the large fold number such as l 〉 20. To corroborate the efficacy and feasibility of fast l-fold cross validation, experiments on five benchmark regression data sets are evaluated.
文摘Distribution-based degradation models （or graphical approach in some literature） occur in a wide range of applications. However, few of existing methods have taken the validation of the built model into consideration. A validation methodology for distribution-based models is proposed in this paper. Since the model can be expressed as consisting of assumptions of model structures and embedded model parameters, the proposed methodology carries out the validation from these two aspects. By using appropriate statistical techniques, the rationality of degradation distributions, suitability of fitted models and validity of degradation models are validated respectively. A new statistical technique based on control limits is also proposed, which can be implemented in the validation of degradation models＇ validity. The case study on degradation modeling of an actual accelerometer shows that the proposed methodology is an effective solution to the validation problem of distribution-based de qradation models.
基金This project was supported by the Foundation of MOE of China (No. 00179).
文摘It is well known that the incorrect results will be given using either the electric or magnetic field integral equation to calculate the radar cross section (RCS) of a closed body at the interior resonance. In this paper, an effective iterative technique is used to correct the calculated surface current density from the electric field integral equation. The radar cross section is computed for an infinite conducting circular cylinder at the interior resonance, and the obtained results are in good agreement with the analytical results. The backscattering cross section of an infinite triangular cylinder in the vicinity of a resonant frequency is also calculated. It is shown that the presence method is efficient and accurate.
基金This project was partially supported by the National Natural Science Foundation of China (60371041).
文摘Based on a Pade approximation, a wide-angle parabolic equation method is introduced for computing the multiobject radar cross section （RCS） for the first time. The method is a paraxial version of the scalar wave equation, which solves the field by marching them along the paraxial direction. Numerical results show that a single wide-angle parabofic equation run can compute multi-object RCS efficiently for angles up to 45 ° . The method provides anew and efficient numerical method for computation electromagnetics.
文摘交叉熵法可显著加速电网可靠性评估,但往往聚焦于独立随机变量,若将其拓展至相关性变量可进一步提升加速性能。为有效获取相关性变量的重要抽样密度函数以实现其重要抽样,针对相关性建模中广泛使用的核密度估计模型(kernel density estimation,KDE)开展了交叉熵优化研究。因KDE模型不属于指数分布家族,传统交叉熵优化难以实施,故利用复合抽样算法特点提出了新颖的直接交叉熵优化方法,推导出KDE模型最优权重参数的解析表达式。因权重参数数量级较小,直接优化易导致准确性退化,故基于子集模拟思想进一步提出间接交叉熵优化方法,将较小的权重参数优化转换成较大的条件概率优化,提升了优化准确性。通过MRTS79和MRTS96可靠性测试系统的评估分析,验证了所提方法在含相关性变量电网可靠性评估中的高效加速性能。
