一种基于FCOS神经网络的小建筑物目标检测方法北大核心

提出了一种基于FCOS神经网络的小建筑物目标检测算法,针对FCOS模型在特征提取阶段提取到的小建筑物目标特征较少问题,引入多尺度检测和可变形卷积方式,加强网络对小建筑物目标的特征提取能力,并通过改进后的SGE注意力机制降低特征图中的干扰噪声权重。改进后的网络可以提取到更多的小建筑物目标特征,对环境干扰噪声的鲁棒性更强。在自己搭建的数据集上进行了实验测试,结果表明,在相同环境下网络改进后建筑物的整体检测准确率提升了1.7%,其中对小建筑物目标提升了3.6%,减少了小建筑物目标漏检、误检的问题。     

一种基于抽取LMS的距离旁瓣抑制方法

在噪声雷达中，传统相关处理方法的距离旁瓣受到时宽带宽积的限制，在有限相关处理时间内得到的距离旁瓣较高，会造成微弱目标被强目标、杂波旁瓣淹没的现象。提出一种基于抽取最小均方（Least Mean Square,LMS）滤波的噪声雷达旁瓣抑制方法，将LMS滤波器的系数作为距离压缩结果，从而获取较低的距离旁瓣。对该方法的性能进行了理论分析，并通过数字仿真验证了算法的有效性和理论分析的正确性。     

Real time power management strategy for fuel cell hybrid electric bus based on Lyapunov stability theorem

The fuel cell/battery durability and hybrid system stability are major considerations for the power management of fuel cell hybrid electric bus (FCHEB) operating on complicated driving conditions. In this paper, a real time nonlinear adaptive control (NAC) with stability analyze is formulated for power management of FCHEB. Firstly, the mathematical model of hybrid power system is analyzed, which is established for control-oriented design. Furthermore, the NAC-based strategy with quadratic Lyapunov function is set up to guarantee the stability of closed-loop power system, and the power split between fuel cell and battery is controlled with the durability consideration. Finally, two real-time power management strategies, state machine control (SMC) and fuzzy logic control (FLC), are implemented to evaluate the performance of NAC-based strategy, and the simulation results suggest that the guaranteed stability of NAC-based strategy can efficiently prolong fuel cell/battery lifespan and provide better fuel consumption economy for FCHEB.     

基于误差估值累加开环校正的诱导式欺骗检测方法

诱导式卫星欺骗干扰可诱导航空器逐渐偏离预定航迹，难以被发现，因此及时有效地检测干扰是飞行安全的保障。在现有紧组合导航体制基础上，设计了一种基于误差估值累加开环校正的紧组合导航结构，并证明了其性能与传统闭环校正紧组合导航性能等效。在此结构中，将紧组合导航系统与自适应序贯概率比检测方法结合，提出了一种基于误差估值累加开环校正的诱导式欺骗检测方法，融合紧组合导航信息与其他不受欺骗影响的导航信息，构建欺骗检测统计量进行诱导式欺骗检测。仿真结果表明，开环校正结构可避免随时间累加的惯性导航系统误差所导致的组合导航滤波器发散问题，同时欺骗检测方法可进一步提高算法对“最坏”情形下微小诱导式欺骗的检测效果。     

Coupling effects of water content,temperature, oxygen density,and polytetrafluoroethylene loading on oxygen transport through ionomer thin film on platinum surface in catalyst layer of proton exchange membrane fuel cell

In this work, coupling effects of water content, temperature, oxygen density, and polytetrafluoroethylene (PTFE) loading on oxygen transport through an ionomer thin film on a platinum surface in a catalyst layer of a proton exchange membrane (PEM) fuel cell are investigated using molecular dynamics approach. Taguchi orthogonal algorithm is employed to comprehensively analyze the coupling effects in a limited number of cases. It is found that the effect of operation temperature is the weakest among the four factors, which has the smallest effect index 14.4. Coupling effects including the PTFE loadings on the oxygen transfer through the ionomer thin film is uncovered. Less PTFE loadings should be beneficial for the oxygen transfer. The chemical potential gradient is considered as the major driven force for the oxygen transport through the ionomer thin film, and oxygen density is the dominating factor, significantly affecting the chemical potential in the thin film.     

注射模生产中智能化控制及应用

分析了注射模生产的现状，针对其生产中智能化调控应用方面的不足，提出模内参数的自适应调节方案，还介绍了自适应工作的原理、可调参数种类、逻辑推理等，并实际验证了基于注塑设备联网集成工艺数据下注射模成型工艺自适应调节的可行性。     

A Tradeoff Between Accuracy and Speed for K-Means Seed Determination

With a sharp increase in the information volume, analyzing and retrieving this vast data volume is much more essential than ever. One of the main techniques that would be beneficial in this regard is called the Clustering method. Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible. One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm. The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters. Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time. Besides, the selection of appropriate initial seeds can reduce the cluster’s inconsistency. In this paper, we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm. For this purpose, a new method is proposed considering the average distance between objects to determine the initial seeds. Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm. The experimental results showed that our proposed approach outperforms the Chithra with 1.7% and 2.1% in terms of clustering accuracy for Wine and Abalone detection data, respectively. Furthermore, achieved results indicate that comparing with the Reverse Nearest Neighbor (RNN) search approach, the proposed method has a higher convergence speed.     

A novel adaptive sampling based methodology for feasible region identification of compute intensive models using artificial neural network

Identification of feasible region of operations in multivariate processes is a problem of interest in several fields. This is particularly challenging when the process model is black-box in nature and/or is computationally expensive, as analytical solutions are not available and the number of possible model evaluations is limited. An efficient methodology is required to identify samples where the model is evaluated for developing a computationally efficient surrogate model. In this work, an artificial neural network based surrogate model is proposed which is integrated with a statistical-based approach (Jack-knifing) to estimate the variance of the surrogate model prediction. This allows implementation of an adaptive sampling approach where new samples are identified close to the feasible region boundary or in regions of high prediction uncertainty. The proposed approach performs better than a previously published kriging based method for different dimensionality case studies.     

基于Matlab的量子激光雷达稳频通信模拟系统设计

传统通信模拟系统设计较为复杂,导致模拟过程消耗能量较大,不能准确模拟稳频通信质量。因此,提出基于Matlab的量子激光雷达稳频通信模拟系统。由于振荡器是雷达形成初始信号源的基础,通过分析振荡电路与相位噪声,获得相位噪声函数与通信频率存在的关系;为确保通信过程的稳定,将准确性与稳定性作为信号质量的评价指标,并采用锁频环稳频技术计算频率偏移程度,根据PID控制算法控制频率,量子激光雷达稳频通信;利用Matlab确定激光器、探测器等硬件组成结构,通过时序与数字阵列的设置完成模拟系统设计。仿真结果表明所提系统结构简便、性能稳定,能够真实模拟出稳频通信的信号质量。     

Cryptanalysis of nonlinear confusion component based encryption algorithm

Recently many substitution box based encryption algorithms ensuring privacy have been proposed. Many, chaotic map based S-boxes have been generated posing high nonlinearity and strong cryptographic properties. Encryption schemes depending on the substitution box (S-box) only are weak and easily breakable with the help of chosen plaintext and ciphertext attacks. In this work, we have completely cryptanalyzed S-box based encryption scheme successfully by two types of attacks. Cryptanalysis in both types of attacks is performed by only one selected image. Moreover, we have suggested some improvements in the algorithm to defeat attacks.