Impedance Calculations for Elements of Sonar Arrays by Neural-Network-Based Integration

In this paper, a technique of neural network based integration is proposed to calculate the self-and mutual-impedances within arrays of sonar transducers. The multi-dimensional integrals appearing in self-and mutual-impedance formulations are transformed into neural-network-based integration and the final results can be found from look-up tables in mathematical handbooks. Initially, the integrand is modeled by a trained neural network. Integration on the integrand then becomes integration on the linear combination of weights and basis functions within the neural network. The results will become the linear combination of error functions which can be looked up in mathematical handbooks. Numerical simulation shows that the results calculated by the proposed method are consistent with those given in other existing studies. The proposed technique requires neither numerical nor artificial integration procedure. Due to the inherent learning and predicting property of neural network, only a small number of sampling points for the integrand are required in the proposed integration technique.     

Neural network modeling of flight control system

Modeling of angle tracking systems in the presence of actuator non-linearity such as angle, position and rate limits is a very significant and difficult task in the design and implementation of aircraft, target-tracking, and missile guided systems. A new recurrent neural network with time-delayed inputs and output feedback is used for the modeling of angle tracking systems, with emphasis on the neural network architecture, principles and algorithms. The neural network controller with modeling units for angle tracking is designed by using TMS320C25 processors. For time and size requirements, limited precision technology and look-up table technology are used in the design of the hardware and software systems. Given a set of input commands, the network is trained to control the system within the constraints imposed by actuators. The results show that the proposed networks are able to model the angle tracking system through learning without separate consideration of the non-linearity of actuators     

ANN技术在复合材料胶接修理分析中的应用

基于改进的BP人工神经网络(ANN)建立了复合材料胶接修理分析模型,结合采用复合材料胶接修理的正交试验及有限元分析的结果为训练和检测神经网络提供样本,有效地利用了神经网络、试验设计技术与有限元分析的优点。胶接修理实例分析结果表明,所建神经网络模型对胶接参数与修理效果之间关系的预测与试验结果一致,说明将人工神经网络应用于复合材料胶接修理参数分析是一种行之有效的方法。     

用遗传算法改进的BP模型在刹车系统诊断中的应用研究

利用神经网络进行故障诊断是近些年来所兴起的一种重要的智能诊断方法。我们就是根据航空维修的特点及神经网络的优点, 提出了应用BP网络对飞行器的故障进行学习、训练和诊断的想法。同时, 为了克服单独应用BP算法时存在的缺陷, 我们利用遗传算法(GA)对其进行了改进。我们利用面向对象的计算机编程技术, 开发了一个软件程序, 初步试验, 取得良好效果。最后讨论了在航空维修方面智能诊断的未来发展趋势。     

Optimum selection of error control coding using neural networks

Significant performance improvements may be obtained in digital communication systems if error control coding is properly applied. However, selection of a coding scheme for specific applications is often a complicated task. The choice is affected by a set of system design goals. Some of these goals impose case-dependent conflicting requirements. Similar scheme selection problems exist in many engineering system design processes. A knowledge-combined neural network approach is developed and applied to optimum coding selection. The proposed approach utilizes a neural network trained not only by precedent examples but also by knowledge rules to draw conclusions. It is shown that artificial neural networks (ANNs) can provide effective solutions to the problems encountered in building systems that emulate a coding specialist's expertise     

基于多智能体混合学习的多星协同动态任务规划算法(英文)

针对多星协同动态任务规划问题,以往多采用基于启发式的重规划算法,但是由于启发式策略依赖于具体任务,使得优化性受到影响。注意到协同规划的历史信息对后续协同规划的影响,本文提出了一种基于策略迭代的多智能体强化学习和迁移学习的混合学习算法求解该问题近似最优策略。本文的多智能体强化学习方法利用神经网络描述各颗卫星的强化学习策略,通过协同进化的方法迭代搜索具有最优拓扑结构和连接权重的策略神经网络个体。针对随机出现的观测任务请求导致历史学习策略失效,通过迁移学习将历史学习策略转换为当前初始策略,保证规划质量前提下加快多星协同任务规划速度。仿真实验及分析结果表明本文算法对动态随机出现的任务请求有良好的适应性。     

Application of neural networks for the design of flight control algorithms. II Adaptive tuning of neural network control law

In this paper, we consider different approaches for the neural network controller tuning in the flight control system. Two of the most common tuning approaches in the adaptive control theory are applied. The first one uses parameter identification technique and consists in solving a real-time regression problem for the control law. The second approach is based on the Lyapunov direct method, which utilizes a tracking error as an absolute measure of tuning performance. The neural network control law are designed for the three-axis flight control problem and tested on the full nonlinear model of a fighter aircraft. Closed loop simulation results are presented and two adaptation algorithms are compared in the case of abrupt change of aircraft dynamics.     

双BP神经网络在磨损颗粒自动识别中的应用

引入了一套磨粒形态学描述子来提取磨损颗粒的显微形态特征 ,然后以此为输入参数提出了一套BP神经网络 ,对磨损颗粒进行自动识别分类。针对本网络输入参数多 ,网络训练耗时长的问题 ,尝试采用因子模糊化的网络训练方法 ,大幅度提高了神经网络的训练速度 ,并取得了较好的应用效果。     

智能故障模式影响分析的推理研究

介绍了应用神经网络和专家系统技术,依托专家知识,基于功能/硬件而建立的功能关系模型图进行推理的智能故障模式影响分析系统。详细论述了其故障模式选择推理模型和应用神经元网络及其扩展技术建立的产品故障模式影响分析推理模型,并对推理流程进行了详细的描述。此外,对其系统结构、各组成部分的相互关系,及系统的功能流程也作了简要的论述。     

A point cloud deep neural network metamodel method for aerodynamic prediction

Aiming to reduce the high expense of 3-Dimensional (3D) aerodynamics numerical simulations and overcome the limitations of the traditional parametric learning methods, a point cloud deep learning non-parametric metamodel method is proposed in this paper. The 3D geometric data, corresponding to the object boundaries, are chosen as point clouds and a deep learning neural network metamodel fed by the point clouds is further established based on the PointNet architecture. This network can learn an end-to-end mapping between spatial positions of the object surface and CFD numerical quantities. With the proposed aerodynamic metamodel approach, the point clouds are constructed by collecting the coordinates of grid vertices on the object surface in a CFD domain, which can maintain the boundary smoothness and allow the network to detect small changes between geometries. Moreover, the point clouds are easily accessible from 3D sensors. The point cloud deep learning neural network, which employs re-sampling technique, the spatial transformer network and the fully connected layer, is developed to predict the aerodynamic characteristics of 3D geometry. The effectiveness of the proposed metamodel method is further verified by aerodynamic prediction and robust shape optimization of the ONERA M6 wing. The results show that the proposed method can achieve more satisfactory agreement with the experimental measurements compared to the parametric-learning-based deep neural network.     

基于神经网络的电子线路故障诊断

分析了故障字典法在实际应用中存在的不足，提出将单位BP算法应用到电子线路的故障诊断中。对基于该方法的航空装备电子线路故障诊断进行了计算机仿真，并分析了网络参数的变化对训练结果的影响。仿真结果表明了该方法的合理性和有效性。     

基于BP网络的武器装备参数估算

根据武器装备设计要求来确定某些参数往往涉及许多不确定因素。为了实现一些武器装备参数的定量化估算,本文基于BP神经网络计算模型提出了一种新的武器装备参数估算方法,并给出了实现这种方法的详细步骤。将该方法应用于导弹主要参数的估算,测试结果证明了此方法的正确性和可行性。该方法为武器装备的参数估算提供了新的途径。     

基于神经网络的民航安检系统风险评价研究

随着民航事业的快速发展,民航安全问题引起了广泛的关注.民航安全检查是民航管理安全重要的组成部分,如何建立一个合理的风险评价模型,指导民航安全检查的管理工作,已成为民航管理者的迫切需求.将BP神经网络模型引入民航安全管理,在分析民航安检系统的基础上,建立了安检系统的风险评价模型.通过实际应用验证了该模型的可行性.     

Bernoulli-Euler梁振动的人工神经元网络控制方法

分析了Bernoulli-Euler梁的振动特性,从控制系统的角度得出梁振动控制系统的传递函数,并采用人工神经元网络的方法对其进行控制,辨识器及控制器均采用非线性神经元网络, 最后用matlab对振动控制系统进行仿真。     

平均场退火算法在GPS姿态确定中的应用

研究了基于GPS载波相位测量载体姿态的技术 ,采用了精度高速度快的平均场退火算法(MFANN)。MEFANN是竞争性的Hopfield神经网络和随机模拟退火算法结合起来的一种算法 ,用来求解最优姿态确定问题。首先阐述了GPS载波相位姿态测量基本原理 ,接下来建立了姿态测量系统数学模型 ,应用MFANN算法来解算整周模糊度和方位角 ,最后给出了应用MFANN方法求解的实例 ,说明该方法是有效的     

基于灰色神经网络的疲劳裂纹预测方法研究

为对构件疲劳损伤进行预测,提出了基于灰色神经网络模型的疲劳裂纹扩展预测方法。将灰色GM（I,1）模型向BP网络映射,建立了一维灰色神经网络GNNM（1,1）模型。基于灰色GM（1,1）模型的发展系数和灰作用量给出了GNNM（1,1）模型初始权值。应用建立的GNNM（1,1）模型预测了某不锈钢构件腐蚀疲劳裂纹的扩展,并与GM（I,1）模型的预测结果进行了对比,表明GNNM（1,1）模型具有更高的预测精度和模型精度。     

基于进化神经网络的压气机结垢性能退化评估

采用进化神经网络方法,通过测量参数对压气机结垢性能退化模式进行了定量监控和评估。运用粒子群算法优化径向基函数(Radial Base Function,RBF)神经网络的初始权值,即由神经网络训练样本所得到的实际和期望的输出之间的误差平方和构造适应度函数,对RBF神经网络的隐层中心、半径以及输入输出权值进行全局寻优搜索,设计了进化RBF神经网络,并对模拟得到的压气机结垢的样本进行训练和测试。结果表明:进化RBF神经网络的模式识别能力比普通RBF神经网络的要强,对燃气轮机性能退化评估和健康管理具有重要理论意义和应用价值。     

基于替代模型的高超声速前体/进气道一体化优化

采用基于替代模型的渐进优化策略对二维高超声速前体/进气道进行一体化设计优化,采用拉丁超立方试验设计法选择样本点,采用二维粘性CFD方法计算进气道流场来建立样本数据库,综合运用了多项式响应面、Kriging模型、BP神经网络和径向基神经网络等替代模型.相对于基准构型,前体/进气道的优化构型在设计态时提高了流量捕获与来流压缩能力,提高了总压恢复性能,同时减小了阻力系数,综合性能提高了5.3%;在非设计态时优化构型的综合性能也有不同程度的改善.      

Neural network learning of low-probability events

In the problem of stationary target identification (STI) via millimeter wave (MMW) seeker radars in heavy clutter environments, it is often necessary to use nonparametric identification procedures, as detailed parametric models of clutter and target returns are generally unavailable. Neural networks provide an attractive approach to perform nonparametric identification. However, when identifying low-probability events, the computational overhead associated with training a neural network can become excessive. This is because low-probability events must be adequately represented in the training sample. We present a modified backpropagation training algorithm based on a likelihood ratio weighting function (LRWF) to train the neural network using a much smaller training set than that required using the standard backpropagation algorithm This algorithm is closely related to the importance sampling technique used in digital communication systems to obtain probability of error estimates by using a much smaller number of simulation runs than what is required with standard Monte Carlo simulation. The modified backpropagation technique results in a significant reduction in computational overhead in training the network, resulting from a substantial reduction in the size of the training set required to achieve a given level of performance. We demonstrate the performance of the algorithm on simulated data for the STI problem in MMW radar     

航空型号项目风险预测的BP神经网络模型及应用

本研究克服了单纯采用专家风险因子测度方法主观性较强的缺点,以及单纯采用人工神经网络评估模型模糊性的缺点,结合两种方法的优点,利用基于BP神经网络算法的Microsoft Visual C++程序,在专家风险因子测度基础上,通过大量风险评估成功案例数据的训练,成功建立了航空型号项目风险预测模型.该模型可以较为精确、客观地...