ENGINE SENSOR FAULT DIAGNOSIS USING MAIN AND DECENTRALIZED NEURAL NET WORKS

ＡｎａｌｙｔｉｃａｌｒｅｄｕｎｄａｎｃｙｔｅｃｈｎｉｑｕｅｓｓｕｃｈａｓｅｘｔｅｎｄｅｄＫａｌｍａｎｆｉｌｔｅｒ，ｃｏｍｐｏｎｅｎｔｓｔｒａｃｋｉｎｇｆｉｌｔｅｒａｎｄｓｏｏｎｃａｎｄｅｔｅｃｔ，ｉｓｏｌａｔｅａｎｄａｃｏｍｍｏｄａｔｅｆａｉｌｕｒ...     

电液力伺服系统的神经网络并行自适应预测 PI 控制

考虑电液伺服系统的复杂非线性和不确定性特性,提出一类基于神经网络的并行自适应预测PI控制结构,该结构使控制参数的调整和系统的实时控制操作可并行进行,不仅做到了神经模型和控制器的在线辨识和设计,而且避免了神经网络方法通常存在的实时控制的困难,使复杂系统的在线学习控制成为可能。仿真结果表明该控制器具有良好的适应性和鲁棒性。      

Improving performance in pulse radar detection using neuralnetworks

A new approach using a multilayered feed forward neural network for pulse compression is presented. The 13 element Barker code was used as the signal code. In training this network, the extended Kalman filtering (EKF)-based learning algorithm which has faster convergence speed than the conventional backpropagation (BP) algorithm was used. This approach has yielded output peak signal to sidelobe ratios which are much superior to those obtained with the BP algorithm. Further, for use of this neural network for real time processing, parallel implementation of the EKF-based learning algorithm is indispensable. Therefore, parallel implementation has also been developed     

利用神经网络诊断火箭发动机的故障

首先简要地介绍了人工神经网络(以下简称神经网络)的BP学习方法。然后将BP学习算法用于火箭发动机的故障诊断。仿真实验的结果表明,神经网络完全可以用于发动机的故障诊断。     

A fault-tolerant neural aided controller for aircraft auto-landing

This paper presents a neural-aided controller that enhances the fault tolerant capabilities of a high performance fighter aircraft during the landing phase when subjected to severe winds and failures such as stuck control surfaces. The controller architecture uses a neural controller aiding an existing conventional controller. The neural controller uses a feedback error learning mechanism and employs a dynamic Radial Basis Function neural network called Extended Minimal Resource Allocating Network (EMRAN), which uses only on-line learning and does not need a priori training. The conventional controller is designed using a classical design approach to achieve the desired autonomous landing profile with tight touchdown dispersions called herein as the pillbox. This design is carried out for no failure conditions but with the aircraft being subjected to winds. The failure scenarios considered in this study are: (i) Single faults of either aileron or elevator stuck at certain deflections, and (ii) double fault cases where both the aileron and elevator are stuck at different deflections. Simulation studies indicate that the designed conventional controller has only a limited failure handling ability. However, neural controller augmentation considerably improves the ability to handle large faults and meet the strict touchdown dispersion requirements, thus enlarging the fault-tolerance envelope.     

On-line gain-tuning IP controller using RFNN

In this study an integral-proportional (IP) controller with on-line gain-tuning using a recurrent fuzzy neural network (RFNN) is proposed to control the mover position of a permanent magnet linear synchronous motor (PMLSM) servo drive system. The structure and operating principle of the PMLSM are first described in detail. A field-oriented control PMLSM servo drive is then introduced. After that, an IP controller with on-line gain tuning using an RFNN is proposed to control the mover of the PMLSM for achieving high-precision position control with robustness. The backpropagation algorithm is used to train the RFNN on line. Moreover to guarantee the convergence of tracking error for the periodic step-command tracking, analytical methods based on a discrete-type Lyapunov function are proposed to determine the varied learning rates of the RFNN. Furthermore, the proposed control system is implemented in a PC-based computer control system, Finally, the effectiveness of the proposed PMLSM servo drive system is demonstrated by some simulated and experimental results. Accurate tracking response and superior dynamic performance can be obtained due to the powerful on-line learning capability of the RFNN. In addition, the proposed on-line gain-tuning servo drive system is robust with regard to parameter variations and external disturbances     

非视距误差神经网络改正的超宽带定位模型研究

非视距环境是造成超宽带定位系统精度下降的主要原因。由于非视距环境的测距精度下降难以通过常规计算方法建立改正模型,提出了一种基于反向传播算法的神经网络改正的超宽带稳健定位模型。该方法通过反向传播神经网络的自适应学习方法建立了一种超宽带非视距误差改正的稳健定位模型,实现了在非视距环境下超宽带定位精度的提升。首先采集非视距环境下超宽带测距值,提取超宽带在非视距环境下的坐标序列,计算得到误差序列,然后通过反向传播神经网络建立误差改正模型预测得到标签的误差改正值,最后使用超宽带Kalman滤波定位模型进行超宽带定位,从而消除非视距环境对定位精度的影响。通过对比实验分析,本模型较多项式拟合模型超宽带测距精度提高46.8%,定位精度提高43.4%;较多面函数拟合模型超宽带测距精度提高28.2%,定位精度提高26.2%。实验结果表明,反向传播算法的神经网络对超宽带非视距定位模型的误差改正有很好的效果,对超宽带定位精度的改正效果显著。     

基于混合神经网络模型的磨粒电荷检测方法研究

由于传统的滑油磨粒在线监测方法无法获取电荷分布位置信息,难以准确测量荷电颗粒数目及其携带的电荷量。为此,本文提出一种基于静电层析成像（Electrostatic tomography,EST）技术和深度学习算法的荷电颗粒检测方法。对EST传感器测量数据采用BP神经网络算法重建出测量截面上电荷的分布图像,采用卷积神经网络（Convolutional neural networks,CNN）算法分析重建图像以识别荷电颗粒数目,将识别的颗粒数目和传感器测量数据组合成输入向量,通过1个多层前馈网络确定带电颗粒数目、感应电荷值与颗粒电荷量值之间的映射关系,得到准确的各颗粒的电荷量值。实验结果表明：混合神经网络模型对数据样本的测量误差为9%,可满足滑油监测对于准确性的要求。     

航空发动机递归神经网络分路式解耦控制

针对航空发动机多变量控制中变量之间的耦合问题,提出了一种基于递归神经网络的分路式动态解耦控制方法,给出了发动机双路式解耦控制系统的结构及其解耦原理和算法。利用递归小波网络较强的动态非线性映射能力,在线完成发动机各控制通道的模型辨识,并回馈对应的灵敏度信息;神经网络PID控制器根据回馈的信息在线自适应调整参数,实现发动机各通道的准确跟踪和分路独立控制。仿真表明,该方法在保证控制系统良好的动态和稳态性能的同时,有效地减小了各回路之间的耦合影响,能够成功应用于发动机控制系统的解耦。      

基于神经网络补偿的室内无人机组合导航系统

针对无人飞行器在环境特征突变情况下数据融合的可靠性大幅下降问题，提出了神经网络预测补偿的组合导航算法。首先利用扩展卡尔曼滤波和粒子滤波对激光、光流等传感器得到的数据进行融合，然后采用径向基函数（RBF）神经网络对粒子滤波前后的误差进行预测。当激光数据可靠时，RBF神经网络进行训练学习模式，当激光数据中断或者不可靠时，利用训练后的模型对系统进行误差补偿。利用无人飞行器在室内环境下进行定点和轨迹实验，结果表明补偿后的位置导航信息能够明显降低激光数据不可靠时带来的定位误差。     

航空发动机神经网络内模控制

基于神经网络内模控制理论研究了神经网络内模控制方法在航空发动机控制系统中的应用,建立了基于Elman网络的航空发动机多变量内模控制系统。采用Elman网络建立发动机内模型和内模控制器,详细介绍了建模、控制的算法及其实现过程。取部分飞行条件下的数据作为学习样本,采用动态BP算法对神经网络权值进行调整,并在飞行包线内其它工作点对整个控制系统进行了仿真。结果表明,使用神经网络建立的航空发动机内模控制系统具有良好的控制品质和较强的自适应能力。      

推力矢量飞机自适应控制系统仿真平台研究

研究了具有自修复功能的推力矢量飞机自适应控制系统的结构功能特点,研究了RHO优化控制算法实现在线控制器设计,利用MSLS辨识算法实现在线飞行参数辨识和等价空间算法、传感器信息融合技术和概率统计理论实现FDI算法。并且根据系统各个部分的算法,采用面向对象技术语言VC 6.0和三维图形语言OpenGL开发了仿真平台,利用仿真平台实时演示了飞机存在舵面故障情况下的飞行控制系统运行仿真,解决了飞机飞行过程中存在舵面损伤和气动参数变化的问题,该仿真平台可以根据需求进行飞机故障加载,具备完备的推力矢量飞机自适应控制系统仿真功能。     

Robust wavelet neuro control for linear brushless motors

Design, simulation and experimental implementation of a wavelet basis function network learning controller for linear brushless dc motors (LBDCM) are considered. Stability robustness with position tracking is the primary concern. The proposed controller deals mainly with external disturbances, e.g. nonlinear friction force and payload variation in motion control of linear motors. It consists of two parts, one is a state feedback component, and the other one is a learning feedback component. The state feedback controller is designed on the basis of a simple linear model, and the learning feedback component is a wavelet neural controller. The attenuation effect of wavelet neural networks on friction force is first verified by the numerical method. The learning effect of wavelet neural networks on friction force is also shown in the numerical results. Then, a wavelet neural network is applied on a real LBDCM to on-line suppress the friction force, which may be variable due to the different lubrication. The effectiveness of the proposed control schemes is demonstrated by simulated and experimental results.     

双并联前向神经网络及其在飞行故障检测仿真研究中的应用

首次把飞行故障检测视为一个非线性数据分类问题,从而可望借助人工神经网络来处理。为了克服ＭＬＦＮＮ在数据分类中存在的学习慢与分类精度低,发展了由ＭＬＦＮＮ和ＳＬＦＮＮ并联并可接收编码输入的ＤＰＦＮＮ模型,还将训练ＭＬＰ的有关算法推广到ＤＰＦＮＮ情形。用计算机仿真了若干飞行故障模式并用于测试ＤＰＦＮＮ。     

Efficient Approximation of Kalman Filter for Target Tracking

A Kalman filter in the Cartesian coordinates is described for a maneuvering target when the radar sensor measures range, bearing, and elevation angles in the polar coordinates at high data rates. An approximate gain computation algorithm is developed to determine the filter gains for on-line microprocessor implementation. In this approach, gains are computed for three uncoupled filters and multiplied by a Jacobian transformation determined from the measured target position and orientation. The algorithm is compared with the extended Kalman filter for a typical target trajectory in a naval gun fire control system. The filter gains and the tracking errors for the proposed algorithm are nearly identical to the extended Kalman filter, while the computation requirements are reduced by a factor of four.     

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。     

基于分支深度强化学习的非合作目标追逃博弈策略求解

为解决航天器与非合作目标的空间交会问题,缓解深度强化学习在连续空间的应用限制,提出了一种基于分支深度强化学习的追逃博弈算法,以获得与非合作目标的空间交会策略。对于非合作目标的空间交会最优控制,运用微分对策描述为连续推力作用下的追逃博弈问题;为避免传统深度强化学习应对连续空间存在维数灾难问题,通过构建模糊推理模型来表征连续空间,提出了一种具有多组并行神经网络和共享决策模块的分支深度强化学习架构。实现了最优控制与博弈论的结合,有效解决了微分对策模型高度非线性且难于利用经典最优控制理论进行求解的难题,进一步提升了深度强化学习对离散行为的学习能力,并通过算例仿真检验了该算法的有效性。     

基于自适应神经网络的非线性飞控系统设计

将动态逆理论、神经网络和自适应控制相结合应用于非线性飞行控制系统设计中，通过动态逆控制律将非线性耦合系统转换为线性解耦系统，采用具有在线学习能力的神经网络来补偿反馈线性化中存在的逆误差，最后利用李亚普诺夫稳定性理论推导了在线网络权值的自适应调整规则。仿真结果表明，这种控制结构具有良好的跟踪能力和极强的鲁棒性。     

基于自调整神经元的航空发动机多变量自适应解耦控制

根据航空发动机性能控制要求, 通过分析自调整神经元及最速下降学习方法, 研究了基于自调整神经元的航空发动机多变量自适应解耦控制系统.利用自调整神经元的结构简单、各神经元之间没有权值连接及在线学习的优点, 在线整定多变量PID控制器的参数.阐明了该方法的结构和原理.并进行了航空发动机多变量自适应解耦控制系统的设计.大量的仿真结果表明, 系统具有良好的解耦特性和自适应能力.      

OLS算法在无人机传感器故障诊断中的应用

在故障诊断领域,神经网络故障诊断方法以其优良的特性正得到越来越广泛的应用。本文针对无人机的特点提出一种基于RBF神经网络故障诊断方法,通过建立神经网络预测器来实现无人机机载传感器的故障诊断,其中网络学习算法的选取将直接影响神经网络故障诊断的性能。正交最小二乘算法(OLS)以其在设定网络参数方面的优点常用来作为RBF神经网络学习算法。本文将介绍OLS算法的原理和实现步骤,通过VC 6.0编程实现OLS算法,并利用无人机机载传感器数据来验证OLS算法的有效性。