数控系统故障的ANN与专家诊断系统的研究及应用

 分析了ＣＮＣ系统的故障特点,针对ＦＡＮＵＣ７数控系统,建立并比较了适用于ＣＮＣ故障的ＢＰ和ＢＡＭ两种ＡＮＮ诊断模型,探讨了模糊神经网络在ＣＮＣ故障诊断中的应用,给出了模糊ＡＮＮ识别ＭＡＣＳ５００数控机床伺服系统故障的数据和结果;介绍了所开发的ＣＮＣ系统故障诊断专家系统ＣＮＣ－ＤＥＳ的总体结构、知识表达与推理等,列举了该系统应用于ＣＮＣ故障诊断的情况和结论。     

A TRACTION CALCULATING FORMULA BASED ON NON-NEWTONIAN RHEOLOGICAL MODEL

ＡＴＲＡＣＴＩＯＮＣＡＬＣＵＬＡＴＩＮＧＦＯＲＭＵＬＡＢＡＳＥＤＯＮＮＯＮ－ＮＥＷＴＯＮＩＡＮＲＨＥＯＬＯＧＩＣＡＬＭＯＤＥＬＡＴＲＡＣＴＩＯＮＣＡＬＣＵＬＡＴＩＮＧＦＯＲＭＵＬＡＢＡＳＥＤＯＮＮＯＮ－ＮＥＷＴＯＮＩＡＮＲＨＥＯＬＯＧＩＣＡＬＭＯＤＥ...     

TWO DIMENSIONAL SUPERSONIC SHOCK TUNNEL AND ITS APPLICATION

ＴＷＯＤＩＭＥＮＳＩＯＮＡＬＳＵＰＥＲＳＯＮＩＣＳＨＯＣＫＴＵＮＮＥＬＡＮＤＩＴＳＡＰＰＬＩＣＡＴＩＯＮＴＷＯＤＩＭＥＮＳＩＯＮＡＬＳＵＰＥＲＳＯＮＩＣＳＨＯＣＫＴＵＮＮＥＬＡＮＤＩＴＳＡＰＰＬＩＣＡＴＩＯＮ￥ＷａｎｇＳｈｉｆｅｎ；Ｗａｎｇｙｕ；Ｔａ...     

NUMERICAL SIMULATION OF IMPACT RESPONSE OF COMPOSED CERAMIC/COMPOSITE ARMOUR

ＮＵＭＥＲＩＣＡＬＳＩＭＵＬＡＴＩＯＮＯＦＩＭＰＡＣＴＲＥＳＰＯＮＳＥＯＦＣＯＭＰＯＳＥＤＣＥＲＡＭＩＣ／ＣＯＭＰＯＳＩＴＥＡＲＭＯＵＲＮＵＭＥＲＩＣＡＬＳＩＭＵＬＡＴＩＯＮＯＦＩＭＰＡＣＴＲＥＳＰＯＮＳＥＯＦＣＯＭＰＯＳＥＤＣＥＲＡＭＩＣ／ＣＯＭＰ...     

多通道动态测试分析系统

多通道动态测试分析系统张令弥,张春宁（南京航空航天大学振动所,南京,２１００１６）ＤＥＶＥＬＯＰＭＥＮＴＡＮＤＡＰＰＬＩＣＡＴＩＯＮＳＯＦＭＵＬＴＩ－ＣＨＡＮＮＥＬＤＹＮＡＭＩＣＴＥＳＴ＆ＡＮＡＬＹＳＩＳＳＹＳＴＥＭ（ＤＴＡＳ）ＺｈａｎｇＬｉｎｇｍｉ...     

STUDY ON THERMAL EXPANSION COEFFICIENT AND DESIGN FOR ZERO－EXPANSION OF SlNGLE AND HYBRID MULTI－DIRECTIONA

ＳＴＵＤＹＯＮＴＨＥＲＭＡＬＥＸＰＡＮＳＩＯＮＣＯＥＦＦＩＣＩＥＮＴＡＮＤＤＥＳＩＧＮＦＯＲＺＥＲＯ－ＥＸＰＡＮＳＩＯＮＯＦＳｌＮＧＬＥＡＮＤＨＹＢＲＩＤＭＵＬＴＩ－ＤＩＲＥＣＴＩＯＮＡＬＣＯＭＰＯＳＩＴＥＳＺｈｏｎｇＷｅｔｈｏｎｇ；ＺｈａｎｇＺｕｏ...     

PARALLEL COMPUTATION OF SUPER-SONIC BLUNT BODY VISCOUS FLOWFIELDS IN PVM

ＰＡＲＡＬＬＥＬＣＯＭＰＵＴＡＴＩＯＮＯＦＳＵＰＥＲ┐ＳＯＮＩＣＢＬＵＮＴＢＯＤＹＶＩＳＣＯＵＳＦＬＯＷＦＩＥＬＤＳＩＮＰＶＭＹａｎｇＸｉａｏｈｕｉ，ＷａｎｇＺｈｅｎｇｈｕａ，ＷａｎｇＣｈｅｎｇｙａｏ（Ｄｅｐｔ．１，ＮａｔｉｏｎａｌＵｎｉｖｅｒｓｉｔ...     

COMPUTATION OF COMPRESSIBLE FLOW PAST SLENDER WING－BODY USING FULL－POTENTIAL EQUATION

ＣＯＭＰＵＴＡＴＩＯＮＯＦＣＯＭＰＲＥＳＳＩＢＬＥＦＬＯＷＰＡＳＴＳＬＥＮＤＥＲＷＩＮＧ－ＢＯＤＹＵＳＩＮＧＦＵＬＬ－ＰＯＴＥＮＴＩＡＬＥＱＵＡＴＩＯＮＨｕａｎｇＭｉｎｇｋｅ（ＤｅｐａｒｔｍｅｎｔｏｆＡｅｒｏｄｙｎａｍｉｃｓ，ＮａｎｊｉｎｇＵｎｉｖｅ...     

EXPERIMENTAL STUDY ON THE STALL FLOW FOR DIFFERENT GEOMETRIC PARAMETERS OF CASCADE

ＥＸＰＥＲＩＭＥＮＴＡＬＳＴＵＤＹＯＮＴＨＥＳＴＡＬＬＦＬＯＷＦＯＲＤＩＦＦＥＲＥＮＴＧＥＯＭＥＴＲＩＣＰＡＲＡＭＥＴＥＲＳＯＦＣＡＳＣＡＤＥＺｈｕＪｕｎｑｉａｎｇ；ＬｉｕＺｈｉｗｅｉ；ＭａＣｕｎｂａｏ（Ｆａｃｕｌｔｙ７０４，Ｎｏｒｔｈｗｅｓｔｅｒｎ...     

A CALCULATION OF OPTIMAL FLIGHT TRAJECTORY USING THE PARAMETERIZED OPTIMIZATION METHOD

ＡＣＡＬＣＵＬＡＴＩＯＮＯＦＯＰＴＩＭＡＬＦＬＩＧＨＴＴＲＡＪＥＣＴＯＲＹＵＳＩＮＧＴＨＥＰＡＲＡＭＥＴＥＲＩＺＥＤＯＰＴＩＭＩＺＡＴＩＯＮＭＥＴＨＯＤＡＣＡＬＣＵＬＡＴＩＯＮＯＦＯＰＴＩＭＡＬＦＬＩＧＨＴＴＲＡＪＥＣＴＯＲＹＵＳＩＮＧＴＨＥＰＡＲＡ...     

动态模糊RBF神经网络焊接接头力学性能预测建模

建立动态模糊径向基神经网络RBF( Radial Basis Function,RBF)焊接接头力学性能预测模型,克服静态RBF和模糊神经网络( Fuzzy Neural Network,FNN)在结构辨识、动态样本训练及学习算法的不足。该模型的结构参数不再提前预设,在训练过程中动态自适应调整,适用动态样本数据学习,学习算法引入分级学习和模糊规则修剪策略,加速训练并使模型结构更加紧凑。利用三种厚度、不同工艺TC4钛合金TIG焊接试验数据对该模型进行仿真。结果表明：模型具有较高的预测精度,适用于预测焊接接头力学性能,为焊接过程在线控制开辟了新的途径。     

基于深度学习的发动机叶片故障检测技术

为了解决航空发动机叶片故障检测中存在的检测精度欠佳、检测效率不高的问题,提出了一种基于深度学习的目标检测方法。针对小样本数据集检测精度低、模型训练速度慢等问题,对Faster R-CNN目标检测算法进行结构优化,引入Res2Net结构,通过分割串联的策略强化残差模块的卷积学习能力,搭建了细粒级的多尺度残差模型Res2Net-50,以提升模型的特征提取能力。同时,在网络的训练过程中,采用多次余弦退火衰减法对学习率进行调整,以加快模型的训练速度,提升模型的训练质量。针对航空发动机叶片裂纹和缺损2种故障类型进行网络训练与检测试验,试验结果表明:优化后的模型识别准确率提高了0.7%,模型的平均检测精度提高了1.8%,训练时间缩短了5.56%,取得了比较好的检测效果。     

An online ensemble semi-supervised classification framework for air combat target maneuver recognition

Online target maneuver recognition is an important prerequisite for air combat situation recognition and maneuver decision-making. Conventional target maneuver recognition methods adopt mainly supervised learning methods and assume that many sample labels are available. However, in real-world applications, manual sample labeling is often time-consuming and laborious. In addition, airborne sensors collecting target maneuver trajectory information in data streams often cannot process information in real time. To solve these problems, in this paper, an air combat target maneuver recognition model based on an online ensemble semi-supervised classification framework based on online learning, ensemble learning, semi-supervised learning, and Tri-training algorithm, abbreviated as Online Ensemble Semi-supervised Classification Framework (OESCF), is proposed. The framework is divided into four parts: basic classifier offline training stage, online recognition model initialization stage, target maneuver online recognition stage, and online model update stage. Firstly, based on the improved Tri-training algorithm and the fusion decision filtering strategy combined with disagreement, basic classifiers are trained offline by making full use of labeled and unlabeled sample data. Secondly, the dynamic density clustering algorithm of the target maneuver is performed, statistical information of each cluster is calculated, and a set of micro-clusters is obtained to initialize the online recognition model. Thirdly, the ensemble K-Nearest Neighbor (KNN)-based learning method is used to recognize the incoming target maneuver trajectory instances. Finally, to further improve the accuracy and adaptability of the model under the condition of high dynamic air combat, the parameters of the model are updated online using error-driven representation learning, exponential decay function and basic classifier obtained in the offline training stage. The experimental results on several University of California Irvine (UCI) datasets and real air combat target maneuver trajectory data validate the effectiveness of the proposed method in comparison with other semi-supervised models and supervised models, and the results show that the proposed model achieves higher classification accuracy.     

Aero-engine fault diagnosis applying new fast support vector algorithm

A new fast learning algorithm was presented to solve the large-scale support vector machine ( SVM ) training problem of aero-engine fault diagnosis.The relative boundary vectors ( RBVs ) instead of all the original training samples were used for the training of the binary SVM fault classifiers.This pruning strategy decreased the number of final training sample significantly and can keep classification accuracy almost invariable.Accordingly , the training time was shortened to 1 / 20compared with basic SVM classifier.Meanwhile , owing to the reduction of support vector number , the classification time was also reduced.When sample aliasing existed , the aliasing sample points which were not of the same class were eliminated before the relative boundary vectors were computed.Besides , the samples near the relative boundary vectors were selected for SVM training in order to prevent the loss of some key sample points resulted from aliasing.This can improve classification accuracy effectively.A simulation example to classify 5classes of combination fault of aero-engine gas path components was finished and the total fault classification accuracy reached 96.1%.Simulation results show that this fast learning algorithm is effective , reliable and easy to be implemented for engineering application.     

支持向量机增量学习方法及应用

基于支持向量机的增量学习作为一种数据挖掘与知识发现技术,已在目标识别,网页分类等诸多领城得到应用.在概述其机理的基础上,从如何提高学习精度与学习速度着手,分析了现有算法及其优缺点和需要改进的问题;论述了增量学习的应用现状,并提出进一步的研究方向.     

一种基于多支持向量机的增量式并行训练算法

为了改进传统算法,利用支持向量的特性,提出了一种基于多支持向量机的增量式并行训练算法(PMSVM)。选择对分类超平面有影响的样本点作为支持向量,以增加单个分类器的训练时间为代价换取整体训练和分类的精度。考虑到训练样本的分布对最终结果的影响,加入反馈向量进行适当的重复训练,以调整各分类器的学习性能。通过在测试数据集上进行的实验表明,该算法与批学习增量BSVM算法相比,在提高训练效率和分类精度的前提下,大大降低了训练时间。     

补偿模糊神经网络在机床热误差预报模型中的应用

提出了一种基于补偿模糊神经网络的数控机床热误差预报模型,讨论了该模型的详细结构、模糊规则、训练算法及相关技术问题,并给出了智能预报结果和精度评价。     

一种适用于情报图像处理的图像集分类算法

无人机情报处理系统是无人机地面控制系统的重要组成部分之一，主要负责对无人机侦察载荷下传的侦察情报进行处理，从复杂的情报中获得直观的情报产品并传递给上级和友邻单位。对于搭载光电载荷的无人机情报处理当前仍以依靠人力鉴别为主。介绍一种基于快速近似最近邻( FLANN) 搜索特征的K 近邻用分类决策，可去除背景信息对分类性能的影响；为了进一步提高算法的运行速度及减少算法的内存开销，采用特征选择的方式分别减少测试图像和训练图像集的特征数目，并尝试同时减少测试图像和训练图像集中的特征数目平衡分类正确率与分类时间之间的矛盾。该算法保留了原始NBNN 算法的优点，无需参数学习的过程，实验结果验证了算法的正确性和有效性。     

Classification of radar targets using synthetic neural networks

Radar target classification performance of neural networks is evaluated. Time-domain and frequency-domain target features are considered. The sensitivity of the neural network algorithm to changes in network topology and training noise level is examined. The problem of classifying radar targets at unknown aspect angles is considered. The performance of the neural network algorithms is compared with that of decision-theoretic classifiers. Neural networks can be effectively used as radar target classification algorithms with an expected performance within 10 dB (worst case) of the optimum classifier     

Drogue detection for autonomous aerial refueling based on convolutional neural networks

Drogue detection is a fundamental issue during the close docking phase of autonomous aerial refueling(AAR). To cope with this issue, a novel and effective method based on deep learning with convolutional neural networks(CNNs) is proposed. In order to ensure its robustness and wide application, a deep learning dataset of images was prepared by utilizing real data of ‘‘Probe and Drogue" aerial refueling, which contains diverse drogues in various environmental conditions without artificial features placed on the drogues. By employing deep learning ideas and graphics processing units(GPUs), a model for drogue detection using a Caffe deep learning framework with CNNs was designed to ensure the method's accuracy and real-time performance. Experiments were conducted to demonstrate the effectiveness of the proposed method, and results based on real AAR data compare its performance to other methods, validating the accuracy, speed, and robustness of its drogue detection ability.