Greedy information acquisition algorithm: A new information theoretic approach to dynamic information acquisition in neural networks

In this paper, we proopose a new information theoretic approach to competitive learning. The new approach is called greedy information acquisition , because networks try to absorb as much information as possible in every stage of learning. In the first phase, with minimum network architecture for realizing competition, information is maximized. In the second phase, a new unit is added, and thereby information is again increased as much as possible. This proceess continues until no more increase in information is possible. Through greedy information maximization, different sets of important features in input patterns can be cumulatively discovered in successive stages. We applied our approach to three problems: a dipole problem; a language classification problem; and a phonological feature detection problem. Experimental results confirmed that information maximization can be repeatedly applied and that different features in input patterns are gradually discovered. We also compared our method with conventional competitive learning and multivariate analysis. The experimental results confirmed that our new method can detect salient features in input patterns more clearly than the other methods.     

Teacher-directed learning: information-theoretic competitive learning in supervised multi-layered networks

In this paper, we propose a new type of efficient learning method called teacher-directed learning. The method can accept training patterns and correlated teachers, and we need not back-propagate errors between targets and outputs into networks. Information flows always from an input layer to an output layer. In addition, connections to be updated are those from an input layer to the first competitive layer. All other connections can take fixed values. Learning is realized as a competitive process by maximizing information on training patterns and correlated teachers. Because information is maximized, information is compressed into networks in simple ways, which enables us to discover salient features in input patterns. We applied this method to the vertical and horizontal lines detection problem, the analysis of US–Japan trade relations and a fairly complex syntactic analysis system. Experimental results confirmed that teacher information in an input layer forces networks to produce correct answers. In addition, because of maximized information in competitive units, easily interpretable internal representations can be obtained.     

Flexible feature discovery and structural information control

In this paper, we propose a new information theoretic method called structural information control for flexible feature discovery. The new method has three distinctive characteristics, which traditional competitive learning fails to offer. First, the new method can directly control competitive unit activation patterns, whereas traditional competitive learning does not have any means to control them. Thus, with the new method, it is possible to extract salient features not discovered by traditional methods. Second, competitive units compete witheach other by maximizing their information content about input patterns. Consequently, this information maximization makes it possible to control flexibly competition processes. Third, in structural information control, it is possible to define many different kinds of information content, and we can choose a specific type of information according to a given objective. When applied to competitive learning, structural information can be used to control the number of dead or spare units, and to extract macro as well as micro features of input patterns in explicit ways. We first applied this method to simple pattern classification to demonstrate that information can be controlled and that different neuron firing patterns can be generated. Second, a dipole problem was used to show that structural information could provide representations similar to those by the conventional competitive learning methods. Finally, we applied the method to a language acquisition problem in which networks must flexibly discover some linguistic rules by changing structural information. Especially, we attempted to examine the effect of the information parameter to control the number of dead neurons, and thus to examine how macro and micro features in input patterns can explicitly be discovered by structural information.     

面向模型重构的冲压零件特征识别技术

从面向特征模型重构的角度,对冲压零件的特征进行了分类,并采用图结构描述分类特征。在此基础上,将特征识别的过程分解为模型有效性检查和基于图匹配的特征提取,所识别出的特征,可根据后续应用的需要重构出新的特征模型。     

3D simulations and experiments of guided wave propagation in adhesively bonded multi-layered structures

Understanding guided wave propagation in multi-layered plates and interaction with discontinuities can be difficult, as well as the interpretation of the ultrasonic signals. Propagation of guided waves can be studied analytically solving the equations of motion with the proper boundary conditions; nevertheless analytical models can be difficult to solve for complex multi-layered structures or having inner discontinuities. The problem can be efficiently studied using numerical techniques. Simulation of guided wave propagation in multi-layered structures, for ultrasonic waves in the MHz range, is solved here with the finite element analysis based on an explicit integration rule to solve the equations of motion in a dynamic analysis. Simulation allows a better understanding of propagation and interference phenomena by creating a window of observation in the multi-layered plate. Numerical results determined for a three-layer Al plate, without or with discontinuities, matched very well with experiments, providing an efficient tool to visualize and extract significant information in the transmitted waves and to optimize wave mode and configuration for a rigorous ultrasonic inspection.     

基于VMD和流形学习的滚动轴承故障诊断研究

针对轴承早期故障信号非线性、非平稳和故障特征难以提取的问题,提出一种变分模态分解(VMD)与流形学习相结合的特征提取方法。该方法应用VMD将信号分解成包含不同故障信息的固有模态分量,然后从中提取特征并构建高维的混合域特征集。最后,应用流形学习等度规映射算法将高维的特征集约简为故障区分度更好的低维混合域特征集,并利用支持向量机实现故障分类识别。滚动轴承实验结果表明该方法能准确清晰地提取故障特征信息,与传统方法相比诊断准确率更高。     

Automatic defects classification — a contribution

The objective of this work is to provide a contribution to defect classification. More precisely, we try to prove that it is possible to identify and classify defects of different types using the pulse-echo technique. The classification process makes use of the time and frequency domain responses of the ultrasonic echo signals acquired from different specimens simulating defects with three different shapes (cylindrical, spherical and planar with rectangular cross-section) and sizes. Although the final goal is the characterisation of practical defects (for instance, voids, cracks, delaminations, and so on) appearing in composite materials during manufacturing and in service, we first use the already mentioned reflectors for simplicity reasons. In these experiments 66 reflectors are used with water as matrix material. The inclusion (reflector) materials are brass, copper, steel and polystyrene. From the time domain signals we extract three features, namely, pulse duration, pulse decay rate and peak-to-peak relative amplitude of the third cycle. From the spectra of the echoes we extract the frequency for maximum amplitude and the standard error estimate from the deconvolved spectrum responses.All experimental signals were obtained using only one normal incident ultrasonic transducer aligned to maximise the direct reflected signal. In spite of the fact that this kind of configuration does not provide complete information about the characteristics of the geometries being studied, all the extracted features proved to be important discriminating factors of the geometrical classes considered, as will be demonstrated by making use of a pattern recognition technique for classification.     

基于Autogram的齿轮断齿故障特征提取方法

针对复杂生产背景下产生的强噪声淹没齿轮有效故障特征信息的问题,利用Autogram方法对其进行特征提取。该方法利用最大重叠离散小波包变换,对齿轮断齿故障振动信号进行不同层数分解处理,每层得到若干个信号,被称为“node”。为了更加全面地描述故障特征信息,对每个node进行包络谱的3种无偏自相关谱峭度求取,以便选取合适node作为信号源进行下一步分析。最后,对该信号源引入阈值处理,以便加强频谱分析的全面性,实现对齿轮断齿故障特征信息的有效提取。通过对比分析仿真和实测齿轮故障振动信号,验证了该方法的有效性。     

基于KECA和BO-SVDD的滚动轴承早期故障检测

为了实现更早地检测出滚动轴承发生故障,提出一种基于核熵成分分析（KECA）和贝叶斯优化（BO）算法优化支持向量数据描述（SVDD）的滚动轴承早期故障检测方法。提取轴承振动信号的时域、频域特征以及小波包分解节点能量特征,组成多维特征矩阵;利用KECA对多维特征矩阵进行降维处理,进而提取有效特征;最后,选取轴承正常状态的特征指标训练模型,利用BO算法确定SVDD的惩罚因子和核宽度,进而得到早期故障检测模型。利用该模型对XJTU-SY数据集中不同工况下的轴承进行早期故障检测,结果表明：KECA能够有效地提取特征信息,减少冗余信息的干扰;该模型整体上能够较早检测出故障的发生,并且有较好的鲁棒性和泛化能力。     

EMD分解与多特征融合的齿轮故障诊断方法

为解决齿轮振动信号在现实中难以获取大量典型故障样本和分类的精确度低的问题,提出基于EMD分解与多特征融合的齿轮故障诊断方法。首先,提取反映信号特征的各项参数指标作为特征向量;其次,利用经验模式分解(EMD)对原始信号进行分解,进而提取分解后各本征模式分量(IMF)的能量指标组成特征向量;然后,将其与信号特征各项参数融合成特征向量组合,并将其作为SVM多故障分类器的训练样本进行训练,实现齿轮的智能诊断。通过实验室轴承的故障诊断研究表明:该方法对于齿轮的各种状态具有很好的分类精确度,更加有效地识别齿轮故障类型。     

Electrochemical characteristics and interfacial contact resistance of multi-layered Ti/TiN coating for metallic bipolar-plate of polymer electrolyte membrane fuel cells

Metallic bipolar-plates have advantages over non-porous graphite ones due to their higher mechanical strength and better electrical conductivity. However, corrosion resistance and interfacial contact resistance are major concerns that remain to be solved, since metals such as stainless steels may develop oxide layers that decrease electrical conductivity, thus lowering fuel cell efficiency. In this study, multi-layered nitride coatings consisting of Ti and TiN were deposited on 316L stainless steel (SS316L) by a D.C magnetron sputtering method to enhance the corrosion resistance and to lower the interfacial contact resistance (ICR) of metallic bipolarplates for a polymer electrolyte membrane fuel cell (PEMFC). Electrochemical methods were conducted and ICRs of the coated specimens were measured to investigate the potential of the coated metallic bipolar-plate for use in PEMFCs. The multi-layered Ti/TiN coating deposited on SS316 showed lower ICR values than the single-layered TiN coating, and improved corrosion resistance when the PEMFC was not in operation while the degradation of the coating layer was observed in both cathodic and anodic working environments.     

实物逆向设计中的特征分析和处理

针对目前国内外的逆向工程研究侧重于形状逆向而少于设计的问题,提出将零件的模型分为装配特征、功能特征、自由曲面的复杂型面特征和其它特征等四种特征,并结合摩托车灯座零件的逆向设计问题对不问的特征部分提出了具体的处理方法。     

基于时频判别特征的焊缝超声检测缺陷分类

根据超声检测信号的瞬变特性,针对焊缝检测的缺陷分类问题,提出用判别追踪算法提取缺陷信号的局部时频判别特征,并结合概率神经网络实现了焊缝超声检测信号的缺陷分类.在提取时频判别特征时,提出考虑新选原子与已选原子的相关性的判别基提取方案,以降低特征之间的冗余,使提取出的特征能更有效地鉴别不同类别的缺陷.用该方法对一电子束焊缝试块中的缺陷进行了分类,结果表明,时频判别特征适合超声信号的缺陷分类,并能有效地抑制晶粒噪声的影响,考虑判别原子间相关性后可获得更高的分类正确率.     

基于WTD-AR谱和MEA-BPNN的轴承故障诊断方法

针对滚动轴承故障诊断模型在噪声干扰下鲁棒性能差的问题,提出一种基于小波阈值去噪（WTD）、AR谱和思维进化算法（MEA）优化反向传播神经网络（BPNN）的轴承故障诊断方法。以原始振动信号为输入,采用小波方法分解重构原始信号滤除高频噪声,然后采用Burg算法估计AR模型参数提取降噪信号功率谱特征,最后将特征向量与对应标签分别作为MEA-BPNN神经网络的输入、输出进行训练,最终实现诊断。将该方法与一些先进的人工神经网络诊断方法作比较,测试该诊断模型的性能。研究结果表明：WTD-AR谱-MEA-BPNN诊断模型能够有效降低轴承振动信号的噪声干扰,实现特征增强,分辨率更高;相较于传统神经网络训练速度更快,在更短时间内甄别故障类型且识别率高。     

Feature extraction and selection for defect classification of pulsed eddy current NDT

Pulsed eddy current (PEC) is a new emerging nondestructive testing (NDT) technique using a broadband pulse excitation with rich frequency information and has wide application potentials. This technique mainly uses feature points and response signal shapes for defect detection and characterization, including peak point, frequency analysis, and statistical methods such as principal component analysis (PCA). This paper introduces the application of Hilbert transform to extract a new descending feature point and use the point as a cutoff point of sampling data for detection and feature estimation. The response signal is then divided by the conventional rising, peak, and the new descending points. Some shape features of the rising part and descending part are extracted. The characters of shape features are also discussed and compared. Various feature selection and integrations are proposed for defect classification. Experimental studies, including blind tests, show the validation of the new features and combination of selected features in defect classification. The robustness of the features and further work are also discussed.     

基于多域空间状态矩阵奇异值与局部保持投影的滚动轴承故障特征提取方法

针对滚动轴承振动信号复杂且难以从中提取有效故障特征的问题,提出了一种总体经验模态分解(EEMD)、奇异值分解(SVD)和局部保持投影(LPP)相结合的故障特征提取方法。首先,对振动信号进行EEMD分解,利用EEMD分解后的固有模态分量(IMF)分别构造时域、频域和时频域空间状态矩阵;其次,利用SVD提炼时域、频域和时频域空间状态矩阵中的故障信息,筛选其中累加百分比大于90%的奇异值组成多域有效奇异值数组,构造多域奇异值特征矩阵;然后,利用LPP约简多域奇异值特征矩阵,提取低维、高区分度的故障特征;最后,利用支持向量机(SVM)对提出的故障特征提取方法进行评估。实验结果证明了该方法提取的故障特征可有效反映滚动轴承的故障状态。     

Behavioural Aspects of Combining Backpropagation Learning and Self-organizing Maps

Backpropagation learning (BP) is known for its serious limitations in generalizing knowledge from certain types of learning material. In this paper, we describe a new learning algorithm, BP-SOM, which overcomes some of these limitations as is shown by its application to four benchmark tasks. BP-SOM is a combination of a multi-layered feedforward network (MFN) trained with BP and Kohonen's self-organizing maps (SOMs). During the learning process, hidden-unit activations of the MFN are presented as learning vectors to SOMs trained in parallel. The SOM information is used when updating the connection weights of the MFN in addition to standard error backpropagation. The effect of the augmented error signal is that, during learning, clusters of hiddenunit activation patterns of instances associated with the same class tend to become highly similar. In a number of experiments, BP-SOM is shown (i) to improve generalization performance (i.e. avoid overfitting); (ii) to increase the amount of hidden units that can be pruned without loss of generalization performance and (iii) to provide a means for automatic rule extraction from trained networks. The results are compared with results achieved by two other learning algorithms for MFNs: conventional BP and BP augmented with weight decay. From the experiments and the comparisons, we conclude that the hybrid BP-SOM architecture, in which supervised and unsupervised and learning co-operate in finding adequate hidden-layer representations, successfully combines the advantages of supervised and unsupervised learning.     

室外温度变化对巴克豪森检测的影响

钢轨常年暴露在外,随着气候的四季变化钢轨温度会有很大的差异,从而产生温度应力。在采用巴克豪森噪声（MBN）检测方法对温度应力进行检测中,温度改变造成的应力变化,以及温度的变化对MBN本身的影响,两方面的因素都造成MBN信号的变化。为了提取反映应力变化的信息,介绍了MBN检测系统的设计,在保证应力不变而环境温度发生改变的情况下进行试验,并讨论分析了各特征值随温度的变化与应力的变化的关系。研究发现,在试样的弹性范围内,MBN的平均值、均方根、振铃数、峰值、峰宽比都随着温度的升高而减小,但变化率有所区别。最后寻找出随温度变化较小而随应力变化较大的特征值,从理论上对温度变化影响钢轨应力这一现象作出解释,并对试验过程中钢轨内部残余应力、温度分布不均等问题及造成的影响进行讨论。     

An old-fashioned connectionist approach to a Cajun chord change problem

In this paper, the problem of changing chords when playing Cajun music is introduced. A number of connectionist network simulations are then described, in which the networks attempted to learn to predict chord changes correctly in a particular Cajun song, ‘Bayou Pompon’. In the various sets of simulations, the amount of information provided to the network was varied. While the network had difficulty in solving the problem with six one-eighths of a bar of melody information, performance radically improved when the network was provided with seven one-eighths of a bar of melody information. A post-training analysis of a trained network revealed a ‘rule’ for solving the problem. In addition to providing useful insight for scholars interested in traditional Cajun music, the results described here also illustrate how a traditional connectionist network, trained with the familiar backpropagation learning algorithm, can be used to generate a theory of the task.