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.     

Information theoretic competitive learning in self-adaptive multi-layered networks

In this paper, we propose self-adaptive multi-layered networks in which information in each processing layer is always maximized. Using these multi-layered networks, we can solve complex problems and discover salient features that single-layered networks fail to extract. In addition, this successive information maximization enables networks gradually to extract important features. We applied the new method to the Iris data problem, the vertical-horizontal lines detection problem, a phonological data analysis problem and a medical data problem. Experimental results confirmed that information can repeatedly be maximized in multi-layered networks and that the networks can extract features that cannot be detected by single-layered networks. In addition, features extracted in successive layers are cumulatively combined to detect more macroscopic features.     

Improving feature extraction performance of greedy network-growing algorithm by inverse euclidean distance

We propose here a new computational method for the information-theoretic method, called the greedy network-growing algorithm, to facilitate a process of information acquisition. We have so far used the sigmoidal activation function for competitive unit outputs. The method can effectively suppress many competitive units by generating strongly negative connections. However, because methods with the sigmoidal activation function are not very sensitive to input patterns, we have observed that in some cases final representations obtained by the method do not necessarily faithfully describe input patterns. To remedy this shortcoming, we employ the inverse of distance between input patterns and connection weights for competitive unit outputs. As the distance becomes smaller, competitive units are more strongly activated. Thus, winning units tend to represent input patterns more faithfully than in the previous method with the sigmoidal activation function. We applied the new method to artificial data analysis and animal classification. Experimental results confirmed that more information can be acquired and more explicit features can be extracted by our new method.     

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。     

基于D S证据理论的轴心轨迹自动识别方法

旋转机械的轴心轨迹包含了其运行状态的丰富信息,是判断转子运行状态和故障征兆的重要依据。提出对轴心轨迹的图像利用不变矩和傅里叶描述子提取特征,采用D-S证据理论对轴心轨迹特征参数进行融合识别诊断,并与传统BP神经网络识别方法比较,证明D-S证据理论提高了识别的准确性。将所提的方法应用于磁轴承故障诊断中,利用实测振动信号验证该方法的实用性,最终结果表明识别结果与轨迹形状相符合,说明文中提出的方法不仅能够较好的提取轴心轨迹图像特征,并能有效地对轴心轨迹进行识别,提高磁轴承故障诊断的精度。     

高强钢焊接缺陷磁光成像分形特征检测

研究一种基于磁光成像原理的焊接缺陷无损检测新方法.以高强钢表面微小焊接缺陷为例,采用分形维数对焊缝磁光图像进行特征识别并估计最优尺度,根据Adabost分类算法对提取的焊接缺陷特征进行分析和训练,构建焊接缺陷特征量并对高强钢表面缺陷磁光图像进行自动识别.结果表明,运用磁光成像方法可以获取高强钢焊接缺陷特征,并通过图像分形维数分析可识别焊缝缺陷的位置、形状和类别.     

An Innovative Methodology for the Performance Evaluation of Coated Cemented Carbide Inserts in Milling of Inconel 718

The performance of cemented carbide inserts coated with various PVD-films in milling Inconel 718 is evaluated by innovative analytical and experimental methods. Three PVD films with different micro and macro structures were applied. The coatings’ strength properties were detected by nanoindentations and by impact tests at various temperatures. These results were considered in FEM calculations of the material removal process to determine the mechanical and thermal loadings of the cutting wedge. Employing this innovative methodology, it is possible to capture proactively the effect of the cutting conditions on tool wear, thus reducing the effort dedicated in traditional sequential cutting experimentation.     

铝土矿的宏观及微观特征剖析

从宏观和微观两方面提出了鉴别铝土矿矿床和矿石的依据。在宏观上，通过对铝土矿形成的古地理特征及铝土矿床在空间上分布规律的研究，提出了寻找、鉴别铝土矿床的依据；在微观上．通过对铝土矿矿石的结构、构造及铝土矿与其它类似矿石区别的论述．提出了辨别铝土矿矿石的有效方法。     

铸造合金凝固组织的计算机模拟与预测

数值模拟技术与计算机技术的迅速发展，使凝固过程的数值模拟正在由宏观向微观转变。微观模拟不仅可以得到材料的凝固组织，而且还能为宏观模拟提供准确的潜热释放信息。对宏观和微观现象的完整耦合可以使我们对铸造凝固过程作出更加准确的模拟预测。针对目前微观组织模拟的研究现状，介绍了几种主要的模拟研究方法，如确定性模拟方法、随机性模拟方法和相场方法等，阐述了其主要特征和模拟微观组织时存在的优缺点，并给出了各种模拟方法的计算实例。由于凝固组织数值模拟的复杂性，对其进行深入的研究是必要的，也是未来计算材料科学的重要发展方向。最后对微观模拟中的问题及发展方向作了分析。     

基于混合时间序列卷积神经网络的轴承故障诊断

在传统滚动轴承故障诊断中,绝大多数方法采用了从振动信号提取特征的诊断模式,但是这种模式必然会使原始信号降维进而导致故障信息的丢失。卷积神经网络(CNN)通过权重共享和稀疏连接直接对原始信号进行操作,实现自适应特征提取,最大化保留故障信息。受CNN原理启发,开发出了一种基于工业振动信号特征的新型诊断框架,称之为混合时间序列CNN(HTS-CNN)。首先,利用估计总体比例的方法自适应确定模型训练样本数目;其次,通过对时间序列片段进行随机组合的方式,使模型能够提取非相邻信号特征;最后,利用Softmax激活函数在模型输出端执行多分类任务。通过对凯斯西储大学及CUT-2平台轴承数据进行分析,实验结果表明:该方法能够准确、有效的对滚动轴承故障进行分类。     

A ganglion-cell-based primary image representation method and its contribution to object recognition

A visual stimulus is represented by the biological visual system at several levels: in the order from low to high levels, they are: photoreceptor cells, ganglion cells (GCs), lateral geniculate nucleus cells and visual cortical neurons. Retinal GCs at the early level need to represent raw data only once, but meet a wide number of diverse requests from different vision-based tasks. This means the information representation at this level is general and not task-specific. Neurobiological findings have attributed this universal adaptation to GCs' receptive field (RF) mechanisms. For the purposes of developing a highly efficient image representation method that can facilitate information processing and interpretation at later stages, here we design a computational model to simulate the GC's non-classical RF. This new image presentation method can extract major structural features from raw data, and is consistent with other statistical measures of the image. Based on the new representation, the performances of other state-of-the-art algorithms in contour detection and segmentation can be upgraded remarkably. This work concludes that applying sophisticated representation schema at early state is an efficient and promising strategy in visual information processing.     

显微偏析数值模拟的微观模型和数值方法

研究显微偏析数值模拟中的微观模型和数值方法,在微观模型中考虑了树枝晶粗化、固相溶质逆扩散、枝晶尖端过冷、随温度变化的溶质扩散系数等影响显微偏析形成的动力学因素.数值方法中采用变网格技术跟踪移动界面,通过迭代求解溶质扩散方程和溶质守恒方程计算显微偏析参数.并给出了微观计算流程图,这种数值方法可以方便地与宏观计算、相图计算相耦合.模拟算例表明模拟结果与实验结果吻合较好.     

《铸造三维设计及优化》学练做一体化教学改革与实践

根据铸造行业人才培养新要求,整合传统专业课程,结合三维设计软件的应用,开展《铸造三维设计及优化》课程的教学改革。课程结构分为铸造工艺设计基础,专业绘图软件的应用,铸造仿真模拟及优化三大模块,采用学练做一体化教学,灵活运用案例法、分组法、任务驱动等教学方法,取得较好的教学效果。最后对教学改革中遇到的问题和改进措施进行了梳理总结。     

SiC/Al-Si复合材料颗粒分布的数值模拟

介绍了颗粒分布的定量分析技术在颗粒增强复合材料性能预测方面的研究方法以及应用进展。在对搅拌铸造法制备SiC颗粒增强Al-7．0Si复合材料凝固过程的宏／微观数值模拟的基础上，将样方法以及方差分析法嵌入数值模型，对不同颗粒体积分数条件下复合材料颗粒分布均匀性进行了定量分析，并与试验结果进行了对比。结果表明：将宏／微观数值模拟与定量分析技术相结合，能够更为准确地分析不同工艺参数对复合材料微观组织以及颗粒分布的影响。在本试验条件下，随着SiC颗粒体积分数的增加，样方法中的颗粒均匀性参数值以及方差系数都逐渐减小，SiC颗粒分布更均匀。     

Bubble size estimation using interfacial morphological information for mineral flotation process monitoring

To relate froth structural information with mineral flotation performance, segmentation analysis was performed on froth images characterized by fully occupied convex bubbles with white spots effect. An improved valley edge detection method was proposed to extract structural features and overcome fake white spot edges seriously affecting the segmentation performance. After preprocessing, detection template was designed based on the local minimal intensity, and a binary image containing segmented boundaries was obtained by applying logical rules, thinning and filtering. Statistical features such as bubble size were estimated for control purpose. Experimental results demonstrate that the proposed method avoids over-segmentation or ill-segmentation caused by uneven illumination, and the industrial application reveals the reliability of bubble size estimation.     

基于GRETA正则表达式的机器人解释器的研究

为了解决传统解释器编译过程复杂,效率低的问题,提出了一种基于GRETA正则表达式的工业机器人解释器的实现方法。利用GRETA正则表达式建立字符匹配表和语法规则后,该解释器即可方便地对指令代码进行解释处理,包括:词法分析、语法分析、语义分析和信息提取。实验表明,该解释器可实现对机器人指令集的正确解释和信息提取,并为机器人控制的开放性和高效性奠定基础。     

基于改进CEEMDAN和t-SNE的故障特征提取方法

针对非线性、非稳定振动信号难以提取有效故障特征的问题,提出一种基于改进自适应噪声完备集合经验模态分解（CEEMDAN）和t-分布随机邻域嵌入（t-SNE）算法相结合的故障特征提取方法。利用三次Hermite插值代替三次样条插值构造包络线,提高传统CEEMDAN对非平稳信号的分解精度;利用改进后的CEEMDAN对原始信号分解并通过相关系数筛选出有效固有模态分量（IMF）,提取有效IMF分量的时频特征、奇异值和能量值构建高维混合域特征集;最后,通过t-SNE算法挖掘高维混合域特征信息得到低维敏感特征,并将其输入到支持向量机中进行分类,以分类准确率作为特征提取效果评价指标。在齿轮箱故障模拟实验台进行实验验证,结果表明该方法能够准确地提取故障特征,为故障特征提取提供新思路。     

基于特种加工的微细制造技术

通过例证概括介绍了特种加工方法在微细加工方面所取得的成就，这些加工技术包括：电火花加工、电化学加工、超声加工、激光加工、精密电铸等。阐述了特种加工技术在微细制造方面的特点：擅长加工复杂的三维微机械结构，且投资小，适于中小批量生产。     

基于宏程序的冶金锯片数控加工方法

新型硬质合金齿圆锯片在钢铁行业中的应用越来越广泛,传统的加工方法已不能满足当前的生产效率及加工精度的需求。提出基于宏程序的卧式加工中心对冶金锯片的数控加工方法,分析了加工工艺,阐述了宏变量的定义,编制了结构化的宏程序,实现了数控宏程序与制造工艺的巧妙结合。利用台湾LEADWELL四轴卧式加工中心制造成品,实践证明:该方法控制方便、加工精度高、效率高、适应性强及程序可读性好。