Transformations in machining. Part 1. enhancement of wavelet transformation neural network (WT-NN) combination with a preprocessor

Properly selected transformation methods obtain the most significant characteristics of metal cutting data efficiently and simplify the classification. Wavelet Transformation (WT) and Neural Networks (NN) combination was used to classify the experimental cutting force data of milling operations previously. Preprocessing (PreP) of the approximation coefficients of the WT is proposed just before the classification by using the Adaptive Resonance Theory (ART2) type NNs. Genetic Algorithm (GA) was used to estimate the weights of each coefficient of the PreP. The WT-PreP-NN (ART2) combination worked at lower vigilances by creating only a few meaningful categories without any errors. The WT-NN (ART2) combination could obtain the same error rate only if very high vigilances are used and many categories are allowed.     

基于ART2神经网络的车辆感应波形识别的方法

在智能交通系统中,无论是在交通监控领域还是在不停车收费系统方面,对车辆进行自动分类都十分重要;环形线圈车辆检测器以其良好的适应性、稳定性和高效性在车辆监测方面得到了广泛的应用,同时利用同类型或同种车辆经过环形线圈产生轮廓相似的电磁感应波形这一特点也可以进行车型识别;对波形进行预处理,以波形轮廓的抽样、量化值作为特征向量,将特征向量作为ART2神经网络的输入向量,经ART2神经网络的自动聚类最终实现车辆感应波形的聚类与识别。     

3n镜像适应性随机测试算法

针对适应性随机测试中的边缘效应问题,借鉴镜像适应性随机测试(MART)的基本思想,在引入镜像距离的基础上,提出3n MART算法,通过改变候选用例与成功用例之间的距离判断策略,使其产生的用例在输入域中更均匀地分布。仿真实验结果证明,该算法可以较好地解决边缘效应问题,相比基于距离的适应性随机测试算法与MART算法,失效发现效率更高。     

模糊ART神经网络模型及其在图像识别中的应用

提出了采用低通过率波、去最小亮度和向量柱状图来提取人脸特征的方法,设计了模糊ART神经网络的结构、学习规则和识别算法,并采用模糊ART神经网络对向量柱状图生成的特征向量进行识别。仿真实验证明,通过调整神经网络的警戒参数值,不同的人具有不同的最大在线识别率,所有人平均的在线最大识别率可以达到89％。     

Growing fuzzy topology adaptive resonance theory models with a push-pull learning algorithm

A new incrementally growing neural network model, called the growing fuzzy topology ART (GFTART) model, is proposed based on integrating the conventional fuzzy ART model with the incremental topology-preserving mechanism of the growing cell structure (GCS) model. This is in addition, to a new training algorithm, called the push-pull learning algorithm. The proposed GFTART model has two purposes: First, to reduce the proliferation of incrementally generated nodes in the F2 layer by the conventional fuzzy ART model based on replacing each F2 node with a GCS. Second, to enhance the class-dependent clustering representation ability of the GCS model by including the categorization property of the conventional fuzzy ART model. In addition, the proposed push-pull training algorithm enhances the cluster discriminating property and partially improves the forgetting problem of the training algorithm in the GCS model.     

一种改进的基于 ART2神经网络的文字识别算法

为了解决 ART2神经网络的漂移问题,提出了一种改进的基于 ART2神经网络的文字分类和识别方法.此方法能够自主学习,收敛速度快,识别率和识别速度都比 BP神经网络高.实践证明,基于此设计的脱机手写体文字识别系统能对较规范的手写体文字进行识别,识别率达到85%.     

A Dynamic Network Model of the Color Visual Pathways for Attentive Recognition

A neural network architecture for the segmentation and recognition of colored and textured visual stimuli is presented. The architecture is based on the Boundary Contour System and Feature Contour System (BCS/FCS) of S. Grossberg and E. Mingolla. The architecture proposes a biologically-inspired mechanism for color processing based on antagonist interactions. It suggests how information from different modalities (i.e. color or texture) can be fused together to form a coherent segmentation of the visual scene. It identifies two stages of visual pattern recognition, namely, a global preattentive recognition of the visual scene followed by a local attentive recognition within a particular visual context. The global and local classification and recognition of visual stimuli use ART-type models of G. Carpenter and S. Grossberg for pattern learning and recognition based on color and texture. One example is presented corresponding to an figure-figure separation task. The architecture provides a mechanism for segmentation, categorization and recognition of images from different classes based on self-organizing principles of perception and pattern recognition.     

不同结构的树脂复鞣剂在皮革中形态的电镜研究

借助扫描电镜(SEM)观察了SCC丙烯酸皮革填充树脂、ART丙烯酸树脂复鞣剂、HMP多功能皮革材料以及RTM三聚氰胺树脂复鞣剂等4种高分子材料在皮革中的微观结构，讨论了每种材料赋予皮革的不同性能，为制革工作者在制革时正确选择皮化材料提供参考。     

Work Hardening Behavior of Ultrafine Grained Duplex Medium‐Mn Steels Processed by ART‐Annealing

The ultrafine grained duplex steels were fabricated by austenite reverted transformation annealing of the medium manganese steels after quenching or cold rolling. The microstructures were examined by scanning electron microscopy (SEM) and transmission electron microscopy (TEM) and X‐ray diffraction (XRD). The mechanical properties were determined by uniaxial tensile test. It was demonstrated that both the quenched and cold rolled structures were transformed into ultrafine grained duplex structures with large fractioned austenite by ART‐annealing. Long time annealing is essential to obtain the large fractioned austenite in quenched steel, but only short time annealing is needed to get large fractioned austenite in the cold rolled sheet. The mechanical examinations indicated that ART‐annealing results in the superhigh tensile elongation (>40%) and superhigh strength (1000 MPa) in quenched steels after long time annealing but in cold rolled steels after short time annealing. Based on the analysis on the work hardening behaviors of these ART‐annealed steels, the abnormal work hardening rate was presented and analyzed. The substantially enhanced ductility was attributed to the Lüders band propagation of the ferrite matrix and/or the TRIP effects of the large fractioned austenite. At last the dynamic phase natures of both fraction and stress was proposed to interpret the abnormal hardening behaviors and the “S” shaped stress–strain curves.     

基于神经网络的电力负荷不良数据的清洗

电力负荷预测前应首先对负荷数据进行清洗,根据电力日负荷曲线的特征,应用改进的ART-2神经网络准确的提取电力日负荷特征曲线,然后利用支持向量数据描述法对不良数据进行精确定位,最后利用特征曲线对不良数据进行修正.由于ART2网络能够动态调整特征曲线以及支持向量数据描述法快速准确性,使得该清洗模型具有对不良数据进行动态清洗的功能,实例分析说明了该模型的高效性.