炭素挤压机型嘴的设计研究

炭素糊料通过型嘴产生挤压形变,挤压制品的形状、尺寸、特性和质量与型嘴关系密切。针对炭素生产工艺对炭素挤压机型嘴的结构、尺寸、曲线进行了分析讨论,提出了型嘴零部件的机械设计方法,以及加热、连接、安装、材料及热处理等设计思路与方法,为该产品的设计提供了依据。     

表面缺陷的超声检测与识别

通过对模拟试样表面缺陷回波的时域、频域和自咽归模型谱等多值域的特征分析，选择了出用于模式分类的最佳特征子集，在此基础上，动用Ｆｉｓｈｅｒ线性分类法对缺陷进行了有效分类 。     

基于小波包分析的超声铜-钢感应熔敷焊焊接界面缺陷特征参量提取

通过信号截取和幅值归一化对铜一钢感应熔敷焊焊接界面超声检测信号进行了预处理研究。采用Db8小波基函数对预处理后的典型缺陷波形进行了3层小波包分解,提取了典型缺陷的时域特征和频域特征;利用欧式距离公式对时域、频域及时频域3种不同的特征向量下缺陷类型的可分性进行了比较。结果表明:选择时频域特征向量作为缺陷性质判定的依据,能确保缺陷分类的准确性与可靠性。     

柴油机灰铸铁铸件常见孔洞缺陷微观特征与形成机理

对柴油机灰铸铁铸件常见孔洞缺陷进行了分类，利用扫描电镜及能谱分析，根据各类缺陷的宏观、微观特征及缺陷处的成分，总结了各类缺陷的主要特点，有助于对其进行准确的识别。同时结合铸造理论和实践生产，对各类缺陷的形成机理进行了分析。     

注射制品表面缺陷在线检测与自动识别

基于机器视觉技术的注射制品表面缺陷检测与识别可有效解决人工抽样检测问题,为克服现有缺陷识别算法对于不同的制品需分别进行样本训练、图像质量要求高、可操作性差等难题,在采用图像处理技术对制品表面缺陷进行检测的同时,提出一种基于缺陷区域轮廓、制品轮廓、区域灰度等特征的缺陷自动识别算法,避免了大量制品图像样本的训练过程,提高了可操作性。基于该方法,开发了一套注射制品表面缺陷在线检测与识别系统,试验表明,对短射、飞边、裂纹3种常见表面缺陷的识别率为91.8%。     

二次创业的带头——记本刊理事、青铜峡铝业集团有限公司总经理黄河

青铜峡铝业集团(原青铜峡铝厂)。于国家“六五”重点建设中诞生。到2005年底，将形成130KA、160KA、200KA、350KA不同档次的大型预焙电解铝先进系列生产线和配套的阳极、阴极炭素制品系列生产线。设计生产能力将达到55万吨电解铝、36万吨阳极炭素制品、2万吨阴极炭素制品。     

基于神经网络的焊接缺陷智能化超声模式识别与诊断

以三种焊接缺陷为对象,研究了缺陷回波特征的评价与模式识别。在实验研究与理论分析的基础上,从每个缺陷回波样本中提取了26个特征值,采用基于统计学假设检验的特征评价和最佳特征子集选择方法,实现了特征空间的降维处理。作者采用B-P型反向传播神经元网络构成了智能化模式分类器,研究了网络模型的学习效果和对未知缺陷的分类识别能力。还探讨了用Dempster方法进行超声检测信息融合处理的可行性。实验结果表明,采用最佳特征子集作为样本的特征向量,获得了良好的识别结果,三类缺陷的平均正确识别率约为87.6％,最佳识别率为97％。     

一种基于小波包和PCA的超声缺陷识别方法

在超声检测中，对缺陷进行定性分析是无损检测与评价的关键内容。本研究提出一种对缺陷类型进行分类的检测方法，通过对不同类型的缺陷波信号进行特征量提取，实现对缺陷的类型识别。首先使用空气耦合超声检测系统采集无缺陷信号与3种不同类型的缺陷波信号，提取信号的时域无量纲参数和小波包能量系数组成多维特征向量；然后使用主成分分析法（Principal component analysis，PCA）对多维特征向量进行降维处理得到特征融合量；最后输入BP神经网络系统进行缺陷类型的分类，并与未经过PCA处理的测试结果进行对比分析。实验结果证明，经过PCA处理的测试结果准确率更高，测试时间更短。     

加入石墨碎对石墨制品质量的影响

石墨碎是生产石墨制品的废品和切削碎屑。生产石墨电极所得的石墨碎约为加工后成品重量的20％。回收这部分石墨碎是非常重要的。而且加入适量的石墨化碎对炭素制品的质量有较好的影响。如生产炭素制品及糊类加入     

铜及铜合金的焊接

目前对铜及铜合金焊接性的系统研究很少，经过长期对铜及铜合金的焊接性研究以及查阅有关资料，简要介绍了铜及铜合金的分类、性质；分析了铜及铜合金的焊接性、钢与铜及铜合金的焊接性以及在焊接过程中易出缺陷（气孔、裂纹）的原因和解决措施；探讨了铜及铜合金、钢与铜及铜合金的焊接工艺。实践证明：焊接方法和工艺选择得当，焊接材料选择合理，在焊接过程中易出现的缺陷是完全可以避免的。     

Improving the accuracy of computer-aided radiographic weld inspection by feature selection

This paper presents new results of our continuous effort to develop a computer-aided radiographic weld inspection system. The focus of this study is on improving accuracy by feature selection. To this end, we propose two versions of ant colony optimization (ACO)-based algorithms for feature selection and show their effectiveness to improve the accuracy in detecting weld flaws and the accuracy in classifying weld flaw types. The performances of ACO-based methods are compared with that of no feature selection and that of sequential forward floating selection, which is a known good feature selection method. Four different classifiers, including nearest mean, k-nearest neighbor, fuzzy k-nearest neighbor, and center-based nearest neighbor, are employed to carry out the tasks of weld flaw identification and weld flaw type classification.     

小波变换和神经网络在漏磁缺陷信号识别中的应用

利用小波变换和RBF（Radius Basis Function）神经网络技术对漏磁检测系统中的缺陷信号进行分类。重点设计了试验系统，采集了四种缺陷信号，首先应用小波变换提取信号特征值，然后利用RBF神经网络训练，采用模糊聚类算法寻找基函数的中心，使缺陷的定性分类获得了很高的准确率。试验获得了较好的缺陷分类效果。     

Evaluation of echo features of ultrasonic flaws and its intelligent pattern recognition

In this paper, three types of weld flaw were taken as target, evaluation and recognition of flaw echo features were studied. On the basis of experimental study and theoretical analysis, 26 features have been extracted from each echo samples.A method which is based on the statistical hypothesis testing and used for feature evaluation and optimum subset selection was explored Thus. the dimensionality reduction of feature space was brought out, and simultaneously, the amount of calculation was decreased. An intelligent pattern classifier with B-P type neural network was constructed which was characterized by high speed and accuracy for learning. Using a half of total samples as training set and others as testing set, the learning efficiency and the classification ability of network model were studied. The results of experiment showed that the learning rate of different training samples was about 100％. The results of recognition was satisfactory when the optimum feature subset was taken as the sample's feat     

Artificial immune system based on adaptive clonal selection for feature selection and parameters optimisation of support vector machines

Artificial immune system (AIS) algorithm based on clonal selection method can be defined as a soft computing method inspired by theoretical immune system in order to solve science and engineering problems. Support vector machine (SVM) is a popular pattern classification method with many diverse applications. Kernel parameter setting in the SVM training procedure along with the feature selection significantly impacts on the classification accuracy rate. In this study, AIS based on Adaptive Clonal Selection (AISACS) algorithm has been used to optimise the SVM parameters and feature subset selection without degrading the SVM classification accuracy. Several public datasets of University of California Irvine machine learning (UCI) repository are employed to calculate the classification accuracy rate in order to evaluate the AISACS approach then it was compared with grid search algorithm and Genetic Algorithm (GA) approach. The experimental results show that the feature reduction rate and running time of the AISACS approach are better than the GA approach.     

基于超声信号和图像融合的焊缝缺陷识别

超声无损检测已被广泛用来检测材料内部的缺陷,然而对缺陷性质的识别始终是检测的难点,为此研究了一种基于超声信号和图像融合的焊缝缺陷识别新方法.该方法充分利用检测数据,通过对缺陷回波信号特征与缺陷形态特征的数据融合,实现了焊缝缺陷的有效识别.利用自主研制的超声成像手动检测系统对含有气孔、夹渣、裂纹、未焊透和未熔合五类典型焊接缺陷的焊件进行了检测,分别提取缺陷的超声回波信号特征和缺陷图像的形态特征,构建神经网络实现超声信号和图像特征的数据融合.结果表明,该方法实现了多类缺陷的识别,提高了缺陷识别率,有助于焊缝质量评定.     

Detection and classification of flaws in concrete structure using bispectra and neural networks

The problem addressed in this paper is the detection and classification of flaws in concrete structure. It is known that higher-order spectra contain information not present in the power spectrum and can suppress Gaussian noise. Thus estimates of higher-order spectra have been shown to be useful in certain signal processing problems. This paper is concerned with the feature extraction from bispectra for concrete flaw detection. Impact-echo experiments are carried out for three different types of flaw in concrete structure. For each monitoring signal, after bispectral estimation, features are selected from the modules of bispectra in the primary region. For automatic interpretation, a multilayer back-propagation neural network is used as a classifier. Both clean data and data with additive white Gaussian noise are used for training and testing. The classification results obtained experimentally demonstrate that this method has good detection rates in varying environments.     

Improving feature ranking for biomarker discovery in proteomics mass spectrometry data using genetic programming

Feature selection on mass spectrometry (MS) data is essential for improving classification performance and biomarker discovery. The number of MS samples is typically very small compared with the high dimensionality of the samples, which makes the problem of biomarker discovery very hard. In this paper, we propose the use of genetic programming for biomarker detection and classification of MS data. The proposed approach is composed of two phases: in the first phase, feature selection and ranking are performed. In the second phase, classification is performed. The results show that the proposed method can achieve better classification performance and biomarker detection rate than the information gain- (IG) based and the RELIEF feature selection methods. Meanwhile, four classifiers, Naive Bayes, J48 decision tree, random forest and support vector machines, are also used to further test the performance of the top ranked features. The results show that the four classifiers using the top ranked features from the proposed method achieve better performance than the IG and the RELIEF methods. Furthermore, GP also outperforms a genetic algorithm approach on most of the used data sets.     

Investigation on particle swarm optimisation for feature selection on high-dimensional data: local search and selection bias

Feature selection is an essential step in classification tasks with a large number of features, such as in gene expression data. Recent research has shown that particle swarm optimisation (PSO) is a promising approach to feature selection. However, it also has potential limitation to get stuck into local optima, especially for gene selection problems with a huge search space. Therefore, we developed a PSO algorithm (PSO-LSRG) with a fast “local search” combined with a gbest resetting mechanism as a way to improve the performance of PSO for feature selection. Furthermore, since many existing PSO-based feature selection approaches on the gene expression data have feature selection bias, i.e. no unseen test data is used, 2 sets of experiments on 10 gene expression datasets were designed: with and without feature selection bias. As compared to standard PSO, PSO with gbest resetting only, and PSO with local search only, PSO-LSRG obtained a substantial dimensionality reduction and a significant improvement on the classification performance in both sets of experiments. PSO-LSRG outperforms the other three algorithms when feature selection bias exists. When there is no feature selection bias, PSO-LSRG selects the smallest number of features in all cases, but the classification performance is slightly worse in a few cases, which may be caused by the overfitting problem. This shows that feature selection bias should be avoided when designing a feature selection algorithm to ensure its generalisation ability on unseen data.     

A multi-objective particle swarm optimisation for filter-based feature selection in classification problems

Feature selection has the two main objectives of minimising the classification error rate and the number of features. Based on binary particle swarm optimisation (BPSO), we develop two novel multi-objective feature selection frameworks for classification, which are multi-objective binary PSO using the idea of non-dominated sorting (NSBPSO) and multi-objective binary PSO using the ideas of crowding, mutation and dominance (CMDBPSO). Four multi-objective feature selection methods are then developed by applying mutual information and entropy as two different filter evaluation criteria in each of the proposed frameworks. The proposed algorithms are examined and compared with a single objective method on eight benchmark data sets. Experimental results show that the proposed multi-objective algorithms can evolve a set of solutions that use a smaller number of features and achieve better classification performance than using all features. In most cases, NSBPSO achieves better results than the single objective algorithm and CMDBPSO outperforms all other methods mentioned above. This work represents the first study on multi-objective BPSO for filter-based feature selection.