新型ART-2A算法及其在BIT故障诊断中的应用

在故障诊断过程中由于样本获取困难，无监督分类方法日益得到重视，自适应共振理论（ART）是一种典型的，无监督的，能够对复杂输入模式实现自组织识别的神经网络，作者发现标准ART－2算法存在预处理信号畸变问题，同相位不同分问题，由此提出了新的F1层非线性变换函数，F2层竞争学习算法和输入预处理方法，该新型ART－2／2A算法的输入域由原来的非负实数域扩大到整个实数域，并且能够正确区分标准ART－2／2A算法不可区分的同相位数据，本文以大型船舶动力装置BIT系统运行状态中的故障模式为对象进行实验验证，结果表明新型ART－2／2A算法能自适应地对BIT系统未知故障模式进行分类识别，分类准确。     

邻域粗糙集融合贝叶斯神经网络在医疗决策中的应用研究

为提高医疗决策的效率和有效性,建立了邻域粗糙集融合贝叶斯神经网络的组合医疗决策模型。首先,通过邻域粗糙集对医疗决策系统进行知识约简,去除系统中冗余、干扰的指标,提取关键指标,并将约简后的指标作为神经网络模型的输入指标;之后针对BP神经网络容易过拟合的缺点,采用贝叶斯正则化方法对神经网络进行优化,提高输出指标的预测效果和效率。最后,通过一个心脏病医疗诊断实例对模型的应用实现效果加以分析及验证,结果表明,模型测试集分类准确率达到了88.89%;并将实验结果同几种常见的属性选择方法、分类模型以及2008~2014年的8个历史参考文献进行了对比。     

基于神经网络的声目标识别融合方法研究

本文介绍了声目标的各种识别方法，将Dempster-Shafer证据推理的基本理论应用到声目标的识别中，并用BP神经网络构造出基本概率赋值函数，从而避开了建立质量函数的麻烦，大大拓宽了这种方法的应用范围．本文给出了改进后的BP神经网络算法并给出了识别目标的决策方法．通过实例计算可以看出，该方法可以提高对声目标识别的准确性。     

基于ALO-BP神经网络和机械零件加工特征的工艺方案决策

针对传统制造企业工艺知识应用不充分,用于工艺方案决策过程的部分BP神经网络决策效率和准确率不高的问题,采用蚁狮优化(Ant Lion Optimizer, ALO)算法优化的BP神经网络构建了基于零件加工特征的工艺方案智能决策模型。首先对产品及工艺数据进行预处理,其次应用蚁狮优化算法对BP神经网络的初始化权值和阈值进行优化,最终基于样本数据集开展神经网络训练,进一步建立智能决策系统,并以柴油机零件为对象进行了工艺方案决策方法的应用验证。实例验证表明,采用优化的BP神经网络后,决策的速度和精度都有明显的提升;所构建决策系统是可行的,能够用于工艺方案的决策。     

工程结构损伤的集成神经网络识别研究

从结构损伤识别的实际出发，提出采用基于信息融合理论的集成神经网络技术对结构损伤状况进行识别，即通过结构损伤特征信息的有效组合，用各种子神经网络从不同侧面对结构损伤进行初步识别诊断，然后对识别结果进行决策融合。给出了系统的实现策略和子网络的组建原则。从识别实例中可以看出，此识别方法充分利用了各种特征信息，可以有效地提高识别率。     

基于神经网络的在线计算机图像识别系统

以二值型自适应共振理论（ART－1）神经网络为识别核心设计了一个应用于生产流水线的计算机识别系统，它可以对生产线上的零件和产品的文字和符号进行实时识别，作自动记录。该系统具有学习和识别速度快、识别率高（＞96％），可以灵活改变识别对象，应用范围广等特点。     

集成小波神经网络在故障诊断中的应用研究

以非线性Morlet小波基作为激励函数,形成神经元,结合小波变换与神经网络各自的优点,建立集小波分析与神经网络于一体的紧致型小波神经网络,并给出了具体的算法。基于信息融合技术的思想,从设备故障诊断的实际出发,建立了基于信息融合技术的集成小波神经网络故障诊断系统,即通过故障特征信息的有效组合,用各种子小波神经网络从不同侧面对设备故障进行初步诊断,然后对诊断结果进行决策融合。给出了系统的实现策略和子网络的组建原则。从诊断实例中可以看出,此诊断系统充分利用各种特征信息,可以有效的提高确诊率。     

用小波神经网络检测结构损伤

用小波和神经网络ART2相结合的方法检测结构的损伤位置。给出了小波变换和人工神经网络的基本理论及其用于损伤检测的原理与特点。通过把小波变换作为神经网络的前处理来构造小波神经网络。首先通过数值试验检验了小波消噪和小波神经网络损伤检测的能力。然后在一个框架结构模型上进行了试验。实验证明这种方法使网络抗噪声能力增强,使损伤识别的效果更好。ART2网络具有自动从环境中学习的能力,能自动的给出新的识别输出。     

基于概率神经网络和KS检验的机械状态监测

机械状态监测中经常需要用非线性分类器对机械状态进行分类.概率神经网络是一种典型的非线性分类器.它与传统BP神经网络分类器相比,具有训练速度快,分类准确性高、稳定性好等优点.但是,概率神经网络分类器和其它神经网络分类器一样,存在分类准确性完全依赖现有训练样本的缺陷.当现有训练样本数量不足或机械设备出现了新的状态时,神经网络分类器就不能进行正确分类了,从而造成误报.因此,需要对神经网络分类器的分类结果进行检验.KS检验是一种非参数统计方法,它通过描述两个统计样本的相似性,可以有效的对分类结果进行检验,及时发现概率神经网络的错误,减少误报.     

基于径向基神经网络的水下振动物体辐射噪声级别分类研究

运用径向基神经网络，利用水下振动物体内表面加速度信号对其辐射噪声级别进行分类．达到判断其声隐身性的目的，该方法的运算量较传统方法大大降低，极大地提高了计算速度。实例表明，该方法能较准确地对水下振动物体辐射声场声压级别进行分类。进而对其推广应用于潜艇提供了较好的依据。     

模糊中心聚类的模式识别学习方法

基于一个约束条件下的非线性规划问题的优化计算思想，把模糊中心聚类中计算输入矢量与中心的距离来实现聚类作为一种优化计算问题，证明了模糊中心聚类方法，取一个适当的属函数，其聚类中心vi为模糊聚类中心价值函数的极小值，推导出了基于模糊中心聚类的模式识别的无导师递推学习方法，提出了模糊中心聚类模式分类神经网络结构，该网络可以实现并行数据处理和模式分类的软划分和硬划分。     

Performance of Fuzzy ART neural network for group technology cell formation

This study investigates the performance of Fuzzy ART neural network for grouping parts and machines, as part of the design of cellular manufacturing systems. Fuzzy ART is compared with ART1 neural network and a modification to ART1, along with direct clustering analysis (DCA) and rank order clustering (ROC2) algorithms. A series of replicated clustering experiments were performed, and the efficiency and consistency with which clusters were identified were examined, using large data sets of differing sizes and degrees of imperfection. The performance measures included the recovery ratio of bond energy and execution times, It is shown that Fuzzy ART neural network results in better and more consistent identification of block diagonal structures than ART1, a recent modification to ART1, as well as DCA and ROC2. The execution times were found to be more than those of ART1 and modified ART1, but they were still superior to traditional algorithms for large data sets.     

Performance of Fuzzy ART neural network and hierarchical clustering for part-machine grouping based on operation sequences

The problem context for this study is one of identifying families of parts having a similar sequence of operations. This is a prerequisite for the implementation of cellular manufacturing, group technology, just-in-time manufacturing systems and for streamlining material flows in general. Given this problem context, this study develops an experimental procedure to compare the performance of a fuzzy ART neural network, a relatively recent neural network method, with the performance of traditional hierarchical clustering methods. For large, industry-type data sets, the fuzzy ART network, with the modifications proposed here, is capable of performance levels equal or superior to those of the widely used hierarchical clustering methods. However, like other ART networks, Fuzzy ART also results in category proliferation problems, an aspect that continues to require attention for ART networks. However, low execution times and superior solution quality make fuzzy ART a useful addition to the set of tools and techniques now available for group technology and design of cellular manufacturing systems.     

An integrated approach for process monitoring using wavelet analysis and competitive neural network

A novel framework involving both a detection module and a classification module is proposed for the recognition of the six main types of process signals. In particular, a multi-scale wavelet filter is used for denoising and its performance is compared with that of single-scale linear filters. Moreover, two kinds of competitive neural networks, based on learning vector quantization (LVQ) and adaptive resonance theory (ART), are adopted for the task of pattern classification and benchmarking. Our results show that denoising through a wavelet filter is best for pattern classification, and the classification accuracy with respect to six predefined categories using a LVQ-X network is a little better than using an ART network. However, when an unexpected novel pattern occurs within the process, LVQ will force the novel pattern to be classified into one of those predefined categories that is most similar to the novel pattern. On the contrary, ART will automatically construct a new class when the similarity measured between the novel pattern and the most similar category is too small to be incorporated. Therefore, under the consideration of the stability–plasticity dilemma, our simplified ART network based on multi-scale wavelet denoising provides a more promising way to adapt unexpected novel patterns.     

基于RBF网络的步行式底盘内力计算优化方法

为了确定步行式底盘局部结构在作业时的最大受力状态,提出了一种基于RBF神经网络的两级优化模型求解方法,第一级优化模型用逐步二次规划法找到局部结构在给定位置参数下的最大受力状态,通过正交试验设计,利用RBF网络构造出局部结构界面最大受力状态与位置参数之间的非线性映射关系;第二级优化模型用GA求解RBF网络的最大值,并通过二分法不断缩小位置参数的搜索空间,提高RBF网络的逼近水平。研究表明,计算结果可为步行式底盘设计提供理论依据,该方法是解决复杂结构系统中非线性、多变量优化问题的有效手段。     

基于小波包时频图特征和卷积神经网络的水声信号分类

水下声信号分类是水声学研究的一个重要方向.一个有效的特征提取和分类决策方法对水声信号分类技术至关重要.文章将鱼声、商船辐射噪声和风关噪声三类实测的水声信号在小波包分解的基础上提取时频图特征,并搭建了一个七层结构的卷积神经网络作为分类器.研究结果表明:三种水声信号的小波包时频图特征结合卷积神经网络在不同测试集可达到(98...     

基于感性意象和BP神经网络的产品CMF决策模型研究

目的 为实现特定感性意象下的产品CMF精准选定与量化,结合BP神经网络和线性回归提出一种产品CMF决策模型。方法 通过文本挖掘形式确定用户感性意象,根据HSV色彩模型与选定的康复辅具的材质与工艺构建CMF要素空间,并基于设计要素空间形成海量CMF方案,同时根据选定感性意象对方案加以评价,获得感性意象与CMF单一设计要素的定性映射关系。将CMF方案编码后与感性意象评价值结合,并通过BP神经网络以定量方式构建CMF决策模型,筛选出最优色彩区间、材质及工艺。对选中色彩区间再次细分出设计方案并进行评价,通过线性回归得到色彩回归方程,从而构建产品CMF的综合决策模型。结果 以膝关节支具为例进行实例研究,通过BP神经网络构建的一阶CMF决策模型预测值与期望值的均方误差MSE为0.038 13,且预测结果与定性映射关系基本一致,表明该阶模型可信度较高且精度良好。利用线性回归构建的二阶决策模型P值小于0.01,表明H、S、V的数值与感性意象评价值具有显著相关性,证明了该CMF决策模型的可行性。结论 构建的CMF决策模型在产品设计领域具有一定的通用性,能够有效实现康复产品CMF的精准选择与量化,在定性和定量层面指导康复产品CMF决策的优选和创新。     

A Fuzzy Neural Network for Fault Pattern Recognition

1　ＩｎｔｒｏｄｕｃｔｉｏｎＩｎｍａｔｈｅｍａｔｉｃｓ,ｆａｕｌｔｒｅｃｏｇｎｉｔｉｏｎｃａｎｂｅｓｕｍｍｅｄｕｐａｓａｍａｐｐｉｎｇｐｒｏｂｌｅｍｂｅｔｗｅｅｎｆａｕｌｔａｇｇｒｅ ｇａｔｅａｎｄｃｈａｒａｃｔｅｒａｇｇｒｅｇａｔｅ .Ｔｈｅｍａｐｐｉｎｇｂｅｔｗｅｅｎａｇｇｒｅｇａｔｅｓｉｓｃａｌｌｅｄａｍａｐｐｉｎｇｆｕｎｃｔｉｏｎ ;ｋｉｎｄｓｏｆｍａｐｐｉｎｇｆｕｎｃｔｉｏｎｓｃａｎｂｅｆｏｒｍｅｄｆｏｒｆａｕｌｔｐａｔｔｅｒｎｒｅｃｏｇｎｉｔｉｏｎ .Ｔｈｅｔｒａｄｉｔｉｏｎａｌｐａｔｔｅｒ…     

Adaptive resonance theory-based neural algorithms for manufacturing process quality control

The demand for quality products in industry is continuously increasing. To produce products with consistent quality, manufacturing systems need to be closely monitored for any unnatural deviation in the state of the process. Neural networks are potential tools that can be used to improve the analysis of manufacturing processes. Indeed, neural networks have been applied successfully for detecting groups of predictable unnatural patterns in the quality measurements of manufacturing processes. The feasibility of using Adaptive Resonance Theory (ART) to implement an automatic on-line quality control method is investigated. The aim is to analyse the performance of the ART neural network as a means for recognizing any structural change in the state of the process when predictable unnatural patterns are not available for training. To reach such a goal, a simplified ART neural algorithm is discussed then studied by means of extensive Monte Carlo simulation. Comparisons between the performances of the proposed neural approach and those of well-known SPC charts are also presented. Results prove that the proposed neural network is a useful alternative to the existing control schemes.     

Distinguishing between mean,variance and autocorrelation changes in statistical quality control

In order to enhance the probability of correct quality diagnosis, it is useful to be able to identify the statistical manner in which the quality signal has changed, i.e. identify change structure. Specifically we wish to distinguish between changes in mean, variance and lag one autocorrelation. Because these change structures yield significant similarities in their corresponding output, a multistage decision tree is necessary. A multistage classification system with a neural network and quadratic discriminant functions is used, where neural network output is an a priori distribution for the Bayesian quadratic discriminant function. Experimental results show that this multistage decision strategy performs significantly better than its single stage counterpart, with an overall success rate of 84%.