Multicomponent Kinetic Determination by Wavelet Packet Transform Based Elman Recurrent Neural Network Method

This paper covers a novel method named wavelet packet transform based Elman recurrent neural network(WPTERNN) for the simultaneous kinetic determination of periodate and iodate. The wavelet packet representations of signals provide a local time-frequency description, thus in the wavelet packet domain, the quality of the noise removal can be improved. The Elman recurrent network was applied to non-linear multivariate calibration. In this case, by means of optimization, the wavelet function, decomposition level and number of hidden nodes for WPTERNN method were selected as D4, 5 and 5 respectively. A program PWPTERNN was designed to perform multicomponent kinetic determination. The relative standard error of prediction(RSEP) for all the components with WPTERNN, Elman RNN and PLS were 3.23%, 11.8% and 10.9% respectively. The experimental results show that the method is better than the others.

Detection and Diagnosis of Urban Rail Vehicle Auxiliary Inverter Using Wavelet Packet and RBF Neural Network

This study concerns with fault diagnosis of urban rail vehicle auxiliary inverter using wavelet packet and RBF neural network. Four statistical features are selected: standard voltage signal, voltage fluctuation signal, impulsive transient signal and frequency variation signal. In this article, the original signals are decomposed into different frequency subbands by wavelet packet. Next, an automatic feature extraction algorithm is constructed. Finally, those wavelet packet energy eigenvectors are taken as fault samples to train RBF neural network. The result shows that the RBF neural network is effective in the detection and diagnosis of various urban rail vehicle auxiliary inverter faults.

Performance comparison of neural network training methods based on wavelet packet transform for classification of five mental tasks

In this study, performances comparison to discriminate five mental states of five artificial neural network (ANN) training methods were investigated. Wavelet Packet Transform (WPT) was used for feature extraction of the relevant frequency bands from raw electroencephalogram (EEG) signals. The five ANN training methods used were (a) Gradient Descent Back Propagation (b) Levenberg-Marquardt (c) Resilient Back Propagation (d) Conjugate Learning Gradient Back Propagation and (e) Gradient Descent Back Propagation with movementum.

Face Recognition Based on Wavelet Packet Coefficients and Radial Basis Function Neural Networks

An efficient face recognition system with face image representation using averaged wavelet packet coefficients, compact and meaningful feature vectors dimensional reduction and recognition using radial basis function (RBF) neural network is presented. The face images are decomposed by 2-level two-dimensional (2-D) wavelet packet transformation. The wavelet packet coefficients obtained from the wavelet packet transformation are averaged using two different proposed methods. In the first method, wavelet packet coefficients of individual samples of a class are averaged then decomposed. The wavelet packet coefficients of all the samples of a class are averaged in the second method. The averaged wavelet packet coefficients are recognized by a RBF network. The proposed work tested on three face databases such as Olivetti-Oracle Research Lab (ORL), Japanese Female Facial Expression (JAFFE) and Essexface database. The proposed methods result in dimensionality reduction, low computational complexity and provide better recognition rates. The computational complexity is low as the dimensionality of the input pattern is reduced.

Fuzzy Cluster Neural Network Based on Wavelet Transform and Its Vibration Application

This paper advances a new approach based on wavelet and wavelet packet transforms in tandem with a fuzzy cluster neural network,abbreviated WPFCNN.Wavelets and wavelet packets decompose a vibration signal into different bands at different levels and provides multiresolution or multiscale views of a signal which is stationary or nonstationary. Fuzzy mathematics processes uncertain problems in engineering and converts the attributes extracted by wavelet packets to fuzzy membership degree.To achieve self-organizing classification,the MAXNET neural network is employed.WPFCNN integrates the advantages of wavelet packets and fuzzy cluster with MAXNET.The approach is adopted to process and classify vibration signal of a NH_3 compressor in a petrochemical plant.The results indicate that it is a useful and effective intelligence classification in the field of condition monitoring and fault diagnosis.

A Novel Transceiver Architecture Based on Wavelet Packet Modulation for UWB-IR WSN Applications

In last few years, several recent developments concern a new proposed techniques of communication for WSN (Wireless Sensors Network) using a complex methods and technics. This network is considered a future platform for many applications like: medical, agriculture, industrial, monitoring and others. The challenge of this work consists in proposing a new design of transceiver for WSN based on IDWPT (Inverse Discrete Wavelet Packet Transform) in emitter and DWPT (Discrete Wavelet Packet Transform) in receiver for mono and multi users using AWGN Channel. We will propose in this paper, a new concept of impulse radio communication for multiband orthogonal communication for UWB (Ultra-wideband) applications. The main objective of this work is to present a new form of pulse communication adapted to low through-put short-range applications and is scalable according to the type of use but also the number of sensors.

小波包和1D CNN结合的刀具磨损状态识别

为监测机床切削加工过程中刀具的非线性磨损变化,提出了一种基于小波包分解和一维卷积神经网络(1D CNN)的刀具磨损状态识别方法。采集机床主轴振动数据作为监测信号,采用经信噪比定量分析后的小波包进行预处理,然后选取小波包分解后各频带的能量特征作为1D CNN的输入,实现了对刀具磨损状态的有效识别。实验表明,该模型能够实现刀具磨损状态的准确预测,相比于BP网络、能量频谱图-Alexnet和Lstm网络模型,刀具磨损状态识别率最优,平均准确率达到98.262%。

小波包与遗传算法优化BP神经网络相结合的井架钢结构损伤识别

井架钢结构损伤影响其承载安全性,为快速、准确对损伤位置进行识别,提出小波包与遗传算法优化BP神经网络相结合的井架钢结构损伤识别方法。首先利用小波包处理非平稳振动信号的优良性能对原始振动信号进行特征提取,获得表征井架钢结构损伤的信息;再通过特征参数建立数据集训练并测试井架钢结构损伤识别模型,该模型结合遗传算法自身特点改善了传统BP神经网络的不足。本文识别方法不需要损伤前的数据特征进行对比,便可对损伤位置进行确定。经过对石油井架钢结构模型实验验证:该方法对井架钢结构损伤识别准确率超过90%,相对于BP网络识别准确率以及识别速度均有所提高。

基于神经网络与改进马尔可夫链中压背景噪声建模研究

在中压电力线通信中,信道噪声构成复杂,需根据不同类型噪声单独分析建模。针对一段特定中压线路的背景噪声,提出了一种基于小波包变换的噪声模型,将得到的小波包系数分别进行神经网络训练和改进马尔可夫链计算转移概率矩阵,得到新的小波包系数重构噪声信号,并进行仿真验证及去噪,同时将2种方法与传统直接神经网络训练比较分析。结果表明,基于改进马尔可夫链方法所建噪声比传统马尔可夫链方法更加准确,基于小波包变换的神经网络方法所建噪声与原噪声相似度更高,去噪效果更好,且优于传统神经网络训练方法,为进一步研究中压电力线通信提供了可行性方案。

基于模式识别的舰船机械电子设备故障自动监测

舰船机械电子设备故障数据量较为庞大,且模式复杂多样,为满足其复杂性的要求,提出基于模式识别的舰船机械电子设备故障自动监测方法,采集舰船机械电子设备运行中的温度、压力、振动等数据作为故障监测的原始数据,计算数据间的相似系数和欧氏距离,结合K均值算法实现数据聚类处理。通过小波包算法对聚类后的数据进行特征提取,将其输入到卷积神经网络中,通过对监测模型进行训练,最终实现对舰船机械电子设备故障自动监测。通过实验分析,该方法与相关人员进行监测的故障情况高度一致,在不同故障类型监测的时间均能够保持在5 ms以内,具有较高的监测效率和监测精准度。

基于WPT-CNN的复合绝缘子内部缺陷智能识别研究

超声波技术常用于复合绝缘子内部缺陷的检测,但缺陷识别过程依赖于试验人员专业经验。为实现复合绝缘子内部缺陷的智能识别,提出了一种基于小波包变换和卷积神经网络的超声波检测信号识别模型。首先,通过小波包变换对超声波检测信号进行时频特征提取,并将一维信息转化为二维特征矩阵;其次,将二维特征矩阵输入卷积神经网络中,实现对信号特征的智能识别;最后,采用试验信号样本集对模型进行训练与测试。结果表明,提出的模型能对缺陷、气孔、裂纹、界面脱粘和夹杂五类复合绝缘子超声波检测信号进行识别,且平均准确率可达98.7%,能为复合绝缘子内部缺陷的智能识别提供很好的工程应用参考。

基于多尺度小波包启发卷积网络的旋转机械故障诊断

在工程实践中,旋转机械故障诊断常面临噪声干扰、故障样本稀缺以及工况变化等各种复杂情况,这给先验知识缺乏的数据驱动深度学习方法应用带来了新的挑战。传统基于小波分析的故障诊断方法可提取到故障丰富的先验知识,但固定(结构化)或单一的小波基难以直接适应复杂故障场景。针对上述问题,在传统多尺度小波包分析思想启发下,提出一种基于多尺度小波包启发卷积网络(multiscale wavelet packet-inspired convolutional network, MWPICNet)的端到端旋转机械故障诊断方法。MWPICNet在神经网络内部实现了时频域转换与滤波降噪、特征提取与分类过程的有机耦合。首先,通过交替使用多尺度小波包启发卷积层和软阈值激活层进行信号分解和非线性变换,逐层挖掘多尺度时频故障特征和过滤噪声冗余信息,该过程的多次迭代可近似视为小波包阈值去噪算法在多个可学习滤波器和可学习阈值下的多层深度展开;然后,设计频带加权层动态调整各频带通道的权重;最后,引入全局功率池化层提取有助于故障状态识别的判别性频带能量特征。在三种不同应用场景下分别采用对应的机械故障数据集进行案例研究,验证了所提模型在复杂故障场景下的可行性和有效性。

基于模态分析和神经网络的分子泵故障检测方法研究

分子泵一种基于气体分子定向运动而产生真空环境的装置,在空间环境模拟等试验中至关重要,其内部结构精密而复杂,长期使用后可能会产生真空度不足等故障,如何及时准确地诊断分子泵的运行状态格外关键。文章提出了一种基于模态分析的降噪技术,并采用神经网络对采集到的信号数据进行故障诊断与识别。实验结果表明,该方法的平均诊断准确率达到了90.0%,有效地实现了分子泵的故障检测和状态评估。

基于多特征融合的脉冲功率电源软故障诊断方法研究

脉冲功率电源作为电热发射、电磁发射等技术的核心器件,其稳定性对整个发射系统的性能起着决定性作用。针对脉冲功率电源软故障,提出一种融合多特征的BP神经网络故障诊断方法。通过建立脉冲功率电源仿真模型,获取放电电流故障数据样本;对故障样本进行时域分析和小波分析,提取时域参数及特定频带能量,以此构建融合了多种特征的特征向量;利用遗传算法对BP神经网络的初始权重和阈值进行优化,实现对脉冲功率电源故障模式的准确识别。实验结果与其他故障诊断方法进行对比,证实了本方法的有效性。

三维荧光光谱融合小波包分解融合Fisher判别分析及支持向量机识别紫苏

为实现紫苏品种的快速鉴别,避免以次充好,选取4个品种的紫苏采集三维荧光数据,提出了一种基于小波包分解融合Fisher判别分析(Fisher discriminant analysis,FDA)的荧光数据特征选择策略,并实施了4种紫苏的有效鉴别。首先,对三维荧光数据进行预处理,采用Delaunay三角形内插值法去除瑞利散射和拉曼散射,以消除它们的不利影响;运用Savitzky-Golar卷积平滑对数据进行平滑处理,以减少噪声的干扰。同时,对三维荧光数据进行初步筛选,去除了荧光强度小于0.01的发射波长。然后,对各激发波长对应的发射光谱进行3层sym4小波包分解,计算得到最低频段的小波包能量值,作为各激发波长光谱数据表征量。接着,再利用FDA对小波包能量进行判别分析,将其所包含的差异性信息进行融合,得到FDA生成的新变量,并选取累计判别能力达到99%的前3个FD变量作为不同品种差异性信息的表征变量,提出三维荧光数据的表征策略。最后,利用BP神经网络(backpropagation neural network,BPNN)和支持向量机(support vector machine,SVM)两种模式识别算法对表征变量进行分析,得到FDA+BPNN和FDA+SVM两种鉴别结果。FDA+BPNN的训练集正确率为97.5%,测试集正确率为95%;FDA+SVM的训练集和测试集的正确率均达到98.33%。结果表明,三维荧光光谱技术结合小波包分解、FDA和SVM算法基本上能够实现紫苏品种的鉴别。这为后续有关紫苏的进一步检测研究(如某些有效成分的定量检测)提供了研究基础。

多域特征融合的脑电信号肢体运动特征提取与动作识别

在脑电信号的肢体运动想象特征分类识别中,融合不同域特征提取时,存在动作识别准确度不高的问题。针对此问题,本文依据多通道采集中肢体运动想象脑电特征的复杂不同域关系,设计了用于识别肢体动作的脑电-对称正定网络运动特征分类模型,有效提取并融合不同域特征,实现了基于脑电信号的肢体特征分类以及动作的有效识别。实验结果表明,在识别四类肢体是否运动的运动想象数据集BCI Competition IV 2a上,基于所构建的分类模型在动作识别时的准确率达到0.85,Kappa系数达到0.80,具有较高精度。

基于卷积神经网络的新奇检测技术在结构损伤识别中的应用

针对新奇检测难以同时识别结构损伤时刻和损伤位置的问题,提出在新奇检测中引入卷积神经网络以实现损伤时刻和损伤位置的一次性确定。首先,采用小波包技术处理结构响应得到小波包能量,并将相邻测点对应频带的能量比作为新奇检测模型的特征向量;然后,以结构健康时的特征向量作为训练数据,建立健康模式下的基于卷积神经网络的新奇检测模型;接着,将结构实时输出的特征向量输入新奇检测模型,所得输出与健康状态的输出进行对比,并将输出和输入的欧氏距离作为新奇指标;最后,根据新奇指标的变化识别结构损伤时刻和损伤位置。数值模拟和实验室试验验证了该方法的有效性。

脑电信号多特征融合与卷积神经网络算法研究

针对脑电信号(electroencephalogram,EEG)运动想象中单一特征无法多维表征信号中的信息导致的分类准确率不高的问题,提出一种基于样本熵和共空间模式特征融合的特征提取算法。算法先对原始脑电信号进行小波包分解,从中选择包含μ和β节律的分量进行重构,然后分别提取重构信号的样本熵和CSP(common spatial pattern,CSP)特征,将两者融合组成新的特征向量,使用所设计的一维卷积神经网络对其进行识别获得分类结果。所提方法在2003年BCI Dataset III中获得了91.66%的分类准确率,在2008年BCI Dataset A中获得了85.29%的平均分类准确率。与近年来文献中提出的多特征融合算法相比,准确率提高了7.96个百分点。