基于多源数据融合的掘进机截割岩壁硬度识别方法

针对煤矿井下掘进机截割岩壁硬度识别难度大的问题,利用其悬臂振动信号、升降油缸和回转油缸压力信号、截割电机电流信号,提出了一种基于多源数据融合的截割岩壁硬度识别方法。该方法首先对各类信号进行小波包分解,单支重构各频带信号并组建时频矩阵,通过奇异值分解得到包含时频信息的若干特征奇异值,以构造特征向量;再利用LDA算法实现数据特征级融合,得到类可分性更好的低维特征。为解决概率神经网络(PNN)平滑参数无法确定和网络结构复杂的问题,提出了基于差分进化算法(DE)和QR分解的PNN优化方法,并通过优化PNN对低维特征进行硬度识别。实验结果表明:所提出的特征量提取和模式识别方法是有效的,与目前常用的其它模式识别算法相比,优化PNN在掘进机三种工况下均有更高的硬度识别准确率。     

用概率社会网络进行结构损伤位置识别

在不计测量误差情况下,神经网络能够成功地识别损伤位置及其程度,但在测量噪声影响下,神经网络的损伤识别效果则比较差,考虑到基于多变量模式分类的概率神经网络具有处理受噪声污染的测试数据的能力,本文将可能的损伤位置作为模式类,利用概率神经网络的分类能力来识别结构的损,地对两个算例,一个六层框架和一个两层框架进行数值模拟分析,并将概率神经网络与BP网络进行了比较,结果表明,概率神经网络具有更好的识别效果,是一种很有潜力的结构损伤位置识别方法。     

High impedance fault detection in power distribution networks using time?frequency transform and probabilistic neural network

An intelligent approach for high impedance fault (HIF) detection in power distribution feeders using advanced signal-processing techniques such as time-time and time-frequency transforms combined with neural network is presented. As the detection of HIFs is generally difficult by the conventional over-current relays, both time and frequency information are required to be extracted to detect and classify HIF from no fault (NF). In the proposed approach, S- and TT-transforms are used to extract time-frequency and time-time distributions of the HIF and NF signals, respectively. The features extracted using S- and TT-transforms are used to train and test the probabilistic neural network (PNN) for an accurate classification of HIF from NF. A qualitative comparison is made between the HIF classification results obtained from feed forward neural network and PNN with same features as inputs. As the combined signal-processing techniques and PNN take one cycle for HIF identification from the fault inception, the proposed approach was found to be the most suitable for HIF classification in power distribution networks with wide variations in operating conditions.     

滚动轴承的MSE和PNN故障诊断方法

针对滚动轴承不同运行状态振动信号具有不同复杂性的特点,提出一种新的基于多尺度熵(multiscale entropy, MSE)和概率神经网络(probabilistic neural networks, PNN)的滚动轴承故障诊断方法。该方法首先利用MSE方法对滚动轴承振动信号进行特征提取,并将其作为PNN神经网络的输入,再利用PNN自动识别轴承故障类型及故障程度。实验数据包括不同故障类型和不同故障程度样本,结果表明,相比于小波包分解和PNN结合的诊断方法,提出的方法具有更高的诊断精度,能有效实现滚动轴承故障类型及程度的诊断。     

Improved probabilistic neural network algorithm for chemical sensor array pattern recognition

An improved probabilistic neural network (IPNN) algorithm for use in chemical sensor array pattern recognition applications is described. The IPNN is based on a modified probabilistic neural network (PNN) with three innovations designed to reduce the computational and memory requirements, to speed training, and to decrease the false alarm rate. The utility of this new approach is illustrated with the use of four data sets extracted from simulated and laboratory-collected surface acoustic wave sensor array data. A competitive learning strategy, based on a learning vector quantization neural network, is shown to reduce the storage and computation requirements. The IPNN hidden layer requires only a fraction of the storage space of a conventional PNN. A simple distance-based calculation is reported to approximate the optimal kernel width of a PNN. This calculation is found to decrease the training time and requires no user input. A general procedure for selecting the optimal rejection threshold for a PNN-based algorithm using Monte Carlo simulations is also demonstrated. This outlier rejection strategy is implemented for an IPNN classifier and found to reject ambiguous patterns, thereby decreasing the potential for false alarms.     

Radial basis probabilistic neural network for differential protection of power transformer

Protection of medium- and large-power transformers has always remained an area of interest of relaying engineers. Conventionally, the protection is done making use of magnitude of various frequency components in differential current. A novel technique to distinguish between magnetising inrush and internal fault condition of a power transformer based on the difference in the current wave shape is developed. The proposed differential algorithm makes use of radial basis probabilistic neural network (RBPNN) instead of the conventional harmonic restraint- based differential relaying technique. A comparison of performance between RBPNN and heteroscedastic-type probabilistic neural network (PNN) is made. The optimal smoothing factor of heteroscedastic-type PNN is obtained by particle swarm optimisation technique. The results demonstrate the capability of RBPNN in terms of accuracy with respect to classification of differential current of the power transformer. For the verification of the developed algorithm, relaying signals for various operating conditions of the transformer, including internal faults and external faults, were obtained through PSCAD/EMTDC. The proposed algorithm has been implemented in MATLAB.     

Performance analysis of neural networks for classification of medical images with wavelets as a feature extractor

In this article, we analyze the performance of artificial neural network, in classification of medical images using wavelets as feature extractor. This work classifies the mammographic image, MRI images, CT images, and ultrasound images as either normal or abnormal. We have tested the proposed approach using 50 mammogram images (13 normal and 37 abnormal), 24 MRI brain images (9 normal and 15 abnormal), 33 CT images (11 normal and 22 abnormal), and 20 ultrasound images (6 normal and 14 abnormal). Four kind of neural network models such as BPN (Back Propagation Network), Hopfield, RBF (Radial Basis Function), and PNN (Probabilistic neural network) were chosen for study. To improve diagnostic accuracy, the feature extracted using wavelets such as Harr, Daubechies (db2, db4, and db8), Biorthogonal and Coiflet wavelets are given as input to the neural network models. Good classification percentage of 96% was achieved using the RBF when Daubechies (db4) wavelet based feature extraction was used. We observed that the classification rate is almost high under the RBF neural network for all the dataset considered. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 33–40, 2015     

Probabilistic neural-network-based protection of power transformer

An optimal probabilistic neural network (PNN) as a core classifier for fault detection and status indication of a power transformer has been presented. In this scheme, various operating conditions of a transformer are distinguished using signatures of the differential currents. The proposed differential protection scheme is implemented through two different structures of PNN, that is, one having one output and the other having five outputs. The developed algorithm is found to be stable against external fault, magnetising inrush, sympathetic inrush and over-excitation conditions for which relay operation is not required. For the test data of fault, it is found to operate successfully. The performance of proposed PNN and classical artificial neural network (ANN) has been compared. For evaluation of the developed algorithm, relaying signals for various operating conditions of a transformer are obtained by modelling the transformer in PSCAD/EMTDC. The algorithms are implemented using MATLAB. The results show the capability of PNN in terms of classification accuracy and speed in comparison to classical ANNs.     

基于自适应小波特征提取一体化神经网络的空调电机振动噪声识别

正确识别空凋电机的噪声类型是改善其噪声效果的重要前提，采用一种集特征提取与识别于一体的神经网络来解决这种识别问题。此网络利用Mexican hat小波作为母小波，同时将基于小波变换的特征提取过程融人为神经网络的一部分，网络学习时可针对输入信号对小波尺度和平移参数进行自适应调整，以实现对信号特征信息的充分获取。给出了此网络的学习算法。利用这一网络对空调电机的三种噪声信号即电磁噪声、不平衡噪声、轴承噪声信号进行了学习和识别，结果表明，学习后的网络以很高的可靠性准确地识别出了电机的不同噪声类型。     

Performance comparison of texture feature analysis methods using PNN classifier for segmentation and classification of brain CT images

A computer software system is designed for the segmentation and classification of benign and malignant tumor slices in brain computed tomography images. In this paper, we present a texture analysis methods to find and select the texture features of the tumor region of each slice to be segmented by support vector machine (SVM). The images considered for this study belongs to 208 benign and malignant tumor slices. The features are extracted and selected using Student's t‐test. The reduced optimal features are used to model and train the probabilistic neural network (PNN) classifier and the classification accuracy is evaluated using k fold cross validation method. The segmentation results are also compared with the experienced radiologist ground truth. Quantitative analysis between ground truth and segmented tumor is presented in terms of quantitative measure of segmentation accuracy and the overlap similarity measure of Jaccard index. The proposed system provides some newly found texture features have important contribution in segmenting and classifying benign and malignant tumor slices efficiently and accurately. The experimental results show that the proposed hybrid texture feature analysis method using Probabilistic Neural Network (PNN) based classifier is able to achieve high segmentation and classification accuracy effectiveness as measured by Jaccard index, sensitivity, and specificity.     

基于改进小波阈值去噪的深度学习水下目标分类

由于海洋环境噪声复杂,噪声等级高,水下待识别目标信噪比低,从而造成了特征提取困难,目标识别率低的问题。基于此,文章提出了基于改进小波阈值的深度学习水下目标分类方法。此方法在传统小波阈值去噪的基础上提出了一种新的小波阈值函数,对于所采用的具体阈值将其与分解尺度相联系,从而实现降低背景噪声,提升水下目标分类识别率的目的。此方法对实测舰船辐射噪声信号进行小波分解,提取每一层的高频小波系数并对其进行处理;对处理完的信号再提取时频特征,最后将其输入后续的深度学习网络中。实验结果发现：在利用原有数据集情况下,利用基于改进小波阈值的深度学习进行水下目标的分类识别,采用卷积神经网络算法可达到88.56%的分类识别率。对前述实验结果进一步分析后,采用生成对抗网络的方法扩充数据样本,可达到96.673%的分类识别率。     

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...     

基于深度学习的舰船辐射噪声多特征融合分类

为了改善分类系统的性能,进一步提高舰船辐射噪声分类的正确率,该文提出了一种基于深度神经网络的多特征融合分类方法。该方法首先提取舰船辐射噪声几种不同的特征,将提取的特征同时用于训练具有多个输入分支的深度神经网络,使网络直接在多种特征参数上进行联合学习,通过神经网络的输入分支和连接层实现特征融合,再对舰船辐射噪声进行分类。为了特征深度学习提取了舰船辐射噪声的频谱特征、梅尔倒谱系数和功率谱特征,并将多特征融合分类方法与在一种特征上进行深度学习分类方法的正确率进行对比。实验结果表明,基于深度学习的多特征融合分类方法可以有效地提高舰船辐射噪声分类的正确率,是一种可行的分类方法。     

Einfluss der Netztopologie der künstlich neuronalen Netze auf das Ergebnis der Abschätzung zyklischer Kennwerte

Several estimation methods have been developed to estimate the cyclic material parameters out of the static material properties. Most of these methods are based on empirical equations. Increasing numbers of input‐ and influencing parameters lead to an rising effort for determining these equations and the accuracy decreases. For this reason new suitable methods are sought to estimate the cyclic material behaviour. A very promising approach is the application of the artificial neural networks, which can derive self‐depended a relationship between in‐ and output parameters. Static parameters such as yield strength, tensile strength …? etc., which can rapidly be determined used as input parameters. The output parameters are the cyclic material parameters of the strain‐life curve and stress‐strain curve according to the Manson‐Coffin‐Basquin‐ and Ramberg‐Osgood curve. Many different artificial neural networks with different structures and complexity can be applied. In this paper the influence of the topology of an artificial neural network on the estimation accuracy will be investigated. Based on the results of a reference artificial neural network it will be shown, that more complex topologies in the network do not lead inevitably to better estimations.     

Frequency invariant classification of ultrasonic weld inspection signals

Automated signal classification systems are finding increasing use in many applications for the analysis and interpretation of large volumes of signals. Such systems show consistency of response and help reduce the effect of variabilities associated with human interpretation. This paper deals with the analysis of ultrasonic NDE signals obtained during weld inspection of piping in boiling water reactors. The overall approach consists of three major steps, namely, frequency invariance, multiresolution analysis, and neural network classification. The data are first preprocessed whereby signals obtained using different transducer center frequencies are transformed to an equivalent reference frequency signal. Discriminatory features are then extracted using a multiresolution analysis technique, namely, the discrete wavelet transform (DWT). The compact feature vector obtained using wavelet analysis is classified using a multilayer perceptron neural network. Two different databases containing weld inspection signals have been used to test the performance of the neural network. Initial results obtained using this approach demonstrate the effectiveness of the frequency invariance processing technique and the DWT analysis method employed for feature extraction.     

基于 EEMD样本熵与小波神经网络的汽车关门声品质预测

针对传统客观心理学参量在非稳态噪声品质预测中的不足,以汽车关门声为对象,提出一种基于EEMD分解的样本熵表征关门声的信号特征,并结合小波神经网络进行声品质预测。对声样本进行EEMD分解得到IMF分量,计算各IMF分量的样本熵,并构造成特征向量。分别以此特征向量和声品质主观评分值作为输入输出构建小波神经网络预测模型。作为对比,构建了基于该特征向量的BP网络预测模型、基于心理学参量的小波神经网络预测模型和BP网络预测模型。分析结果表明,在关门声品质预测中,EEMD样本熵比客观心理学参数能更好的反映信号的时变非稳态特性,预测效果更好;且小波神经网络较BP网络的预测精度更高,模型训练速度更快。     

ECG Classification Using Deep CNN Improved by Wavelet Transform

Atrial fibrillation is the most common persistent form of arrhythmia. A method based on wavelet transform combined with deep convolutional neural network is applied for automatic classification of electrocardiograms. Since the ECG signal is easily inferred, the ECG signal is decomposed into 9 kinds of subsignals with different frequency scales by wavelet function, and then wavelet reconstruction is carried out after segmented filtering to eliminate the influence of noise. A 24-layer convolution neural network is used to extract the hierarchical features by convolution kernels of different sizes, and finally the softmax classifier is used to classify them. This paper applies this method of the ECG data set provided by the 2017 PhysioNet/CINC challenge. After cross validation, this method can obtain 87.1% accuracy and the F1 score is 86.46%. Compared with the existing classification method, our proposed algorithm has higher accuracy and generalization ability for ECG signal data classification.     

海洋平台油气管道疲劳裂纹AE信号特征提取及识别研究

为了将声发射(AE)技术实际应用到监测海洋平台油气管道疲劳裂纹中,需要解决管道振动干扰以及疲劳裂纹AE信号有效特征提取的问题,而问题的关键在于对管道结构疲劳裂纹AE信号特征提取及识别算法的研究。在已有研究的基础上,提出了一种基于经验模态分解(EMD)为特征提取的疲劳裂纹识别方法,将管道振动干扰问题和疲劳裂纹AE信号有效特征提取问题联系在一起,对特征元素进行优化并剔除无效噪声干扰信息,通过概率神经网络(PNN)对疲劳裂纹信号进行识别。试验结果表明,PNN结合基于EMD为特征提取的疲劳裂纹识别法能够取得良好的效果,为声发射技术监测海洋平台油气管道疲劳裂纹提供了试验和理论依据。     

Probabilistic analysis of concrete cracking using neural networks and random fields

In this paper an algorithm for the probabilistic analysis of concrete structures is proposed which considers material uncertainties and failure due to cracking. The fluctuations of the material parameters are modeled by means of random fields and the cracking process is represented by a discrete approach using a coupled meshless and finite element discretization. In order to analyze the complex behavior of these nonlinear systems with low numerical costs a neural network approximation of the performance functions is realized. As neural network input parameters the important random variables of the random field in the uncorrelated Gaussian space are used and the output values are the interesting response quantities such as deformation and load capacities. The neural network approximation is based on a stochastic training which uses wide spanned Latin hypercube sampling to generate the training samples. This ensures a high quality approximation over the whole domain investigated, even in regions with very small probability.     

基于小波包分解和PCA-Attention-LSTM的舰船辐射噪声识别技术

为了改进舰船辐射噪声分类系统的性能,进一步提高识别准确率,文章提出了一种基于多特征的小波包分解在长短期记忆(LongShort-TermMemory,LSTM)网络中分类的方法。该方法首先通过小波包分解技术,分频段提取舰船辐射噪声的多种特征,将提取的特征利用主成分分析法(Principal Component Analysis, PCA)进行数据降维,通过添加注意力机制(Attention Mechanism)算法的LSTM网络,对辐射噪声结果分类,提高了学习效率和识别准确率。为了更精细地提取特征,分频段提取了舰船辐射噪声的时频域特征、小波变换特征和梅尔倒谱系数等特征,并将分频段与不分频段的特征、多特征与单一特征、不同信噪比间的算法性能进行对比。实验结果表明,基于小波包分解和PCA-Attention-LSTM的模型可以有效地提高舰船辐射噪声分类的性能,是一种可行的分类方法。