Adaptive S transform for feature extraction in voltage sags

This paper proposes an adaptive S transform (AST) to extract the feature vectors of voltage sags. With the effective window width matches the Fourier spectrum of sag signals, the standard deviation $\sigma$ of Gaussian window may be determined as well. The narrowest and the widest window width of AST are obtained without additional parameters and iterative computing. Then, the optimal frequency resolution and time resolution are got respectively. Compared with ST, AST provides better time–frequency resolution to extract more precise feature vectors of eight types of voltage sags. Based on the time–frequencyrepresentation of AST, five disturbance features are extracted to construct the feature vector in this paper. In addition, four machine learning classifiers and two fuzzy clustering classifiers are used to analyze the validity and redundancy of these features. Through analyzing the classification accuracies and time costs of these classifiers with different training sets and different level of noise, it can be concluded that the machine learning classifiers perform better in classification accuracy and stability than fuzzy clustering classifiers.     

Analog fault diagnosis using S-transform preprocessor and a QNN classifier

A novel method for fault diagnosis in analog circuits using S-transform (ST) as a preprocessor and a quantum neural network (QNN) as a classifier is proposed in this paper. The ST provides a frequency-dependent resolution and the features obtained from ST are distinct, and easy to understand. The QNN identifier, a computational tool for fuzzy classification combining the advantages of neural modeling and fuzzy-theoretic principles, has the ability to autonomously detect the presence of uncertainty, adaptively learn the existing uncertainty, properly approximate any membership profile, and autonomously quantify uncertainty in sample data. The comparison between the ST-based method and the wavelet-transform-based method, and comparison between the QNN method and the traditional NN method for analog fault diagnosis is provided. Simulation results show that the proposed method is effective in enhancing the efficiency of the training phase and the performance of the fault diagnostic system. The results clearly indicate more than 97.61% correct classification of fault classes in the example circuits of various sizes in the presence of similar faults.     

Detection,Classification, and Estimation of Fault Location on an Overhead Transmission Line Using S-transform and Neural Network

This article demonstrates a technique for diagnosis of fault type and faulty phase on overhead transmission lines. A method for computation of fault location is also incorporated in this work. The proposed method is based on the multi-resolution S-transform, which is used for generating complex S-matrices of the current signals measured at the sending and receiving ends of the line. The peak magnitude of the absolute value of every S-matrix is noted. The phase angle corresponding to every peak component is obtained from the argument of the relevant S-matrix. These features are used as input vectors of a probabilistic neural network for fault detection and classification. Detection of faulty phase(s) is followed by estimation of fault location. The voltage signal of the affected phase is processed to generate the S-matrix. The frequency components of the S-matrices for different fault locations are used as input vectors for training a back-propagation neural network. The results are obtained with satisfactory accuracy and speed. All the simulations have been done in MATLAB (The MathWorks, Natick, Massachusetts, USA) environment for different values of fault locations, fault resistances, and fault inception angles. The effect of noise on both the current and voltage signals has been investigated.     

基于谱分解的气藏识别技术与应用

 地震波传播穿过含油气砂岩时,高频能量发生明显衰减,研究地震波的这种衰减特征可以为油气检测提供有效信息。本文利用三类含气砂岩模型,针对完全弹性介质和盖层为弹性介质、储层为衰减介质两种情形,利用基于波动理论的反射率法分别正演模拟其相应的叠前地震记录,并利用广义S变换对模拟记录进行分频处理,分析不同频率时AVO特征。研究表明,弹性介质条件下AVO响应曲线不受频率影响;盖层为弹性介质、储层为衰减介质时不同频率的AVO响应曲线不同,随频率增加地震波衰减增大。据此对S油田实际资料进行分析,结果表明含气层表现出异常高衰减特性,利用谱分解技术可以有效预测气层的分布。     

基于S变换和IWOA-SVM的复合电能质量扰动识别

针对目前复合电能质量扰动（PQD）信号特征冗余,分类识别准确率低的问题,提出了一种基于S变换和改进鲸鱼算法支持向量机（IWOA-SVM）的复合电能质量扰动识别方法。首先,利用S变换对7种单一电能质量扰动和生成的13种复合扰动信号进行时频分析,使复杂扰动信号的特征得以凸显。设计特征提取方法,从实频矩阵中尽可能地获取便于分类的信号特征信息;其次,引入自适应权重因子和随机差分变异策略对WOA进行优化,提升其搜索能力;最后建立IWOA-SVM分类预测模型,优化SVM高斯核函数参数,以获得更好的鲁棒性和泛化能力,对提取的特征样本进行自动分类和识别。实验结果表明,所提方法分类识别准确率高,能有效识别多种复合PQD信号,有助于评估与治理电能质量问题。     

基于S变换的结构损伤信号处理

针对结构损伤信号的非平稳特性,推导了离散S变换及其基本实现算法,并验证其在信号处理中的有效性,探讨了S变换与傅里叶变换的数值关系;基于S变换分析了一单跨两层钢结构试验模型的节点损伤信号的时频特性,提取各损伤信号的每时能量最大值作为特性指标,对不同节点损伤程度的信号进行了对比。结果表明：当节点损伤程度加剧时,结构损伤信号的能量最大值的极值先减小后增大;当节点损伤程度超过50％时,损伤信号的能量最大值的极值高于节点健康状态的极值。     

基于改进S变换和ICA的相关源分离方法

含有同频成分的机械振源信号不满足统计独立条件,无法直接采用传统盲源分离方法进行分离与识别,为解决该问题,提出了一种基于改进S变换(modified S-transform,简称MST)和独立成分分析(independent component analysis,简称ICA)的相关源分离方法。首先,通过改进S变换对观测信号进行时频化处理,利用相关成分在时频域中实部和虚部的向量夹角,识别并剔除混合信号中的相关项,保证新的观测信号满足独立性条件;其次,以负熵为独立性测度,基于快速固定点独立成分分析进行分离矩阵估计;最后,将该矩阵用于最初的观测信号,从而分离出振源信号,定量计算各个振源的贡献比。通过仿真和实例分析验证了该方法在相关性振源分离中的有效性。     

广义S 变换在地震信号特征信息提取中的应用

基于S 变换具有良好的时频聚焦性,将可灵活选取窗函数的广义S 变换引入到地震信号特征信息提取中,系统研究广义S 变换在地震信号局部刻画和总体描述中的应用。通过理论模型和实际资料的试算表明,广义S 变换在特征信息提取方面是行之有效的,具有较强的抗干扰能力。同时可根据目标体的研究需要,合理选择瞬时频率振幅谱剖面、某频率段地震剖面和单频剖面来识别地震剖面中特征信息,为进一步地震资料处理和解释提供可靠依据。     

A telemedicine tool to detect pulmonary pathology using computerized pulmonary acoustic signal analysis

BackgroundDetection and monitoring of respiratory related illness is an important aspect in pulmonary medicine. Acoustic signals extracted from the human body are considered in detection of respiratory pathology accurately.ObjectivesThe aim of this study is to develop a prototype telemedicine tool to detect respiratory pathology using computerized respiratory sound analysis.MethodsAround 120 subjects (40 normal, 40 continuous lung sounds (20 wheeze and 20 rhonchi)) and 40 discontinuous lung sounds (20 fine crackles and 20 coarse crackles) were included in this study. The respiratory sounds were segmented into respiratory cycles using fuzzy inference system and then S-transform was applied to these respiratory cycles. From the S-transform matrix, statistical features were extracted. The extracted features were statistically significant with p < 0.05. To classify the respiratory pathology KNN, SVM and ELM classifiers were implemented using the statistical features obtained from of the data.ResultsThe validation showed that the classification rate for training for ELM classifier with RBF kernel was high compared to the SVM and KNN classifiers. The time taken for training the classifier was also less in ELM compared to SVM and KNN classifiers. The overall mean classification rate for ELM classifier was 98.52%.ConclusionThe telemedicine software tool was developed using the ELM classifier. The telemedicine tool has performed extraordinary well in detecting the respiratory pathology and it is well validated.     

S-Transform and its contribution to wind turbine condition monitoring

Condition monitoring (CM) has long been recognised as one of the best methods of reducing the operation and maintenance (O&M) costs of wind turbines (WTs). However, its potential in the wind industry has not been fully exploited. One of the major reasons is due to the lack of an efficient tool to properly process the WT CM signals, which are usually non-stationary in both time and frequency domains owing to the constantly varying operational and loading conditions experienced by WTs. For this reason, S-transform and its potential contribution to WT CM are researched in this paper. Following the discussion of the superiorities of S-transform to the Short-Time Fourier Transform (STFT) and Wavelet Transform, two S-transform based CM techniques are developed, dedicated for use on WTs. One is for tracking the energy variations of those fault-related characteristic frequencies under varying operational conditions (the energy rise of these frequencies usually indicates the presence of a fault); another is for assessing the health condition of WT gears and bearings, which have shown significant reliability issues in both onshore and offshore wind projects. In the paper, both proposed techniques have been verified experimentally, showing that they are valid for detecting both the mechanical and electrical faults occurring in the WT despite its varying operational and loading conditions.