Research on runoff variations based on wavelet analysis and wavelet neural network model： A case study of the Heihe River drainage basin （1944-2005）

The Heihe River drainage basin is one of the endangered ecological regions of China. The shortage of water resources is the bottleneck, which constrains the sustainable development of the region. Many scholars in China have done researches concerning this problem. Based on previous researches, this paper analyzed characteristics, tendencies, and causes of annual runoff variations in the Yingluo Gorge （1944-2005） and the Zhengyi Gorge （1954-2005）, which are the boundaries of the upper reaches, the middle reaches, and the lower reaches of the Heihe River drainage basin, by wavelet analysis, wavelet neural network model, and GIS spatial analysis. The results show that： （1） annual runoff variations of the Yingluo Gorge have principal periods of 7 years and 25 years, and its increasing rate is 1.04 m^3/s.10y; （2） annual runoff variations of the Zhengyi Gorge have principal periods of 6 years and 27 years, and its decreasing rate is 2.25 m^3/s.10y; （3） prediction results show that： during 2006-2015, annual runoff variations of the Yingluo and Zhengyi gorges have ascending tendencies, and the increasing rates are respectively 2.04 m^3/s.10y and 1.61 m^3/s.10y; （4） the increase of annual runoff in the Yingluo Gorge has causal relationship with increased temperature and precipitation in the upper reaches, and the decrease of annual runoff in the Zhengyi Gorge in the past decades was mainly caused by the increased human consumption of water resources in the middle researches. The study results will provide scientific basis for making rational use and allocation schemes of water resources in the Heihe River drainage basin.

Tide Forecasting of Tides Around Taiwan by Artificial Neural Network Method and Wavelet Analysis

In maltiresolution analysis （MRA） by wavelet function Daubechies （db）, we decompose the signal to two parts, the low and high frequency content. The high-frequency content of the data is removed first and a new ＂de-noise＂ signal is reconstructed by using inverse wavelet transform. The wavelet spectrum and harmonic analysis were used to analyze the characteristics of tidal data before constructing the input and output structure of ANN model. That is, the concept of tidal constituent phase-lags was introduced and the new ＂de-noise＂ signal was used as the input data set of ANN and the forecasting accuracy of ANN model is significantly improved.

Artificial Neural Networks Applied to Gas Mixture Analysis

An array composed of sixteen gas sensors was constructed to analyze gas mixtures quantitatively. The data of responses from the sensor array to ethane, propane and propylene were treated by three-layer ANN with BP algorithms and PLS. The analytical results indicated that the concentration predicted with ANN is better than that with PLS. The average prediction errors for ethane, propane and propylene were 5.11%, 8.28%, 2.64%, respectively.

Dynamic prediction of gas emission based on wavelet neural network toolbox

This paper presents a method for dynamically predicting gas emission quantity based on the wavelet neural network （WNN） toolbox. Such a method is able to predict the gas emission quantity in adjacent subsequent time intervals through training the WNN with even time-interval samples. The method builds successive new model with the width of sliding window remaining invariable so as to obtain a dynamic prediction method for gas emission quantity. Furthermore, the method performs prediction by a self-developed WNN toolbox. Experiments indicate that such a model can overcome the deficiencies of the traditional static prediction model and can fully make use of the feature extraction capability of wavelet base function to reflect the geological feature of gas emission quantity dynamically. The method is characterized by simplicity, flexibility, small data scale, fast convergence rate and high prediction precision. In addition, the method is also characterized by certainty and repeatability of the predicted results. The effectiveness of this method is confirmed by simulation results. Therefore, this method will exert practical significance on promoting the application of WNN.

Wavelet neural network based fault diagnosis in nonlinear analog circuits

The theories of diagnosing nonlinear analog circuits by means of the transient response testing are studled. Wavelet analysis is made to extract the transient response signature of nonlinear circuits and compress the signature dada. The best wavelet function is selected based on the between-category total scatter of signature. The fault dictionary of nonlinear circuits is constructed based on improved back-propagation（BP） neural network. Experimental results demonstrate that the method proposed has high diagnostic sensitivity and fast fault identification and deducibility.

Wet Gas Meter Development Based on Slotted Orifice Couple and Neural Network Techniques

A slotted orifice has many superiorities over a standard orifice. For single-phase flow measurement, its flow coefficient is insensitive to the upstream velocity profile. For two phase flow measurement, various characteristics of its differential pressure （DP） are stable and closely correlated with the mass flow rate of gas and liquid. The complex relationships between the signal features and the two-phase flow rate are established through the use of a back propagation （BP） neural network. Experiments were carried out in the horizontal tubes with 50ram inner diameter, ooerated with water flow rate in the range of 0.2m^3·h^-1 to 4m3·h^-1, gas flow rate in the range of 100m^3·h^-1 to 1000m^3·h^-1, and pressure at 400kPa and 850kPa respectively, where the temperature is ambient temperature. This article includes the principle of wet gas meter development, the experimental matrix, the signal processing techniques and the achieved results. On the basis of the results it is suggested that the slotted orifice couple with a trained neural network may provide a simple but efficient solution to the wet gas meter development.

Underwater Acoustic Signal Noise Reduction Based on a Fully Convolutional Encoder-Decoder Neural Network

Noise reduction analysis of signals is essential for modern underwater acoustic detection systems.The traditional noise reduction techniques gradually lose efficacy because the target signal is masked by biological and natural noise in the marine environ-ment.The feature extraction method combining time-frequency spectrograms and deep learning can effectively achieve the separation of noise and target signals.A fully convolutional encoder-decoder neural network(FCEDN)is proposed to address the issue of noise reduc-tion in underwater acoustic signals.The time-domain waveform map of underwater acoustic signals is converted into a wavelet low-frequency analysis recording spectrogram during the denoising process to preserve as many underwater acoustic signal characteristics as possible.The FCEDN is built to learn the spectrogram mapping between noise and target signals that can be learned at each time level.The transposed convolution transforms are introduced,which can transform the spectrogram features of the signals into listenable audio files.After evaluating the systems on the ShipsEar Dataset,the proposed method can increase SNR and SI-SNR by 10.02 and 9.5dB,re-spectively.

Discrete Wavelet Transmission and Modified PSO with ACO Based Feed Forward Neural Network Model for Brain Tumour Detection

In recent years,the development in the field of computer-aided diagnosis(CAD)has increased rapidly.Many traditional machine learning algorithms have been proposed for identifying the pathological brain using magnetic resonance images.The existing algorithms have drawbacks with respect to their accuracy,efficiency,and limited learning processes.To address these issues,we propose a pathological brain tumour detection method that utilizes the Weiner filter to improve the image contrast,2D-discrete wavelet transformation(2D-DWT)to extract the features,probabilistic principal component analysis(PPCA)and linear discriminant analysis(LDA)to normalize and reduce the features,and a feed-forward neural network(FNN)and modified particle swarm optimization(MPSO)with ant colony optimization(ACO)to improve the accuracy,stability,and overcome fitting issues in the classification of brain magnetic resonance images.The proposed method achieves better results than other existing algorithms.

A Study on Integrated Wavelet Neural Networks in Fault Diagnosis Based on Information Fusion

The tight wavelet neural network was constituted by taking the nonlinear Morlet wavelet radices as the excitation function. The idiographic algorithm was presented. It combined the advantages of wavelet analysis and neural networks. The integrated wavelet neural network fault diagnosis system was set up based on both the information fusion technology and actual fault diagnosis, which took the sub-wavelet neural network as primary diagnosis from different sides, then came to the conclusions through decision-making fusion. The realizable policy of the diagnosis system and established principle of the sub-wavelet neural networks were given. It can be deduced from the examples that it takes full advantage of diversified characteristic information, and improves the diagnosis rate.

Data Fusion Fault Diagnosis Based on Wavelet Transform and Neural Network

According to the time-frequency localization characteristic of the wavelet transform (WT)and the nonlinear reflection of the neural network,this paper presents the neural network data fusion fault diagnosis method based on wavelet transform.The network construction and the signal processing steps are introduced in detail.The correct result was attained by using this method in rotary machinery fault diagnosis.It proves the method efficient in fault diagnosis, which is expected to have a wide application.

Fabric Defect Detection Technique Based on Two-double Neural Network

This paper introduces the identification of the defects on the fabric by using two-double neural network and wavelet analysis. The purpose is to fit for the automatic cloth inspection system and to avoid the disadvantages of traditional human inspection. Firstly, training the normal fabric to acquire its characteristics and then using the BP neural network to tell the normal fabric apart from the one with defects. Secondly, doing the two-dimeusional discrete wavelet transformation based on the image of the defects, then wiping off the proper characteristics of the fabric, and identifying the defects utilizing the trained BP neural network. It is proved that this method is of high speed and accuracy. It comes up to the requirement of automatic cloth inspection.

蜣螂算法优化概率神经网络的变压器故障诊断

针对仅靠人工经验选取平滑因子的概率神经网络(PNN)变压器故障诊断模型存在诊断正确率偏低的问题,提出1种采用蜣螂算法(DBO)优化PNN平滑因子的变压器故障诊断模型。选取测试函数对DBO算法进行寻优测试,并与粒子群算法(PSO)、人工蜂群算法(ABC)、灰狼优化算法(GWO)对比,DBO在寻优精度、收敛速度和避免局部最优方面更具优势;采用DBO对PNN平滑因子寻优以建立DBO-PNN诊断模型,并与PSO-PNN、ABC-PNN和GWO-PNN模型进行诊断对比,结果表明DBO-PNN模型的诊断效果更好,正确率达96%。

极端气象条件下基于深度学习网络特征的变压器故障预测

根据极端气象条件下变压器产生故障时的环境参数,结合变压器故障预测中常用的油中溶解气体的含量,提出一种基于深度学习网络的故障预测方法。针对已有的变压器故障诊断方法泛化能力弱、时效性低、精度低等缺点,引入极端气象参数,并通过对多组数据序列进行时因分析,提取数据随着时间的变化关系;其次,设计一种新型的神经网络,将油气参数与极端气象参数的时间特征融合,并通过深度学习网络进行故障分类与预测。仿真实验结果表明,相比于其他传统故障预测方法,所提出的极端气象条件下基于深度学习网络的变压器故障预测方法准确率有显著提高。

基于小波变换与神经网络的非侵入式家电负荷监测研究

智能家电智能化程度越来越高,同一电器对应的工作模式也越来越多。目前家电的非侵入式负荷监测仅仅采用传统家电单一负荷曲线进行研究,极大局限了非侵入式负荷监测技术的应用推广。为此,以智能洗衣机不同工作模式为例,研究了同一家电不同模式下的用电负荷特征,采集了智能家电中洗衣机不同工作模式下的用电负荷数据,通过小波变换的方法对负荷曲线进行平滑与特征信息提取,并基于统计学思想对表征特征信息的特征向量进行了评价,建立神经网络模型对不同工作模式的负荷曲线进行了识别,通过MATLAB平台仿真,证明了基于小波分析特征提取及神经网络特征识别的方法在非侵入式智能家电负荷监测中的可行性,识别准确率较高,具有良好的应用推广价值。

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。

基于小波分析的智能轮胎磨损和载荷的检测方法

为了获取轮胎运行状态下的状态信息,提出了一种基于小波变换的智能轮胎磨损和载荷检测方法,用于实时检测轮胎的载荷和磨损状态。为研究轮胎在运行时胎面的震动情况,通过贴装于轮胎内壁中央的三轴加速度传感器获取加速度波形,再通过莫尔斯小波多尺度分析轮胎接地点处的胎面震动情况,提取特征,输入BP神经网络,获取检测结果。结果表明:所提出的算法可以较为精确地监测轮胎的磨损和载荷状态;在90%以上的情况下,可以实现磨损绝对误差在0.3 mm以内,载荷绝对误差在12 kg以内。为车辆提供关键轮胎信息,助力安全驾驶,有广泛的应用前景。

基于遗传优化小波网络的随机载况下裂纹扩展预报

疲劳问题作为工程领域常见的破坏形式受到了广泛关注。基于断裂力学的疲劳分析方法可以获取可无损检测的疲劳损伤-裂纹尺寸,但计算较为复杂。针对海洋工程结构物疲劳分析中的谱分析法,本文通过遗传优化的小波神经网络建立一种同一热点下各随机载况的应力强度因子谱,结合有限元分析获取的应力强度因子进行网络训练。结果表明,该模型可对各随机载况下的SIF谱进行较好的预测。本文所提出的方法可大幅减少重复性有限元计算,为裂纹扩展方法应用于随机载况下工程结构的疲劳寿命预报提供一种思路。最后,结合裂纹扩展单一曲线模型实现随机载况下裂纹扩展量的快速预报。

基于卷积神经网络的肌电信号人体运动模式识别技术

随着外骨骼机器人等肌电控制设备的快速发展,表面肌电信号此类非平稳、非周期信号在高性能运动识别系统中的应用已成为相关研究领域的重点。为实现肌电信号跨域特征融合,提出一种基于肌电信号的双卷积链神经网络模型,采集7块关键肌肉的原始肌电信号,经特征提取,转化为能量核相图和离散小波变换系数特征图,分别输入双卷积链神经网络的卷积神经网络分支和MobileNetV2分支,利用融合模块提取高层隐藏特征并进行充分交互。制备包括以上两种特征图像和传统肌电信号图谱在内的3种数据集。3组交叉实验结果表明:所提方法对6种自测下肢运动的平均识别准确率达94.19%,显著优于其他特征组合与网络架构;在ENABL3S开源数据集识别7种下肢运动中取得98.32%的稳态识别准确率,进一步验证了所提方法优良的肌电特征捕捉能力和模式识别准确性。

小波降噪及改进遗传算法的BP神经网络在基坑变形中的组合应用

以某市人民医院基坑工程为例,针对实测数据建立实测数据结合BP神经网络预测模型,小波降噪结合BP神经网络模型和小波降噪结合改进遗传算法优化的BP神经网络模型,并利用误差分析理论对基坑变形数据预测效果评价。结果表明:对比3种模型实际处理、预测数据能力,实测数据结合BP神经网络模型预测精度在1%-4%之间,小波降噪结合BP神经网络模型预测精度1%-2%之间,小波降噪结合改进遗传算法优化的BP神经网络模型预测精度在1%以内,小波降噪结合改进遗传算法优化的BP神经网络模型的预测准确率最高。针对基坑变形监测,小波降噪结合改进遗传算法优化的BP神经网络模型具有更高预测精度,可为类似工程提供实际参考。

基于ISSA-LSTM的黄鳝池溶氧量多参数预测

为提高溶氧量的多参数预测精度,文中基于改进的麻雀搜索算法(Improved Sparrow Search Algorithm,ISSA)与长短期记忆神经网络(Long and Short-Term Memory Neural Networks,LSTM)建立ISSA-LSTM溶氧量预测模型,并将该模型用于上海市农业科学院黄鳝养殖池溶氧量预测。利用混沌映射、透镜成像反向学习、自适应调节和柯西变异对麻雀搜索算法进行优化,通过小波变换进行数据预处理,并利用主成分分析法确定模型训练的输入参数。训练结果表明,相关系数、均方根误差、均方误差和平均绝对误差分别为0.911、1.392 mg·L^(-1)、1.938 mg·L^(-1)和0.992 mg·L^(-1),均优于对照模型。选择模型输入参数对模型预测结果也会产生影响,使用与溶氧量中等相关和强相关的参数同时作为输入参数的模型预测效果最优。训练结果为溶氧量多参数预测模型的发展提供了新视角。