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.

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.

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.

Town gas daily load forecasting based on machine learning combinatorial algorithms:A case study in North China

Timely and accurate gas load forecasting is critical for optimal scheduling under tight winter gas supply conditions.Under the background of the implementation of“coal-to-gas”for winter heating in rural areas of North China and the sufficient field research,this paper proposes a correction algorithm for daily average temperature based on the cumulative effect of temperature and a set of combined forecasting models for gas load forecasting based on machine learning and introduces its application through a detailed case study.In order to solve the problems of forecasting performance degradation and complexity increase caused by too many influencing factors,a combined forecasting model back-propagation-improved complete ensemble empirical mode decomposition with adaptive-noise-gated recurrent unit based on residual sequence analysis is proposed.Back propagation(BP)neural network is used to analyze the main influencing factors,so that the secondary influencing factors are reflected in the residual sequence generated by the forecasting.After decomposition,reconstruction,and re-forecast,the mean absolute percentage error(MAPE)of the combined models for the daily gas load in the case study has been controlled under 1.9%,which is significantly improved compared with each single algorithm.The forecasting error before and after the temperature correction are also compared.It is found that the MAPE with the temperature correction is reduced by 1.7%,which reflects the effectiveness of the temperature correction to eliminate the impact of temperature cumulative effect and its contribution to the improvement of the forecasting accuracy for the combined forecasting models.

基于小波包分解卷积神经网络的停运输电线路故障识别方法

当输电线路处于热备用状态时,停运线路上仍可能发生短路故障,准确地判断停运线路的故障状态能有效地避免合闸到故障线路时对电力系统造成冲击并对故障的排除提供便利,因此有必要对停运输电线路进行故障识别。对于双回输电线路提出一种采用小波包分解生成的频谱图作为卷积神经网络(convolutional neural network,CNN)输入进行特征提取的停运线路故障识别方法。为减少人为提取特征产生的误差,首先对停运输电线路故障时三相电压暂态波形进行测量,采用小波包分解得到三相电压波形时频特性,最终通过CNN提取特征并进行故障分类。为验证该方法的故障识别效果,以河北省3条线路的实际数据为基础,在ATP-EMTP中建立500 kV同塔双回输电线路模型,为模拟现场各因素产生的误差在测得电压波形中加入10 dB高斯白噪声。结果表明,对热备用线路上故障状态识别准确率为99.98%,在一定程度上为停运线路的故障诊断及排除提供了参考。

基于机器学习的水库溶解氧预测模型比较研究

快速精准预测低氧发生对维持水生生态系统的健康有着重要意义,利用皮尔逊相关性分析和最大信息系数两种方法,依据闽江上游水口水库典型渔业养殖区G1、G2和Z1点位2021年3月至2022年3月的数据,从多个水质、气象和水文参数中筛选出影响溶解氧的关键驱动因子。基于机器学习算法,构建了独立BP、皮尔逊相关性-BP、MIC-BP和MIC-SVR等溶解氧预测模型,对比分析了各模型的预测结果。结果表明:电导率、水温、pH、叶绿素a和水位是影响溶解氧的5个主要因素;经过相关性分析筛选后,构建的预测模型性能得到提升,其中最大信息系数(MIC)法的筛选效率优于皮尔逊相关性法的;MIC-SVR模型是最优的溶解氧预测模型,其R 2均大于0.98,RMSE均小于0.56,MAE均小于0.28,可以将溶解氧的预测误差控制在±0.30 mg/L以内。该研究成果可为湖库低氧预测预警提供借鉴。

基于两维WAVELET分解的纹理图像分割方法

提出了一种纹理图像的分割方法，主要利用ＷＡＶＥＬＥＴ变换的多分辨率分析的特性，通过两维分解抽取图像的纹理特征，并对图像小窗口区域的特征进行聚类，该聚类结果可作为多层ＢＰ（Ｂａｃｋｐｒｏｐａｇａｔｉｏｎ）网权值学习的训练样本，进而利用ＢＰ网对各小窗口的特征进行分类以实现纹理图像的分割，实验证明，该方法对于纹理图像具有较好的分割效果。

Multi-objective optimization of high-sulfur natural gas purif ication plant

There exists large space to save energy of high-sulfur natural gas purification process.The multi-objective optimization problem has been investigated to effectively reduce the total comprehensive energy consumption and further improve the production rate of purified gas.A steady-state simulation model of high-sulfur natural gas purification process has been set up by using ProMax.Seven key operating parameters of the purification process have been determined based on the analysis of comprehensive energy consumption distribution.To solve the problem that the process model does not converge in some conditions,back-propagation(BP)neural network has been applied to substitute the simulation model to predict the relative parameters in the optimization model.The uniform design method and the table U21(107)have been applied to design the experiment points for training and testing BP model.High prediction accuracy can be achieved by using the BP model.Nondominated sorting genetic algorithm-II has been developed to optimize the two objectives,and 100 Pareto optimal solutions have been obtained.Three optimal points have been selected and evaluated further.The results demonstrate that the total comprehensive energy consumption is reduced by 13.4%and the production rate of purified gas is improved by 0.2%under the optimized operating conditions.

Power Transformer Fault Diagnosis Using Fuzzy Reasoning Spiking Neural P Systems

This paper presents an intelligent technique to fault diagnosis of power transformers dissolved and free gas analysis (DGA). Fuzzy Reasoning Spiking neural P systems (FRSN P systems) as a membrane computing with distributed parallel computing model is powerful and suitable graphical approach model in fuzzy diagnosis knowledge. In a sense this feature is required for establishing the power transformers faults identifications and capturing knowledge implicitly during the learning stage, using linguistic variables, membership functions with “low”, “medium”, and “high” descriptions for each gas signature, and inference rule base. Membership functions are used to translate judgments into numerical expression by fuzzy numbers. The performance method is analyzed in terms for four gas ratio (IEC 60599) signature as input data of FRSN P systems. Test case results evaluate that the proposals method for power transformer fault diagnosis can significantly improve the diagnosis accuracy power transformer.

基于小波分析和BP神经网络的农业机械化作业水平预测

为提高我国农业机械化作业水平的预测精度,针对农业机械化作业水平非线性和非平稳性的特点,基于小波分析和BP神经网络的基本原理,建立小波-BP神经网络的预测模型。首先,系统地分析并提取农业机械化作业水平主要影响因素,采用主成分分析的方法进行降维处理;然后,对我国农业机械化作业水平时间序列和影响因素主成分序列进行小波分解获取低频分量和高频分量,进而对低频分量与高频分量分别建立BP神经网络预测模型;最后,将预测得到的低频分量和高频分量通过线性叠加得到最终预测结果。以我国农业机械化作业水平预测为例对该方法进行验证,结果表明:小波-BP神经网络预测模型具有较好的预测效果,模型评价指标平均相对误差、均方根误差、希尔不等系数、一致性指标、有效系数和优秀率分别为0.44%、0.293、0.002 4、0.90、0.972 7和100%,各评价指标均优于其他模型。

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%。

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。