Optimized Wavelet Neural Network Research Articles

Constitutive Model of Shape Memory Alloy Wavelet Neural Network Based on Improved Bat Algorithm

Based on the experiment of austenite SMA wire properties, the influence of strain amplitude on the dynamic properties of SMA wire is studied, and a constitutive model of SMA wire based on a chaotic Gaussian bat (GS-BA) optimized wavelet neural network (GS-BA-WNN) is proposed. In view of such shortcomings as easy early-maturing and low diversity in late period of the basic bat algorithm (BA), the Gaussian disturbance is used to enhance algorithm’s ability to escape local optimum and promote the bat population chaos optimization to improve the population diversity. GS-BA is combined with wavelet neural network to obtain the initial parameter configuration of WNN, and the model of GS-BA-WNN is used to simulate the constitutive relationship of SMA wire under different amplitudes of strain, and at the same time it is compared with the model of WNN and model of WNN (BA-WNN) optimized by BA. The results show that the GS-BA-WNN model established using experimental data as model training data has higher prediction precision and smaller error than other models, and has advantages in predicting the constitutive relationship of SMA wire.

A New Hybrid Model Based on Fruit Fly Optimization Algorithm and Wavelet Neural Network and Its Application to Underwater Acoustic Signal Prediction

The local predictability of underwater acoustic signal plays an important role in underwater acoustic signal processing, and it is the basis of nonstationary signal detection. Wavelet neural network model, with the advantages of both wavelet analysis and artificial neural network, makes full use of the time-frequency localization characteristics of wavelet analysis and the self-learning ability of artificial neural network; however, this model is prone to fall into local minima or creates convergence. To overcome these disadvantages, a new hybrid model based on fruit fly optimization algorithm (FOA) and wavelet neural network (WNN) is proposed in this paper. The FOA-WNN prediction model is constructed by optimizing the weights and thresholds of wavelet neural network, and the model is applied to underwater acoustic signal prediction. The experimental results show that the FOA-WNN prediction model has higher prediction accuracy and smaller prediction error, compared with wavelet neural network prediction model and BP neural network prediction model.

Fault diagnosis of gearbox based on RBF-PF and particle swarm optimization wavelet neural network

The gear cracks of gear box are one of most common failure forms affecting gear shaft drive. It has become significant for practice and economy to diagnose the situation of gearbox rapidly and accurately. The extracted signal is filtered first to eliminate noise, which is pretreated for the diagnostic classification based on the particle filter of radial basis function. As traditional error back-propagation of wavelet neural network with falling into local minimum easily, slow convergence speed and other shortcomings, the particle swarm optimization algorithm is proposed in this paper. This particle swarm algorithm that optimizes the weight values of wavelet neural network (scale factor) and threshold value (the translation factor) was developed to reduce the iteration times and improve the convergence precision and rapidity so that the various parameters of wavelet neural network can be chosen adaptively. Experimental results demonstrate that the proposed method can accurately and quickly identify the damage situation of the gear crack, which is more robust than traditional back-propagation algorithm. It provides guidances and references for the maintenance of the gear drive system schemes.

Scenario Analysis of Natural Gas Consumption in China Based on Wavelet Neural Network Optimized by Particle Swarm Optimization Algorithm

Natural gas consumption has increased with an average annual growth rate of about 10% between 2012 and 2017. Total natural gas consumption accounted for 6.4% of consumed primary energy resources in 2016, up from 5.4% in 2012, making China the world’s third-largest gas user. Therefore, accurately predicting natural gas consumption has become very important for market participants to organize indigenous production, foreign supply contracts and infrastructures in a better way. This paper first presents the main factors affecting China’s natural gas consumption, and then proposes a hybrid forecasting model by combining the particle swarm optimization algorithm and wavelet neural network (PSO-WNN). In PSO-WNN model, the initial weights and wavelet parameters are optimized using PSO algorithm and updated through a dynamic learning rate to improve the training speed, forecasting precision and reduce fluctuation of WNN. The experimental results show the superiority of the proposed model compared with ANN and WNN based models. Then, this study conducts the scenario analysis of the natural gas consumption from 2017 to 2025 in China based on three scenarios, namely low scenario, reference scenario and high scenario, and the results illustrate that the China’s natural gas consumption is going to be 342.70, 358.27, 366.42 million tce (“standard” tons coal equivalent) in 2020, and 407.01, 437.95, 461.38 million tce in 2025 under the low, reference and high scenarios, respectively. Finally, this paper provides some policy suggestions on natural gas exploration and development, infrastructure construction and technical innovations to promote a sustainable development of China’s natural gas industry.

Prediction of CO2 Emission in China’s Power Generation Industry with Gauss Optimized Cuckoo Search Algorithm and Wavelet Neural Network Based on STIRPAT model with Ridge Regression

Power generation industry is the key industry of carbon dioxide (CO2) emission in China. Assessing its future CO2 emissions is of great significance to the formulation and implementation of energy saving and emission reduction policies. Based on the Stochastic Impacts by Regression on Population, Affluence and Technology model (STIRPAT), the influencing factors analysis model of CO2 emission of power generation industry is established. The ridge regression (RR) method is used to estimate the historical data. In addition, a wavelet neural network (WNN) prediction model based on Cuckoo Search algorithm optimized by Gauss (GCS) is put forward to predict the factors in the STIRPAT model. Then, the predicted values are substituted into the regression model, and the CO2 emission estimation values of the power generation industry in China are obtained. It’s concluded that population, per capita Gross Domestic Product (GDP), standard coal consumption and thermal power specific gravity are the key factors affecting the CO2 emission from the power generation industry. Besides, the GCS-WNN prediction model has higher prediction accuracy, comparing with other models. Moreover, with the development of science and technology in the future, the CO2 emission growth in the power generation industry will gradually slow down according to the prediction results.

A New Prediction Model for Transformer Winding Hotspot Temperature Fluctuation Based on Fuzzy Information Granulation and an Optimized Wavelet Neural Network

Winding hotspot temperature is the key factor affecting the load capacity and service life of transformers. For the early detection of transformer winding hotspot temperature anomalies, a new prediction model for the hotspot temperature fluctuation range based on fuzzy information granulation (FIG) and the chaotic particle swarm optimized wavelet neural network (CPSO-WNN) is proposed in this paper. The raw data are firstly processed by FIG to extract useful information from each time window. The extracted information is then used to construct a wavelet neural network (WNN) prediction model. Furthermore, the structural parameters of WNN are optimized by chaotic particle swarm optimization (CPSO) before it is used to predict the fluctuation range of the hotspot temperature. By analyzing the experimental data with four different prediction models, we find that the proposed method is more effective and is of guiding significance for the operation and maintenance of transformers.

Ocean Oil Spill Classification with RADARSAT-2 SAR Based on an Optimized Wavelet Neural Network

Oil spill accidents from ship or oil platform cause damage to marine and coastal environment and ecosystems. To monitor such spill events from space, fully polarimetric (Pol-SAR) synthetic aperture radar (SAR) has been greatly used in improving oil spill observation. Aiming to promote ocean oil spill classification accuracy, we developed a new oil spill identification method by combining multiple fully polarimetric SAR features data with an optimized wavelet neural network classifier (WNN). Two sets of RADARSAT-2 fully polarimetric SAR data are applied to test the validity of the developed method. The experimental results show that: (1) the convergence ability of optimized WNN can be enhanced, improving overall classification accuracy of ocean oil spill, in comparison to the classification results based on a common un-optimized WNN classifier; and (2) the joint use of the multiple fully Pol-SAR features as the inputs of the classifier can achieve better classification result than that only with single fully Pol-SAR feature. The developed method can improve classification accuracy by 4.96% and 7.75%, compared with the classification results with un-optimized WNN and only with one single fully polarimetric SAR feature. The classification overall accuracy based on the proposed approach can reach 97.67%. Experimental results have proven that the proposed approach is effective and applicable to classify the ocean oil spill.

Predicting the Yield of Spring Maize Based on an Optimized Wavelet Neural Network with an Improved Double-Chain Quantum Genetic Algorithm

Predicting the Yield of Spring Maize Based on an Optimized Wavelet Neural Network with an Improved Double-Chain Quantum Genetic Algorithm

Development of a method for comprehensive water quality forecasting and its application in Miyun reservoir of Beijing, China

Water quality forecasting is an essential part of water resource management. Spatiotemporal variations of water quality and their inherent constraints make it very complex. This study explored a data-based method for short-term water quality forecasting. Prediction of water quality indicators including dissolved oxygen, chemical oxygen demand by KMnO4 and ammonia nitrogen using support vector machine was taken as inputs of the particle swarm algorithm based optimal wavelet neural network to forecast the whole status index of water quality. Gubeikou monitoring section of Miyun reservoir in Beijing, China was taken as the study case to examine effectiveness of this approach. The experiment results also revealed that the proposed model has advantages of stability and time reduction in comparison with other data-driven models including traditional BP neural network model, wavelet neural network model and Gradient Boosting Decision Tree model. It can be used as an effective approach to perform short-term comprehensive water quality prediction.

Electric load simulator system control based on adaptive particle swarm optimization wavelet neural network with double sliding modes

In this article, an adaptive particle swarm optimization wavelet neural network with double sliding modes controller is proposed to address the complex nonlinearities and uncertainties in the electric load simulator. The adaptive double sliding modes–particle swarm optimization wavelet neural network algorithm with the self-learning structures and parameters is designed as a torque tracking controller, in which a number of hidden nodes are added and pruned by the structure learning algorithm, and the parameters are online adjusted by the adaptive particle swarm optimization at the same time. Moreover, one conventional sliding mode is introduced to track the time-varying reference command, and the other complementary sliding mode is adopted to attenuate the effect of the approximation error. Furthermore, the relative parameters should comply with some estimation laws on the basis of the Lyapunov theory used to guarantee the system stability. Finally, the simulation experiments are carried out on the hardware-in-the-loop platform for the electric load simulator, the performance of the adaptive double sliding modes–particle swarm optimization wavelet neural network with structure learning is verified compared with some similar control methods. In addition, different amplitudes and frequencies of the reference commands are introduced to further evaluate the effectiveness and robustness of the proposed algorithms.

Localized genetically optimized wavelet neural network for semi-active control of buildings subjected to earthquake

Control algorithm is one of the most important aspects in successful control of buildings against earthquake. In recent years, because of their capabilities, soft computing methods, stemmed from human brain abilities, have become of particular interest to researchers. In this paper, a wavelet neural network-based semi-active control model is proposed in order to provide accurately computed input voltage to the magneto rheological dampers to generate the optimum control force of structures. This model is optimized by a localized genetic algorithm and then applied to a nine-story benchmark structure subjected to 1.5× El Centro earthquake. The results show an average of 43% reduction of maximum drift in the controlled structure versus the uncontrolled one. The capability of the controller is also validated by applying other far-field and near-field earthquakes. The capability and efficiency of the proposed model are demonstrated in terms of drift, acceleration and base shear reduction. The proposed wavelet neural network is also compared with a tangent hyperbolic-based feed forward neural network, linear quadratic Gaussian, clipped optimal controller, and genetic algorithm-based fuzzy inference systems to show the superiority of the proposed controller. Copyright © 2016 John Wiley & Sons, Ltd.

Optimization of Parameters in Twist Springback Process for High-strength Sheets Based on Improved Particle Swarm Optimization Algorithm and Wavelet Neural Network

Optimization of Parameters in Twist Springback Process for High-strength Sheets Based on Improved Particle Swarm Optimization Algorithm and Wavelet Neural Network

Improved fruit fly optimization algorithm optimized wavelet neural network for statistical data modeling for industrial polypropylene melt index prediction

This paper presents the development of wavelet neural network (WNN) with an improved fruit fly optimization algorithm (IFOA) for the melt index prediction in the industrial propylene polymerization process. The structure, calculation, and prediction process of WNN are proposed, and the improved details of IFOA are introduced, which can enhance the searching efficiency and improve the searching quality over the traditional fruit fly optimization algorithm. Finally, the WNN–IFOA model can obtain the least predicting errors compared with other existing models and shows better generality for the online melt index prediction from the experimental results. Copyright © 2015 John Wiley & Sons, Ltd.

Analysis of PSO, AIS and GA-based optimal Wavelet-Neural Network classifier in Brain–Robot Interface

ObjectivesThis paper studies the effectiveness of three classifiers (Particle Swarm Optimization (PSO) based optimal Wavelet Neural Network (WNN), Artificial Immune System (AIS) based optimal WNN and Genetic Algorithm (GA) based optimal Neural Network) in Brain–Robot Interface system. Material and methodsC3 & C4 are selected as inputs. Wavelet coefficients, auto-regressive and the power of wavelet coefficients are employed as features. WNN is used as classifier and its performance in terms of accuracy is improved through meta-heuristic optimization techniques (PSO, AIS and GA). They are used to optimize neural network weights and wavelet parameters. ResultsAccuracy of three classification algorithms: a) PSO-based optimal WNN, b) AIS-based optimal WNN and c) GA-based optimal ANN is calculated. Results show that the mean accuracy/standard deviation of a), b) and c) are 76%/4.9, 65%/2.6 and 64%/2.2, respectively. In addition, results of the best classifier (PSO-based optimal WNN), are compared with Support Vector Machine (the mean accuracy of SVM is 60%). ConclusionPSO-based optimal WNN results in the best classification accuracy. Outputs of this classifier are implemented on a mobile robot named K-junior and a fixed robot named Tabriz-Puma. The experimental results show the applicability and effectiveness of these methods.

Prediction for Short-Term Traffic Flow Based on Optimized Wavelet Neural Network Model

Prediction for Short-Term Traffic Flow Based on Optimized Wavelet Neural Network Model

A hybrid Wavelet Neural Network and Switching Particle Swarm Optimization algorithm for face direction recognition

Face direction recognition is an important research issue in human–computer interaction. In order to improve recognition accuracy, a novel hybrid approach called Switching Particle Swarm Optimization–Wavelet Neural Network (SPSO–WNN) is presented. In this model, we employ the recently proposed Switching Particle Swarm Optimization (SPSO) algorithm to optimize the parameters of weights, scale factors, translation factors and threshold in Wavelet Neural Network (WNN). The proposed SPSO–WNN method has fast convergence speed and higher learning ability than conventional WNNs. Especially, a mode-dependent velocity updating equation with Markovian switching parameters is introduced in SPSO to overcome the contradiction between the local search and the global search, which makes it easy to jump the local minimum. The experiment results of the recognition for face direction show the feasibility and effectiveness of the proposed method. Compared with Particle Swarm Optimization–Wavelet Neural Network (PSO–WNN), Genetic Algorithm–Wavelet Neural Network (GA–WNN) and WNN, the proposed method has much better performance over them.

Wavelet neural network applied for prognostication of contact pressure between soil and driving wheel

This paper describes the measurement of contact pressure in the context of wheel–terrain interaction as affected by wheel load and tire inflation pressure when fusion of the wavelet transform with the back-propagation (BP) neural network is applied to construct the wavelet neural network contact pressure prediction model. To this aim, a controlled soil bin testing facility equipped with single-wheel tester was utilized while three levels of velocity, three levels of slippage and three levels of wheel load were applied. Using image processing technique, contact area values were determined which were subsequently used for quantification of contact pressure. Performances of the different predictor models incorporated of various mother wavelets were evaluated using standard statistical evaluation criteria. Root mean square error and coefficient of determination values of 0.1382 and 0.9864 achieved by the optimal wavelet neural network are better than that of BP neural network. The proposed tool typifies a high learning speed, enhanced predicting accuracy, and strong robustness.

Computer-aided detection of breast cancer on mammograms: A swarm intelligence optimized wavelet neural network approach

Breast cancer is the second leading cause of cancer death in women. Accurate early detection can effectively reduce the mortality rate caused by breast cancer. Masses and microcalcification clusters are an important early signs of breast cancer. However, it is often difficult to distinguish abnormalities from normal breast tissues because of their subtle appearance and ambiguous margins. Computer aided diagnosis (CAD) helps the radiologist in detecting the abnormalities in an efficient way. This paper investigates a new classification approach for detection of breast abnormalities in digital mammograms using Particle Swarm Optimized Wavelet Neural Network (PSOWNN). The proposed abnormality detection algorithm is based on extracting Laws Texture Energy Measures from the mammograms and classifying the suspicious regions by applying a pattern classifier. The method is applied to real clinical database of 216 mammograms collected from mammogram screening centers. The detection performance of the CAD system is analyzed using Receiver Operating Characteristic (ROC) curve. This curve indicates the trade-offs between sensitivity and specificity that is available from a diagnostic system, and thus describes the inherent discrimination capacity of the proposed system. The result shows that the area under the ROC curve of the proposed algorithm is 0.96853 with a sensitivity 94.167% of and specificity of 92.105%.

The application of Shuffled Frog Leaping Algorithm to Wavelet Neural Networks for acoustic emission source location

When using acoustic emission to locate the friction fault source of rotating machinery, the effects of strong noise and waveform distortion make accurate locating difficult. Applying neural network for acoustic emission source location could be helpful. In the BP Wavelet Neural Network, BP is a local search algorithm, which falls into local minimum easily. The probability of successful search is low. We used Shuffled Frog Leaping Algorithm (SFLA) to optimize the parameters of the Wavelet Neural Network, and the optimized Wavelet Neural Network to locate the source. After having performed the experiments of friction acoustic emission's source location on the rotor friction test machine, the results show that the calculation of SFLA is simple and effective, and that locating is accurate with proper structure of the network and input parameters.

Modified method for wavelet neural network model

To improve the performance of Wavelet Neural Network( WNN) model in dealing with complex nonlinear problems, concerning the shortcomings of premature convergence, poor late diversity, poor search accuracy of Quantumbehaved Particle Swarm Optimization( QPSO) algorithm, a modified quantum-behaved particle swarm algorithm was proposed for WNN training by introducing weighting coefficients, introducing Cauchy random number, improving contraction-expansion coefficient and introducing natural selection at the same time. And then, it replaced the gradient descent method with the modified quantum-behaved particle swarm algorithm, trained the wavelet coefficients and network weights, and then input the optimized combination of parameters into wavelet neural network to achieve the algorithm coupling. The simulation results on three UCI standard datasets show that the running time of the Modified Quantum-behaved Particle Swarm Optimization-Wavelet Neural Network( MQPSO-WNN) was reduced by 11% ~ 43%, while the calculation error was decreased by 8% ~ 57%,compared with wavelet neural network, PSO-WNN and QPSO-WNN. Therefore, the MQPSO-WNN model can approximate the optimal value more quickly and more accurately.