Wavelet Neural Network Model Research Articles

Wavelet Neural Network Based Multiobjective Interval Prediction for Short-Term Wind Speed

As a source of clean and pollution-free renewable energy, wind power has attracted much attention and has been increasingly integrated into the existing power system. However, the uncertain and volatile wind speed makes the utilization of wind power a challenging task. Hence, it is essential to design an accurate forecast method to deal with the uncertainty caused by wind speed. This paper proposes a multiobjective interval prediction method based on wavelet neural network (WNN) for short-term wind speed forecast. This method can generate a set of Pareto optimal solutions which represents a set of prediction models that can directly construct the prediction intervals. An advanced multiobjective evolutionary algorithm, preference inspired co-evolutionary algorithm using goal vectors, is investigated to train the WNN model. Two case studies are carried out with real wind speed data of Victoria and Edmonton in Canada to justify the effectiveness of the proposed method. The numerical results also show the superiority of the proposed forecast approach compared with some benchmark methods.

Wavelet Neural Network Model for Yield Spread Forecasting

In this study, a hybrid method based on coupling discrete wavelet transforms (DWTs) and artificial neural network (ANN) for yield spread forecasting is proposed. The discrete wavelet transform (DWT) using five different wavelet families is applied to decompose the five different yield spreads constructed at shorter end, longer end, and policy relevant area of the yield curve to eliminate noise from them. The wavelet coefficients are then used as inputs into Levenberg-Marquardt (LM) ANN models to forecast the predictive power of each of these spreads for output growth. We find that the yield spreads constructed at the shorter end and policy relevant areas of the yield curve have a better predictive power to forecast the output growth, whereas the yield spreads, which are constructed at the longer end of the yield curve do not seem to have predictive information for output growth. These results provide the robustness to the earlier results.

Prediction of carbon dioxide concentration in weaned piglet buildings by wavelet neural network models

Carbon dioxide concentration is a major factor in air quality, animal welfare and air exchange rates inside livestock buildings. CO2 concentration series show a dynamic, non-linear and non-stationary behavior. This type of process can be handled by Wavelet Neural Network (WNN) models, which have been developed in recent years. The purpose of this paper is to develop WNN models capable of predicting the dynamics of CO2 in weaner buildings.Outdoor temperatures, CO2 concentration and temperature in the animal zone and animal activity were recorded in a commercial piglet farm during two complete production cycles. Two WNN models were generated from the recorded data: an autoregressive model (AM) that used the CO2 series and outdoor temperatures for the prediction, and an explanatory model (EM) that used only exogenous variables, namely outdoor temperature, temperature in the animal zone and animal activity.Because CO2 is a highly autoregressive variable, the best results are obtained with the AM. The AM yield an RMSE of 26.330 ppm and a Pearson’s r of 0.995. The EM, with an RMSE of 154.361 ppm and a Pearson’s r of 0.895, reveal the importance of indoor and outdoor temperatures and, consequently, of ventilation rate, for CO2 concentration inside the building. In addition, our results show the effects of animal activity on CO2 concentration, which are delayed by 40–50 min. Based on these results, the CO2 concentrations in the animal zone of weaner buildings can be accurately predicted by WNN models. Therefore, WNN modeling could be widely used to predict and understand the dynamics of environmental variables inside livestock buildings.

Temperature based generalized wavelet-neural network models to estimate evapotranspiration in India

In this paper, generalized wavelet-neural network (WNN) based models were developed for estimating reference evapotranspiration (ETo) corresponding to Hargreaves (HG) method for different agro-ecological regions (AERs): semi-arid, arid, sub-humid, and humid in India. The input and target to the WNN models are climate data (minimum and maximum air temperature) and ETo (estimated from FAO-56 Penman Monteith method), respectively. The developed WNN models were compared with the various generalized conventional models such as artificial neural networks (ANN), linear regression (LR), wavelet regression (WR), and HG method to test the best performed model. The performance indices used for the comparison include root mean squared error (RMSE), Nash-Sutcliffe efficiency (NSE), the ratio of average output to the average target ETo values (Rratio), and relative percentage (RP). The WNN and ANN models were performed better as compared to LR, WR and HG methods. Further, the best performed WNN and ANN models were tested on locations, which were not included in training to test their generalizing capability. It is concluded that the WNN and ANN models were shown good generalizing capability for the tested locations as compared to HG method.

Wavelet Neural Network with Random Wavelet Function Parameters

The training algorithm of Wavelet Neural Networks (WNN) is a bottleneck which impacts on the accuracy of the final WNN model. Several methods have been proposed for training the WNNs. From the perspective of our research, most of these algorithms are iterative and need to adjust all the parameters of WNN. This paper proposes a one-step learning method which changes the weights between hidden layer and output layer of the network; meanwhile, the wavelet function parameters are randomly assigned and kept fixed during the training process. Besides the simplicity and speed of the proposed one-step algorithm, the experimental results verify the performance of the proposed method in terms of final model accuracy and computational time.

Prediction of the performance and exhaust emissions of a compression ignition engine using a wavelet neural network with a stochastic gradient algorithm

Abstract The purpose of this research is to use a wavelet neural network (WNN) and stochastic gradient algorithm (SGA) to predict the performance and exhaust emissions of a compression ignition engine with nanoparticles-diesel fuel. The percentage of the additive of nanoparticles to the fuel ranges between 20 and 80 ppm. A model of WNN has been applied in order to predict the relationship between the power, fuel consumption (FC), specific fuel consumption (SFC), CO, NOx, and HC with the amount of nanoparticles at different speeds. The input variables are of two parameters (the percentage of nanoparticles and engine speed), while the output variables are of six parameters (power, FC, SFC, CO, NOx, and HC). In this work, considering the characteristics of the utilized wavelet function and application of the SGA method, satisfactory results were obtained in prediction of exhaust emissions and performance of the target engine. In addition, two common artificial neural networks (ANNs) (back propagation (BP) and non-linear autoregressive with exogenous input (NARX)) were used in predicting the performance of internal combustion engines compared with WNN results. Therefore, evaluation results of these three networks showed that the WNN with the SGA are very accurate and useful method to perform the prediction and model nonlinear phenomena of internal combustion engines.

Wavelet neural network–based wind speed forecasting and application of shuffled frog leap algorithm for economic dispatch with prohibited zones incorporating wind power

Wind speed and wind power generation are characterized by their inherent variability and uncertainty. To overcome this drawback, an accurate prediction of wind speed is essential. The purpose of this article is to develop a hybrid wavelet neural network model for wind speed forecasting and thus, in turn, for wind power generation. The combined optimal economic scheduling of the wind generators and conventional generators has also been investigated in this article. This article proposes shuffled frog leap algorithm for solving economic dispatch problem in power systems. The non-linear characteristics of the generator such as prohibited operating zone and non-smooth functions are considered. The feasibility of the proposed algorithm is demonstrated for 5 units, 6 units and 15 units systems and it is compared with the existing solution techniques. The results show that the proposed algorithm is indeed capable of handling economic dispatch problems.

Multi-models for SPI drought forecasting in the north of Haihe River Basin, China

Drought is one of the most devastating climate disasters. Hence, drought forecasting plays an important role in mitigating some of the adverse effects of drought. Data-driven models are widely used for drought forecasting such as ARIMA model, artificial neural network (ANN) model, wavelet neural network (WANN) model, support vector regression model, grey model and so on. Three data-driven models (ARIMA model; ANN model; WANN model) are used in this study for drought forecasting based on standard precipitation index of two time scales (SPI; SPI-6 and SPI-12). The optimal data-driven model and time scale of SPI are then selected for effective drought forecasting in the North of Haihe River Basin. The effectiveness of the three data-models is compared by Kolmogorov–Smirnov (K–S) test, Kendall rank correlation, and the correlation coefficients (R2). The forecast results shows that the WANN model is more suitable and effective for forecasting SPI-6 and SPI-12 values in the north of Haihe River Basin.

An improved seasonal rolling grey forecasting model using a cycle truncation accumulated generating operation for traffic flow

• A seasonal rolling grey forecasting model for urban traffic flow was proposed. • The new information priority of the proposed model was proved by rigorous matrix perturbation analysis. • The proposed model provides a new perspective on the seasonal and limited data characteristics of traffic flows. • Four time intervals of traffic forecasting show that the proposed model has good adaptability and stability. Accurate real-time prediction of urban traffic flows is one of the most important problems in traffic management and control optimization research. Short-term traffic flow has complex stochastic and nonlinear characteristics, and it shows a similar seasonality within intraday and weekly trends. Based on these properties, we propose an improved binding cycle truncation accumulated generating operation seasonal grey rolling forecasting model. In the new model, the traffic flow sequence of seasonal fluctuation is converted to a flat sequence using the cycle truncation accumulated generating operation. Then, grey modeling of the cycle truncation accumulated generating operation sequence weakens the stochastic disturbances and highlights the intrinsic grey exponential law after the sequence is accumulated. Finally, rolling forecasts of the limited data reflect the new information priority and timeliness of the grey prediction. Two numerical traffic flow examples from China and Canada, including four groups at different time intervals (1 h, 15 min, 10 min, and 5 min), are used to verify the performance of the new model under different traffic flow conditions. The prediction results show that the model has good adaptability and stability and can effectively predict the seasonal variations in traffic flow. In 15 or 10 min traffic flow forecasts, the proposed model shows better performance than the autoregressive moving average model, wavelet neural network model and seasonal discrete grey forecasting model.

Generalized wavelet neural networks for evapotranspiration modeling in India

This study focuses on the application of generalized wavelet neural network (GWNN) models corresponding to the FAO-56 Penman Monteith (FAO-56 PM), Turc, and Hargreaves (HG) methods for estimating daily reference evapotranspiration (ETo). The daily pooled climate data from 15 different locations under 4 different agro-ecological regions (AERs: semi-arid, arid, sub-humid, and humid) in India are used as an input to GWNN models. The inputs include three combinations of climate data (minimum and maximum air temperatures, minimum and maximum relative humidity, wind speed, and solar radiation) and the target consists of the FAO-56 PM estimated ETo. Further, the GWNN models were applied to 15 individual model development locations and 10 different model testing locations to test the generalizing capability. Comparison of developed GWNN models was made with the classic generalized artificial neural network (GANN), generalized linear regression (GLR), generalized wavelet regression (GWR), and corresponding conventional methods to test the superiority of one model over the other. Results reveal that the GWNN models followed by GANN models performed better than GWR and GLR models for four AERs. The testing results suggest that the GWNN and GANN models have better generalizing capabilities than the GWR and GLR for almost all region locations.

Real-time prediction of water level change using adaptive neuro-fuzzy inference system

ABSTRACTAccurate water levels modelling and prediction is essential for maritime applications. Water prediction is traditionally developed using the least-squares-based harmonic analysis method based on water level change (WLC) measurements. If long water level measurements are not obtained from the tide gauge, accurate water levels prediction cannot be estimated. To overcome the above limitations, the wavelet neural network (WNN) has recently been developed for the WLC prediction from short water level measurements. However, a new adaptive neuro-fuzzy inference system (ANFIS) model is proposed and developed in this paper. The ANFIS model is utilized to predict and select the WLC models of one month of hourly WLC for Yarmouth, Sain-John and Charlottetown stations in Canadian waters and compared with the current-state-of-the-art WNN model. The statistical analysis is applied to analyse the performance of the developed model in training and testing stages. The results showed an accurate modelling level using ANFIS technique for each station in training and testing stage. A comparison between the developed ANFIS method and the current-state-of-the-art WNN method shows that the accuracy of the developed ANFIS model is superior to the current-state-of-the-art model by 21.5% in average.

Research and application of a hybrid wavelet neural network model with the improved cuckoo search algorithm for electrical power system forecasting

Electricity forecasting plays an important role in the operation of electrical power systems. Many models have been developed to obtain accurate forecasting results, but most of them focus more on a single forecasting indicator, such as short-term load forecasting (STLF), short-term wind speed forecasting (STWSF) or short-term electricity price forecasting (STEPF). In this paper a new hybrid model based on the singular spectrum analysis (SSA) and modified wavelet neural network (WNN) is proposed for all the short-term load forecasting, short-term wind speed forecasting and short-term electricity price forecasting. In this model, a new improved cuckoo search (CS) algorithm is proposed to optimize the initial weights and the parameters of dilation and translation in WNN. Case studies of half-hourly electrical load data, 10-min-ahead wind speed data and half-hourly electricity price data are applied as illustrative examples to evaluate the proposed hybrid model, respectively. Experiments show that the hybrid model resulted in 46.4235%, 31.6268% and 25.8776% reduction in the mean absolute percentage error compared to the comparison models in short-term load forecasting, short-term wind speed forecasting and short-term electricity price forecasting, respectively.

Variable infiltration capacity model with BGSA-based wavelet neural network

In this study, we developed a hybrid form of rainfall-runoff model by integrating the variable infiltration capacity (VIC) model with a wavelet neural network (WNN) based on the binary gravitational search algorithm (BGSA). The streamflow of each subbasin in the Jinshajiang River Basin was first simulated by VIC model, then the simulated runoff of each subbasin and antecedent total basin runoff were decomposed via discrete wavelet transformation into a number of subseries components with different time scales. Finally, BGSA was employed to optimize the number of hidden layers and identify the appropriate subset of WNN inputs from a set of candidate subseries components. The proposed VIC_BGSA_WNN model was then compared to the traditional VIC model and reference methods based on correlation to determine effective wavelet components, and results indicated that our approach is feasible and effective.

Multidye Biosorption: Wavelet Neural Network Modeling and Taguchi L16 Orthogonal Array Design

Biosorption of safranin (SF), malachite green (MG), and Janus green B (JG) onto Sargassum ilicifolium was studied in single and ternary systems. Principal component‐wavelet neural network was used for the simultaneous determination SF, MG, and JG in mixture. Biosorbent dose, pH and time were optimized by Taguchi L16 experimental design and optimum values were 0.1 g L−1, 8.5, and 85 min, respectively. The maximum biosorption capacity was 0.671 mmol g−1. Kinetic, equilibrium and thermodynamic of the biosorption process were also investigated. The biosorption kinetic was described by pseudo‐second order model. Several isotherm models were fitted to experimental biosorption data and among the models, Hill, and Sips isotherms had the best fits. Negative ΔG° values confirmed the feasibility and spontaneous nature and of the biosorption process.

Performance evaluation of ANNs and an M5 model tree in Sattarkhan Reservoir inflow prediction

In this research, done from 2002 to 2012 at the Sattarkhan Reservoir in Iran, different combinations of values of a time series related to precipitation, evaporation, and discharge at upstream stations were used as the inputs and the next-day discharge was used as the output, in order to evaluate an artificial neural network (ANN), Support Vector Regression (SVR), Wavelet Neural Networks (WANN) and M5 model tree. Twelve scenarios consisting of input variables with different combinations of flow and climatological data by different lag times were created to study the role played by input variables in the accuracy of the model. Results of the various scenarios showed that when the inputs were consisted of the amount of temperature, precipitation and previous discharges (scenario 2), the next-day discharge could be estimated with higher accuracy by the WANN model with a RMSE value of 0.31 m3/s in comparison with the SVR model with RMSE value of 0.873 m3/s, M5 model tree with RMSE value of 0.880 m3/s and ANN model with RMSE value of 0.896 m3/s. Conclusively, the obtained results revealed that the wavelet transformation creates significant effect for increasing the prediction accuracies of the ANN model.

Prediction models of calorific value of coal based on wavelet neural networks

New prediction models based on wavelet neural networks (WNNs) have been proposed to estimate the gross calorific value (GCV) of coals. The input sets for the prediction models are involved of the proximate and ultimate analysis components of coal and the oxide analyses of ash. The coal samples, which have been employed to develop and verify the prediction models, are from United States Geological Survey (USGS) and China Huaneng Group. Some published methods have also been employed and redeveloped to make a comparison with the models proposed in this paper. The comparison reveals that the WNN models proposed here based on the proximate (ultimate) analysis components of coal, are consistently better than the published ones. The WNN models based on the oxide analyses of ash have higher accuracy in estimating the GCV of Chinese coals than US coals. Here we also analyze the possible reasons that could lead to the low estimated accuracy.

A novel hybrid approach based on cuckoo search optimization algorithm for short‐term wind speed forecasting

A type of renewable energy, wind power, which has a large generating capacity, has increasingly captured the world's attention. Forecasting wind speed is of great significance in wind‐related engineering studies, the planning and designing of wind packs, wind farm management and the integration of wind power into electricity grids. Because of the chaotic nature and intrinsic complexity of wind speed, reducing forecasting errors related to wind speed has been an important research subject. This article proposes a hybrid forecasting model based on the wavelet neural network (WNN) method and ensemble empirical mode decomposition (EEMD) de‐noise technology. Moreover, the cuckoo search optimization (CSO) algorithm is employed to optimize the parameters of the WNN model to avoid the over‐fitting problem and improve fitting accuracy. A case study is performed to forecast 10‐min wind speed data for wind farms in the coastal areas of China, and a comparison of the forecasting results with other models demonstrates that the proposed model can provide desirable forecasting results and improve forecasting accuracy. © 2017 American Institute of Chemical Engineers Environ Prog, 36: 943–952, 2017

A Novel Pattern Clustering Algorithm Based on Particle Swarm Optimization Joint Adaptive Wavelet Neural Network Model

Cluster analysis as an important function of the data mining has made great progress in recent years a series of methods for analysis of accuracy provides a solid foundation. This paper proposes the novel pattern clustering algorithm based on particle swarm optimization joint adaptive wavelet neural network model. Nonlinear adaptive filter has the stronger ability of that signal processing. However, due to complicated calculation of the nonlinear adaptive filter, the actual use of linear adaptive filter is still. To deal with this challenge, we integrate the wavelet neural network for modification. Usually, the wavelet neural network learning process using the gradient descent method, even if the error function that along the negative gradient direction, and which requires the step length direction along the negative gradient direction. As well, we revise the PSO to enhance the wavelet NN in the process of search, the equilibrium relation between the global search ability and local search ability for the success of the algorithm plays an important role. With this modification, our method obtains the better performance. The experimental result shows the feasibility and the effectiveness of the method compared with the other latest and state-of-the-art methods.

The Application of Wavelet Neural Network in the Settlement Monitoring of Subway

The settlement monitoring of subway runs through the entire construction stage of subway. It is very important to predict the accurate settlement value for construction safety of subway. In this paper, the wavelet transform is used to denoise the settlement data. The auxiliary wavelet neural network, embedded wavelet neural network and single BP neural network are applied to predict the settlement of Tianjin subway. Compared with single BP neural network and auxiliary wavelet neural network, the embedded wavelet neural network model has a higher accuracy and better prediction effect. The embedded wavelet neural network is more valuable than the BP neural network model so it can be used in the prediction of subway settlement

Modeling for output fiber length distribution of refining process using wavelet neural networks trained by NSGA II and gradient based two-stage hybrid algorithm

The chemi-thermo-mechanical pulping (CTMP) is an important process that produces fibers for paper-making, whose output fiber length distribution (FLD) directly determines the energy consumption and product quality of the subsequent papermaking production. Therefore, study on modeling and control of the output FLD is essential for improving pulp quality and saving energy in refining process. However, the output FLD of refining process has non-Gaussian stochastic distribution property, making it difficult to use conventional methods to establish the output FLD model effectively. Under the framework of stochastic distribution control theory, this paper presents a novel modeling approach for output probability density function (PDF) of fiber length in CTMP by combining with the improved wavelet neural network (WNN). In this context, the square root B-spline approximation principle is firstly adopted to extract the B-spline weights of fiber length PDF shape as the target outputs for the WNN based B-spline weights model. Secondly, a novel two-stage hybrid learning algorithm is proposed to establish the parameters system for the WNN based weighs model by defining a multi-objective evaluation index for modeling accuracy in advance. This learning algorithm integrates multi-objective NSGA II algorithm in the first stage for better initial solutions at a global scope, and gradient descent method is employed in the second stage for accurate solutions of WNN model parameters inside a local range. As a result, the final output PDF of fiber length is reconstructed by the estimated B-spline weights using the B-spline approximation principle again. Experiments using actual industrial data have demonstrated the superiority and practicability of the proposed method.