Back-propagation Network Model Research Articles

Detection of potential fishing zones for neon flying squid based on remote-sensing data in the Northwest Pacific Ocean using an artificial neural network

Ommastrephes bartramii is a short-lived species of squid and reacts rapidly to changes in the regional environmental conditions of the fishing ground. Understanding the preferred range of key environmental variables and predicting potential resource distributions are critical to conserve and manage its resources. Commercial fishery data for the western winter–spring cohort of O. bartramii from Chinese squid-jigging vessels during 2003–2013 were used to evaluate a suitable range of three key environmental variables, sea surface temperature (SST), sea surface height (SSH), and chlorophyll-a (chl-a) concentration, and to explore potential fishing zones (PFZs) using an artificial neural network. The neural interpretation diagram and independent variable relevance analysis indicate that month, latitude, and SST had significant influences on the PFZ distribution of O. bartramii, yielding 21.78%, 23.91%, and 26.04% of contribution rates, respectively. Based on the sensitivity analyses, a high abundance of O. bartramii mainly occurred in the waters between 150°–165° E and 37°–42° N during July to August. Suitable ranges of environmental variables for O. bartramii were 11–18°C for SST, −10 to 60 cm for SSH, and 0.1–1.7 mg/m3 for chl-a concentration, respectively. The back-propagation network model was well developed and could be used to predict the PFZ with 80% accuracy. The actual fishing grounds coincided with the predicted PFZ, suggesting that the established model of PFZ is effective in forecasting the potential habitat of O. bartramii in the Northwest Pacific Ocean.

An ultrasound-based liquid pressure measurement method in small diameter pipelines considering the installation and temperature.

Liquid pressure is a key parameter for detecting and judging faults in hydraulic mechanisms, but traditional measurement methods have many deficiencies. An effective non-intrusive method using an ultrasound-based technique to measure liquid pressure in small diameter (less than 15 mm) pipelines is presented in this paper. The proposed method is based on the principle that the transmission speed of an ultrasonic wave in a Kneser liquid correlates with liquid pressure. Liquid pressure was calculated using the variation of ultrasonic propagation time in a liquid under different pressures: 0 Pa and X Pa. In this research the time difference was obtained by an electrical processing approach and was accurately measured to the nanosecond level through a high-resolution time measurement module. Because installation differences and liquid temperatures could influence the measurement accuracy, a special type of circuit called automatic gain control (AGC) circuit and a new back propagation network (BPN) model accounting for liquid temperature were employed to improve the measurement results. The corresponding pressure values were finally obtained by utilizing the relationship between time difference, transient temperature and liquid pressure. An experimental pressure measurement platform was built and the experimental results confirm that the proposed method has good measurement accuracy.

The forecast for precious metal indexes and precious metal ETFs: an artificial neural network analysis

This paper applies chaos effect, grey relational analysis (GRA) and artificial neural network (ANN) to forecast the return volatility of precious metals and precious metal ETFs. The results showed that all the data series performed deterministic chaos. The GRA results emphasised in all samples, the West Texas Intermediate (WTI) index represents the greatest influence, followed by stock index, exchange rate, commodity research bureau (CRB) index, volatility index, interest rate and put-call (P/C) ratio. Moreover, the backpropagation network (BPN) model is the most powerful model among four ANN models like BPN, radial basic function (RBP), recurrent neural network (RNN) and time-delay recurrent neural network (TDRNN) in forecasting precious metals and precious metal ETFs. 'All variables' group has stronger influence than high- or low-grey relational grade (GRG) variables for predicting precious metals. Whereas, precious metal ETFs have better forecasting results by using 'all variables' group for iShares Silver Trust (SLV) and ETFs physical platinum shares (PPLT) and high-GRG variables for SPDR gold shares (GLD) and ETFs physical palladium shares (PALL). Therefore, investors and traders can get profit through linkage seven determinants in forecasting precious metals and precious metal ETFs.

Forecast Model of Water Quantity Based on Back Propagation Artificial Neural Network

Back Propagation (BP) neural network, Widely adopted and utilized in automatic control, image recognition, hydrological forecasting and water quality evaluation, etc., as one of the Artificial Neural Networks, has stronger function and property of mapping, classification, functional fitting. This article takes the water flow of Lanzhou section of Yellow river in China as an example by the way of BP model to predict the water quantity. It is well proved that BP network model can reach the purposes of early warning and forecasting. DOI : http://dx.doi.org/10.11591/telkomnika.v12i6.5444

Application of Improved Back-Propagation Neural Network to the Technologic Processing of Korshunskite Whiskers

The korshunskite samples were prepared in precipitation by the one-step reaction method at atmospheric pressure. The three-layer structure back-propagation network model based on the non-linear relationship between the amount of the korshunskite whiskers and the technological factors, such as the adding amount of raw materials NaOH, MgCl2, MgO, and reaction temperature, is established. And the results show that the improved back propagation neural networks model is very efficient for predication of the korshunskite whiskers preparation.

Displacement back analysis for a high slope of the Dagangshan Hydroelectric Power Station based on BP neural network and particle swarm optimization.

The right bank high slope of the Dagangshan Hydroelectric Power Station is located in complicated geological conditions with deep fractures and unloading cracks. How to obtain the mechanical parameters and then evaluate the safety of the slope are the key problems. This paper presented a displacement back analysis for the slope using an artificial neural network model (ANN) and particle swarm optimization model (PSO). A numerical model was established to simulate the displacement increment results, acquiring training data for the artificial neural network model. The backpropagation ANN model was used to establish a mapping function between the mechanical parameters and the monitoring displacements. The PSO model was applied to initialize the weights and thresholds of the backpropagation (BP) network model and determine suitable values of the mechanical parameters. Then the elastic moduli of the rock masses were obtained according to the monitoring displacement data at different excavation stages, and the BP neural network model was proved to be valid by comparing the measured displacements, the displacements predicted by the BP neural network model, and the numerical simulation using the back-analyzed parameters. The proposed model is useful for rock mechanical parameters determination and instability investigation of rock slopes.

The Estimation of Global Warming Potential Due to the Temporary Storage of Municipal Solid Waste by an Artificial Neural Network—A Case Study

Temporary storage for collection of municipal solid waste is designed with various parameters, such as size of bin, collection frequency, average filling rate, number of bins, volume of material needed for bin production, bin density, and catchment area. The environmental impact of temporary storage is evaluated with emissions generated due to the production of net material used for bin production. An artificial neural network-back propagation method is proposed for modeling the temporary storage. In this proposed artificial neural network-back propagation network, the number of bins and global warming potential (GWP) based on the quantity of generated wastes are predicted. Thus, a set of different structures of artificial neural network-back propagation are investigated and then the best model is developed for temporary storage of municipal solid waste. The artificial neural network-back propagation model is trained using various parameters, such as number of neurons in the hidden layers, training tolerance, momentum, and learning rate. This model is helpful for the decision makers in choosing the environmentally sound options in the design of temporary storage for municipal solid waste management. Artificial neural network-back propagation can be successfully used to predict number of bins, GWP from waste generation rate of the city.

IUKF neural network modeling for FOG temperature drift

A novel neural network based on iterated unscented Kalman filter (IUKF) algorithm is established to model and compensate for the fiber optic gyro (FOG) bias drift caused by temperature. In the network, FOG temperature and its gradient are set as input and the FOG bias drift is set as the expected output. A 2-5-1 network trained with IUKF algorithm is established. The IUKF algorithm is developed on the basis of the unscented Kalman filter (UKF). The weight and bias vectors of the hidden layer are set as the state of the UKF and its process and measurement equations are deduced according to the network architecture. To solve the unavoidable estimation deviation of the mean and covariance of the states in the UKF algorithm, iterative computation is introduced into the UKF after the measurement update. While the measurement noise R is extended into the state vectors before iteration in order to meet the statistic orthogonality of estimate and measurement noise. The IUKF algorithm can provide the optimized estimation for the neural network because of its state expansion and iteration. Temperature rise (-20-20°C) and drop (70-20°C) tests for FOG are carried out in an attemperator. The temperature drift model is built with neural network, and it is trained respectively with BP, UKF and IUKF algorithms. The results prove that the proposed model has higher precision compared with the back-propagation (BP) and UKF network models.

Calculation of Load-Carrying Capacity of Square Concrete Filled Tube Columns Based on Neural Network

Steel tube and filled concrete of square CFT columns under axial load are in complicated stress condition, the influence of every kind of factors on mechanics performance is difficult to ascertain accurately. On the other hand, neural network is good at obtaining the relationship between input and output variables by self-studying, self-organizing, self-adapting and nonlinear mapping. Therefore, it is suitable that use neural network to calculating the bearing capacity of square CFT columns. In this paper a three-layer back-propagation model of network is trained according to experimental data of square CFT columns under axial load, a neural network model for axial loaded square CFT columns is set up. The model is verified by six groups of experimental data, the results show the predicted values are in good agreement with test values, precision in calculation is good enough to be used as an auxiliary method for structure design.

Research on Thermal Error Compensation of Gear Hobbing Machine

The purpose of this research is to improve the machining accuracy of YK3610 Hobbing machine through thermal error compensation. This study presents the whole process of thermal error modeling and compensation by using Back Propagation Network (BPN) and ant colony optimization is introduced into the training of BPN. The results show that the BPN model based on ant colony algorithm improves the prediction accuracy of thermal errors on the gear hobbing machine and the thermal drift has been reduced from 14.2 μm to 4.5 μm after compensation.

English

In developing countries such as Rwanda whose economy depends on agriculture and where more than 70% of the population relies on rain-fed agriculture for their livelihoods and which is among the highly populated countries in the world, changes in temperature, precipitation, humidity and arable land extremely affect the agricultural production. In response to these changing risks, forecasting cereals production study based on regression and back-propagation (BP) network model was carried out in Eastern Province of Rwanda. 22 years data from 1989 to 2010 of temperature, precipitation, humidity, percentage of cultivated area and cultivated area were taken as dependent variables and cereals production in the same period was considered as independent variable for the regression, while temperature, precipitation, humidity, percentage of cultivated area and cultivated area constituted the input variables to build BP Network model for forecasting cereals production. The model was consistently verified; results were efficient and showed that the general trend of cereals production in Eastern Province of Rwanda is increasing.   Key words: Cereals production, regression, back-propagation (BP) Network model, forecasting, Eastern Province of Rwanda.

Prediction of temperature of tubular truss under fire using artificial neural networks

A three-layer Back-Propagation neural network has been developed to predict the limiting temperature of steel planar tubular truss under fire. The input parameters of the network model include the diameter ratio (β), the wall thickness ratio (τ), the diameter–thickness ratio (γ) and the load ratio. The output parameters include the limiting temperature. In this paper, the training and testing samples of the neural network were obtained by using the finite element software ABAQUS. 105 sets of data were used to train the Back-Propagation neural network; 15 sets of data were used to test and validate the BP network. In the process of training the Back-Propagation network, the Levenberg–Marquardt Back-Bropagation algorithm was adopted. The ‘tansig’ function was adopted in the hidden layer, and the ‘purelin’ function was adopted in the output layer. The results obtained by analyzing show that the prediction of the limiting temperature using the Back-Propagation network model is accurate and effective.

Thermal Error Modeling of a CNC Machine Tool

The purpose of this research is to improve the machining accuracy of a CNC machine tool through thermal error modeling and compensation. In this paper, a thermal error model based on back propagation networks (BPN) is presented, and the compensation is fulfilled. The results show that the BPN model improves the prediction accuracy of thermal errors on the CNC machine tool, and the thermal drift has been reduced from 15 to 5 after compensation.

Box & Jenkins Model Identification:A Comparison of Methodologies

This paper focuses on a presentation of a comparison of a neuro-fuzzy back propagation network and Forecast automatic model Identification to identify automatically Box & Jenkins non seasonal models.Recently some combinations of neural networks and fuzzy logic technologies have being used to deal with uncertain and subjective problems. It is concluded on the basis of the obtained results that this type of approach is very powerful to be used.

Artificial neural network model research on effects of cross-wind to performance parameters of wet cooling tower based on level Froude number

Based on level Froude number (Frl), an artificial neural network (ANN) model is set up to predict performance parameters of wet cooling tower under cross-wind conditions in this paper, enough data are gathered by a thermal state model experiment to finish ANN training and prediction. Then three-layer back propagation network model which has one hidden layer is developed, and the node number in input layer, hidden layer and output layer are 4, 8 and 6, respectively. This model adopts the improved BP algorithm, that is, the gradient descent method with momentum, and the input parameters are level Froude number, water spraying density, inlet water temperature and relative humidity of inlet air, the output parameters are air gravity wind velocity of inlet tower, temperature difference, cooling efficiency, heat transfer coefficient, mass transfer coefficient and evaporative loss proportion. This BP model demonstrated a good statistical performance with the MRE and R in the range of 0.48%–3.92% and 0.992–0.999, and the RMSE values for the ANN training and predictions were very low relative to the range of the experiments. Thus, the developed BP model can be used to predict successfully the thermal performance of wet cooling tower under cross-wind conditions.

Simulation of phytoplankton biomass in Quanzhou Bay using a back propagation network model and sensitivity analysis for environmental variables

Prediction and sensitivity models, to elucidate the response of phytoplankton biomass to environmental factors in Quanzhou Bay, Fujian, China, were developed using a back propagation (BP) network. The environmental indicators of coastal phytoplankton biomass were determined and monitoring data for the bay from 2008 was used to train, test and build a three-layer BP artificial neural network with multi-input and single-output. Ten water quality parameters were used to forecast phytoplankton biomass (measured as chlorophyll-a concentration). Correlation coefficient between biomass values predicted by the model and those observed was 0.964, whilst the average relative error of the network was −3.46% and average absolute error was 10.53%. The model thus has high level of accuracy and is suitable for analysis of the influence of aquatic environmental factors on phytoplankton biomass. A global sensitivity analysis was performed to determine the influence of different environmental indicators on phytoplankton biomass. Indicators were classified according to the sensitivity of response and its risk degree. The results indicate that the parameters most relevant to phytoplankton biomass are estuary-related and include pH, sea surface temperature, sea surface salinity, chemical oxygen demand and ammonium.

Development and comparison of neural network based soft sensors for online estimation of cement clinker quality

The online estimation of process outputs mostly related to quality, as opposed to their belated measurement by means of hardware measuring devices and laboratory analysis, represents the most valuable feature of soft sensors. As of now there have been very few attempts for soft sensing of cement clinker quality which is mostly done by offline laboratory analysis resulting at times in low quality clinker. In the present work three different neural network based soft sensors have been developed for online estimation of cement clinker properties. Different input and output data for a rotary cement kiln were collected from a cement plant producing 10,000 tons of clinker per day. The raw data were pre-processed to remove the outliers and the resulting missing data were imputed. The processed data were then used to develop a back propagation neural network model, a radial basis network model and a regression network model to estimate the clinker quality online. A comparison of the estimation capabilities of the three models has been done by simulation of the developed models. It was observed that radial basis network model produced better estimation capabilities than the back propagation and regression network models.

Bearing Capacity of Concrete Filled Square Steel Tubular Columns Based on Neural Network

Steel tube and filled concrete of square CFT (concrete filled steel tubular structures) columns under eccentric load are in complicated stress condition, the influence of every kind of factors on mechanics performance is difficult to ascertain accurately. On the other hand, neural network is good at obtaining the relationship between input and output variables by self-studying, self-organizing, self-adapting and nonlinear mapping. Therefore, it is suitable that use neural network to calculating the bearing capacity of square CFT columns. In this paper a four-layer back-propagation model of network is trained according to experimental data of square CFT columns under eccentric load, a neural network model for eccentrically loaded square CFT columns is set up. The model is verified by six groups of experimental data, the results show the predicted values are in good agreement with test values, precision in calculation is good enough to be used as an auxiliary method for structure design.

Seismic Behavior of Concrete Filled Circular Steel Tubular Columns Based on Artificial Neural Network

Artificial neural network (ANN) is self-adaptability, fault toleration and fuzziness. It is suitable to solve the seismic properties of high strength reinforced concrete columns with concrete filled steel tube core (HRCCFT). A three-layer back-propagation network model is build up to study the seismic properties of HRCCFT. The model is trained according to 30 sets of experimental data. The network convergence is fast. The model is verified by 8 groups of experimental data, the results show the predicted values of displacement ductility are in good agreement with test values. The precision of model is better than that of formula from other reference. This method is good enough to be used as an auxiliary method for structure design.

The thermal error optimization models for CNC machine tools

Thermal error compensation is becoming a cost-effective way to improve accuracy of machine tools especially with the increasing demand for machining accuracy in recent years. The compensation effectiveness mainly depends on the accuracy of the thermal error model. In order to explore the robustness, versatility, and prediction accuracy of the thermal error modeling, linear regression (LR) model, backpropagation (BP) network model, and radial basis function (RBF) network model are developed, analyzed, and compared. Experimental validation on a high precision four-axes machining center demonstrates that LR model has high prediction accuracy yet it has low robustness because the estimation of the regression coefficients and thermal key points are strongly correlated to the measurement data and their noise level. The neural network model is more adaptive to the case of different feed rates, rotational speeds, and ambient temperatures and has certain versatility on machine tools of the same type. The fitting accuracy and the prediction correctness of the BP network usually vary according to the hidden neurons, thresholds, and weights and cannot achieve the peak performance simultaneously. Experimental results show that the thermal error in Z axial direction could be reduced to as less as 25% of the original thermal error with compensation using the RBF model under the machining conditions of various feed rates and rotational speeds. It is also demonstrated that RBF model could improve the thermal precision in Z axle of the machine tool by about 65% under the distinct environmental temperature conditions.