BP Artificial Neural Network Model Research Articles

Feasibility of measuring moisture content of green sand by a low frequency multiprobe detector based on dielectric characteristics

Green sand is a mixture of silica sand, bentonite, water and coal powder, and other additives. Moisture content is an important index to characterize the properties of green sand. Based on the dielectric characteristics of green sand and transmission line theory, a method for rapidly measuring the moisture content of green sand by means of a low frequency multiprobe detector was proposed. A system was constructed, where six detectors with different arrangements and probes were designed. The experimental results showed that the voltage difference of transmission line increases with the increasing frequency before 29 MHz while decreases after 35 MHz. A voltage difference platform occurs in the range of 29–35 MHz, which is suitable for measuring the moisture content due to its insensitivity to frequency. The electric field intensity gradually decreases with the increase of the probe depth, and the intensity of central probe is always greater than that of the edge probe. When the distance of the probe away from the sand sample surface is 80 mm, the electric field intensity of the edge probe is found to be very weak. The optimal excitation frequency for measuring the moisture content of green sand is 29–33 MHz. The optimal detector is the one with one center probe and three edge probes, and their lengths are 80 mm and 60 mm, respectively. The distance between the center and edge probes is 25 mm, and the diameter of probes is 5 mm. Taking the voltage difference of transmission line, bentonite content, coal powder content and compactability as parameters of the input layer, and the moisture content as a parameter of the output layer, a three-layer BP artificial neural network model for predicting the moisture content of green sand was constructed according to the experimental results at 33 MHz. The prediction error of the model is not higher than 3.3% when the moisture content of green sand is within the range of 3wt.%–7wt.%.

Constitutive model research on the hot deformation behavior of Ti6Al4V alloy under wide temperatures

The hot compression tests of Ti6Al4V alloy were carried out at different temperatures (500, 600, 700, 800, and 900 °C) and different strain rates (0.01 s−1, 0.1 s−1, and 1 s−1). The hot deformation behavior of Ti6Al4V alloy is complex in a wide temperature range, and the phenomenon of negative strain rate sensitivity even appears at low temperature (500 °C and 600 °C). The phenomenological Arrhenius model, modified Fields-Backofen model (m-FB) and Gray Wolf Optimization Algorithm optimizing BP artificial neural network model (GWO-BPNN) were established. A new FB model (n-FB) was proposed based on m-FB model. The prediction accuracy and computational cost of these constitutive models were evaluated by mean absolute percentage error (MAPE), correlation coefficient (R) and the number of parameters. The comparison results show that the m-FB model, the GWO-BPNN model, and the n-FB model can predict the flow stress at all temperatures, but the Arrhenius model cannot be fitted at low temperature conditions, and the fitting effect of the Arrhenius model is the worst. The GWO-BPNN has the highest prediction accuracy based on that it has the maximum number of parameters. The MAPE and R values of n-FB model are 1.9093% and 0.993 respectively. Compared with the m-FB model, the MAPE value of n-FB is reduced by 64.64%.

Improving BP artificial neural network model to predict the SPI in arid regions: a case study in Northern Shaanxi, China

Abstract Drought prediction plays an important guiding role in drought risk management. The standardized precipitation index (SPI) is a popular meteorological drought indicator to measure the degree of drought. The SPI time series is non-stationary, whereas the conventional artificial neural network (ANN) model has limitations to predict non-stationary time series. To overcome this limitation, it is essential to investigate input data preprocessing to improve the ANN model. In this paper, a hybrid model coupled with singular spectrum analysis (SSA) and backpropagation ANN is proposed (SSA-BP-ANN). The advantage of this model is that the SSA of finite-length SPI sequences does not require the adoption of boundary extensions to suppress boundary effects, while the most predictable components of the SPI can be efficiently extracted and incorporated into the model. The proposed SSA-BP-ANN model is tested in case studies at three meteorological stations in Northern Shannxi Province, China. The results show that the SSA-BP-ANN model can produce more accurate predictions than the BP-ANN model. In addition, the performance improvement of SSA on the BP-ANN model is slightly better than wavelet decomposition and empirical mode decomposition. This new hybrid prediction model has great potential for promoting drought early warning in arid regions.

Catalyst Optimization Design Based on Artificial Neural Network

Artificial neural network (ANN) has the characteristics of self-adaptation, self-learning, parallel processing and strong nonlinear mapping ability. Compared with traditional experimental analysis modeling, ANN has obvious advantages in dealing with multivariable nonlinear complex relationships in the process of industrial catalyst design. In the face of the complex structure of catalyst, the unclear reaction mechanism and conditions, the use of neural network for small-scale experimental data analysis can save the time and energy invested in large-scale experimental research and obtain more perfect results in catalyst formulation optimization and condition selection. This paper summarizes the development of artificial neural network. The application principle, construction method and research progress of BP artificial neural network model in catalyst optimization design are summarized and analyzed. The development and innovation of artificial neural network in the future, as well as its continuous application and accumulation, will provide a powerful tool for the research of catalyst design and optimization in the future.

The paths of prevention and treatment on air pollution and simulation analysis: a case study

ABSTRACT Atmospheric environment is an important resource for human survival. However, existing studies on air pollution often focus on one aspect of occurrence, impact, or prevention while neglecting dynamic mechanism inside. Besides, previous literature neither explores the influencing paths of this mechanism nor lacks the simulation analysis on the prevention and treatment of air pollution. To prevent the environment from deteriorating further, this paper first explores the causal path of air pollution under the framework of DPSIR model. Results show that the path coefficients of driving force to pressure, pressure to state, and state to influence are 0.696, −3.165, and 0.871, respectively. And the adjustment coefficient of the response layer to “pressure to state” is −0.918 at 10% significant level. Then, BP artificial neural network model is established to simulate and analyze the changes of air pollution state and influence in different scenarios in Jiangsu province. The results indicated that air pollution has a causal path of “Driver-Pressure-State-Influence.” Jiangsu should take measures to adjust the regulation intensity reasonably and avoid air pollution accompanied by industry GDP growing.

A comparative study on the prediction of the BP artificial neural network model and the ARIMA model in the incidence of AIDS

BackgroundAs a kind of widely distributed disease in China, acquired immune deficiency syndrome (AIDS) has been quickly growing each year, become a serious problem and caused serious damage to the life and health of people and the social events of China and the world because of its high fatality rate. It has been much concerned by all aspects of society. Therefore, developing early warning technology and finding the trend of early development are of quite significance to prevent and control human immunodeficiency virus (HIV)/AIDS. This study aimed to explore a suitable model for the morbidity of AIDS in China and establish a professional and feasible disease prediction model for the prevention and control works of AIDS.MethodsAt present, the traditional linear model is still utilized by most scholars to predict the incidence of HIV/AIDS. In addition, some scholars may attempt to use the nonlinear prediction model. Both prediction models showed good fitting and prediction effects. In China, the incidence of AIDS presents linear and nonlinear characteristics. In this research, the nonlinear back propagation artificial neural network (BP-ANN) model and the typical auto-regressive integrated moving average (ARIMA) linear model were applied to predict the incidence of HIV/AIDS and compare their fitting effects.ResultsBoth models were capable of predicting the expected cases of AIDS. It was seen that ARIMA and BP-ANN models could be used to forecast the monthly incidence of HIV/AIDS, but the fitting and forecasting effects of the nonlinear BP neural network model were better than those of the traditional linear ARIMA model.ConclusionsIn summary, it was further concluded that the BP-ANN model was a suitable way to monitor and predict the change trend and morbidity of AIDS in China.

Research on diabetes prediction method based on electronic medical record data analysis

The continuous progress of computer science and technology has accelerated the pace of informatization construction of the medical system. Medical technology has developed rapidly in various research directions, and the construction of medical IT systems has been continuously improved. The popular application of electronic medical records has produced massive medical data in the medical process. At the same time, in medical behavior, more and more rely on data to make relevant judgments. The coverage of medical equipment is becoming more and more extensive, and the accuracy of data is constantly improving, and the clinical diagnosis is gradually shifting from qualitative judgment to quantitative analysis. Based on the analysis of electronic medical record data, this article studies and analyzes the risk factors leading to diabetes. By analyzing the characteristic variables, the risk factors significantly related to diabetes are obtained as the input variables of the BP neural network model. For complex problems, machine learning algorithms have higher accuracy and stronger generalization capabilities. Based on the BP artificial neural network model, this paper builds and builds a machine learning simulation to predict diabetes.

The Early, Rapid, and Non-Destructive Detection of Citrus Huanglongbing (HLB) Based on Microscopic Confocal Raman

Citrus huanglongbing (HLB) as a devastating disease seriously affects the advance in agriculture, so early detection or accurate diagnosis is the key to control its spread. This paper reported a method for early, rapid, and non-destructive detection of HLB using microscopic confocal Raman (MCR). The spectra of healthy (HE), HLB-asymptomatic (HA), and HLB-symptomatic (HS) leaves were very different at 730–810 cm−1, 866 cm−1, 942 cm−1, 1082 cm−1, 1250 cm−1, 1455 cm−1, and 1510–1630 cm−1, which could be clearly distinguished mutually. Meanwhile, the spectra of relative compounds inside leaves were connected to further analyze spectral differences. The contents of glucose, sucrose, carotene, and chlorophyll in HA leaves were distinctly decreased, but increased in starch and polyphenols compared with HE leaves. In addition, three types of leaves could be well classified by principal component analysis (PCA) whose cumulative percentage variance (CPV) accounted for about 91.01% (three principal components). Partial least square discriminant analysis (PLS-DA) also demonstrated the good clustering effect with an accuracy of 97.2%. Finally, BP-artificial neural network (BP-ANN) model was utilized to evaluate datasets (75% for training, 25% for testing). The low root mean square errors (RMSE 0.0616) and high squared correlation coefficients (R2 0.9598) values showed the high prediction accuracy and stability of the classification model. These results indicated that MCR had excellent practical values for horticulturists to constantly and early detect HLB, which was conducive to prevent and timely control of the spread of HLB.

Prediction of Developing Modern Agriculture Demands for the Agricultural Scientific Research Institutions Services Based on BP Artificial Neural Network

BP artificial neural network model is used to predict developing modern agriculture demands for the agricultural scientific research institutions services. Starting from the brief introduction of the usages of BP neural network, we analyzed the demand factors of the agricultural scientific research institutions services and the affective elements of the demands, use the BP neural network model to predict, and then run the BP neural network model on the MATLAB platform, and finally carry out the case studies of Heilongjiang Province.

Application of BP neural network model in productivity prediction and evaluation of CBM wells fracturing

The geological conditions of coal-bed methane (CBM) are complex in China, so it is difficult to predict the production of CBM wells. Methodology of artificial intelligence was introduced in the mining of CBM. According to the characteristics of target block reservoir, the gray correlation analysis technology is used for analyzing the degree of correlation between each parameter and CBM production. And then the BP artificial neural network model is used in prediction and evaluation of CBM wells fracturing production. Application results show that the method improves the prediction and evaluation accuracy of CBM production.

RETRACTED: Evaluation of Water Resource Security Based on an MIV-BP Model in a Karst Area

Evaluation of water resource security deserves particular attention in water resource planning and management. A typical karst area in Guizhou Province, China, was used as the research area in this paper. First, based on data from Guizhou Province for the past 10 years, the mean impact value–back propagation (MIV-BP) model was used to analyze the factors influencing water resource security in the karst area. Second, 18 indices involving five aspects, water environment subsystem, social subsystem, economic subsystem, ecological subsystem, and human subsystem, were selected to establish an evaluation index of water resource security. Finally, a BP artificial neural network model was constructed to evaluate the water resource security of Guizhou Province from 2005 to 2014. The results show that water resource security in Guizhou, which was at a moderate warning level from 2005 to 2009 and a critical safety level from 2010 to 2014, has generally improved. Groundwater supply ratio, industrial water utilization rate, water use efficiency, per capita grain production, and water yield modulus were the obstacles to water resource security. Driving factors were comprehensive utilization rate of industrial solid waste, qualifying rate of industrial wastewater, above moderate rocky desertification area ratio, water requirement per unit gross domestic product (GDP), and degree of development and utilization of groundwater. Our results provide useful suggestions on the management of water resource security in Guizhou Province and a valuable reference for water resource research.

Research on the image of sweeping robot based on the Artificial Neural Network

Based on the theory of Artificial Neural Network and Kansei Engineering, the image of sweeping robots are formed using the content analysis method, and propose four kinds of sweeping robot as the experimental samples, which have a strong influence on the market. The image questionnaires are compiled by the semantic differences methods. 200 office workers, half men and half women, are chose as the survey respondents. And use SPSS statistical software for data analysis. Afterwards, the BP Artificial Neural Network model is established by Matlab based on the questionnaire results, and the optimized design scheme with image feature combination for sweeping robot products is generated on the basis of BP Artificial Neural Network model. This study construct the emotional demands on the image level, and carry out experiments and statistical analysis, which lays a solid foundation for the study of product image in theory and approach.

Prediction of PM2.5 Concentration in a Agricultural Park Based on BP Artificial Neural Network

The accurate prediction of PM2.5 concentration in a agricultural park is important to understand the role agricultural park plays in regulating PM2.5 pollution and guide public close to the nature healthily. An artificial neural network model was established, with meteorological data, atmospheric PM2.5 concentration outside the agricultural park and agricultural park structure as the input factors and PM2.5 hourly average concentration inside the agricultural park as the output factors. Its prediction accuracy was also evaluated in this study. The results show that it can be concluded that BP artificial neural network model is a promising approach in predicting PM2.5 concentration inside a agricultural park.

Research on Load Balance Method in SDN

In order to improve the performance of data transmission in SDN, this paper proposes a load balance solution scheme by taking advantage of the global network view of SDN. We collect 4 load features from each transmission path. These features are bandwidth utilization ratio, packet loss rate, transmission latency and transmission hops. By using this 4 load features, BP Artificial Neural Network model is trained to predict the integrated load for different path and to choose one with least load as the data-flow transmission path. The contrast experiment results show that load balancing strategy proposed in this paper can select more rational transmission path for data-flow and achieve 19.3% network latency decrease at most.

Settlement Prediction of Road Soft Foundation Using a Support Vector Machine (SVM) Based on Measured Data

The suppor 1 t vector machine (SVM) is a relatively new artificial intelligence technique which is increasingly being applied to geotechnical problems and is yielding encouraging results. SVM is a new machine learning method based on the statistical learning theory. A case study based on road foundation engineering project shows that the forecast results are in good agreement with the measured data. The SVM model is also compared with BP artificial neural network model and traditional hyperbola method. The prediction results indicate that the SVM model has a better prediction ability than BP neural network model and hyperbola method. Therefore, settlement prediction based on SVM model can reflect actual settlement process more correctly. The results indicate that it is effective and feasible to use this method and the nonlinear mapping relation between foundation settlement and its influence factor can be expressed well. It will provide a new method to predict foundation settlement.

A BP Artificial Neural Network Model for Earthquake Magnitude Prediction in Himalayas, India

The aim of this study is to evaluate the performance of BP neural network techniques in predicting earthquakes occurring in the region of Himalayan belt (with the use of different types of input data). These parameters are extracted from Himalayan Earthquake catalogue comprised of all minor, major events and their aftershock sequences in the Himalayan basin for the past 128 years from 1887 to 2015. This data warehouse contains event data, event time with seconds, latitude, longitude, depth, standard deviation and magnitude. These field data are converted into eight mathematically computed parameters known as seismicity indicators. These seismicity indicators have been used to train the BP Neural Network for better decision making and predicting the magnitude of the pre-defined future time period. These mathematically computed indicators considered are the clustered based on every events above 2.5 magnitude, total number of events from past years to 2014, frequency-magnitude distribution b-values, Gutenberg-Richter inverse power law curve for the n events, the rate of square root of seismic energy released during the n events, energy released from the event, the mean square deviation about the regression line based on the Gutenberg-Richer inverse power law for the n events, coefficient of variation of mean time and average value of the magnitude for last n events. We propose a three-layer feed forward BP neural network model to identify factors, with the actual occurrence of the earthquake magnitude M and other seven mathematically computed parameters seismicity indicators as input and target vectors in Himalayan basin area. We infer through comparing curve as observed from seismometer in Himalayan Earthquake catalogue comprised of all events above magnitude 2.5 mg, their aftershock sequences in the Himalayan basin of year 2015 and BP neural network predicting earthquakes in 2015. The model yields good prediction result for the earthquakes of magnitude between 4.0 and 6.0.

Electric Load Movement Forecasting Based on the DFT Interpolation with Periodic Extension

Electric load forecasting is increasingly important for the industry. This study addresses the load forecasting based on the discrete Fourier transform (DFT) interpolation. As the most common analysis method in the frequency domain, the conventional Fourier analysis cannot be directly applied to prediction. From the perspective of time-series analysis, electric load movement influenced by various factors is also a time-series, which is usually subject to cyclical variations. Then with periodic extension for the load movement, a forecasting approach based on the DFT interpolation is proposed for predicting its movement. The proposed DFT interpolation prediction model is applied to experiments of forecasting the daily EUNITE load movement and annual load movement of State Grid Corporation in China. The experimental results and analysis show potentiality of the proposed method. Performance comparisons indicate that the proposed DFT interpolation model performs better than the three commonly used interpolation algorithms as well as the classical autoregressive (AR) model, the ARMA model, and the BP-artificial neural network (ANN) model on the same forecasting tasks.

Research on Neural Network Theory of the Toxicity of Aromatic Hydrocarbons on <i>Chlorella vulgaris</i>

Using BP neural network method, we calculate and analyze the molecular structure of aromatic hydrocarbons. Then, we get the electrotopological state indices and the molecular electronegativity distance vectors of 25 aromatic hydrocarbons based on the calculation of molecular structure characteristics and adjacency matrix. By regression, we get and optimize the structural parametersE9,E13,E17andM15. The four structural parameters are used as the input variables and a 4-2-1 network structure is employed to construct a BP artificial neural network model for predicting acute toxicitypEC50. The total correlation coefficientRis 0.994 and the average error between the predicted value and experimental value ofpEC50is 0.079, which indicate that the ANN model has good stability and superior predictive ability. The results show that there is a good nonlinear correlation between acute toxicitypEC50and the four structural parameters. The results of our research reveal that the toxicity of aromatic hydrocarbons is closely affected by electrotopological state indices and the molecular electronegativity distance vectors. Therefore, it will be helpful in assessing the hazard of aromatic hydrocarbons to environment.

Water Quality Forecast Based on BP-Artificial Neural Network Model in Qiantang River

This study aims at providing a back propagation-artificial neural network (BP-ANN) model on forecasting the water quality change trend of Qiantang River basin. To achieve this goal, a three-layer (one input layer, one hidden layer, and one output layer) BP-ANN with the LM regularization training algorithm was used. Water quality variables such as pH value, dissolved oxygen, permanganate index and ammonia-nitrogen was selected as the input data to obtain the output of the neural network. The ANN structure with 17 hidden neurons obtained the best selection. The comparison between the original measured and forecast values of the ANN model shows that the relative errors, with a few exceptions, were lower than 9%. The results indicated that the BP neural network can be satisfactorily applied to forecast precise water quality parameters and is suitable for pre-alarm of water quality trend.

Dynamic Sensitivity Research for the Spindle of High-Speed Grinder Based on the Artificial Neural Network

Three-dimensional parametric entity model was established for the high speed grinder spindle using Pro/Pragram in this article, the sample data of the artificial neural network model was obtained with the modal analysis performed by MSC.Patran/Nastran finite element analysis software, and the dynamic analysis model of high-speed grinder was established based on BP artificial neural network, the the modal analysis experiment of high speed grinder spindle and the sensitivity analysis of first-order natural frequency for design parameters were finished. Research shows that the dynamic characteristic of hollow spindle structure is much better than solid structure, compared with finite element model, BP artificial neural network model can realize optimization design and calculation of complex structure more quickly.