基于不同算法优化的back propagation神经网络在三元乙丙橡胶混炼胶门尼黏度预测中的应用

分别采用遗传算法(GA)和粒子群算法(PSO)优化的back propagation(BP)神经网络建立了三元乙丙橡胶(EPDM)混炼胶门尼黏度的预测模型,并对预测结果的误差进行了对比分析。结果表明,两种算法优化后的BP神经网络模型的预测值与实测值均保持较高的拟合度和相关性;相比单一的BP神经网络,GA优化后BP神经网络模型的精度提高了58.9%,PSO优化后BP神经网络模型的精度提高了3.57%,说明两种算法优化后的预测模型,特别是GA优化的BP神经网络预测模型对EPDM混炼胶门尼黏度的预测精度改善明显。

Shallow water bathymetry based on a back propagation neural network and ensemble learning using multispectral satellite imagery

The back propagation(BP)neural network method is widely used in bathymetry based on multispectral satellite imagery.However,the classical BP neural network method faces a potential problem because it easily falls into a local minimum,leading to model training failure.This study confirmed that the local minimum problem of the BP neural network method exists in the bathymetry field and cannot be ignored.Furthermore,to solve the local minimum problem of the BP neural network method,a bathymetry method based on a BP neural network and ensemble learning(BPEL)is proposed.First,the remote sensing imagery and training sample were used as input datasets,and the BP method was used as the base learner to produce multiple water depth inversion results.Then,a new ensemble strategy,namely the minimum outlying degree method,was proposed and used to integrate the water depth inversion results.Finally,an ensemble bathymetric map was acquired.Anda Reef,northeastern Jiuzhang Atoll,and Pingtan coastal zone were selected as test cases to validate the proposed method.Compared with the BP neural network method,the root-mean-square error and the average relative error of the BPEL method can reduce by 0.65–2.84 m and 16%–46%in the three test cases at most.The results showed that the proposed BPEL method could solve the local minimum problem of the BP neural network method and obtain highly robust and accurate bathymetric maps.

Prediction of SMILE surgical cutting formula based on back propagation neural network

AIM:To predict cutting formula of small incision lenticule extraction(SMILE)surgery and assist clinicians in identifying candidates by deep learning of back propagation(BP)neural network.METHODS:A prediction program was developed by a BP neural network.There were 13188 pieces of data selected as training validation.Another 840 eye samples from 425 patients were recruited for reverse verification of training results.Precision of prediction by BP neural network and lenticule thickness error between machine learning and the actual lenticule thickness in the patient data were measured.RESULTS:After training 2313 epochs,the predictive SMILE cutting formula BP neural network models performed best.The values of mean squared error and gradient are 0.248 and 4.23,respectively.The scatterplot with linear regression analysis showed that the regression coefficient in all samples is 0.99994.The final error accuracy of the BP neural network is-0.003791±0.4221102μm.CONCLUSION:With the help of the BP neural network,the program can calculate the lenticule thickness and residual stromal thickness of SMILE surgery accurately.Combined with corneal parameters and refraction of patients,the program can intelligently and conveniently integrate medical information to identify candidates for SMILE surgery.

FORCE RIPPLE SUPPRESSION TECHNOLOGY FOR LINEAR MOTORS BASED ON BACK PROPAGATION NEURAL NETWORK

Various force disturbances influence the thrust force of linear motors when a linear motor （LM） is running. Among all of force disturbances, the force ripple is the dominant while a linear motor runs in low speed. In order to suppress the force ripple, back propagation（BP） neural network is proposed to learn the function of the force ripple of linear motors, and the acquisition method of training samples is proposed based on a disturbance observer. An off-line BP neural network is used mainly because of its high running efficiency and the real-time requirement of the servo control system of a linear motor. By using the function, the force ripple is on-line compensated according to the position of the LM. The experimental results show that the force ripple is effectively suppressed by the compensation of the BP neural network.

Fashion Color Forecasting by Applying an Improved Back Propagation Neural Network

Fashion color forecasting is one of the most important factors for fashion marketing and manufacturing. Several models have been applied by previous researchers to conduct fashion color forecasting. However, few convincing forecasting systems have been established. A prediction model for fashion color forecasting was established by applying an improved back propagation neural network (BPNN) model in this paper. Successive six-year fashion color palettes, released by INTERCOLOR, were used as learning information for the neural network to develop a reliable prediction model. Colors in the palettes were quantified by PANTONE color system. Additionally, performance of the established model was compared with other GM(1, 1) models. Results show that the improved BPNN model is suitable to predict future fashion color trend.

Projected change in precipitation forms in the Chinese Tianshan Mountains based on the Back Propagation Neural Network Model

In the context of global warming,precipitation forms are likely to transform from snowfall to rainfall with a more pronounced trend.The change in precipitation forms will inevitably affect the processes of regional runoff generation and confluence as well as the annual distribution of runoff.Most researchers used precipitation data from the CMIP5 model directly to study future precipitation trends without distinguishing between snowfall and rainfall.CMIP5 models have been proven to have better performance in simulating temperature but poorer performance in simulating precipitation.To overcome the above limitations,this paper used a Back Propagation Neural Network(BNN)to predict the rainfall-to-precipitation ratio(RPR)in months experiencing freezing-thawing transitions(FTTs).We utilized the meteorological(air pressure,air temperature,evaporation,relative humidity,wind speed,sunshine hours,surface temperature),topographic(altitude,slope,aspect)and geographic(longitude,latitude)data from 28 meteorological stations in the Chinese Tianshan Mountains region(CTMR)from 1961 to 2018 to calculate the RPR and constructed an index system of impact factors.Based on the BNN,decision-making trial and evaluation laboratory method(BP-DEMATEL),the key factors driving the transformation of the RPR in the CTMR were identified.We found that temperature was the only key factor affecting the transformation of the RPR in the BP-DEMATEL model.Considering the relationship between temperature and the RPR,the future temperature under different representative concentration pathways(RCPs)(RCP2.6/RCP4.5/RCP8.5)provided by 21 CMIP5 models and the meteorological factors from meteorological stations were input into the BNN model to acquire the future RPR from 2011 to 2100.The results showed that under the three scenarios,the RPR in the number of months experiencing FTTs during 2011-2100 will be higher than that in the historical period(1981-2010)in the CTMR.Furthermore,in terms of spatial variation,the RPR values on the south slope will be larger than those on the north slope under the three emission scenarios.Moreover,the RPR values exhibited different variation characteristics under different emission scenarios.Under the low-emission scenario(RCP2.6),as time passed,the RPR values changed slightly at more stations.Under the mediumemission scenario(RCP4.5),the RPR increased in the whole CTMR and stabilized on the north slope by the end of this century.Under the high-emission scenario(RCP8.5),the RPR values increased significantly through the 21 st century in the whole CTMR.This study may help to provide a scientific management basis for agricultural production and hydrology.

Gear Fault Detection Analysis Method Based on Fractional Wavelet Transform and Back Propagation Neural Network

A gear fault detection analysis method based on Fractional Wavelet Transform(FRWT)and Back Propagation Neural Network(BPNN)is proposed.Taking the changing order as the variable,the optimal order of gear vibration signals is determined by discrete fractional Fourier transform.Under the optimal order,the fractional wavelet transform is applied to eliminate noise from gear vibration signals.In this way,useful components of vibration signals can be successfully separated from background noise.Then,a set of feature vectors obtained by calculating the characteristic parameters for the de-noised signals are used to characterize the gear vibration features.Finally,the feature vectors are divided into two groups,including training samples and testing samples,which are input into the BPNN for learning and classification.Experimental results showed that this gear fault detection analysis method could well maintain the useful signal components related to gear faults and effectively extract the weak fault feature.The accuracy rate reached 96.67%in the identification of the type of gear fault.

Combinatorial Optimization Based Analog Circuit Fault Diagnosis with Back Propagation Neural Network

Electronic components' reliability has become the key of the complex system mission execution. Analog circuit is an important part of electronic components. Its fault diagnosis is far more challenging than that of digital circuit. Simulations and applications have shown that the methods based on BP neural network are effective in analog circuit fault diagnosis. Aiming at the tolerance of analog circuit,a combinatorial optimization diagnosis scheme was proposed with back propagation( BP) neural network( BPNN).The main contributions of this scheme included two parts:( 1) the random tolerance samples were added into the nominal training samples to establish new training samples,which were used to train the BP neural network based diagnosis model;( 2) the initial weights of the BP neural network were optimized by genetic algorithm( GA) to avoid local minima,and the BP neural network was tuned with Levenberg-Marquardt algorithm( LMA) in the local solution space to look for the optimum solution or approximate optimal solutions. The experimental results show preliminarily that the scheme substantially improves the whole learning process approximation and generalization ability,and effectively promotes analog circuit fault diagnosis performance based on BPNN.

Classification of Epileptic Electroencephalograms Using Time-Frequency and Back Propagation Methods

Today,electroencephalography is used to measure brain activity by creating signals that are viewed on a monitor.These signals are frequently used to obtain information about brain neurons and may detect disorders that affect the brain,such as epilepsy.Electroencephalogram(EEG)signals are however prone to artefacts.These artefacts must be removed to obtain accurate and meaningful signals.Currently,computer-aided systems have been used for this purpose.These systems provide high computing power,problem-specific development,and other advantages.In this study,a new clinical decision support system was developed for individuals to detect epileptic seizures using EEG signals.Comprehensive classification results were obtained for the extracted filtered features from the time-frequency domain.The classification accuracies of the time-frequency features obtained from discrete continuous transform(DCT),fractional Fourier transform(FrFT),and Hilbert transform(HT)are compared.Artificial neural networks(ANN)were applied,and back propagation(BP)was used as a learning method.Many studies in the literature describe a single BP algorithm.In contrast,we looked at several BP algorithms including gradient descent with momentum(GDM),scaled conjugate gradient(SCG),and gradient descent with adaptive learning rate(GDA).The most successful algorithm was tested using simulations made on three separate datasets(DCT_EEG,FrFT_EEG,and HT_EEG)that make up the input data.The HT algorithm was the most successful EEG feature extractor in terms of classification accuracy rates in each EEG dataset and had the highest referred accuracy rates of the algorithms.As a result,HT_EEG gives the highest accuracy for all algorithms,and the highest accuracy of 87.38%was produced by the SCG algorithm.

A Back Propagation-Type Neural Network Architecture for Solving the Complete n ×n Nonlinear Algebraic System of Equations

The objective of this research is the presentation of a neural network capable of solving complete nonlinear algebraic systems of n equations with n unknowns. The proposed neural solver uses the classical back propagation algorithm with the identity function as the output function, and supports the feature of the adaptive learning rate for the neurons of the second hidden layer. The paper presents the fundamental theory associated with this approach as well as a set of experimental results that evaluate the performance and accuracy of the proposed method against other methods found in the literature.

Classification Using Two Layer Neural Network Back Propagation Algorithm

Worldwide breast cancer is the most common form of cancer death occurring in 12.6% of women. This paper presents a cost effective approach to classify the normal, malignant and benign tumor using two layer neural network back propagation algorithm. Back propagation algorithm is used to train the neural network. Parallelization techniques speed up the computation process and as a result two layer neural networks outperform the previous work in terms of accuracy. Breast cancer tumor database used for the testing purpose is from the CIA machine learning repository. The highest accuracy of 97.12% is achieved using the two layer neural network back propagation algorithm.

Age and Gender Classification Using Backpropagation and Bagging Algorithms

Voice classification is important in creating more intelligent systems that help with student exams,identifying criminals,and security systems.The main aim of the research is to develop a system able to predicate and classify gender,age,and accent.So,a newsystem calledClassifyingVoice Gender,Age,and Accent(CVGAA)is proposed.Backpropagation and bagging algorithms are designed to improve voice recognition systems that incorporate sensory voice features such as rhythm-based features used to train the device to distinguish between the two gender categories.It has high precision compared to other algorithms used in this problem,as the adaptive backpropagation algorithm had an accuracy of 98%and the Bagging algorithm had an accuracy of 98.10%in the gender identification data.Bagging has the best accuracy among all algorithms,with 55.39%accuracy in the voice common dataset and age classification and accent accuracy in a speech accent of 78.94%.

Hybrid algorithm combining genetic algorithm with back propagation neural network for extracting the characteristics of multi-peak Brillouin scattering spectrum

In this study, a hybrid algorithm combining genetic algorithm （GA） with back propagation （BP） neural network （GA-BP） was proposed for extracting the characteristics of multi-peak Brillouin scattering spectrum. Simulations and experimental results show that the GA-BP hybrid algorithm can accurately identify the position and amount of peaks in multi-peak Brillouin scattering spectrum. Moreover, the proposed algorithm obtains a fitting degree of 0.9923 and a mean square error of 0.0094. Therefore, the GA-BP hybrid algorithm possesses a good fitting precision and is suitable for extracting the characteristics of multi-peak Brillouin scattering spectrum.

Porosity Prediction from Well Logs Using Back Propagation Neural Network Optimized by Genetic Algorithm in One Heterogeneous Oil Reservoirs of Ordos Basin, China

A reliable and effective model for reservoir physical property prediction is a key to reservoir characterization and management.At present,using well logging data to estimate reservoir physical parameters is an important means for reservoir evaluation.Based on the characteristics of large quantity and complexity of estimating process,we have attempted to design a nonlinear back propagation neural network model optimized by genetic algorithm(BPNNGA)for reservoir porosity prediction.This model is with the advantages of self-learning and self-adaption of back propagation neural network(BPNN),structural parameters optimizing and global searching optimal solution of genetic algorithm(GA).The model is applied to the Chang 8 oil group tight sandstone of Yanchang Formation in southwestern Ordos Basin.According to the correlations between well logging data and measured core porosity data,5 well logging curves(gamma ray,deep induction,density,acoustic,and compensated neutron)are selected as the input neurons while the measured core porosity is selected as the output neurons.The number of hidden layer neurons is defined as 20 by the method of multiple calibrating optimizations.Modeling results demonstrate that the average relative error of the model output is 10.77%,indicating the excellent predicting effect of the model.The predicting results of the model are compared with the predicting results of conventional multivariate stepwise regression algorithm,and BPNN model.The average relative errors of the above models are 12.83%,12.9%,and 13.47%,respectively.Results show that the predicting results of the BPNNGA model are more accurate than that of the other two,and BPNNGA is a more applicable method to estimate the reservoir porosity parameters in the study area.

A Hybrid Model Based on Back-Propagation Neural Network and Optimized Support Vector Machine with Particle Swarm Algorithm for Assessing Blade Icing on Wind Turbines

With the continuous increase in the proportional use of wind energy across the globe,the reduction of power generation efficiency and safety hazards caused by the icing on wind turbine blades have attracted more consideration for research.Therefore,it is crucial to accurately analyze the thickness of icing on wind turbine blades,which can serve as a basis for formulating corresponding control measures and ensure a safe and stable operation of wind turbines in winter times and/or in high altitude areas.This paper fully utilized the advantages of the support vector machine(SVM)and back-propagation neural network(BPNN),with the incorporation of particle swarm optimization(PSO)algorithms to optimize the parameters of the SVM.The paper proposes a hybrid assessment model of PSO-SVM and BPNN based on dynamic weighting rules.Three sets of icing data under a rotating working state of the wind turbine were used as examples for model verification.Based on a comparative analysis with other models,the results showed that the proposed model has better accuracy and stability in analyzing the icing on wind turbine blades.

基于Cornell的自适应电离层闪烁强度的模型研究

针对Cornell模型在同一闪烁条件下,数据更新周期越长,估计和模型输入的幅度闪烁指数S4的偏差越大,并随着电离层闪烁的增强而增强的问题,提出基于Cornell模型的自适应S4的电离层闪烁模型即AS4-Cornell模型。模型以S4的偏差作为BP(back propagation)神经网络比例积分微分(proportional integral derivative,PID)算法的反馈,自动调整输入的复高斯白噪声的区段权值,使最终产生的闪烁信号满足模型输入的闪烁指数S4的指标。结果表明:仿真时,AS4-Cornell模型的幅度和相位闪烁序列概率分布均符合电离层闪烁理论,估算得到的电离层幅度指数S4与模型输入S4指数的最大偏差为0.001;全球定位系统(global positioning system,GPS)电离层闪烁模拟器测试时,AS4-Cornell模型估算得到的电离层幅度指数S4与模型输入S4指数的最大偏差为0.09;相比Cornell模型,AS4-Cornell模型产生的电离层闪烁信号更能够很好地反映模型输入的电离层闪烁指数S4的强度。

Influencing Factors and Prediction of Risk of Returning to Ecological Poverty in Liupan Mountain Region,China

China has resolved its overall regional poverty in 2020 by attaining moderate societal prosperity.The country has entered a new development stage designed to achieve its second centenary goal.However,ecological fragility and risk susceptibility have increased the risk of returning to ecological poverty.In this paper,the Liupan Mountain Region of China was used as a case study,and the counties were used as the scale to reveal the spatiotempora differentiation and influcing factors of the risk of returning to poverty in study area.The indicator data for returning to ecological poverty from 2011-2020 were collected and summarized in three dimensions:ecological,economic and social.The autoregressive integrated moving average model(ARIMA)time series and exponential smoothing method(ES)were used to predict the multidimensional indicators of returning to ecological poverty for 61 counties(districts)in the Liupan Mountain Region for 2021-2030.The back propagation neural network(BPNN)and geographic information system(GIS)were used to generate the spatial distribution and time variation for the index of the risk of returning to ecological poverty(RREP index).The results show that 1)ecological factors were the main factors in the risk of returning to ecological poverty in Liupan Mountain Region.2)The RREP index for the 61 counties(districts)exhibited a downward trend from 2021-2030.The RREP index declined more in medium-and high-risk areas than in low-risk areas.From 2021 to 2025,the RREP index exhibited a slight downward trend.From 2026 to2030,the RREP index was expected to decline faster,especially from 2029-2030.3)Based on the RREP index,it can be roughly divided into three types,namely,the high-risk areas,the medium-risk areas,and the low-risk areas.The natural resource conditions in lowrisk areas of returning to ecological poverty,were better than those in medium-and high-risk areas.

A comparative study on the application of various artificial neural networks to simultaneous prediction of rock fragmentation and backbreak

In blasting operation,the aim is to achieve proper fragmentation and to avoid undesirable events such as backbreak.Therefore,predicting rock fragmentation and backbreak is very important to arrive at a technically and economically successful outcome.Since many parameters affect the blasting results in a complicated mechanism,employment of robust methods such as artificial neural network may be very useful.In this regard,this paper attends to simultaneous prediction of rock fragmentation and backbreak in the blasting operation of Tehran Cement Company limestone mines in Iran.Back propagation neural network（BPNN） and radial basis function neural network（RBFNN） are adopted for the simulation.Also,regression analysis is performed between independent and dependent variables.For the BPNN modeling,a network with architecture 6-10-2 is found to be optimum whereas for the RBFNN,architecture 636-2 with spread factor of 0.79 provides maximum prediction aptitude.Performance comparison of the developed models is fulfilled using value account for（VAF）,root mean square error（RMSE）,determination coefficient（R2） and maximum relative error（MRE）.As such,it is observed that the BPNN model is the most preferable model providing maximum accuracy and minimum error.Also,sensitivity analysis shows that inputs burden and stemming are the most effective parameters on the outputs fragmentation and backbreak,respectively.On the other hand,for both of the outputs,specific charge is the least effective parameter.

Rock mass quality classification based on deep learning:A feasibility study for stacked autoencoders

Objective and accurate evaluation of rock mass quality classification is the prerequisite for reliable sta-bility assessment.To develop a tool that can deliver quick and accurate evaluation of rock mass quality,a deep learning approach is developed,which uses stacked autoencoders(SAEs)with several autoencoders and a softmax net layer.Ten rock parameters of rock mass rating(RMR)system are calibrated in this model.The model is trained using 75%of the total database for training sample data.The SAEs trained model achieves a nearly 100%prediction accuracy.For comparison,other different models are also trained with the same dataset,using artificial neural network(ANN)and radial basis function(RBF).The results show that the SAEs classify all test samples correctly while the rating accuracies of ANN and RBF are 97.5%and 98.7%,repectively,which are calculated from the confusion matrix.Moreover,this model is further employed to predict the slope risk level of an abandoned quarry.The proposed approach using SAEs,or deep learning in general,is more objective and more accurate and requires less human inter-vention.The findings presented here shall shed light for engineers/researchers interested in analyzing rock mass classification criteria or performing field investigation.

An Improved BPNN Prediction Method Based on Multi-Strategy Sparrow Search Algorithm

Data prediction can improve the science of decision-making by making predictions about what happens in daily life based on natural law trends.Back propagation(BP)neural network is a widely used prediction method.To reduce its probability of falling into local optimum and improve the prediction accuracy,we propose an improved BP neural network prediction method based on a multi-strategy sparrow search algorithm(MSSA).The weights and thresholds of the BP neural network are optimized using the sparrow search algorithm(SSA).Three strategies are designed to improve the SSA to enhance its optimization-seeking ability,leading to the MSSA-BP prediction model.The MSSA algorithm was tested with nine different types of benchmark functions to verify the optimization performance of the algorithm.Two different datasets were selected for comparison experiments on three groups of models.Under the same conditions,the mean absolute error(MAE),root mean square error(RMSE),andmean absolute percentage error(MAPE)of the prediction results of MSSA-BPwere significantly reduced,and the convergence speed was significantly improved.MSSA-BP can effectively improve the prediction accuracy and has certain application value.