Interval finite difference method for steady-state temperature field prediction with interval parameters

A new numerical technique named interval finite difference method is proposed for the steady-state temperature field prediction with uncertainties in both physical parameters and boundary conditions. Interval variables are used to quantitatively describe the uncertain parameters with limited information. Based on different Taylor and Neumann series, two kinds of parameter perturbation methods are presented to approximately yield the ranges of the uncertain temperature field. By comparing the results with traditional Monte Carlo simulation, a numerical example is given to demonstrate the feasibility and effectiveness of the proposed method for solving steady-state heat conduction problem with uncertain-but-bounded parameters.

Prediction of Aircraft Engine Health Condition Parameters Based on Ensemble ELM

In view of aircraft engine health condition parameters prediction,an ensemble ELM based prediction approach is proposed in this paper. In the approach,the AdaBoost. RT algorithm is improved to adjust its threshold adaptively,and is utilized as the basic framework to establish the ensemble learning model using ELM as weak learners. The proposed approach is evaluated through the prediction of the actual engine fuel flow deviation time series,and the results demonstrate that this approach is feasible for the prediction of aircraft engine health condition parameters. The performance of the proposed approach is compared with single ELM, single process neural network ( PNN) ,and a similar ensemble ELM based approach using AdaBoost. RT as basic framework. The results show that,the proposed approach is more accurate than single ELM and single PNN,and no worse than the ensemble prediction approach for contrast,furthermore,the given approach is more convenient for practical application. Therefore,the proposed approach is better suited to the prediction of aircraft engine health parameters.

Optimized Two-Level Ensemble Model for Predicting the Parameters of Metamaterial Antenna

Employing machine learning techniques in predicting the parameters of metamaterial antennas has a significant impact on the reduction of the time needed to design an antenna with optimal parameters using simulation tools.In this paper,we propose a new approach for predicting the bandwidth of metamaterial antenna using a novel ensemble model.The proposed ensemble model is composed of two levels of regression models.The first level consists of three strong models namely,random forest,support vector regression,and light gradient boosting machine.Whereas the second level is based on the ElasticNet regression model,which receives the prediction results from the models in the first level for refinement and producing the final optimal result.To achieve the best performance of these regression models,the advanced squirrel search optimization algorithm(ASSOA)is utilized to search for the optimal set of hyper-parameters of each model.Experimental results show that the proposed two-level ensemble model could achieve a robust prediction of the bandwidth of metamaterial antenna when compared with the recently published ensemble models based on the same publicly available benchmark dataset.The findings indicate that the proposed approach results in root mean square error(RMSE)of(0.013),mean absolute error(MAE)of(0.004),and mean bias error(MBE)of(0.0017).These results are superior to the other competing ensemble models and can predict the antenna bandwidth more accurately.

Fast determination of meso-level mechanical parameters of PFC models

To solve the problems of blindness and inefficiency existing in the determination of meso-level mechanical parameters of particle flow code (PFC) models, we firstly designed and numerically carried out orthogonal tests on rock samples to investigate the correlations between macro-and meso-level mechanical parameters of rock-like bonded granular materials. Then based on the artificial intelligent technology, the intelligent prediction systems for nine meso-level mechanical parameters of PFC models were obtained by creating, training and testing the prediction models with the set of data got from the orthogonal tests. Lastly the prediction systems were used to predict the meso-level mechanical parameters of one kind of sandy mudstone, and according to the predicted results the macroscopic properties of the rock were obtained by numerical tests. The maximum relative error between the numerical test results and real rock properties is 3.28% which satisfies the precision requirement in engineering. It shows that this paper provides a fast and accurate method for the determination of meso-level mechanical parameters of PFC models.

Energy Balance-related Behaviors Are Related to Cardiometabolic Parameters and Predict Adiposity in 8-14-year-old Overweight Chinese Children One Year Later

To identify target energy balance-related behaviors（ERBs）,baseline data from 141overweight or obese schoolchildren（aged 8-14years old）was used to predict adiposity[body mass index（BMI）and fat percentage]one year later.The ERBs included a modified Dietary Approach to Stop Hypertension diet score（DASH score）,leisure-time physical activity（PA,days/week）,and leisure screen time（minutes/day）.Several cardiometabolic variables were measured in the fasting state, including systolic blood pressure （SBP）, diastolic blood pressure （DBP）, blood glucose （GLU）, total cholesterol （TC）, triglycerides （TG）, low-density lipoprotein （LDL-C）, and high-density lipoprotein （HDL-C）.

Prediction of Superconductivity for Oxides Based on Structural Parameters and Artificial Neural Network Method

Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.

Developing Weibull-based diameter distributions for the major coniferous species in Heilongjiang Province,China

Diameter distribution models play an important role in forest inventories,growth prediction,and management.The Weibull probability density function is widely used in forestry.Although a number of methods have been proposed to predict or recover the Weibull distribution,their applicability and predictive performance for the major tree species of China remain to be determined.Trees in sample plots of three even-aged coniferous species(Larix olgensis,Pinus sylvestris and Pinus koraiensis)were measured both in un-thinned and thinned stands to develop parameter prediction models for the Weibull probability density function.Ordinary least squares(OLS)and maximum likelihood regression(MLER),as well as cumulative distribution function regression(CDFR)were used,and their performance compared.The results show that MLER and CDFR were better than OLS in predicting diameter distributions of tree plantations.CDFR produced the best results in terms of fitting statistics.Based on the error statistics calculated for different age groups,CDFR was considered the most suitable method for developing prediction models for Weibull parameters in coniferous plantations.

Rock physics inversion based on an optimized MCMC method

Rock physics inversion is to use seismic elastic properties of underground strata for predicting reservoir petrophysical parameters.The Markov chain Monte Carlo(MCMC)algorithm is commonly used to solve rock physics inverse problems.However,all the parameters to be inverted are iterated simultaneously in the conventional MCMC algorithm.What is obtained is an optimal solution of combining the petrophysical parameters with being inverted.This study introduces the alternating direction(AD)method into the MCMC algorithm(i.e.the optimized MCMC algorithm)to ensure that each petrophysical parameter can get the optimal solution and improve the convergence of the inversion.Firstly,the Gassmann equations and Xu-White model are used to model shaly sandstone,and the theoretical relationship between seismic elastic properties and reservoir petrophysical parameters is established.Then,in the framework of Bayesian theory,the optimized MCMC algorithm is used to generate a Markov chain to obtain the optimal solution of each physical parameter to be inverted and obtain the maximum posterior density of the physical parameter.The proposed method is applied to actual logging and seismic data and the results show that the method can obtain more accurate porosity,saturation,and clay volume.

Prediction of length-of-day using extreme learning machine

Traditional artificial neural networks （ANN） such as back-propagation neural networks （BPNN） provide good predictions of length-of-day （LOD）. However, the determination of network topology is difficult and time consuming. Therefore, we propose a new type of neural network, extreme learning machine （ELM）, to improve the efficiency of LOD predictions. Earth orientation parameters （EOP） C04 time-series provides daily values from International Earth Rotation and Reference Systems Service （IERS）, which serves as our database. First, the known predictable effects that can be described by functional models-such as the effects of solid earth, ocean tides, or seasonal atmospheric variations--are removed a priori from the C04 time-series. Only the residuals after the subtraction of a priori model from the observed LOD data （i.e., the irregular and quasi-periodic variations） are employed for training and predictions. The predicted LOD is the sum of a prior extrapolation model and the ELM predictions of the residuals. Different input patterns are discussed and compared to optimize the network solution. The prediction results are analyzed and compared with those obtained by other machine learning-based prediction methods, including BPNN, generalization regression neural networks （GRNN）, and adaptive network-based fuzzy inference systems （ANFIS）. It is shown that while achieving similar prediction accuracy, the developed method uses much less training time than other methods. Furthermore, to conduct a direct comparison with the existing prediction tech- niques, the mean-absolute-error （MAE） from the proposed method is compared with that from the EOP prediction comparison campaign （EOP PCC）. The results indicate that the accuracy of the proposed method is comparable with that of the former techniques. The implementation of the proposed method is simple.

Optimized Weighted Ensemble Using Dipper Throated Optimization Algorithm in Metamaterial Antenna

Metamaterial Antennas are a type of antenna that uses metamaterial to enhance performance.The bandwidth restriction associated with small antennas can be solved using metamaterial antennas.Machine learning is gaining popularity as a way to improve solutions in a range of fields.Machine learning approaches are currently a big part of current research,and they’re likely to be huge in the future.The model utilized determines the accuracy of the prediction in large part.The goal of this paper is to develop an optimized ensemble model for forecasting the metamaterial antenna’s bandwidth and gain.The basic models employed in the developed ensemble are Support Vector Regression(SVR),K-NearestRegression(KNR),Multi-Layer Perceptron(MLP),Decision Trees(DT),and Random Forest(RF).The percentages of contribution of these models in the ensemble model are weighted and optimized using the dipper throated optimization(DTO)algorithm.To choose the best features from the dataset,the binary(bDTO)algorithm is exploited.The proposed ensemble model is compared to the base models and results are recorded and analyzed statistically.In addition,two other ensembles are incorporated in the conducted experiments for comparison.These ensembles are average ensemble and K-nearest neighbors(KNN)-based ensemble.The comparison is performed in terms of eleven evaluation criteria.The evaluation results confirmed the superiority of the proposed model when compared with the basic models and the other ensemble models.

Numerical Simulation and Prediction for Sticking Type Breakout Behavior in Slab Contiuous Casting

A two-dimensional heat transfer model was developed to calculate the mould wall temperature field under normal operations condition and to determine its changing behavior when breakout occured. On the numerical simulation of sticking type breakout process and the breakout related wall temperature evolution, parameters of prediction were suggested.

Predictive phase equilibria for the aqueous ternary system(Li_2SO_4 + K_2SO_4 + H_2O) from 273.15 to 373.15 K

1 Introduction Many variable temperature chemical models were developed to predict mineral solubility in the natural waters(Na+,K+,Ca2+,Mg2+//Cl-,SO42-–H2O)in the temperature range below 298.15 K(to near 213.15 K)and(Na+,K+,

Ensemble-transfer-learning-based channel parameter prediction in asymmetric massive MIMO systems

Asymmetric massive multiple-input multiple-output(MIMO)systems have been proposed to reduce the burden of data processing and hardware cost in sixth-generation mobile networks(6G).However,in the asymmetric massive MIMO system,reciprocity between the uplink(UL)and downlink(DL)wireless channels is not valid.As a result,pilots are required to be sent by both the base station(BS)and user equipment(UE)to predict doubledirectional channels,which consumes more transmission and computational resources.In this paper we propose an ensemble-transfer-learning-based channel parameter prediction method for asymmetric massive MIMO systems.It can predict multiple DL channel parameters including path loss(PL),multipath number,delay spread(DS),and angular spread.Both the UL channel parameters and environment features are chosen to predict the DL parameters.Also,we propose a two-step feature selection algorithm based on the SHapley Additive exPlanations(SHAP)value and the minimum description length(MDL)criterion to reduce the computation complexity and negative impact on model accuracy caused by weakly correlated or uncorrelated features.In addition,the instance transfer method is introduced to support the prediction model in new propagation conditions,where it is difficult to collect enough training data in a short time.Simulation results show that the proposed method is more accurate than the back propagation neural network(BPNN)and the 3GPP TR 38.901 channel model.Additionally,the proposed instancetransfer-based method outperforms the method without transfer learning in predicting DL parameters when the beamwidth or the communication sector changes.

A progressive approach to predict shot peening process parameters for forming integral panel of Al7050-T7451

In this paper,a progressive approach to predict the multiple shot peening process parameters for complex integral panel is proposed.Firstly,the invariable parameters in the forming process including shot size,mass flow,peening distance and peening angle are determined according to the empirical and machine type.Then,the optimal value of air pressure for the whole shot peening is selected by the experimental data.Finally,the feeding speed for every shot peening path is predicted by regression equation.The integral panel part with thickness from 2 mm to 5 mm and curvature radius from 3200 mm to 16000 mm is taken as a research object,and four experiments are conducted.In order to design specimens for acquiring the forming data,one experiment is conducted to compare the curvature radius of the plate and stringer-structural specimens,which were peened along the middle of the two stringers.The most striking finding of this experiment is that the outer shape error range is below 3.9%,so the plate specimens can be used in predicting feeding speed of the integral panel.The second experiment is performed and results show that when the coverage reaches the limit of 80%,the minimum feeding speed is 50 mm/s.By this feeding speed,the forming curvature radius of the specimens with different thickness from the third experiment is measured and compared with the research object,and the optimal air pressure is 0.15 MPa.Then,the plate specimens with thickness from 2 mm to 5 mm are peened in the fourth experiment,and the measured curvature radius data are used to calculate the feeding speed of different shot peening path by regressive analysis method.The algorithm is validated by forming a test part and the average deviation is 0.496 mm.It is shown that the approach can realize the forming of the integral panel precisely.

Estimation of boundary parameters and prediction of transmission loss based upon ray acoustics

Estimation of boundary parameters and prediction of transmission loss using a coherent channel model based upon ray acoustics and sound propagation data collected in field experiments are presented. Comparison between the prediction results and the experiment data indicates that the adopted sound propagation model is valuable, both selection and estimation methods on boundary parameters are reasonable, and the prediction performance of transmission loss is favorable.

Research on predicting prosodic parameters for Chinese synthesis by data mining approach

Prosodic control is an important part of speech synthesis system. Prosodic parameters choice right or wrong influences the quality of synthetic speech directly. At present, text to speech system has less effective describe to reflect data relationships in the corpus. A new research approach - data mining technology to discover those relationships by association rules modeling is presented. And a new algorithm for generating association rules of prosodic parameters including pitch parameters and duration parameters from corpus is developed. The output rules improve the correctness of syllable choice in text to speech system.

A novel method to eliminate the bending-induced collapse of hexagonal honeycomb

A novel grooving method for eliminating the bending-induced collapse of hexagonal honeycombs has been proposed,which lies in determining the appropriate grooving parameters,including the grooving spacing,angle,and depth.To this end,a framework built upon the experiment-based,machine learning approach for grooving parameters prediction was presented.The continuously grooved honeycomb bending experiments with various radii,honeycomb types,and thicknesses were carried out,and then the deformation level of honeycombs at different grooving spacing was quantitatively evaluated.A criterion for determining the grooving spacing was proposed by setting an appropriate tolerance for the out-of-plane compression strength.It was found that as the curvature increases,the grooving spacing increases due to the deformation level of honeycombs being more severe at a smaller bending radius.Besides,the grooving spacing drops as the honeycomb thickness increases,and the cell size has a positive effect on the grooving spacing,while the relative density has a negative effect on the grooving spacing.Furthermore,the data-driven Gaussian Process(GP)was trained from the collected data to predict the grooving spacing efficiently.The grooving angle and depth were calculated using the geometrical relationship of honeycombs before and after bending.Finally,the grooving parameters design and verification of a honeycomb sandwich fairing part were conducted based on the proposed grooving method.

Design Methods and Strategies for Forward and Inverse Problems of Turbine Blades Based on Machine Learning

To study the feasibility of using machine learning technology to solve the forward problem(prediction of aerodynamic parameters)and the inverse problem(prediction of geometric parameters)of turbine blades,this paper built a forward problem model based on backpropagation artificial neural networks(BP-ANNs)and an inverse problem model based on radial basis function artificial neural networks(RBF-ANNs).The S2(a stream surface obtained by extending a radial curve in turbo blades)calculation program was used to generate the dataset for single-stage turbo blades,and the back propagation algorithm was used to train the model.The parameters of five blade sections in a single-stage turbine were selected as inputs of the forward problem model,including stagger angle,inlet geometric angle,outlet geometric angle,wedge angle of leading edge pressure side,wedge angle of leading edge suction side,wedge angle of trailing edge,rear bending angle,and leading edge diameter.The outputs are efficiency,power,mass flow,relative exit Mach number,absolute exit Mach number,relative exit flow angle,absolute exit flow angle and reaction degree,which are eight aerodynamic parameters.The inputs and outputs of the inverse problem model are the opposite of that of the forward problem model.The models can accurately predict the aerodynamic parameters and geometric parameters,and the mean square errors(MSEs)of the forward problem test set and the inverse problem test set are 0.001 and 0.00035,respectively.This study shows that machine learning technology based on neural networks can be flexibly applied to the design of forward and inverse problems of turbine blades,and the models built by this method have practical application value in regression prediction problems.

Improvement of the ANFIS-based wave predictor models by the Particle Swarm Optimization

In this paper,the Particle Swarm Optimization(PSO)algorithm is employed to deal with the Adaptive Network based Fuzzy Inference System(ANFIS)model drawbacks in prediction of wind-driven waves.In the ANFIS model selection of fuzzy IF-THEN rules structure and numbers is not an automatic process.In addition,in the ANFIS model extraction of fuzzy antecedent and consequent parameters is a gradient-based method which makes the answer susceptible to entrap in local optima.To cope with the ANFIS deficiencies,herein the PSO algorithm is coupled with the wave predictor FIS models in three viewpoints to optimize fuzzy subtractive clustering parameters,i.e.radii of clustering and quash factor,and the antecedent and consequent parameter of fuzzy IF-THEN rules.At first viewpoint,two PSO algorithms are used to optimize fuzzy subtractive clustering parameters and fuzzy IF-THEN rule parameters.In the second viewpoint,a PSO algorithm is used to optimize subtractive clustering parameters while the ANFIS model is used to tune the fuzzy IF-THEN rule parameters.In the third viewpoint,only a PSO algorithm is used to optimize the subtractive clustering parameters along with fuzzy IF-THEN rule parameters.Gathered data sets by National Data Buoy Center(NDBC)at Lake Michigan are used to evaluate the developed models for prediction of wave parameters including significant wave height and peak spectral period.Results indicate the efficiency of PSO algorithm to improve the ANFIS model accuracy.

Multiaxial fatigue life prediction of composite materials

In order to analyze the stress and strain fields in the fibers and the matrix in composite materials,a fiber-scale unit cell model is established and the corresponding periodical boundary conditions are introduced.Assuming matrix cracking as the failure mode of composite materials,an energy-based fatigue damage parameter and a multiaxial fatigue life prediction method are established.This method only needs the material properties of the fibers and the matrix to be known.After the relationship between the fatigue damage parameter and the fatigue life under any arbitrary test condition is established,the multiaxial fatigue life under any other load condition can be predicted.The proposed method has been verified using two different kinds of load forms.One is unidirectional laminates subjected to cyclic off-axis loading,and the other is filament wound composites subjected to cyclic tension-torsion loading.The fatigue lives predicted using the proposed model are in good agreements with the experimental results for both kinds of load forms.