Utilizing neural networks to supplant chemical kinetics tabulation through mass conservation and weighting of species depletion

Artificial Neural Networks(ANNs)have emerged as a powerful tool in combustion simulations to replace memory-intensive tabulation of integrated chemical kinetics.Complex reaction mechanisms,however,present a challenge for standard ANN approaches as modeling multiple species typically suffers from inaccurate predictions on minor species.This paper presents a novel ANN approach which can be applied on complex reaction mechanisms in tabular data form,and only involves training a single ANN for a complete reaction mechanism.The approach incorporates a network architecture that automatically conserves mass and employs a particular loss weighting based on species depletion.Both modifications are used to improve the overall ANN performance and individual prediction accuracies,especially for minor species mass fractions.To validate its effectiveness,the approach is compared to standard ANNs in terms of performance and ANN complexity.Four distinct reaction mechanisms(H_(2),C_(7)H_(16),C_(12)H_(26),OME_(34))are used as a test cases,and results demonstrate that considerable improvements can be achieved by applying both modifications.

Prediction of nuclear charge density distribution with feedback neural network

Nuclear charge density distribution plays an important role in both nuclear and atomic physics,for which the two-parameter Fermi(2pF)model has been widely applied as one of the most frequently used models.Currently,the feedforward neural network has been employed to study the available 2pF model parameters for 86 nuclei,and the accuracy and precision of the parameter-learning effect are improved by introducing A^(1∕3)into the input parameter of the neural network.Furthermore,the average result of multiple predictions is more reliable than the best result of a single prediction and there is no significant difference between the average result of the density and parameter values for the average charge density distribution.In addition,the 2pF parameters of 284(near)stable nuclei are predicted in this study,which provides a reference for the experiment.

Artificial Neural Network(ANN)Approach for Predicting Concrete Compressive Strength by SonReb

The compressive strength of concrete is one of most important mechanical parameters in the performance assessment of existing reinforced concrete structures.According to various international codes,core samples are drilled and tested to obtain the concrete compressive strengths.Non-destructive testing is an important alternative when destructive testing is not feasible without damaging the structure.The commonly used non-destructive testing(NDT)methods to estimate the in-situ values include the Rebound hammer test and the Ultrasonic Pulse Velocity test.The poor reliability of these tests due to different aspects could be partially contrasted by using both methods together,as proposed.in the SonReb method.There are three techniques that are commonly used to predict the compressive strength of concrete based on the SonReb measurements:computational modeling,artificial intelligence,and parametric multi-variable regression models.In a previous study the accuracy of the correlation formulas deduced from the last technique has been investigated in comparison with the effective compressive strengths based on destructive test results on core drilled in adjacent locations.The aim of this study is to verify the accuracy of Artificial Neural Approach comparing the estimated compressive strengths based on NDT measured parameters with the same effective compressive strengths.The comparisons show the best performance of ANN approach.

Lateral-torsional buckling capacity assessment of web opening steel girders by artificial neural networks- elastic investigation

Bridge girders exposed to aggressive environmental conditions are subject to time-variant changes in resistance. There is therefore a need for evaluation procedures that produce accurate predictions of the load-carrying capacity and reliability of bridge structures to allow rational decisions to be made about repair, rehabilitation and expected life-cycle costs. This study deals with the stability of damaged steel I-beams with web opening subjected to bending loads. A three-dimensional （3D） finite element （FE） model using ABAQUS for the elastic flexural torsional analysis of I-beams has been used to assess the effect of web opening on the lateral buckling moment capacity. Artificial neural network （ANN） approach has been also employed to derive empirical formulae for predicting the lateral-torsional buckling moment capacity of deteriorated steel I-beams with different sizes of rectangular web opening using obtained FE results. It is found out that the proposed formulae can accurately predict residual lateral buckling capacities of doubly-symmetric steel I-beams with rectangular web opening. Hence, the results of this study can be used for better prediction of buckling life of web opening of steel beams by practice engineers.

Magnetic moment predictions of odd-A nuclei with the Bayesian neural network approach

The Bayesian neural network approach has been employed to improve the nuclear magnetic moment predictions of odd-A nuclei.The Schmidt magnetic moment obtained from the extreme single-particle shell model makes large root-mean-square(rms)deviations from data,i.e.,0.949μN and 1.272μN for odd-neutron nuclei and odd-proton nuclei,respectively.By including the dependence of the nuclear spin and Schmidt magnetic moment,the machine-learning approach precisely describes the magnetic moments of odd-A uclei with rms deviations of 0.036μN for odd-neutron nuclei and 0.061μN for odd-proton nuclei.Furthermore,the evolution of magnetic moments along isotopic chains,including the staggering and sudden jump trend,which are difficult to describe using nuclear models,have been well reproduced by the Bayesian neural network(BNN)approach.The magnetic moments of doubly closed-shell±1 nuclei,for example,isoscalar and isovector magnetic moments,have been well studied and compared with the corresponding non-relativistic and relativistic calculations.

Research on a Neural Network Approach Based Diagnosis Expert System of Crack Control in Massive Concrete

A detailed study of the capabilities of artificial neural networks to diagnoses cracks in massive concrete structures is presented. This paper includes the components of the expert system such as design thought, basic structure, building of knowledge base and the implementation of neural network applied model. The realizing method of neural network based clustering algorithm in the knowledge base and self study is analyzed emphatically and stimulated by means of the computer. From the above study, some important conclusions have been drawn and some new viewpoints have been suggested.

A neural network approach based on more input neurons to predict nuclear mass

The study of nuclear mass is very important,and the neural network(NN)approach can be used to improve the prediction of nuclear mass for various models.Considering the number of valence nucleons of protons and neutrons separately in the input quantity of the NN model,the root-mean-square deviation of binding energy between data from AME2016 and liquid drop model calculations for 2314 nuclei was reduced from 2.385 MeV to 0.203 MeV.In addition,some defects in the Weizsacker-Skyrme(WS)-type model were repaired,which well reproduced the two-neutron separation energy of the nucleus synthesized recently by RIKEN RI Beam Factory[Phys.Rev.Lett.125,(2020)122501].The masses of some of the new nuclei appearing in the latest atomic mass evaluation(AME2020)are also well reproduced.However,the results of neural network methods for predicting the description of regions far from known atomic nuclei need to be further improved.This study shows that such a statistical model can be a tool for systematic searching of nuclei beyond existing experimental data.

A MULTISCALE MODELING APPROACH INCORPORATING ARIMA AND ANNS FOR FINANCIAL MARKET VOLATILITY FORECASTING

The financial market volatility forecasting is regarded as a challenging task because of irreg ularity, high fluctuation, and noise. In this study, a multiscale ensemble forecasting model is proposed. The original financial series are decomposed firstly different scale components （i.e., approximation and details） using the maximum overlap discrete wavelet transform （MODWT）. The approximation is pre- dicted by a hybrid forecasting model that combines autoregressive integrated moving average （ARIMA） with feedforward neural network （FNN）. ARIMA model is used to generate a linear forecast, and then FNN is developed as a tool for nonlinear pattern recognition to correct the estimation error in ARIMA forecast. Moreover, details are predicted by Elman neural networks. Three weekly exchange rates data are collected to establish and validate the forecasting model. Empirical results demonstrate consistent better performance of the proposed approach.