In silico optimization of actuation performance in dielectric elastomercomposites via integrated finite element modeling and deep learning

Dielectric elastomers(DEs)require balanced electric actuation performance and mechanical integrity under applied voltages.Incorporating high dielectric particles as fillers provides extensive design space to optimize concentration,morphology,and distribution for improved actuation performance and material modulus.This study presents an integrated framework combining finite element modeling(FEM)and deep learning to optimize the microstructure of DE composites.FEM first calculates actuation performance and the effective modulus across varied filler combinations,with these data used to train a convolutional neural network(CNN).Integrating the CNN into a multi-objective genetic algorithm generates designs with enhanced actuation performance and material modulus compared to the conventional optimization approach based on FEM approach within the same time.This framework harnesses artificial intelligence to navigate vast design possibilities,enabling optimized microstructures for high-performance DE composites.

Big Model Strategy for Bridge Structural Health Monitoring Based on Data-Driven, Adaptive Method and Convolutional Neural Network (CNN) Group

This study introduces an innovative“Big Model”strategy to enhance Bridge Structural Health Monitoring(SHM)using a Convolutional Neural Network(CNN),time-frequency analysis,and fine element analysis.Leveraging ensemble methods,collaborative learning,and distributed computing,the approach effectively manages the complexity and scale of large-scale bridge data.The CNN employs transfer learning,fine-tuning,and continuous monitoring to optimize models for adaptive and accurate structural health assessments,focusing on extracting meaningful features through time-frequency analysis.By integrating Finite Element Analysis,time-frequency analysis,and CNNs,the strategy provides a comprehensive understanding of bridge health.Utilizing diverse sensor data,sophisticated feature extraction,and advanced CNN architecture,the model is optimized through rigorous preprocessing and hyperparameter tuning.This approach significantly enhances the ability to make accurate predictions,monitor structural health,and support proactive maintenance practices,thereby ensuring the safety and longevity of critical infrastructure.

Determination of penetration depth at high velocity impact using finite element method and artificial neural network tools

Determination of ballistic performance of an armor solution is a complicated task and evolved significantly with the application of finite element methods(FEM) in this research field.The traditional armor design studies performed with FEM requires sophisticated procedures and intensive computational effort,therefore simpler and accurate numerical approaches are always worthwhile to decrease armor development time.This study aims to apply a hybrid method using FEM simulation and artificial neural network(ANN) analysis to approximate ballistic limit thickness for armor steels.To achieve this objective,a predictive model based on the artificial neural networks is developed to determine ballistic resistance of high hardness armor steels against 7.62 mm armor piercing ammunition.In this methodology,the FEM simulations are used to create training cases for Multilayer Perceptron(MLP) three layer networks.In order to validate FE simulation methodology,ballistic shot tests on 20 mm thickness target were performed according to standard Stanag 4569.Afterwards,the successfully trained ANN(s) is used to predict the ballistic limit thickness of 500 HB high hardness steel armor.Results show that even with limited number of data,FEM-ANN approach can be used to predict ballistic penetration depth with adequate accuracy.

Neural network method for solving elastoplastic finite element problems

A basic optimization principle of Artificial Neural Network—the Lagrange Programming Neural Network (LPNN) model for solving elastoplastic finite element problems is presented. The nonlinear problems of mechanics are represented as a neural network based optimization problem by adopting the nonlinear function as nerve cell transfer function. Finally, two simple elastoplastic problems are numerically simulated. LPNN optimization results for elastoplastic problem are found to be comparable to traditional Hopfield neural network optimization model.

Development of a Methodology for Determination and Analysis of Thermal Displacements of Machine Tools Using Finite Elements Method and Artificial Neural Network

In the processes of manufacturing, MT （machine tools） plays an important role in the manufacture of work pieces with complex and high dimensional and geometric accuracy. Much of the errors of a machine tool are those which are thermally induced which are from internal and external heat sources acting on the machine. In this paper, a methodology for determining and analyzing the thermal deformation of machine tools using FEM （finite element method） and ANN （artificial neural networks） is presented. After modeling the machine using FEM is defined the location of the heat sources, it is possible to obtain the temperature gradient and the corresponding thermal deformation at predetermined periods. Results obtained with simulations using the software NX.7.5 showed that this methodology is an effective tool in determining the thermal deformation of the machine, correlating the temperature reading at strategic points with volumetric deformation at the tool tip. Therefore, the thermal analysis of the errors in the pair tool part can be established. After training and validation process, the network will be able to make the prediction of thermal errors just stating the temperature values of specific points of each heat source, providing a way for compensation of thermally induced errors.

Numerical Study of the Biomechanical Behavior of a 3D Printed Polymer Esophageal Stent in the Esophagus by BP Neural Network Algorithm

Esophageal disease is a common disorder of the digestive system that can severely affect the quality of life andprognosis of patients. Esophageal stenting is an effective treatment that has been widely used in clinical practice.However, esophageal stents of different types and parameters have varying adaptability and effectiveness forpatients, and they need to be individually selected according to the patient’s specific situation. The purposeof this study was to provide a reference for clinical doctors to choose suitable esophageal stents. We used 3Dprinting technology to fabricate esophageal stents with different ratios of thermoplastic polyurethane (TPU)/(Poly-ε-caprolactone) PCL polymer, and established an artificial neural network model that could predict the radial forceof esophageal stents based on the content of TPU, PCL and print parameter. We selected three optimal ratios formechanical performance tests and evaluated the biomechanical effects of different ratios of stents on esophagealimplantation, swallowing, and stent migration processes through finite element numerical simulation and in vitrosimulation tests. The results showed that different ratios of polymer stents had different mechanical properties,affecting the effectiveness of stent expansion treatment and the possibility of postoperative complications of stentimplantation.

AN UPDATING METHOD FOR LOCAL MODEL ERRORS

The location of model errors in a stiffness matrix by using test data has been investigated by the others.The present paper deals with the problem of updating stiffness elements in the erroneous areas. Firstly,a model that bears relation to erroneous elements only is derived.This model is termed local errors model,which reduces orders and computational loads compared with global stiffness matrix. Secondly,an inverse eigenvalue method is used to update model errors. The results of a numerical experiment demonstrate that the method is quite effective.

Aero-engine Blade Fatigue Analysis Based on Nonlinear Continuum Damage Model Using Neural Networks

Fatigue life and reliability of aero-engine blade are always of important significance to flight safety.The establishment of damage model is one of the key factors in blade fatigue research.Conventional linear Miner＇s sum method is not suitable for aero-engine because of its low accuracy.A back propagation neutral network（BPNN） based on the combination of Levenberg-Marquardt（LM） and finite element method（FEM） is used to describe process of nonlinear damage accumulation behavior in material and predict fatigue life of the blade.Fatigue tests of standard specimen made from TC4 are carried out to obtain material fatigue parameters and S-N curve.A nonlinear continuum damage model（CDM）,based on the BPNN with one hidden layer and ten neurons,is built to investigate the nonlinear damage accumulation behavior,in which the results from the tests are used as training set.Comparing with linear models and previous nonlinear models,BPNN has the lowest calculation error in full load range.It has significant accuracy when the load is below 500 MPa.Especially,when the load is 350 MPa,the calculation error of the BPNN is only 0.4%.The accurate model of the blade is built by using 3D coordinate measurement technology.The loading cycle in fatigue analysis is defined from takeoff to cruise in 10 min,and the load history is obtained from finite element analysis（FEA）.Then the fatigue life of the compressor blade is predicted by using the BPNN model.The final fatigue life of the aero-engine blade is 6.55 104 cycles（10 916 h） based on the BPNN model,which is effective for the virtual design of aero-engine blade.

Calculation method of ship collision force on bridge using artificial neural network

Ship collision on bridge is a dynamic process featured by high nonlinearity and instantaneity. Calculating ship-bridge collision force typically involves either the use of design-specification-stipulated equivalent static load, or the use of finite element method (FEM) which is more time-consuming and requires supercomputing resources. In this paper, we proposed an alternative approach that combines FEM with artificial neural network (ANN). The radial basis function neural network (RBFNN) employed for calculating the impact force in consideration of ship-bridge collision mechanics. With ship velocity and mass as the input vectors and ship collision force as the output vector, the neural networks for different network parameters are trained by the learning samples obtained from finite element simulation results. The error analyses of the learning and testing samples show that the proposed RBFNN is accurate enough to calculate ship-bridge collision force. The input-output relationship obtained by the RBFNN is essentially consistent with the typical empirical formulae. Finally, a special toolbox is developed for calculation efficiency in application using MATLAB software.

An Artificial Neural Network-Based Response Surface Method for Reliability Analyses of c-φ Slopes with Spatially Variable Soil

This paper presents an artificial neural network（ANN）-based response surface method that can be used to predict the failure probability of c-φslopes with spatially variable soil.In this method,the Latin hypercube sampling technique is adopted to generate input datasets for establishing an ANN model;the random finite element method is then utilized to calculate the corresponding output datasets considering the spatial variability of soil properties;and finally,an ANN model is trained to construct the response surface of failure probability and obtain an approximate function that incorporates the relevant variables.The results of the illustrated example indicate that the proposed method provides credible and accurate estimations of failure probability.As a result,the obtained approximate function can be used as an alternative to the specific analysis process in c-φslope reliability analyses.

Finite element model updating of a tied-arch bridge using Douglas-Reid method and Rosenbrock optimization algorithm

Condition assessment of bridges has become increasingly important. In order to accurately simulate the real bridge, finite element （FE） model updating method is often applied. This paper presents the calibration of the FE model of a reinforced concrete tied-arch bridge using Douglas-Reid method in combination with Rosenbrock optimization algorithm. Based on original drawings and topographic survey, a FE model of the investigated bridge is created. Eight global modes of vibration of the bridge are identified by ambient vibration tests and the frequency domain decomposition technique. Then, eight structural parameters are selected for FE model updating procedure through sensitivity analysis. Finally, the optimal structural parameters are identified using Rosenbrock optimization algorithm. Results show that although the identified parameters lead to a perfect agreement between approximate and measured natural frequencies, they may not be the optimal variables which minimize the differences between numerical and experimental modal data. However, a satisfied agreement between them is still presented. Hence, FE model updating based on Douglas-Reid method and Rosenbrock optimization algorithm could be used as an alternative to other complex updating procedures.

Finite element model updating of a rod-type ultrasonicmotor based on response surface method

The conventional finite element model （FEM） of a rod-type ultrasonic motor is usually simplified by means of continuous composite structure. Because the actual contact characteristics between the parts of the ultrasonic motor is ignored, there is bigger error between the calculated values and experimental results. Aiming at solving problem, a new modeling method of a rod-type ultrasonic motor is presented to obtain a high-accuracy FEM. The bolt pretension and the normal contact stiffness and friction coefficient of the contact surface of ultrasonic motor are all considered in this method, and the significant parameters of working mode of the motor are selected by the response surface method, and the goal of calculating the structural response rapidly is realized by building the response surface model to replace the FEM. The result of finite element model updating shows that the average error of modal frequencies of updated model drops to 0.21% from 1.20%. The accuracy of FEM is obviously improved, which indicates that the FEM updating based on response surface method is of great application value on the design for a rod-type ultrasonic motor.

An Improved Model Updating Method of Reduced-Models for Finite Element Model

Most of exiting model updating methods based on the substructure matrices did not consider the effect of model reduction process on model updating which led to the updating results could not become more and more accurate with the improvement of the model reduction precision and the convergence rate was greatly reduced.In order to solve this problem,this paper analyses the basic reason about this problem,and proposes an improved model updating method of reduced-models,named as improved reduced cross-model cross-mode(IRCMCM) method.The proposed method eliminates the disadvantageous effect by adding a correction term to the model updating formula and employing an iterative process.The results obtained by the referenced method and IRCMCM method are compared by numerical examples of satellite's plates,which indicate the model updating results are more accurate by using the proposed method,and the model updating precision becomes better with the precision of the model reduction upgraded and the convergence rate is improved to a large extent at the same time.

A deep neural network based surrogate model for damage identification in full-scale structures with incomplete noisy measurements

The paper introduces a novel approach for detecting structural damage in full-scale structures using surrogate models generated from incomplete modal data and deep neural networks(DNNs).A significant challenge in this field is the limited availability of measurement data for full-scale structures,which is addressed in this paper by generating data sets using a reduced finite element(FE)model constructed by SAP2000 software and the MATLAB programming loop.The surrogate models are trained using response data obtained from the monitored structure through a limited number of measurement devices.The proposed approach involves training a single surrogate model that can quickly predict the location and severity of damage for all potential scenarios.To achieve the most generalized surrogate model,the study explores different types of layers and hyperparameters of the training algorithm and employs state-of-the-art techniques to avoid overfitting and to accelerate the training process.The approach’s effectiveness,efficiency,and applicability are demonstrated by two numerical examples.The study also verifies the robustness of the proposed approach on data sets with sparse and noisy measured data.Overall,the proposed approach is a promising alternative to traditional approaches that rely on FE model updating and optimization algorithms,which can be computationally intensive.This approach also shows potential for broader applications in structural damage detection.

A Quantitative Seismic Topographic Effect Prediction Method Based upon BP Neural Network Algorithm and FEM Simulation

Topography can strongly affect ground motion,and studies of the quantification of hill surfaces’topographic effect are relatively rare.In this paper,a new quantitative seismic topographic effect prediction method based upon the BP neural network algorithm and three-dimensional finite element method(FEM)was developed.The FEM simulation results were compared with seismic records and the results show that the PGA and response spectra have a tendency to increase with increasing elevation,but the correlation between PGA amplification factors and slope is not obvious for low hills.New BP neural network models were established for the prediction of amplification factors of PGA and response spectra.Two kinds of input variables’combinations which are convenient to achieve are proposed in this paper for the prediction of amplification factors of PGA and response spectra,respectively.The absolute values of prediction errors can be mostly within 0.1 for PGA amplification factors,and they can be mostly within 0.2 for response spectra’s amplification factors.One input variables’combination can achieve better prediction performance while the other one has better expandability of the predictive region.Particularly,the BP models only employ one hidden layer with about a hundred nodes,which makes it efficient for training.

Assessment of bearing capacity of interfering strip footings located near sloping surface considering artificial neural network technique

The bearing capacity of interfering footings located near the slope face suffers from reduced bearing capacity due to the formation of the curtailed passive zone. Depending upon the position of the footing, their spacing and steepness of the slope different extents of bearing capacity reduction can be exhibited. A series of finite element investigation has been done with the aid of Plaxis 3 D v AE.01 to elucidate the influence of various geotechnical and geometrical parameters on the ultimate bearing capacity of interfering surface strip footings located at the crest of the natural soil slope. Based on the large database obtained from the numerical simulation, a6-8-1 Artificial Neural Network architecture has been considered for the assessment of the ultimate bearing capacity of interfering strip footings placed on the crest of natural soil slope. Sensitivity analyses have been conducted to establish the relative significance of the contributory parameters, which exhibited that for the stated problem, apart from shear strength parameters, the setback ratio and spacing of footing are the prime contributory parameters.

RELU DEEP NEURAL NETWORKS AND LINEAR FINITE ELEMENTS

In this paper,we investigate the relationship between deep neural net works(DNN)with rectified linear unit(ReLU)function as the activation function and continuous piecewise linear(CPWL)functions,especially CPWL functions from the simplicial linear finite element method(FEM).We first consider the special case of FEM.By exploring the DNN representation of its nodal basis functions,we present a ReLU DNN representation of CPWL in FEM.We theoretically establish that at least 2 hidden layers are needed in a ReLU DNN to represent any linear finite element functions inΩ■R^2 when d≥2.Consequently,for d=2,3 which are often encountered in scientific and engineering computing,the minimal number of two hidden layers are necessary and sufficient for any CPWL function to be represented by a ReLU DNN.Then we include a detailed account on how a general CPWL in R^d can be represented by a ReLU DNN with at most[log2(d+1)]|hidden layers and we also give an estimation of the number of neurons in DNN that are needed in such a represe ntation.Furthermore,using the relationship bet ween DNN and FEM,we theoretically argue that a special class of DNN models with low bit-width are still expected to have an adequate representation power in applications.Finally,as a proof of concept,we present some numerical results for using ReLU DNNs to solve a two point boundary problem to demonstrate the potential of applying DNN for numerical solution of partial differential equations.

Structural finite element model updating using incomplete ambient vibration modal data

This paper presents an effective approach for updating finite element dynamic model from incomplete modal data identified from ambient vibration measurements.The proposed method is based on the relationship between the perturbation of structural parameters such as stiffness and mass changes and the modal data measurements of the tested structure such as measured mode shape readings.Structural updating parameters including both stiffness and mass parameters are employed to represent the differences in structural parameters between the finite element model and the associated tested structure.These updating parameters are then evaluated by an iterative solution procedure,giving optimised solutions in the least squares sense without requiring an optimisation technique.In order to reduce the influence of modal measurement uncertainty,the truncated singular value decomposition regularization method incorporating the quasi-optimality criterion is employed to produce reliable solutions for the structural updating parameters.Finally,the numerical investigations of a space frame structure and the practical applications to the Canton Tower benchmark problem demonstrate that the proposed method can correctly update the given finite element model using the incomplete modal data identified from the recorded ambient vibration measurements.

A Neural Network Approach to Predicting Car Tyre Micro-Scale and Macro-Scale Behaviour

Finite Element (FE) analysis has become the favoured tool in the tyre industry for virtual development of tyres because of the ability to represent the detailed lay-up of the tyre carcass. However, application of FE analysis in tyre design and development is still very time-consuming and expensive. Here, the application of various Artificial Neural Network (ANN) architectures to predicting tyre performance is assessed to select the most effective and efficient architecture, to allow extensive parametric studies to be carried out inexpensively and to optimise tyre design before a much more expensive full FE analysis is used to confirm the predicted performance.