Crushing behavior of laterally compressed composite elliptical tubes: Experiments and predictions using artificial neural networks

Composite materials have been increasingly used in the automobile industry for weight saving and part integration purposes. In this regard, composite elliptical tubes have been effectively employed as energy absorber devices. This increases the need for accurate and simple prediction techniques to optimize these structures.

The present work deals with the implementation of artificial neural networks (ANN) technique in the prediction of the crushing behavior and energy absorption characteristics of laterally loaded glass fiber/epoxy composite elliptical tubes. Predicted results are compared with actual experimental data in terms of load carrying capacity and energy absorption capability showing good agreement. This shows that ANN techniques could effectively be used to predict the response of collapsible composite energy absorber devices subjected to different loading conditions. As is the case for experimental findings, the predictions obtained using ANN also show the significant effect of the ellipticity ratio on the crushing behavior of laterally loaded tubes.     

Reliability analysis of laminated composite structures using finite elements and neural networks

Saving of computer processing time on the reliability analysis of laminated composite structures using artificial neural networks is the main objective of this work. This subject is particularly important when the reliability index is a constraint in the optimization of structural performance, because the task of looking for an optimum structural design demands also a very high processing time. Reliability methods, such as Standard Monte Carlo (SMC), Monte Carlo with Importance Sampling (MC–IS), First Order Reliability Method (FORM) and FORM with Multiple Check Points (FORM–MCPs) are used to compare the solution and the processing time when the Finite Element Method (FEM) is employed and when the finite element analysis (FEA) is substituted by trained artificial neural networks (ANNs). Two ANN are used here: the Multilayer Perceptron Network (MPN) and the Radial Basis Network (RBN). Several examples are presented, including a shell with geometrically non-linear behavior, which shows the advantages using this methodology.     

Fatigue life prediction of composite laminates by FEA simulation method

This paper is to simulate the fatigue damage evolution in composite laminates and predict fatigue life of the laminates with different lay-up sequences on the basis of the fatigue characteristics of longitudinal, transverse and in-plane shear directions by finite element analysis (FEA) method. In FEA model, considering the scatter of the material’s properties, each element was assigned with different material’s properties. The stress analysis was carried out in MSC Patran/Nastran, and a modified Hashin’s failure criterion was applied to predict the failure of the elements. A new stiffness degradation model was proposed and applied in the simulation and then a strength degradation model was deduced, which is coupled with the presented stiffness degradation model. The reduced or discounted elastic constants were determined based on the failure mechanism of the laminates and the restrictive conditions of orthotropic property. The fatigue behavior and fatigue life of six kinds of E-glass/epoxy composite laminates with different lay-up sequences were experimentally studied, and the S–N curves and stiffness degradation models in longitudinal, transverse and in-plane shear direction were obtained. These fatigue data were adopted in the simulation to simulate fatigue behavior and estimate life of the laminates. The simulation results, including the fatigue life predicted and the residual stiffness, were coincident with the experimental results well except for the quasi-isotropic laminate for the lack of consideration of the out-of-plane fatigue character in the simulation.     

Fatigue life prediction of carbon/epoxy laminates by stochastic numerical simulation

A three dimensional (3D) finite element model is developed to predict the progressive fatigue damage and the life of a plain carbon/epoxy laminate (AS4/3501-6) based on the longitudinal, transverse and in-plane shear fatigue characteristic. The model takes into account stress analysis, fatigue failure analysis, random distribution and material property degradation. Different cross- and angle-ply laminates including [0₈], [90₈], [0/90₂]_s, [0/90₄]_s, [0₂/90₂]_s, [30₁₆], [45/−45]_2s with the available experimental data are considered for the fatigue life simulation. In order to consider the random distribution of the laminate’s properties from element to element in the model, the laminate’s stiffness, and strength are randomly generated using a Gaussian distribution function. Sudden and gradual material properties degradation are considered during the fatigue simulation. The progressive fatigue damage and failure analysis is implemented in ABAQUS through user subroutines UMAT (user-defined material) and USDFLD (user-defined field variables). The predicted fatigue life of the simulation for different laminates is in good agreement with the experimental results.     

Water distribution under trickle irrigation predicted using artificial neural networks

An artificial neural network (ANN) technology is presented as an alternative to physical-based modeling of subsurface water distribution from trickle emitters. Three options are explored to prepare input–output functional relations from a database created using a numerical model (HYDRUS-2D). From the database the feasibility and advantages of the three alternative options are evaluated: water-content at defined coordinates, moment analysis describing the shape of the plume, and coordinates of individual water-content contours. The best option is determined in a way by the application objectives, but results suggest that prediction using moment analyses is probably the most versatile and robust and gives an adequate picture of the subsurface distribution. Of the other two options, the direct determination of the individual water contours was subjectively judged to be more successful than predicting the water content at given coordinates, at least in terms of describing the subsurface distribution. The results can be used to estimate subsurface water distribution for essentially any soil properties, initial conditions or flow rates for trickle sources.     

Residual strength prediction of composite materials: Random spectrum loading

The goal of this project is to identify if and how load order impacts residual strength in an E-glass/vinyl ester composite laminate subjected to variable amplitude fatigue loading. This paper presents results for constant amplitude loading data which, are used to fit parameters for a phenomenological model that can then applied to the spectrum loading cases. The residual strength distribution shape, in addition to median values, is modeled using Weibull statistics. Three cases are run experimentally and modeled for a 735,641 cycle spectrum containing 22 stress levels. The first two are ordered block loading, from highest stress to lowest and from lowest stress to the highest. In both cases, the model predicts the resulting residual strength distribution very accurately. A final case where the entire spectrum was randomized produced unexpected results with every specimen failing after 200,000-400,000 cycles while the model predicts identical residual strength when compared with the block loading case. This work points to a dire need for focus on developing a better understanding of load order impacts in design of composite structures based on constant amplitude fatigue tests.     

Computational homogenization of nonlinear elastic materials using neural networks

In this work, a decoupled computational homogenization method for nonlinear elastic materials is proposed using neural networks. In this method, the effective potential is represented as a response surface parameterized by the macroscopic strains and some microstructural parameters. The discrete values of the effective potential are computed by finite element method through random sampling in the parameter space, and neural networks are used to approximate the surface response and to derive the macroscopic stress and tangent tensor components. We show through several numerical convergence analyses that smooth functions can be efficiently evaluated in parameter spaces with dimension up to 10, allowing to consider three‐dimensional representative volume elements and an explicit dependence of the effective behavior on microstructural parameters like volume fraction. We present several applications of this technique to the homogenization of nonlinear elastic composites, involving a two‐scale example of heterogeneous structure with graded nonlinear properties. Copyright © 2015 John Wiley & Sons, Ltd.     

Efficiency parameters estimation in gemstones cut design using artificial neural networks

This paper deals with the problem of estimating cut results for faceted gemstones. The proposed approach applies artificial neural networks for a faceted gemstones analysis tool that could be further developed for incorporation in a computer-aided-design (CAD) context. Basic concepts concerning gemstone processing are introduced and the design of computational tools using neural networks is discussed. The model presented proposes two criteria to assess the efficiency of lapidary designs for rock crystal quartz: brilliance and yield. Closing the article, 62 different lapidary models were used to train and test the neural network tool.     

Robust recurrent neural network modeling for software fault detection and correction prediction

Software fault detection and correction processes are related although different, and they should be studied together. A practical approach is to apply software reliability growth models to model fault detection, and fault correction process is assumed to be a delayed process. On the other hand, the artificial neural networks model, as a data-driven approach, tries to model these two processes together with no assumptions. Specifically, feedforward backpropagation networks have shown their advantages over analytical models in fault number predictions. In this paper, the following approach is explored. First, recurrent neural networks are applied to model these two processes together. Within this framework, a systematic networks configuration approach is developed with genetic algorithm according to the prediction performance. In order to provide robust predictions, an extra factor characterizing the dispersion of prediction repetitions is incorporated into the performance function. Comparisons with feedforward neural networks and analytical models are developed with respect to a real data set.     

Prediction of fatigue life for spot welds using back-propagation neural networks

In this research, the authors developed back-propagation neural networks (BNNs) to predict the fatigue life of spot welds subjected to various geometric factors and loading conditions. This paper described the developing procedures of the BNNs in detail for the spot weld fatigue. Then, the BNNs developed in this study were employed to predict the fatigue life of the spot welds subjected to combined tension and shear loading and tensile-shear loading. The BNNs showed reasonable accuracy for the cases tested in this study. The BNNs can be employed as a practical method for calculating fatigue life of spot welds under various geometric dimensions and loading conditions.     

Prediction of FRP-confined compressive strength of concrete using artificial neural networks

Strengthening and retrofitting of concrete columns by wrapping and bonding FRP sheets has become an efficient technique in recent years. Considerable investigations have been carried out in the field of FRP-confined concrete and there are many proposed models that predict the compressive strength which are developed empirically by either doing regression analysis using existing test data or by a development based on the theory of plasticity. In the present study, a new approach is developed to obtain the FRP-confined compressive strength of concrete using a large number of experimental data by applying artificial neural networks. Having parameters used as input nodes in ANN modeling such as characteristics of concrete and FRP, the output node was FRP-confined compressive strength of concrete. The idealized neural network was employed to generate empirical charts and equations for use in design. The comparison of the new approach with existing empirical and experimental data shows good precision and accuracy of the developed ANN-based model in predicting the FRP-confined compressive strength of concrete.     

Fatigue life prediction of magnetorheological elastomers subjected to dynamic equi-biaxial cyclic loading

Prediction of fatigue life is of great significance in ensuring that dynamically loaded rubber components exhibit safety and reliability in service. In this text, the dynamic equi-biaxial fatigue behaviour of magnetorheological elastomer (MREs) using a bubble inflation method is described. Wöhler (S–N) curves for both isotropic and anisotropic MREs were produced by subjecting the compounds to cycling over a range of stress amplitudes (σ_a) between 0.75 MPa and 1.4 MPa. Changes in physical properties, including variation in stress–strain relations and complex modulus (E*) during the fatigue process were analysed. It was found that the complex modulus of MRE samples decreased throughout the entire fatigue test and failure took place at a limiting value of approximately 1.228MPa ± 4.38% for isotropic MREs and 1.295 ± 10.33% for anisotropic MREs. It was also determined that a dynamic stored energy criterion can be used as a plausible predictor in determining the fatigue life of MREs.     

Fatigue life prediction of cracked attachment lugs using XFEM

In the present paper, a three dimensional finite element method (FEM) is used to compute the stress intensity factor (SIF) in straight lugs of Aluminum 7075-T6. Extended finite element method (XFEM) capability available in ABAQUS is used to calculate the stress intensity factor. Crack growth and fatigue life of single through-thickness and single quarter elliptical corner cracks in attachment lug are estimated and then compared with the available experimental data for two different load ratios equal to 0.1 and 0.5. The SIF calculated from XFEM shows that the introduction of different loading boundary conditions significantly affect the estimated fatigue life.     

Fatigue and fracture analysis of aluminum plate with composite patches under the hygrothermal effect

In this paper, fatigue life of the repaired cracks in 2024-T 3 aluminum with bonded patches made of unidirectional composite plates has been investigated experimentally and numerically for hygrothermal effect. The problem is handled in plane stress and Mode I condition. In the experimental study the mechanical properties of the aluminum plate and patch materials are determined and fatigue experiments are conducted. The results obtained from these experiments and numerical solutions are compared. Thus the reliability of the numerical solution has been proven. For all conditions, numerical solutions have been made and stress intensity factor (K_I) and fatigue life are calculated. Different plate and patch thicknesses are also considered in the experiments.     

Probabilistic analysis of concrete cracking using neural networks and random fields

In this paper an algorithm for the probabilistic analysis of concrete structures is proposed which considers material uncertainties and failure due to cracking. The fluctuations of the material parameters are modeled by means of random fields and the cracking process is represented by a discrete approach using a coupled meshless and finite element discretization. In order to analyze the complex behavior of these nonlinear systems with low numerical costs a neural network approximation of the performance functions is realized. As neural network input parameters the important random variables of the random field in the uncorrelated Gaussian space are used and the output values are the interesting response quantities such as deformation and load capacities. The neural network approximation is based on a stochastic training which uses wide spanned Latin hypercube sampling to generate the training samples. This ensures a high quality approximation over the whole domain investigated, even in regions with very small probability.     

人工神经网络在材料科学中的应用与展望

人工神经网络因其具有较强的非线性问题处理能力且容错性强而在材料科学中得到广泛的应用.本文对其在材料设计、材料制备工艺优化、塑性加工、热处理等领域的应用进行了探讨,并对其发展前景进行了展望.     

Design of artificial neural networks using a genetic algorithm to predict collection efficiency in venturi scrubbers

In this study, a new approach for the auto-design of neural networks, based on a genetic algorithm (GA), has been used to predict collection efficiency in venturi scrubbers. The experimental input data, including particle diameter, throat gas velocity, liquid to gas flow rate ratio, throat hydraulic diameter, pressure drop across the venturi scrubber and collection efficiency as an output, have been used to create a GA-artificial neural network (ANN) model. The testing results from the model are in good agreement with the experimental data. Comparison of the results of the GA optimized ANN model with the results from the trial-and-error calibrated ANN model indicates that the GA-ANN model is more efficient. Finally, the effects of operating parameters such as liquid to gas flow rate ratio, throat gas velocity, and particle diameter on collection efficiency were determined.     

Fatigue life prediction of copper single crystals using a critical plane approach

A critical plane multiaxial fatigue criterion was employed to predict the fatigue life of copper single crystals. The detailed stress-strain response was obtained through the constitutive modeling using a newly developed crystal plasticity theory. The constitutive model was capable of capturing the major deformation features of copper single crystals under cyclic loading including the cyclic stress-strain curves, cyclic hardening behavior, and the evolution of the hysteresis loops with increasing number of loading cycles. Fatigue life prediction of the single crystal copper was conducted based upon the stress-strain response obtained from the cyclic plasticity model. The fatigue criterion takes into account the plastic strain localization within a single crystal. The critical plane (cracking plane) was identified as the material plane where the fatigue damage accumulation first reached a critical value. For copper single crystals with the crystal orientations being within the standard crystallographic triangle, the fatigue criterion can predict both fatigue life and cracking direction consistent with the experimental observations. More importantly, the constants used in the fatigue criterion were found to be identical to those used for the pure polycrystalline copper with different grain sizes and texture.     

Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks

Understanding the circumstances under which drivers and passengers are more likely to be killed or more severely injured in an automobile accident can help improve the overall driving safety situation. Factors that affect the risk of increased injury of occupants in the event of an automotive accident include demographic or behavioral characteristics of the person, environmental factors and roadway conditions at the time of the accident occurrence, technical characteristics of the vehicle itself, among others. This study uses a series of artificial neural networks to model the potentially non-linear relationships between the injury severity levels and crash-related factors. It then conducts sensitivity analysis on the trained neural network models to identify the prioritized importance of crash-related factors as they apply to different injury severity levels. In the process, the problem of five-class prediction is decomposed into a set of binary prediction models (using a nationally representative sample of 30358 police-recorded crash reports) in order to obtain the granularity of information needed to identify the "true" cause and effect relationships between the crash-related factors and different levels of injury severity. The results, mostly validated by the findings of previous studies, provide insight into the changing importance of crash factors with the changing injury severity levels.