Nonlinear constitutive models for FRP composites using artificial neural networks

This paper presents a new approach to generate nonlinear and multi-axial constitutive models for fiber reinforced polymeric (FRP) composites using artificial neural networks (ANNs). The new nonlinear ANN constitutive models are complete and have been integrated with displacement-based FE software for the nonlinear analysis of composite structures. The proposed ANN constitutive models are trained with experimental data obtained from off-axis tension/compression and pure shear (Arcan) tests. The proposed ANN constitutive model is generated for plane–stress states with assumed functional response in some parts of the multi-axial stress space with no experimental data. The ability of the trained ANN models to predict material response is examined directly and through FE analysis of a notched composite plate. The experimental part of this study involved coupon testing of thick-section pultruded FRP E-glass/polyester material. Nonlinear response was pronounced including in the fiber direction due to the relatively low overall fiber volume fraction (FVF). Notched composite plates were also tested to verify the FE, with ANN material models, to predict general non-homogeneous responses at the structural level.     

Homogenisation Metamodelling of Perforated Plates

Abstract:  The use of finite element (FE)-based homogenisation has improved the study of composite material properties. However, it involves enormous computational effort when implemented in engineering design problems. Therefore an artificial neural network (ANN) surrogate model is proposed here to avoid this issue. In this study, a numerical homogenisation code was developed based on a commercial FE package. It is used to develop the ANN metamodel for an individual composite structure. The effectiveness of the metamodel was examined through an analytical optimisation procedure.     

Modular artificial neural network for prediction of petrophysicalproperties from well log data

An application of Kohonen's self-organizing map (SOM), learning-vector quantization (LVQ) algorithms, and commonly used backpropagation neural network (BPNN) to predict petrophysical properties obtained from well-log data are presented. A modular, artificial neural network (ANN) comprising a complex network made up from a number of subnetworks is introduced. In this approach, the SOM algorithm is applied first to classify the well-log data into a predefined number of classes, This gives an indication of the lithology in the well. The classes obtained from SOM are then appended back to the training input logs for the training of supervised LVQ. After training, LVQ can be used to classify any unknown input logs. A set of BPNN that corresponds to different classes is then trained. Once the network is trained, it is then used as the classification and prediction model for subsequent input data. Results obtained from example studies using the proposed method have shown to be fast and accurate as compared to a single BPNN network     

Prediction of mechanical properties of a warm compacted molybdenum prealloy using artificial neural network and adaptive neuro-fuzzy models

Predictive models using artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) were successfully developed to predict yield strength and ultimate tensile strength of warm compacted 0.85 wt.% molybdenum prealloy samples. To construct these models, 48 different experimental data were gathered from the literature. A portion of the data set was randomly chosen to train both ANN with back propagation (BP) learning algorithm and ANFIS model with Gaussian membership function and the rest was implemented to verify the performance of the trained network against the unseen data. The generalization capability of the networks was also evaluated by applying new input data within the domain covered by the training pattern. To compare the obtained results, coefficient of determination (R²), root mean squared error (RMSE) and average absolute error (AAE) indexes were chosen and calculated for both of the models. The results showed that artificial neural network and adaptive neuro-fuzzy system were both potentially strong for prediction of the mechanical properties of warm compacted 0.85 wt.% molybdenum prealloy; however, the proposed ANFIS showed better performance than the ANN model. Also, the ANFIS model was subjected to a sensitivity analysis to find the significant inputs affecting mechanical properties of the samples.     

Identification of Constitutive Parameters using Hybrid ANN multi-objective optimization procedure

This paper deals with the identification of material parameters for an elastoplastic behaviour model with isotropic hardening using several experimental tests at the same time. But, these tests are generally inhomogeneous and finite element simulations are necessary for their analysis. Therefore an inverse analysis is carried out and the identification problem is converted into a multi-objective optimization where prohibitive computing time is required. We propose in this work a hybrid approach where Artificial Neural Networks (ANN) are trained by finite element results. Then, the multi objective procedure calls the ANN function in place of the finite element code. The proposed approach is exemplified on the identification of non-associative Hill’48 criterion and Voce parameters model of the Stainless Steel AISI 304.     

Prediction and control of surface roughness for the milling of Al/SiC metal matrix composites based on neural networks

In recent years, there has been a significant increase in the utilization of Al/SiC particulate composite materials in engineering fields, and the demand for accurate machining of such composite materials has grown accordingly. In this paper, a feed-forward multi-layered artificial neural network (ANN) roughness prediction model, using the Levenberg-Marquardt backpropagation training algorithm, is proposed to investigate the mathematical relationship between cutting parameters and average surface roughness during milling Al/SiC particulate composite materials. Milling experiments were conducted on a computer numerical control (CNC) milling machine with polycrystalline diamond (PCD) tools to acquire data for training the ANN roughness prediction model. Four cutting parameters were considered in these experiments: cutting speed, depth of cut, feed rate, and volume fraction of SiC. These parameters were also used as inputs for the ANN roughness prediction model. The output of the model was the average surface roughness of the machined workpiece. A successfully trained ANN roughness prediction model could predict the corresponding average surface roughness based on given cutting parameters, with a 2.08% mean relative error. Moreover, a roughness control model that could accurately determine the corresponding cutting parameters for a specific desired roughness with a 2.91% mean relative error was developed based on the ANN roughness prediction model. Finally, a more reliable and readable analysis of the influence of each parameter on roughness or the interaction between different parameters was conducted with the help of the ANN prediction model.The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-020-00326-x     

Generalized correlation of refrigerant mass flow rate through adiabatic capillary tubes using artificial neural network

A capillary tube is a common expansion device widely used in small-scale refrigeration and air-conditioning systems. Generalized correlation method for refrigerant flow rate through adiabatic capillary tubes is developed by combining dimensional analysis and artificial neural network (ANN). Dimensional analysis is utilized to provide the generalized dimensionless parameters and reduce the number of input parameters, while a three-layer feedforward ANN is served as a universal approximator of the nonlinear multi-input and single-output function. For ANN training and test, measured data for R12, R134a, R22, R290, R407C, R410A, and R600a in the open literature are employed. The trained ANN with just one hidden neuron is good enough for the training data with average and standard deviations of 0.4 and 6.6%, respectively. By comparison, for two test data sets, the trained ANN gives two different results. It is well interpreted by evaluating the outlier with a homogeneous equilibrium model.     

适用于城市高层建筑群的震害预测模型研究

高层建筑是城市建筑的重要组成部分,现有建筑震害预测模型难以满足城市区域高层建筑群震害分析的要求。该文提出了一套非线性多自由度弯剪耦合模型（NMFS）以及其参数标定方法。该模型:1）能模拟高层建筑显著的弯剪耦合变形行为。与传统的剪切层模型对比,该模型能准确的模拟高层建筑的层间位移角包络,其结果与精细有限元模型的结果非常接近;2）具有非常高的计算效率。与精细有限元模型对比,该模型的计算加速比超过60000倍;3）参数标定简单。仅需要借助于少量的建筑属性信息（结构高度、建设年代、设计信息和结构类型）就能生成整个模型的弹塑性参数;4）能输出各层时程响应以及层间位移角情况,使未来基于工程需求参数（EDP）的区域高层建筑经济损失预测成为了可能。论文针对一栋典型高层结构详细展示了模型的建立与标定流程,并对标定参数的准确性进行了校验。最后对北京CBD地区高层建筑群进行了震害模拟,验证了该方法在城市区域中应用的可行性。该文的成果期望为未来区域高层建筑的地震损失预测提供参考。     

ANN approach to sorption hysteresis within a coupled hygro‐thermo‐mechanical FE analysis

Non‐linear deformable porous media with sorption (capillary condensation) hysteresis are considered. An artificial neural network with two hidden layers is trained to interpolate the sorption hysteresis using a set of experimental data. The performance of the ANN, which is applied as a procedure in the FE code, is investigated, both from numerical, as well as from physical viewpoint. The ANN‐FE code has been developed and tested for 1‐D and 2‐D problems concerning cyclic wetting–drying of concrete elements. In general, the application of the ANN procedure inside the classical FE program does not have any negative effect on the numerical performance of the code. The results obtained indicate that the sorption isotherm hysteresis is of importance during analysis of hygrothermal and mechanical behaviour of capillary‐porous materials. The most distinct differences are observed for the saturation and displacement solutions. The ANN‐FE approach seems to be an efficient way to take into account the influence of hysteresis during analysis of hygro‐thermal behaviour of capillary‐porous materials. Copyright © 2001 John Wiley & Sons, Ltd.     

一种确定管材本构参数的新方法及其应用

管材力学性能参数是研究管材数控弯曲变形行为的关键因素之一.采用将人工神经网络、有限元模拟以及基于平面应力状态的拉伸实验相结合的参数识别方法,获得了尺寸因子(D/t)为50的铝合金管(5052O)的塑性本构参数.同时,基于ABAQUS软件平台,建立了数控弯管三维弹塑性有限元模型,并利用该模型研究了不同本构参数对弯管塑性变形行为的影响.结果表明:与传统单向拉伸测试相比,采用本文方法获得的管材塑性本构参数模拟的管材外弧面塑性变形行为与实验结果更接近.     

Artificial neural network analysis for evaluation of peptide MS/MS spectra in proteomics

The aim of the work was to explore usefulness of artificial neural network (ANN) analysis for the evaluation of proteomics data. The analysis was applied to the data generated by the widely used protein identification program Sequest, completed with several structural parameters readily calculated from peptide molecular formulas. Proteins from yeast cells were identified based on the MS/MS spectra of peptides. The constructed ANN was demonstrated to classify automatically as either "good" or "bad" the peptide MS/MS spectra otherwise classified manually. An appropriately trained ANN proves to be a high-throughput tool facilitating examination of Sequest's results. ANNs are recommended as a means of automatic processing of large amounts of MS/MS data, which normally must be considered in the analysis of complex mixtures of proteins in proteomics.     

基于结构响应统计特征的神经网络损伤识别方法

提出一种采用结构动态响应的统计特征作为损伤指标的神经网络损伤识别方法,并对其进行了数值模拟和实验验证。首先,通过敏感性分析,分析了采用结构动力响应的统计特征作为损伤指标的可行性;然后数值模拟了一三跨连续梁采用结构位移方差作为损伤指标的神经网络损伤识别过程,其结果表明,经过训练的神经网络可以准确的识别出单损伤和多损伤工况中的损伤位置和损伤程度;最后进行一组两端固定的简支梁模型实验来验证所提出损伤识别方法的有效性。实验结果表明,对于单损伤工况,神经网络可以准确地识别出结构中损伤位置和损伤程度,对于双损伤工况,神经网络可以准确地识别出损伤位置,而损伤程度识别略有偏差。最后得出结论,采用结构动力响应的统计特征作为损伤指标的神经网络损伤识别方法是可靠有效的。     

Partitioning and interpolation based hybrid ARIMA–ANN model for time series forecasting

Time series data (TSD) originating from different applications have dissimilar characteristics. Hence for prediction of TSD, diversified varieties of prediction models exist. In many applications, hybrid models provide more accurate predictions than individual models. One such hybrid model, namely auto regressive integrated moving average – artificial neural network (ARIMA–ANN) is devised in many different ways in the literature. However, the prediction accuracy of hybrid ARIMA–ANN model can be further improved by devising suitable processing techniques. In this paper, a hybrid ARIMA–ANN model is proposed, which combines the concepts of the recently developed moving average (MA) filter based hybrid ARIMA–ANN model, with a processing technique involving a partitioning–interpolation (PI) step. The improved prediction accuracy of the proposed PI based hybrid ARIMA–ANN model is justified using a simulation experiment. Further, on different experimental TSD like sunspots TSD and electricity price TSD, the proposed hybrid model is applied along with four existing state-of-the-art models and it is found that the proposed model outperforms all the others, and hence is a promising model for TSD prediction.     

Prediction of permeability coefficients of compounds through caco-2 cell monolayer using artificial neural network analysis

Artificial neural network (ANN) analysis was used to predict the permeability of selected compounds through Caco-2 cell monolayers. Previously reported models, which were shown to be useful in the prediction of permeability values, use many structural parameters. More complex equations have also been proposed using both linear and non-linear relationships, including ANN analysis and various structural parameters. But proposed models still need to be developed using different neuron patterns for more precise predictions and a better understanding of which factors affect the permeation. To develop a simple and useful model or method for easy prediction is also a general need. Permeability coefficients (log k_p) were obtained from various literature sources. Some structural parameters were calculated using computer programs. Multiple linear regression analysis (MLRA) was used to predict Caco-2 cell permeability for the set of 50 compounds (r² = 0.403). A successful ANN model was developed, and the ANN produced log kp values that correlated well with the experimental ones (r² = 0.952). The permeability of a compound, famotidine, which has not previously been studied, through the Caco-2 cell monolayer was investigated, and its permeability coefficient determined. It was then possible to compare the experimental data with that predicted using the trained ANN with previously determined Caco-2 cell permeability values and structural parameters of compounds. The model was also tested using literature values. The developed and described ANN model in this publication does not require any experimental parameters; it could potentially provide useful and precise prediction of permeability for new drugs or other penetrants.     

Quantification of ternary mixtures of heavy metal cations from metallochromic absorbance spectra using neural network inversion

A new method based on artificial neural networks (ANN) for the processing of spectrophotometric data is proposed and illustrated on the example of the simultaneous quantification of ternary mixtures of zinc, cadmium, and mercury cations in aqueous solutions. Three types of commercially available metallochromic indicators were used as a simple model setup to create spectral data analogous to those normally received from an optical sensor array. In conventional ANN training methods for chemical sensors based on spectrophotometric data, a calibration is established by mathematically correlating the measured optical signal as network input with the concentration of the calibration sample as network output. In several situations, however, especially when dealing with mixed sample solutions, the relationship between a measured absorption spectrum and the corresponding ion concentrations is ambiguous, resulting in an "ill-posed problem". On the other hand, if the training direction is reversed by correlating known sample concentrations with measured optical signals, the relationship becomes reasonable for the ANN to obtain its structure. The proposed model illustrated in this paper is based on a more reasonable direct mapping and estimation by artificial neural network inversion (ANNI). In the training step, sample mixtures of known concentrations are optically measured to construct networks correlating the input data (ion concentrations) and the output data (absorption spectra). In the estimation step, the ion concentrations of unknown samples are estimated using the constructed ANN. The measured spectra of the unknown samples are fed to the output layer, and the appropriate input concentrations are determined by ANNI. When training the ANN system with 143 ternary mixtures of Zn2+, Cd2+, and Hg2+ in a concentration range from 1 to 100 microM, root-mean-square errors of prediction (RMSEP) of 0.45 (Zn2+), 0.96 (Cd2+), and 0.32 microM (Hg2+) were observed for the estimation of concentrations in 30 test samples, using the ANNI procedure. This newly proposed model, which involves the construction of an ANN based on direct mapping and estimation by ANNI, opens up one way to overcome the limitations of nonselective sensors, allowing the use of more easily accessible semiselective receptors to realize smart chemical sensing systems.     

Optimization of Cutting Parameters in Face Milling with Neural Networks and Taguchi based on Cutting Force,Surface Roughness and Temperatures

Prediction of cutting parameters as a function of cutting force, surface roughness and cutting temperature is very important in face milling operations. In the present study, the effect of cutting parameters on the mentioned responses were investigated by using artificial neural networks (ANN) which were trained by using experimental results obtained from Taguchi’s L8 orthogonal design. The experimental results are compared with the results predicted by ANN and the Taguchi method. By training the ANN with the results of experiments which are corresponding with the Taguchi L8 design, with only eight experiments an effective ANN model is trained. By using this network model the other combinations of experiments which did not perform previously, could be predicted with acceptable error.     

Aging process optimization for a copper alloy considering hardness and electrical conductivity

A multi-objective optimization methodology for the aging process parameters is proposed which simultaneously considers the mechanical performance and the electrical conductivity. An optimal model of the aging processes for Cu–Cr–Zr–Mg is constructed using artificial neural networks and genetic algorithms. A supervised artificial neural network (ANN) to model the non-linear relationship between parameters of aging treatment and hardness and conductivity properties is considered for a Cu–Cr–Zr–Mg lead frame alloy. Based on the successfully trained ANN model, a genetic algorithm is adopted as the optimization scheme to optimize the input parameters. The result indicates that an artificial neural network combined with a genetic algorithm is effective for the multi-objective optimization of the aging process parameters.     

An Early Stopping-Based Artificial Neural Network Model for Atmospheric Corrosion Prediction of Carbon Steel

The optimization of network topologies to retain the generalization ability by deciding when to stop overtraining an artificial neural network (ANN) is an existing vital challenge in ANN prediction works. The larger the dataset the ANN is trained with, the better generalization the prediction can give. In this paper, a large dataset of atmospheric corrosion data of carbon steel compiled from several resources is used to train and test a multilayer backpropagation ANN model as well as two conventional corrosion prediction models (linear and Klinesmith models). Unlike previous related works, a grid searchbased hyperparameter tuning is performed to develop multiple hyperparameter combinations (network topologies) to train multiple ANNs with mini-batch stochastic gradient descent optimization algorithm to facilitate the training of a large dataset. After that, one selection strategy for the optimal hyperparameter combination is applied by an early stopping method to guarantee the generalization ability of the optimal network model. The correlation coefficients (R) of the ANN model can explain about 80% (more than 75%) of the variance of atmospheric corrosion of carbon steel, and the root mean square errors (RMSE) of three models show that the ANN model gives a better performance than the other two models with acceptable generalization. The influence of input parameters on the output is highlighted by using the fuzzy curve analysis method. The result reveals that TOW, Cl- and SO2 are the most important atmospheric chemical variables, which have a well-known nonlinear relationship with atmospheric corrosion.     

基于人工神经网络的藏式结构有限元模型修正

针对典型藏式传统建筑年代久远、建造过程无设计图纸、存在太多不确定性,通过有限元数值分析所得结果与实验结果不能较好吻合问题,建立所测结构的有限元模型,并通过人工神经网络方法,以实测结构模态参数为目标对典型藏式结构的有限元模型中部分不确定因素—梁及雀替的等效变截面梁高、材料密度及弹性模量进行修正,得到更接近真实状态的有限元模型。该模型对该典型藏式结构的损伤识别、可靠度评估具有重要意义。     

Optimization of chemical composition for TC11 titanium alloy based on artificial neural network and genetic algorithm

It is quite difficult for materials to develop the quantitative model of chemical elements and mechanical properties, because the relationship between them presents the multivariable and non-linear. In this work, the combined approach of artificial neural network (ANN) and genetic algorithm (GA) was employed to synthesize the optimum chemical composition for satisfying mechanical properties for TC11 titanium alloy based on the large amount of experimental data. The chemical elements (Al, Mo, Zr, Si, Fe, C, O, N and H) were chosen as input parameters of the ANN model, and the output parameters are mechanical properties, including ultimate tensile strength, yield strength, elongation and reduction of area. The fitness function for GA was obtained from trained ANN model. It is found that the percentage errors between experimental and predicted are all within 5%, which suggested that the ANN model has excellent generalization capability. The results strongly indicated that the proposed optimization model offers an optimal chemical composition for TC11 titanium alloy, which implies it is a novel and effective approach for optimizing materials chemical composition.