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.     

Supervised algorithms for particle classification by a transition radiation detector

Support vector machines (SVMs) provide an interesting computational paradigm for the classification of data from high-energy physics and particle astrophysics experiments. In this study, the classification power of SVMs is compared with those from standard supervised algorithms, i.e. likelihood ratio and artificial neural networks (ANN), using test beam data from the transition radiation detector prototype of the PAMELA satellite-borne magnetic spectrometer. Concerning signal/background discrimination, SVM and ANN show the best performance. Moreover, our analysis shows that the use of SVM allows an accurate estimate of the discrimination efficiency of unseen data points: indeed, since almost the same efficiency is obtained with or without the cross-validation technique, the performance of SVM appears to be stable. On the other hand, the ANN shows a tendency to overfit the data, while this tendency is not observed using SVM. For these reasons, SVM could be used in particle astrophysics experiments where, due to the harsh experimental conditions, efficient and robust classification algorithms are needed.     

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.     

Predicting the bake hardenability of steels using neural network modeling

In this work, an artificial neural network (ANN) model for prediction of mechanical properties of baked steels was established. The model introduced here considers the content of carbon, the prestrain amount, the initial yield stress and the baking temperature as inputs. While, the bake hardenability, work hardening values and yield stresses after steel baking are presented as outputs. The network was trained using the data from experimental work and back-propagation algorithm. The results show that the predicted values by the model are much more accurate than the experimental ones. The model suggested a two-stage strengthening for baking of ultra low carbon (ULC) steels, whereas, in the case of low carbon steels only one increment step in strength was reported. Comparing the predicted amounts by ANN model with the experimental ones indicates that well-trained neural network model provides very accurate results.     

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.     

Artificial neural networks for pattern recognition

This tutorial article deals with the basics of artificial neural networks (ANN) and their applications in pattern recognition. ANN can be viewed as computing models inspired by the structure and function of the biological neural network. These models are expected to deal with problem solving in a manner different from conventional computing. A distinction is made between pattern and data to emphasize the need for developing pattern processing systems to address pattern recognition tasks. After introducing the basic principles of ANN, some fundamental networks are examined in detail for their ability to solve simple pattern recognition tasks. These fundamental networks together with the principles of ANN will lead to the development of architectures for complex pattern recognition tasks. A few popular architectures are described to illustrate the need to develop an architecture specific to a given pattern recognition problem. Finally several issues that still need to be addressed to solve practical problems using ANN approach are discussed. This paper is mostly a consolidation of work reported by several researchers in the literature, some of which is cited in the references. The author has borrowed several ideas and illustrations from the references quoted in this paper.     

神经网络和贝叶斯网络在汉语词义消歧上的对比研究

神经网络和贝叶斯网络是两种经典的机器学习方法。本文通过实验考察了这两种网络模型在汉语词义消歧上的应用效果。实验对象是通过特定规则构造的6个伪词。使用伪词可以避免有指导的词义消歧方法中的数据稀疏问题,充分验证词义分类器的实验效果。贝叶斯网络用于词义分类简单高效,模型容易构造,而神经网络的结构则相对复杂,用于词义消歧需要先解决输入问题。实验中采用词间互信息成功构造了神经网络的输入模型,实验效果较为理想。实验数据表明贝叶斯网络比神经网络更适合解决汉语词义消歧问题。但贝叶斯网络的抗噪声能力却明显逊色于神经网络。     

Artificial neural network-based prediction technique for coating thickness in Fe-Al coatings fabricated by mechanical milling

The objective of this study was to evaluate the effect of milling time, milling speed and particle size of initial powders on the coating thickness of Fe-Al intermetallic coating by using artificial neural network (ANN). Coating morphology and cross-section microstructures were evaluated using a scanning electron microscope (SEM). It was found that an increase in the milling time provided an increase in the coating-layer thickness due to the cold welding process between particles and the steel substrate. The microstructure of the coating surface was refined by ball impacts in the milling process. As a result of this study, the ANN was found to be successful for predicting the coating thickness of Fe-Al intermetallic coatings. The correlation between the predicted values and the experimental data of the feed-forward back-propagation ANN was quite adequate. The mean absolute percentage error (MAPE) for the predicted values didn’t exceed 7.46%. The ANN model can be used for predicting the coating thickness of Fe-Al intermetallic coating produced for different milling time, milling speed and particle size.     

Prediction of Concrete Cubic Compressive Strength Using ANN Based Size Effect Model

Size effect is a major issue in concrete structures and occurs in concrete in any loading conditions. In this study, size effect on concrete cubic compressive strength is modeled with a back-propagation neural network. The main advantage in using an artificial neural network (ANN) technique is that the network is built directly from experimental data without any simplifying assumptions via the self-organizing capabilities of the neural network. The proposed ANN model is verified by using 27 experimental data sets collected from the literature. For the large specimens, a modified ANN is developed in the paper to further improve the forecast accuracy. The results demonstrate that the ANN-based size effect model has a strong potential to predict the cubic compressive strength of concrete     

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.     

In-process monitoring of drilling burr formation using acoustic emission and a wavelet-based artificial neural network

Prediction/detection of exit burrs is critical in manufacturing automation. In this research, an intelligent burr sensing/monitoring scheme is proposed. Acoustic emission (AE) was selected to detect burr formation during drilling. For effective extraction of information contained in the collected AE signals, wavelet transform (WT) was adopted and the selected features through WT were fed into a back-propagation artificial neural net (ANN) as input vectors. To validate the in-process AE monitoring system, both WT-based ANN and cutting condition-based ANN outputs (cutting speed, feed, drill diameter, etc.) were compared with experimental data. The results show that the proposed scheme is not only efficient with fewer inputs, but more reliable in predicting drilling burr types over cutting condition-based ANN.     

The use of artificial neural networks (ANN) for modeling of decolorization of textile dye solution containing C. I. Basic Yellow 28 by electrocoagulation process

In this paper, electrocoagulation has been used for removal of color from solution containing C. I. Basic Yellow 28. The effect of operational parameters such as current density, initial pH of the solution, time of electrolysis, initial dye concentration, distance between the electrodes, retention time and solution conductivity were studied in an attempt to reach higher removal efficiency. Our results showed that the increase of current density up to 80 Am(-2) enhanced the color removal efficiency, the electrolysis time was 7 min and the range of pH was determined 5-8. It was found that for achieving a high color removal percent, the conductivity of the solution and the initial concentration of dye should be 10 mS cm(-1) and 50 mg l(-1), respectively. An artificial neural networks (ANN) model was developed to predict the performance of decolorization efficiency by EC process based on experimental data obtained in a laboratory batch reactor. A comparison between the predicted results of the designed ANN model and experimental data was also conducted. The model can describe the color removal percent under different conditions.     

Predicting of mechanical properties of Fe–Mn–(Al, Si) TRIP/TWIP steels using neural network modeling

In this work, an artificial neural network (ANN) model was established in order to predict the mechanical properties of transformation induced plasticity/twinning induced plasticity (TRIP/TWIP) steels. The model developed in this study was consider the contents of Mn (15–30 wt%), Si (2–4 wt%) and Al (2–4 wt%) as inputs, while, the total elongation, yield strength and tensile strength are presented as outputs. The optimal ANN architecture and training algorithm were determined. Comparing the predicted values by ANN with the experimental data indicates that trained neural network model provides accurate results.     

Cryogenic adsorption of nitrogen on activated carbon: Experiment and modeling

A cryo-sorption device was built based on a commercial gas sorption analyzer with its sample chamber connected to the 2nd stage of the Gifford-McMahon (GM) cryocooler (by SUMITOMO Corporation), which could provide the operation temperature ranging from 4.5 K to 300 K; The nitrogen adsorption isotherms ranging from 95 to 160 K were obtained by volumetric method on the PICATIF activated carbon. Isosteric heat of adsorption was calculated using the Clausius–Clapeyron equation and was around 8 kJ/mol. Conventional isotherm models and the artificial neural network (ANN) were applied to analyze the adsorption data, the Dual-site Langmuir and the Toth equation turned out to be the most suitable empirical isotherm model; Adsorption equilibrium data at some temperature was used to train the neural network and the rest was used to validate and predict, it turned out that the accuracy of the prediction by the ANN increased with increasing hidden-layer, and it was within ±5% for the three-hidden-layer ANN, and it showed better performance than the conventional isotherm model; Considering large time consumption and complexity of the adsorption experiment, the ANN method can be applied to get more adsorption data based on the already known experimental data.     

Prediction of Drug Content and Hardness of Intact Tablets Using Artificial Neural Network and Near-Infrared Spectroscopy

The purpose of this study was to predict drug content and hardness of intact tablets using artificial neural networks (ANN) and near-infrared spectroscopy (NIRS). Tablets for the drug content study were compressed from mixtures of Avicel® PH-101, 0.5% magnesium stearate, and varying concentrations (0%, 1%, 2%, 5%, 10%, 20%, and 40% w/w) of theophylline. Tablets for the hardness study were compressed from mixtures of Avicel PH-101 and 0.5% magnesium stearate at varying compression forces ranging from 0.4 to 1 ton. An Intact Analyzer™ was used to obtain near infrared spectra from the tablets with varying drug contents, whereas a Rapid Content Analyzer™ (RCA) was used to obtain spectral data from the tablets with varying hardness. Two sets of tablets from each batch (i.e., tablets with varying drug content and hardness) were randomly selected. One set of tablets was used to generate appropriate calibration models, while the other set was used as the unknown (test) set. A total of 10 ANN calibration models (5 each with 10 and 160 inputs at appropriate wavelengths) and five separate 4-factor partial least squares (PLS) calibration models were generated to predict drug contents of the test tablets from the spectral data. For the prediction of tablet hardness, two ANN calibration models (one each with 10 and 160 inputs) and two 4-factor PLS calibration models were generated and used to predict the hardness of test tablets. The PLS calibration models were generated using Vision® software. Prediction of drug contents of test tablets using the ANN calibration models generated with 10 inputs was significantly better than the prediction obtained with the ANN calibration models with 160 inputs. For tablets with low drug concentrations (less than or equal to 2%w/w), prediction of drug content was better with either of the two ANN calibration models than with the PLS calibration models. However, prediction of drug contents of tablets with greater than or equal to 5% w/w drug was better with the PLS calibration models than with the ANN calibration models. Prediction of tablet hardness was better with the ANN calibration models generated with either 10 or 160 inputs than with the PLS calibration models. This work demonstrated that a well-trained ANN model is a powerful alternative technique for analysis of NIRS data. Moreover, the technique could be used in instances when the conventional modeling of data does not work adequately.     

Incorporating Artificial Neural Networks in the dynamic thermal–hydraulic model of a controlled cryogenic circuit

A model based on Artificial Neural Networks (ANNs) is developed for the heated line portion of a cryogenic circuit, where supercritical helium (SHe) flows and that also includes a cold circulator, valves, pipes/cryolines and heat exchangers between the main loop and a saturated liquid helium (LHe) bath. The heated line mimics the heat load coming from the superconducting magnets to their cryogenic cooling circuits during the operation of a tokamak fusion reactor. An ANN is trained, using the output from simulations of the circuit performed with the 4C thermal–hydraulic (TH) code, to reproduce the dynamic behavior of the heated line, including for the first time also scenarios where different types of controls act on the circuit. The ANN is then implemented in the 4C circuit model as a new component, which substitutes the original 4C heated line model. For different operational scenarios and control strategies, a good agreement is shown between the simplified ANN model results and the original 4C results, as well as with experimental data from the HELIOS facility confirming the suitability of this new approach which, extended to an entire magnet systems, can lead to real-time control of the cooling loops and fast assessment of control strategies for heat load smoothing to the cryoplant.     

Predicting Drying Performance of Osmotically Treated Heat Sensitive Products Using Artificial Intelligence

The main goal of this research is to develop and apply a robust Artificial Neural Networks (ANNs) model for predicting the characteristics of the osmotically drying treated potato and apple samples as a model heat-sensitive product in vacuum contact dryer. Concentrated salt and sugar solutions were used as the osmotic solutions at 27C. Series of experiments were performed at various temperatures of 35C, 40C, and 55C for conduction heat input under vacuum ( −760 mm Hg) condition. Some experiments were also performed in a pure vacuum without heat addition. Dimensionless moisture content (DMC), effective moisture diffusivity, and mass flux were considered as the performance parameters in this study. Results revealed that the osmotic dehydration using a concentrated sugar solution shows a higher reduction in the initial moisture loss of 19.87% compared to 5.3% in the salt solution. Furthermore, a significant enhancement of drying performance of about 27% in DMC was observed for both samples at vacuum and 40C compared to pure vacuum drying conditions. Using the experimental data, a robust artificial neural network (ANN) was proposed to describe the osmotic dehydration’s behavior on the drying process. The ANN model outputs are the dimensionless moisture contents (DMC), the diffusivity, and the mass flux. Whereas the ANN inputs were the drying time, the percent of sugar solution, and the percent of salt solution. For the ANN apple’s model, the minimum root mean square error (RMSE) values were 0.0261, 0.0349 and 0.0406, for DMC, diffusivity, and mass flux, respectively. Whereas the best correlation coefficients of the above three parameters’ determination values were 0.9909, 0.9867 and 0.9744, respectively. For the ANN potato’s model, the minimum RMSE values were 0.0124, 0.0140 and 0.0333, for DMC, diffusivity, and mass flux, respectively. And the best correlation coefficients of the parameters’ values were found 0.9969, 0.9968 and 0.9736, respectively. Accordingly, the ANN model’s prediction has a perfect agreement with the experimental dataset, which confirmed the ANN model’s accuracy.     

Diagnostic system for identification of accident scenarios in nuclear power plants using artificial neural networks

This paper presents the work carried out towards developing a diagnostic system for the identification of accident scenarios in 220 MWe Indian PHWRs. The objective of this study is to develop a methodology based on artificial neural networks (ANNs), which assists in identifying a transient quickly and suggests the operator to initiate the corrective actions during abnormal operations of the reactor. An operator support system, known as symptom-based diagnostic system (SBDS), has been developed using ANN that diagnoses the transients based on reactor process parameters, and continuously displays the status of the reactor. As a pilot study, the large break loss of coolant accident (LOCA) with and without the emergency core cooling system (ECCS) in reactor headers has been considered. Several break scenarios of large break LOCA have been analyzed. The time-dependent transient data have been generated using the RELAP5 thermal hydraulic code assuming an equilibrium core, which conforms to a realistic estimation. The diagnostic results obtained from the ANN study are satisfactory. These results have been incorporated in the SBDS software for operator assistance. A few important outputs of the SBDS have been discussed in this paper.     

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.     

Using GA–ANN algorithm to optimize soft magnetic properties of nanocrystalline mechanically alloyed Fe–Si powders

In this investigation a theoretical model based on artificial neural network (ANN) and genetic algorithm (GA) has been developed to optimize the magnetic softness in nanocrystalline Fe–Si powders prepared by mechanical alloying (MA). The ANN model was used to correlate the milling time, chemical composition, milling speed, and ball to powders ratio (BPR) to coercivity and crystallite size of nanocrystalline Fe–Si powders. The GA–ANN combined algorithm was incorporated to find the optimal conditions for achieving the minimum coercivity. By comparing the predicted values with the experimental data it is demonstrated that the combined GA–ANN algorithm is a useful, efficient and strong method to find the optimal milling conditions and chemical composition for producing nanocrystalline Fe–Si powders with minimum coercivity.