Taguchi approach for characterization of three-body abrasive wear of carbon-epoxy composite with and without SiC filler

Fiber–matrix interfacial bonding plays a critical role in controlling performance properties of polymer composites. Carbon fibers have major constraints of chemical inertness with the matrix and need the surface treatment to improve the adhesion with the matrix. In this work, parametric appraisal of three-body abrasive wear behavior was presented for silane treated carbon fabric reinforced epoxy (C-E) composites with and without silane treated silicon carbide (SiC) as filler. The fiber content was fixed at 60?wt.%, while the weight fraction of SiC was varied (5 and 10?wt.%) to obtain three different compositions. Three-body abrasive wear tests were conducted using design of experiments approach based on Taguchi’s orthogonal arrays. The findings of experiments indicate that the wear loss is greatly influenced by load and grain size of abrasive. An optimal parameter combination was determined, which leads to maximization of abrasion resistance. Inclusion of SiC filler reasonably increased the abrasion resistance of C-E composite. Analysis of variance results showed that the load significantly influenced the abrasion of SiC filled C-E composites. Efforts were also made to correlate the abrasive wear performance of SiC filled C-E composites using artificial neural network (ANN). The wear behavior of composite by ANN prediction closely matched the experimental results and finally, optimal wear settings for minimum wear were identified.     

The string prediction models as invariants of time series in the forex market

In this paper we apply a new approach of string theory to the real financial market. The models are constructed with an idea of prediction models based on the string invariants (PMBSI). The performance of PMBSI is compared to support vector machines (SVM) and artificial neural networks (ANN) on an artificial and a financial time series. A brief overview of the results and analysis is given. The first model is based on the correlation function as invariant and the second one is an application based on the deviations from the closed string/pattern form (PMBCS). We found the difference between these two approaches. The first model cannot predict the behavior of the forex market with good efficiency in comparison with the second one which is, in addition, able to make relevant profit per year. The presented string models could be useful for portfolio creation and financial risk management in the banking sector as well as for a nonlinear statistical approach to data optimization.     

Millimeter-wave Micromachined Filter Design by Artificial Neural Network Modeling Technique

This paper presents a design approach for a 34 GHz λ/2 resonator micormachined bandpass filter by using the artificial neural network (ANN) modeling technique. Three important dimensions of the filter layout are used to capture critical input-output relationships in the ANN model. Once fully developed, the ANN model has been shown to be as accurate as an EM simulator and much more efficient computationally in the design optimization of the filter.     

An a priori evaluation of a principal component and artificial neural network based combustion model in diesel engine conditions

A principal component analysis (PCA) and artificial neural network (ANN) based chemistry tabulation approach is presented. ANNs are used to map the thermochemical state onto a low-dimensional manifold consisting of five control variables that have been identified using PCA. Three canonical configurations are considered to train the PCA-ANN model: a series of homogeneous reactors, a nonpremixed flamelet, and a two-dimensional lifted flame. The performance of the model in predicting the thermochemical manifold of a spatially-developing turbulent jet flame in diesel engine thermochemical conditions is a priori evaluated using direct numerical simulation (DNS) data. The PCA-ANN approach is compared with a conventional tabulation approach (tabulation using ad hoc defined control variables and linear interpolation). The PCA-ANN model provides higher accuracy and requires several orders of magnitude less memory. These observations indicate that the PCA-ANN model is superior for chemistry tabulation, especially for modelling complex chemistries that present multiple combustion modes as observed in diesel combustion. The performance of the PCA-ANN model is then compared to the optimal estimator, i.e. the conditional mean from the DNS. The results indicate that the PCA-ANN model gives high prediction accuracy, comparable to the optimal estimator, especially for major species and the thermophysical properties. Higher errors are observed for the minor species and reaction rate predictions when compared to the optimal estimator. It is shown that the prediction of minor species and reaction rates can be improved by using training data that exhibits a variation of parameters as observed in the turbulent flame. The output of the ANN is analysed to assess mass conservation. It is observed that the ANN incurs a mean absolute error of 0.05% in mass conservation. Furthermore, it is demonstrated that this error can be reduced by modifying the cost function of the ANN to penalise for deviation from mass conservation.     

Predicting the Capacity of RC Beams Strengthened in Shear with Side-Bonded FRP Reinforcements Using Artificial Neural Networks

The application of artificial neural network (ANN) to predict the shear capacity of reinforced concrete (RC) beams retrofitted in shear by means of side-bonded fiber-reinforced polymer (FRP) is investigated in this paper. An extensive literature review has been carried out. In addition, ten shear deficient RC beams with different carbon fiber-reinforced polymer (CFRP) configurations were tested and added as data to the collected data. It was aimed to build an efficient and practical ANN model with parameters which can easily be obtained without any calculation and/or experimental investigation. The results are compared with the design guideline equations that emerge as predictions of the FRP contribution using the trained neural networks: these are in good agreement with the experimental results and better than those calculated from the theoretical guideline equations. Based on ANN results, a parametric study has been carried out to study the importance of different influencing parameters on the FRP contribution. Thereafter, a new simple expression is proposed for determining the contribution of externally bonded side-bonded FRP. Accordingly, the suggested design formula is capable of predicting the experimental FRP satisfactorily so that it can be admitted as an alternative to the existing guideline equations within the range of parameters covered in the study.     

Prediction of airblast-overpressure induced by blasting using a hybrid artificial neural network and particle swarm optimization

Blasting is an inseparable part of the rock fragmentation process in hard rock mining. As an adverse and undesirable effect of blasting on surrounding areas, airblast-overpressure (AOp) is constantly considered by blast designers. AOp may impact the human and structures in adjacent to blasting area. Consequently, many attempts have been made to establish empirical correlations to predict and subsequently control the AOp. However, current correlations only investigate a few influential parameters, whereas there are many parameters in producing AOp. As a powerful function approximations, artificial neural networks (ANNs) can be utilized to simulate AOp. This paper presents a new approach based on hybrid ANN and particle swarm optimization (PSO) algorithm to predict AOp in quarry blasting. For this purpose, AOp and influential parameters were recorded from 62 blast operations in four granite quarry sites in Malaysia. Several models were trained and tested using collected data to determine the optimum model in which each model involved nine inputs, including the most influential parameters on AOp. In addition, two series of site factors were obtained using the power regression analyses. Findings show that presented PSO-based ANN model performs well in predicting the AOp. Hence, to compare the prediction performance of the PSO-based ANN model, the AOp was predicted using the current and proposed formulas. The training correlation coefficient equals to 0.94 suggests that the PSO-based ANN model outperforms the other predictive models.     

Prediction of the acoustic form function by neural network techniques for immersed tubes

A new approach is used to predict the acoustic form function (FF) for an infinite length cylindrical shell excited perpendicularly to its axis using the artificial neural network (ANN) techniques. The Wigner-Ville distribution is used like a comparison tool between the FF calculated by the analytical method and that predicted by the ANN techniques for a stainless steel tube. During the development of the network, several configurations are evaluated for various radius ratios ba (a: outer radius: b: inner radius of the tube). The optimal model is a network with one hidden layer. It is able to predict the FF with a mean relative error about 1.61% for the cases studied in this paper.     

Modelling the soundscape quality of urban waterfronts by artificial neural networks

The renewal of the urban waterfronts has become a major focus of attention for politicians and decision makers in the city’s management programs. The recognition of the patterns that define the waterfronts’ identity is essential to select new strategies of intervention for the environmental recovery. In order to create adequate environments for everyday life within a sustainable development, new links between human senses, human perception and design need to be created. Within this wide approach, the landscape and the soundscape play a significant role and can become a key driving force in the implementation of the changes. New techniques have to be tested to identify the sonic and visual parameters capable to explain the specificity of a waterfront. With this purpose, an artificial neural network (ANN) was developed, and the relative importance of the input variables was evaluated. The collected database was also analysed by multiple linear regression (MLR) to compare the outcomes of both models. The urban waterfront of Naples (Italy) was chosen as case study. The results obtained show that the performance of the neural network is better than the one of the linear regression (rANN = 0.949, rMLR = 0.639). The interpretation of the relative importance method is also quite satisfactory in the ANN.     

Inversion for acoustic impedance of a wall by using artificial neural network

A new approach for measuring acoustic impedance is developed by using artificial neural network (ANN) algorithm. Instead of using impedance tube, a rectangular room or a box is simulated with known boundary conditions at some boundaries and an unknown acoustic impedance at one side of the wall. A training data basis for the ANN algorithm is evaluated by similar source method which was developed earlier by Too and Su [Too G-PJ, Su T-K. Estimation of scattering sound field via nearfield measurement by source methods. Appl Acoust. 1999;58:261-81 (SCI) (EI)] for the estimation of interior and exterior sound field. The training data basis is constructed by evaluating of acoustic pressure at a field point with various acoustic impedance conditions at one side of the wall. Then, the inversion for unknown acoustic impedance of a wall is performed by measuring several field data and substituting these data into ANN algorithm. The simulation result indicates that the prediction of acoustic impedance is very accurate with error percentage under 1%. In addition, one field point measurement in the present approach for acoustic impedance provides more straightforward and easier evaluation than that in the two point measurement of impedance tube.     

光谱油样分析监测技术中的神经网络预测方法

光谱油样分析是机械磨损状态监测与故障诊断的重要技术,基于光谱数据的机械状态预测有利于发现机械系统的早期磨损故障。由于神经网络对于非线性模型的辨识和非平稳信号的预测,与传统预测模型相比具有明显的优势,文章将神经网络预测方法运用于光谱分析,提出了基于神经网络预测的光谱分析监测技术。在预测模型中采用了三层BP网络模型,针对神经网络的结构对于信号预测或模型辨识的精度具有影响很大的问题,文章利用遗传算法,对神经网络输入节点数、隐层节点数和网络收敛的均方误差(MSE)目标值进行了优化,得到了最优的网络预测模型。最后,对某发动机实际的光谱分析数据进行了预测和分析,并与传统ARMA模型的预测结果进行了比较,结果充分表明了本方法的有效性和优越性。     

二维光电位置敏感器件的非线性修正

根据二维光电位置敏感器件 (PSD)的工作原理 ,分析了影响PSD线性度的主要因素 ,提出了一种用神经网络对PSD进行非线性修正的方法。以PSD的输入输出数据对作为样本训练的神经网络 ,利用神经网络所具有地能够以任意精度逼近非线性函数的能力 ,实现PSD的输出与实际光点位置之间的映射 ,在神经网络的输出端得到线性响应。该方法的优点是不需要很大的数据存储量即可得到很好的修正效果。结果表明 ,修正后的PSD能在较宽的位置范围内输出高线性度的信号     

基于神经网络的高压输电线路单端测距方法

针对单端行波故障测距第二个行波波头性质辨识问题,提出一种将小波模极大值方法和神经网络算法相结合的测距方法。采集故障波头时间差和极性等信息作为样本,利用神经网络的非线性拟合能力对样本进行训练、测试,从而建立相应的故障测距神经网络模型。将故障信息代入神经网络模型得到初步测距结果,根据初测结果和波头极性、时间差等性质的关系,对第二个行波波头进行正确辨识,从而得到优化的测距结果。经Matlab/Simulink仿真验证,该方法有较高的可靠性和精确性。     

Novel model of a AlGaN/GaN high electron mobility transistor based on an artificial neural network

In this paper we present a novel approach to modeling AlGaN/GaN high electron mobility transistor(HEMT) with an artificial neural network(ANN).The AlGaN/GaN HEMT device structure and its fabrication process are described.The circuit-based Neuro-space mapping(neuro-SM) technique is studied in detail.The EEHEMT model is implemented according to the measurement results of the designed device,which serves as a coarse model.An ANN is proposed to model AlGaN/GaN HEMT based on the coarse model.Its optimization is performed.The simulation results from the model are compared with the measurement results.It is shown that the simulation results obtained from the ANN model of AlGaN/GaN HEMT are more accurate than those obtained from the EEHEMT model.     

Application of multifractal wavelet analysis to spontaneous fermentation processes

An algorithm is presented here to get more detailed information, of mixed-culture type, based exclusively on the biomass concentration data for fermentation processes. The analysis is performed with only the on-line measurements of the redox potential being available. It is a two-step procedure which includes an Artificial Neural Network (ANN) that relates the redox potential to the biomass concentrations in the first step. Next, a multifractal wavelet analysis is performed using the biomass estimates of the process. In this context, our results show that the redox potential is a valuable indicator of microorganism metabolic activity during the spontaneous fermentation. In this paper, the detailed design of the multifractal wavelet analysis is presented, as well as its direct experimental application at the laboratory level.     

Wooden windows: Sound insulation evaluation by means of artificial neural networks

Windows are the weakest part of a façade in terms of acoustic performance: the weighted sound insulation index (R_w), measured according to ISO 140-3, is the fundamental parameter to evaluate the façade acoustic insulation.The paper aims at developing an artificial neural network (ANN) model to estimate the R_w value of wooden windows based on a limited number of windows parameters; this is a new approach because acoustic phenomena are non-linear and affected by a plurality of factors and, therefore, usually investigated through experimentation.Data set is taken from experimental campaigns carried out at the Laboratory of Acoustics, University of Perugia. A multilayer feed-forward approach was chosen and the model was implemented in MATLAB. On the basis of the results obtained by means of a preliminary training and test campaign of several ANN architectures, five main parameters were selected as network inputs: window typology, frame and shutters thickness, number of gaskets, R_w of glazing; R_w value of the window is the network output. Different ANN configurations were trained and a root mean-square error less than 3% was obtained, comparable to measurement uncertainty.This approach allows to develop a model which, with input parameters varying within appropriate ranges, can easily estimate the acoustic performance of wooden windows without experimental campaign on prototypes, saving both money and time. If the training data set is large enough, the presented approach could be very useful for design and optimization of acoustic performance of new products.     

ANN based modelling of hydrodynamic cavitation processes: Biomass pre-treatment and wastewater treatment

We have developed artificial neural network (ANN) based models for simulating two application examples of hydrodynamic cavitation (HC) namely, biomass pre-treatment to enhance biogas and degradation of organic pollutants in water. The first case reports data on influence of number of passes through HC reactor on bio-methane generation from bagasse. The second case reports data on influence of HC reactor scale on degradation of dichloroaniline (DCA). Similar to most of the HC based applications, the availability of experimental data for these two applications is rather limited. In this work a systematic methodology for developing ANN model is presented. The models were shown to describe the experimental data very well. The ANN models were then evaluated for their ability to interpolate and extrapolate. Despite the limited data, the ANN models were able to simulate and interpolate the data for two very different and complex HC applications very well. The extrapolated results of biomethane generation in terms of number of passes were consistent with the intuitive understanding. The extrapolated results in terms of elapsed time were however not consistent with the intuitive understanding. The ANN model was able to generate intuitively consistent extrapolated results for degradation of DCA in terms of number of passes as well as scale of HC reactor. The results will be useful for developing quantitative models of complex HC applications.     

RSM and ANN modeling-based optimization approach for the development of ultrasound-assisted liposome encapsulation of piceid

Piceid, a naturally occurring derivative of resveratrol found in many plants, has recently been considered as a potential nutraceutical. However, its poorly water-soluble property could cause a coupled problem of biological activities concerning drug dispersion and absorption in human body, which is still unsolved now. Liposome, a well-known aqueous carrier for water-insoluble ingredients, is commonly applied in drug delivery systems. In this study, a feasible approach for solving the problem is that the targeted piceid was encapsulated into a liposomal formula as aqueous substrate to overcome its poor water-solubility. The encapsulation process was assisted by ultrasound, with investigation of lipid content, ultrasound power and ultrasound time, for controlling encapsulation efficiency (E.E%), absolute loading (A.L%) and particle size (PS). Moreover, both RSM and ANN methodologies were further applied to optimize the ultrasound-assisted encapsulation process. The data indicated that the most important effects on the encapsulation performance were found to be of lipid content followed by ultrasound time and ultrasound power. The maximum E.E% (75.82%) and A.L% (2.37%) were exhibited by ultrasound assistance with the parameters of 160 mg lipid content, ultrasound time for 24 min and ultrasound power of 90 W. By methodological aspects of processing, the predicted E.E% and A.L% were respectively in good agreement with the experimental results for both RSM and ANN. Moreover, RMSE, R² and AAD statistics were further used to compare the prediction abilities of RSM and ANN based on the validation data set. The results indicated that the prediction accuracy of ANN was better than that of RSM. In conclusion, ultrasound-assisted liposome encapsulation can be an efficient strategy for producing well-soluble/dispersed piceid, which could be further applied to promote human health by increased efficiency of biological absorption, and the process of ultrasound-mediated liposome encapsulation can be well established by a methodological approach using either RSM or ANN, but it is worth mentioning that the ANN model used here showed the superiority over RSM for predicting and optimizing encapsulation.     

Integrating artificial neural networks and empirical correlations for the prediction of water-subcooled critical heat flux

The critical heat flux (CHF) is an important parameter for the design of nuclear reactors, heat exchangers and other boiling heat transfer units. Recently, the CHF in water-subcooled flow boiling at high mass flux and subcooling has been thoroughly studied in relation to the cooling of high-heat-flux components in thermonuclear fusion reactors. Due to the specific thermal-hydraulic situation, very few of the existing correlations, originally developed for operating conditions typical of pressurized water reactors, are able to provide consistent predictions of water-subcooled-flow-boiling CHF at high heat fluxes. Therefore, alternative predicting techniques are being investigated. Among these, artificial neural networks (ANN) have the advantage of not requiring a formal model structure to fit the experimental data; however, their main drawbacks are the loss of model transparency (‘black-box’ character) and the lack of any indicator for evaluating the accuracy and reliability of the ANN answer when ‘never-seen’ patterns are presented. In the present work, the prediction of CHF is approached by a hybrid system which couples a heuristic correlation with a neural network. The ANN role is to predict a datum-dependent parameter required by the analytical correlation; this parameter was instead set to a constant value obtained by usual best-fitting techniques when a pure analytical approach was adopted. Upper and lower boundaries can be possibly assigned to the parameter value, thus avoiding the case of unexpected and unpredictable answer failure. The present approach maintains the advantage of the analytical model analysis, and it partially overcomes the ‘black-box’ character typical of the straight application of ANNs because the neural network role is limited to the correlation tuning. The proposed methodology allows us to achieve accurate results and it is likely to be suitable for thermal-hydraulic and heat transfer data processing.     

Prediction of lattice constant in perovskites of GdFeO3 structure

Lattice constants in GdFeO₃-type ABO₃ perovskites are correlated to their constituent elemental properties by using linear regression (LR) and artificial neural networks (ANN) techniques and a sample set of 157 known GdFeO₃-type ABO₃ perovskites. LR models are first obtained using two elemental ionic radii only and ANN models, using five elemental properties; ionic radii, electronegativities of cation A and B, and the valence of ion A, are further developed to improve the model predictability, which reaches an error limits of less than 2%. It is shown that lattice constants of these compounds only roughly correlate to their ionic radii, and for a good prediction model 3 more elemental properties (electronegativity and valence) are necessary. In new materials research, where lattice constant is one of the key design target, the developed LR and ANN models may be used to screen and shortlist promising perovskites from a large pool of all possible candidates. These selected compounds may undergo further test using relatively more expensive experiments or quantum mechanics computations.     

A different approach to gain computation in laser diodes with respect to different number of quantum-wells

This study presents a different approach for the modelling of optical gain in laser diodes as a function of quantum-well (QW) number based on Artificial Neural Networks (ANNs). Different learning algorithms with different network configurations are tried and tested in order to minimize the rms errors in terms of the ANN structure, number of layers, and number of neurons in each layer. The optical gain results obtained by using this method are in very good agreement with the experimental results reported elsewhere.