The use of artificial neural networks in electrostatic force microscopy

ABSTRACT: The use of electrostatic force microscopy (EFM) to characterize and manipulate surfaces at the nanoscale usually faces the problem of dealing with systems where several parameters are not known. Artificial neural networks (ANNs) have demonstrated to be a very useful tool to tackle this type of problems. Here, we show that the use of ANNs allows us to quantitatively estimate magnitudes such as the dielectric constant of thin films. To improve thin film dielectric constant estimations in EFM, we first increase the accuracy of numerical simulations by replacing the standard minimization technique by a method based on ANN learning algorithms. Second, we use the improved numerical results to build a complete training set for a new ANN. The results obtained by the ANN suggest that accurate values for the thin film dielectric constant can only be estimated if the thin film thickness and sample dielectric constant are known.PACS: 07.79.Lh; 07.05.Mh; 61.46.Fg.     

Optimization of an Artificial Neural Network Topology for Predicting Drying Kinetics of Carrot Cubes Using Combined Response Surface and Genetic Algorithm

In this study, the advantages of integrated response surface methodology (RSM) and genetic algorithm (GA) for optimizing artificial neural network (ANN) topology of convective drying kinetic of carrot cubes were investigated. A multilayer feed-forward ANN trained by back-propagation algorithms was developed to correlate output (moisture ratio) to the four exogenous input variables (drying time, drying air temperature, air velocity, and cube size). A predictive response surface model for ANN topologies was created using RSM. The response surface model was interfaced with an effective GA to find the optimum topology of ANN. The factors considered for building a relationship of ANN topology were the number of neurons, momentum coefficient, step size, number of training epochs, and number of training runs. A second-order polynomial model was developed from training results for mean square error (MSE) of 50 developed ANNs to generate 3D response surfaces and contour plots. The optimum ANN had minimum MSE when the number of neurons, step size, momentum coefficient, number of epochs, and number of training runs were 23, 0.37, 0.68, 2,482, and 2, respectively. The results confirmed that the optimal ANN topology was more precise for predicting convective drying kinetics of carrot cubes.     

Modeling of paper mill sewage sludge drying using artificial neural networks: Reduction of the training database through Taguchi’s method

Drying of sewage sludge is typically modeled as simultaneous heat and mass transfer phenomena. The capability of conventional models to take into account crust formation, cracks, and shrinking is limited. Artificial neural networks (ANNs) are suitable tools for dynamic representation of drying processes; however, obtaining a suitable database is a resource consuming task. Based on the Taguchi method, nine experiments were defined to set up a training database and to develop an ANN model. A high Pearson correlation coefficient was verified when comparing the drying kinetic curve generated by the ANN model with the one obtained during the validation experiments.     

Artificial neural network-based modeling of pressure drop coefficient for cyclone separators

In order to build the complex relationships between cyclone pressure drop coefficient (PDC) and geometrical dimensions, representative artificial neural networks (ANNs), including back propagation neural network (BPNN), radial basic functions neural network (RBFNN) and generalized regression neural network (GRNN), are developed and employed to model PDC for cyclone separators. The optimal parameters for ANNs are configured by a dynamically optimized search technique with cross-validation. According to predicted accuracy of PDC, performance of configured ANN models is compared and evaluated. It is found that, all ANN models can successfully produce the approximate results for training sample. Further, the RBFNN provides the higher generalization performance than the BPNN and GRNN as well as the conventional PDC models, with the mean squared error of 5.84 × 10^?4 and CPU time of 120.15 s. The result also demonstrates that ANN can offer an alternative technique to model cyclone pressure drop.     

遗传算法与神经网络(Ⅱ)──用EGA-GDR训练神经网络

为了更有效地解决神经网络培训中遇到的局部最优解问题，提出一种融合EGA和GDR算法特长的新算法──EGA-GDR算法．通过分别对拓扑为2×3×3和8×8×4两个神经网络的训练，表明该算法较之SA-GDR算法可以更有效地解决神经网络训练中的局部最优解问题．     

Prediction of the functional properties of ceramic materials from composition using artificial neural networks

We describe the development of artificial neural networks (ANN) for the prediction of the properties of ceramic materials. The ceramics studied here include polycrystalline, inorganic, non-metallic materials and are investigated on the basis of their dielectric and ionic properties. Dielectric materials are of interest in telecommunication applications, where they are used in tuning and filtering equipment. Ionic and mixed conductors are the subjects of a concerted effort in the search for new materials that can be incorporated into efficient, clean electrochemical devices of interest in energy production and greenhouse gas reduction applications. Multi-layer perceptron ANNs are trained using the back-propagation algorithm and utilise data obtained from the literature to learn composition–property relationships between the inputs and outputs of the system. The trained networks use compositional information to predict the relative permittivity and oxygen diffusion properties of ceramic materials. The results show that ANNs are able to produce accurate predictions of the properties of these ceramic materials, which can be used to develop materials suitable for use in telecommunication and energy production applications.     

Nonlinear system identification and model reduction using artificial neural networks

We present a technique for nonlinear system identification and model reduction using artificial neural networks (ANNs). The ANN is used to model plant input–output data, with the states of the model being represented by the outputs of an intermediate hidden layer of the ANN. Model reduction is achieved by applying a singular value decomposition (SVD)-based technique to the weight matrices of the ANN. The sequence of state values is used to convert the model to a form that is useful for state and parameter estimation. Examples of chemical systems (batch and continuous reactors and distillation columns) are presented to demonstrate the performance of the ANN-based system identification and model reduction technique.     

Application of Artificial Neural Networks (ANNs) in Drying Technology: A Comprehensive Review

Inspired by the functional behavior of the biological nervous system of the human brain, the artificial neural network (ANN) has found many applications as a superior tool to model complex, dynamic, highly nonlinear, and ill-defined scientific and engineering problems. For this reason, ANNs are employed extensively in drying applications because of their favorable characteristics, such as efficiency, generalization, and simplicity. This article presents a comprehensive review of numerous significant applications of the ANN technique to solve problems of nonlinear function approximation, pattern detection, data interpretation, optimization, simulation, diagnosis, control, data sorting, clustering, and noise reduction in drying technology. We summarize the use of the ANN approach in modeling various dehydration methods; e.g., batch convective thin-layer drying, fluidized bed drying, osmotic dehydration, osmotic-convective drying, infrared, microwave, infrared- and microwave-assisted drying processes, spray drying, freeze drying, rotary drying, renewable drying, deep bed drying, spout bed drying, industrial drying, and several miscellaneous applications. Generally, ANNs have been used in drying technology for modeling, predicting, and optimization of heat and mass transfer, thermodynamic performance parameters, and quality indicators as well as physiochemical properties of dried products. Moreover, a limited number of researchers have focused on control of drying systems to achieve desired product quality by online manipulating of the drying conditions using previously trained ANNs. Opportunities and limitations of the ANN technique for drying process simulation, optimization, and control are outlined to guide future R&D in this area.     

Prediction of Energy and Exergy of Carrot Cubes in a Fluidized Bed Dryer by Artificial Neural Networks

In this study both static and recurrent artificial neural networks (ANNs) were used to predict the energy and exergy of carrot cubes during fluidized bed drying. Drying experiments were conducted at air temperatures of 50, 60, and 70°C; bed depths of 3, 6, and 9 cm; and square-cubed carrot dimensions of 4, 7, and 10 mm. Five hundred eighteen patterns, obtained from experiments, were used to develop the ANN models. Initially, a static ANN was applied to correlate the outputs (energy and exergy of carrot cubes) to the four exogenous inputs (drying time, drying air temperature, carrot cube size, and bed depth). In the recurrent ANNs, in addition to the four exogenous inputs, two state inputs and outputs (energy and exergy of carrot cubes) were used. To find optimum ANN models, various numbers of hidden neurons were investigated. The energy and exergy of carrot cubes were predicted with R ² values of greater than 0.95 and 0.97 using static and recurrent ANNs, respectively. Accordingly, the optimal recurrent model could be utilized for determining the appropriate drying conditions of carrot cubes to reach the optimal energy efficiency in fluidized bed drying.     

Artificial neural network approach for flow regime classification in gas-liquid-fiber flows based on frequency domain analysis of pressure signals

The feasibility of a transportable artificial neural network (ANN)-based technique for the classification of flow regimes in three phase gas/liquid/pulp fiber systems by using pressure signals as input was examined. Experimental data obtained in a vertical, circular column in height and in diameter, with air/water/Kraft softwood paper pulp, were used. The pulp consistency (weight percent of dry pulp in the pulp-water mixture) was varied in the 0.0-1.5% range. Local pressure fluctuations were recorded at three different stations along the column using three independent but principally similar transducers. An ANN was designed, trained and tested for the classification of the flow regimes using as input some density characteristics of the power spectrum for one of the normalized pressure signals (from Sensor 1), and was shown to predict the flow regimes with good accuracy. A voting scheme was also examined in which the three sensors fed separately trained ANNs, and a correct flow regime would require a vote from at least two of the three ANNs. This scheme improved the agreement between the model predictions and the data.The ANN trained and tested for Sensor 1 predicted the flow regimes reasonably well when applied directly to the normalized pressure power spectrum density characteristics of the other two sensors, indicating a good deal of transportability. For further improvement of transportability, an ANN-based method was also developed, whereby the power spectrum density characteristics of other sensors were adjusted before they were used as input to the ANN that was based on Sensor 1 alone. The method was shown to improve the accuracy of the flow regime predictions. This method requires in practice, that the “replacement” sensor to which regime identification is transported will be, for some while, in simultaneous use with the sensor to be replaced; then the training of the “input-adjusting” ANN would be possible in industry practice. Such a situation is realistic for sensitive processes, where redundant sensors are implemented for fault tolerance.     

Fuzzy logic model for the prediction of cement compressive strength

A fuzzy logic prediction model for the 28-day compressive strength of cement mortar under standard curing conditions was created. Data collected from a cement plant were used in the model construction and testing. The input variables of alkali, Blaine, SO₃, and C₃S and the output variable of 28-day cement strength were fuzzified by the use of artificial neural networks (ANNs), and triangular membership functions were employed for the fuzzy subsets. The Mamdani fuzzy rules relating the input variables to the output variable were created by the ANN model and were laid out in the If-Then format. Product (prod) inference operator and the centre of gravity (COG; centroid) defuzzification methods were employed. The prediction of 50 sets of the 28-day cement strength data by the developed fuzzy model was quite satisfactory. The average percentage error levels in the fuzzy model were successfully low (2.69%). The model was compared with the ANN model for its error levels and ease of application. The results indicated that through the application of fuzzy logic algorithm, a more user friendly and more explicit model than the ANNs could be produced within successfully low error margins.     

IDENTIFICATION OF LIQUID-LIQUID FLOW PATTERN IN A HORIZONTAL PIPE USING ARTIFICIAL NEURAL NETWORKS

Identification of flow pattern during the simultaneous flow of two immiscible liquids requires knowledge of the flow rate of each fluid as well as knowledge of other physical parameters like conduit inclination, pipe material, pipe diameter, viscosity of the oil, wetting characteristics of the pipe, design of the entry mixer, and fluid-fluid interfacial tension. This article presents an artificial neural network (ANN)-based novel technique to determine the liquid-liquid flow regime. This approach uses phase superficial velocities as input parameters, which are obtained from a specific set of data obtained from experimental investigations. Both experimental and ANN-based determinations of liquid-liquid flow pattern have been undertaken for a common data set and the results are compared to prove the effectiveness of ANNs in pattern recognition. A unique ANN architecture is identified with three hidden layers, and the inputs and outputs are modeled into binary form. Levenberg-Marquardt (LM) learning algorithm is used for training this neural network. The design details of the ANN, parameter modeling, and training aspects are presented.     

基于粒子群算法的软仪表技术

在软测量建模中,最常见的非机理建模方式就是利用神经网络进行建模,而近年来兴起的粒子群算法目前已应用于神经网络的训练。在对粒子群算法提出改进方案后,提出了基于改进的粒子群算法的前馈神经网络训练方案。然后再将神经网络应用到焦化装置分流塔柴油95％点软仪表模型参数估计中,得到了满意的结果,可以满足工业过程中的实际需要。     

基于自适应神经网络的芳烃异构化过程建模

针对芳烃异构化过程(AHIP)中影响对二甲苯(PX)产率的因素众多且复杂等特点,提出一种自适应神经网络(Adaptive ANN)以建立AHIP的各因素与PX产率的关联模型.Adaptive ANN将样本分成训练样本和校验样本,并设计过拟合判据参数.通过训练样本对网络进行训练,训练过程中以模型对校验样本的预测性能为指标,通过过拟合判据参数的计算自适应地在获得具有最佳预测性能模型时终止网络训练,克服了传统的神经网络以模型的拟合精度为指标,造成训练时间过长和过拟合等缺点.     

Artificial Neural Network Modeling of Mixing Efficiency in a Split-Cylinder Gas-Lift Bioreactor for Yarrowia lipolytica Suspensions

The mixing efficiency in a split-cylinder gas-lift bioreactor has been analyzed for Yarrowia lipolytica cells suspensions. Based on the experimental results, three different approaches for modeling have been applied to predict the mixing time depending on yeast concentration, aeration rate, as well as position on the riser or downcomer regions height. These approaches are represented by: an algorithm mixing differential evolution (DE) with artificial neural networks (ANNs), named hSADE-NN, regression, and the Multilayer Perceptron module from IBM SPSS. In the hSADE-NN, ANN models the process, while DE simultaneously optimizes the topology and the internal parameters of the ANN, so that an optimal model is obtained. It was found from simulations that ANNs are able to model the targeted process with a high degree of efficiency (average absolute relative error less than 8.5%), a small difference among the two ANN-based approaches being observed. Additionally, a sensitivity analysis was performed for determining the model inputs influence on the mixing time.     

DEVELOPMENT OF ANN MODEL FOR NON-LINEAR DRYING PROCESS

ABSTRACT

This paper presents an application of artificial neural network (ANN) technique to develop a model representing the non-linear drying process. The air heat plant (AHP), an important component in drying process is fabricated and used for building the ANN model. An optimal feed forward neural network topology is identified for the air heating system set-up. The training sets are obtained from experimental data. Back propogation algorithm with momentum factor is used for training. The results show that the back propogation ANN can learn the functional mapping between input and output. The advantages of ANN model developed for AHP is highlighted. The developed model can be used for control purposes.     

Using Artificial Neural Network to Predict the Pressure Drop in a Rotating Packed Bed

Although rotating beds are good equipments for intensified separations and multiphase reactions, but the fundamentals of its hydrodynamics are still unknown. In the wide range of operating conditions, the pressure drop across an irrigated bed is significantly lower than dry bed. In this regard, an approach based on artificial intelligence, that is, artificial neural network (ANN) has been proposed for prediction of the pressure drop across the rotating packed beds (RPB). The experimental data sets used as input data (280 data points) were divided into training and testing subsets. The training data set has been used to develop the ANN model while the testing data set was used to validate the performance of the trained ANN model. The results of the predicted pressure drop values with the experimental values show a good agreement between the prediction and experimental results regarding to some statistical parameters, for example (AARD% = 4.70, MSE = 2.0 × 10^?5 and R² = 0.9994). The designed ANN model can estimate the pressure drop in the countercurrent flow rotating packed bed with unexpected phenomena for higher pressure drop in dry bed than in wet bed. Also, the designed ANN model has been able to predict the pressure drop in a wet bed with the good accuracy with experimental.     

Asphaltene precipitation and deposition in oil reservoirs – Technical aspects,experimental and hybrid neural network predictive tools

Precipitation of asphaltene is considered as an undesired process during oil production via natural depletion and gas injection as it blocks the pore space and reduces the oil flow rate. In addition, it lessens the efficiency of the gas injection into oil reservoirs. This paper presents static and dynamic experiments conducted to investigate the effects of temperature, pressure, pressure drop, dilution ratio, and mixture compositions on asphaltene precipitation and deposition. Important technical aspects of asphaltene precipitation such as equation of state, analysis tools, and predictive methods are also discussed. Different methodologies to analyze asphaltene precipitation are reviewed, as well. Artificial neural networks (ANNs) joined with imperialist competitive algorithm (ICA) and particle swarm optimization (PSO) are employed to approximate asphaltene precipitation and deposition with and without CO₂ injection. The connectionist model is built based on experimental data covering wide ranges of process and thermodynamic conditions. A good match was obtained between the real data and the model predictions. Temperature and pressure drop have the highest influence on asphaltene deposition during dynamic tests. ICA-ANN attains more reliable outputs compared with PSO-ANN, the conventional ANN, and scaling models. In addition, high pressure microscopy (HPM) technique leads to more accurate results compared with quantitative methods when studying asphaltene precipitation.     

Experimental methods in chemical engineering: Artificial neural networks–ANNs

Artificial neural networks (ANNs) are one of the most powerful and versatile tools provided by artificial intelligence and they have now been exploited by chemical engineers for several decades in countless applications. ANNs are computational tools providing a minimalistic mathematical model of neural functions. Coupled with raw data and a learning algorithm, they can be applied to tasks such as modelling, classification, and prediction. Recently, their popularity has grown remarkably and they now constitute one of the most relevant research areas within the fields of artificial intelligence and machine learning. ANNs are large collections of simple classifiers called neurons. Chemical engineers apply them to model complex relationships, predict reactor performance, and to automate process controllers. ANNs can leverage their ability to learn and exploit large data sets, but they can also get stuck in local minima or overfit and are difficult to reverse engineer. In 2016 and 2017, ANNs were cited in 13 245 Web of Science (WoS) articles, 538 of which were in chemical engineering; the top WoS categories were electrical & electronic engineering (1615 occurrences) artificial intelligence (1253), and energy & fuels (980). The top 4 journals mentioning ANNs were Neural Computing & Applications (117), Neurocomputing (84), Energies (76), and Renewable & Sustainable Energy Reviews (76). In the near future, as larger data sets become available (and arduous to analyze), chemical engineers will be able to apply and leverage more sophisticated ANN architectures.     

A neural network approach to predict activity coefficients

Artificial neural networks (ANNs) and a group‐contribution approach were used to develop an algorithm to predict activity coefficients for binary solutions. The Levenberg–Marquardt algorithm was used to train the ANN and to predict the parameters of the Margules equation. The ANN was trained using phase‐equilibrium database from DECHEMA. The selected systems include alcohols, phenols, aldehydes, ketones, and ethers. The trim mean based on 20% data elimination was selected as the best representation of the Margules‐equation parameters. The algorithm was validated with 121 VLE systems and results show that the ANN provides a relative improvement over the UNIFAC method.