人工神经网络用于 PBX 炸药装药密度的研究

比较了利用人工神经网络（ＡＮＮ）和混合物密度计算公式对一种聚合物粘结炸药（ＰＢＸ）的装药密度计算的结果。发现利用人工神经网络所得的结果可以正确反映配方组成和温度与装药密度的关系，而且对于新配方和温度，可以利用人工神经网络得到正确的密度数值预报。     

Density measurements of coal samples by different probe gases and their interrelation

Density is useful in deducing the spatial structure of coals. In this paper, nitrogen has been used instead of the commonly employed helium, for the gas displacement pycnometer based density determination of a number of coals of Indian origin. The results show that the nitrogen-based densities are always higher than the helium-based ones. Also, empirical relationships between the helium-based and nitrogen-based coal densities have been developed by two modeling methods, namely, multi-variable regression and artificial neural networks. Although the two models have fared well, the neural network model exhibits a relatively better prediction accuracy and generalization performance than the regression model. This study thus demonstrates that nitrogen, which is cheaper and easily available, can be used gainfully as the probe gas for estimating the true density of coals.     

Prediction of Timber Kiln Drying Rates by Neural Networks

The purpose of this exploratory work was to apply artificial neural network (ANN) modeling to the prediction of timber kiln drying rates based on species and basic density information for the hem-fir mix that grows along the local coastal areas. The ANN models with three inputs (initial moisture content, basic density, and drying time) were developed to predict one output, namely, average final moisture content. The back-propagation algorithm, the most common neural network learning method, was implemented for testing, training, and validation. Optimal configuration of the network model was obtained by varying its main parameters, such as transfer function, learning rule, number of neurons and layers, and learning runs. Accurate prediction of the experimental drying rate data by the ANN model was achieved with a mean absolute relative error less than 2%, thus supporting the powerful predictive capacity of this modeling method.     

Estimation of free-swelling index based on coal analysis using multivariable regression and artificial neural network

The effects of proximate, ultimate and elemental analysis for a wide range of American coal samples on Free-swelling Index (FSI) have been investigated by multivariable regression and artificial neural network methods (ANN). The stepwise least square mathematical method shows that variables of ultimate analysis are better predictors than those from proximate analysis. The non linear multivariable regression, correlation coefficients (R²) from ultimate analysis inputs was 0.71, and for proximate analysis input variables was 0.49. With the same input sets, feed-forward artificial neural network (FANN) procedures improved accuracy of predicted FSI with R² = 0.89, and 0.94 for proximate and ultimate analyses, respectively. The ANN based prediction method, as a first report, shows FSI is a predictable variable, and ANN can be further employed as a reliable and accurate method in the free-swelling index prediction.     

Prediction of Timber Kiln Drying Rates by Neural Networks

The purpose of this exploratory work was to apply artificial neural network (ANN) modeling to the prediction of timber kiln drying rates based on species and basic density information for the hem-fir mix that grows along the local coastal areas. The ANN models with three inputs (initial moisture content, basic density, and drying time) were developed to predict one output, namely, average final moisture content. The back-propagation algorithm, the most common neural network learning method, was implemented for testing, training, and validation. Optimal configuration of the network model was obtained by varying its main parameters, such as transfer function, learning rule, number of neurons and layers, and learning runs. Accurate prediction of the experimental drying rate data by the ANN model was achieved with a mean absolute relative error less than 2%, thus supporting the powerful predictive capacity of this modeling method.     

Prediction of thermodynamic properties of polyvinylpyrrolidone solutions by artificial neural networks coupled with genetic algorithm

In the present study, the artificial neural networks coupled with the genetic algorithm (ANN–GA) models were used to predict the thermodynamic properties of polyvinylpyrrolidone (PVP) solutions in water and ethanol at various temperatures, mass fractions, and molecular weights of polymer. The genetic algorithm (GA) was used to find the best weights and biases of the network and improve the performance of ANNs. The proposed model was composed of three input variables including the temperature of the solution, the mass fraction, and molecular weight of the polymer. Density, viscosity, and surface tension of PVP solutions with various molecular weights (10,000, 25,000, and 40,000) in water and ethanol have been measured in the temperature range 20–55°C and various mass fractions of polymer. The ANN–GA models were trained by the experimental datasets and the prediction of density, surface tension, and viscosity of PVP solutions was performed using these models. The predicted values were compared with the experimental ones and the mean absolute relative error was less than 0.5% for the density and surface tension and about 3% for the viscosity of solutions.     

Neural network (ANN) approach to biodiesel analysis: Analysis of biodiesel density, kinematic viscosity, methanol and water contents using near infrared (NIR) spectroscopy

The use of ethanol and biodiesel, which are alternative fuels or biofuels, has increased in the last few years. Modern official standards list 25 parameters that must be determined to certify biodiesel quality, and these analyses are expensive and time-consuming. Near infrared (NIR/NIRS) spectroscopy (4000-12,820 cm⁻¹) is a cheap and fast alternative to analyse biodiesel quality, when compared with infrared, Raman, or NMR methods, and quality control can be done in realtime (on-line).We compared the performance of linear and non-linear calibration techniques - namely, multiple linear regression (MLR), principal component regression (PCR), partial least squares regression (PLS), polynomial and Spline-PLS versions, and artificial neural networks (ANN) - for prediction of biodiesel properties from near infrared spectra. The model was created for four important biodiesel properties: density (at 15 °C), kinematic viscosity (at 40 °C), water content, and methanol content. We also investigated the influence of different pre-processing methods (Savitzky-Golay derivatives, orthogonal signal correction) on the model prediction capability. The lowest root mean squared errors of prediction (RMSEP) of ANN for density, viscosity, water percentage, and methanol content were 0.42 kg m⁻³, 0.068 mm² s⁻¹, 45 ppm, and 51 ppm, respectively. The artificial neural network (ANN) approach was superior to the linear (MLR, PCR, PLS) and “quasi”-non-linear (Poly-PLS, Spline-PLS) calibration methods.     

Artificial neural network approaches on composition-property relationships of jet fuels based on GC-MS

The relationships of composition-properties of 80 jet fuels concerning chemical compositions and several specification properties including density, flashpoint, freezing point, aniline point and net heat of combustion were studied. The chemical compositions of the jet fuels were determined by GC-MS, and grouped into eight classes of hydrocarbon compounds, including n-paraffins, isoparaffins, monocyclopraffins, dicyclopraffins, alkylbenzens, naphthalenes, tetralins, hydroaromatics. Several quantitative composition-property relationships were developed with three artificial neural network (ANN) approaches, including single-layer feedforward neural network (SLFNN), multiple layer feedforward neural network (MLFNN) and general regressed neural network (GRNN). It was found that SLFNNs are adequate to predict density, freezing point and net heat of combustion, while MLFNNs produce better results as far as the flash point and aniline point prediction are concerned. Comparisons with the multiple linear regression (MLR) correlations reported and the standard ASTM methods showed that ANN approaches of composition-property relationships are significant improvement on MLR correlations, and are comparable to the standard ASTM methods.     

Response Surface Methodology and Artificial Neural Networks for Optimization of Catalytic Esterification of Lactic Acid

Response surface methodology (RSM) and artificial neural network (ANN) models were employed to study the esterification of lactic acid and isoamyl alcohol. A carbon-based solid acid catalyst prepared by wet impregnation was used in the esterification reaction. Experimental characterization revealed its potential to serve as catalyst for the esterification reaction. The experiments were performed based on the design of experiments provided by RSM and ANN models. Both models were compared on the basis of prediction efficacies and deviation from actual data. The prediction data results demonstrated that the ANN model gave better prediction efficiency and lower prediction deviation than the RSM model. The ANN model provided a higher coefficient of determination and lower error values than the RSM model. Moreover, the catalyst exhibited a good stability and recyclability up to four reaction cycles.     

Viscosity of ionic liquids using the concept of mass connectivity and artificial neural networks

Artificial neural networks (ANN) and the concept of mass connectivity index are used to correlate and predict the viscosity of ionic liquids. Different topologies of a multilayer feed forward artificial neural network were studied and the optimum architecture was determined. Viscosity data at several temperatures taken from the literature for 58 ionic liquids with 327 data points were used for training the network. To discriminate among the different substances, the molecular mass of the anion and of the cation, the mass connectivity index and the density at 298 K were considered as the independent variables. The capabilities of the designed network were tested by predicting viscosities for situations not considered during the training process (31 viscosity data for 26 ionic liquids). The results demonstrate that the chosen network and the variables considered allow estimating the viscosity of ionic liquids with acceptable accuracy for engineering calculations. The program codes and the necessary input files to calculate the viscosity for other ionic liquids are provided.     

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.     

ANN model for prediction of powder packing

A multilayer feed forward backpropagation (MFFB) learning algorithm was used as an artificial neural network (ANN) tool to predict packing of fused alumina powder mixtures of three different sizes in green state. The data used in model construction were collected by mixing and pressing powders with average particle sizes of 350, 30 and 3 μm and with narrow particle size distributions. The data sets that were composed of green densities of cylindrical pellets were first randomly partitioned into two for training and testing of the ANN models. Based on the training data an ANN model of the packing efficiencies was created with low average error levels (3.36%). Testing of the model was also performed with successfully good average error levels of 3.39%.     

Ultra-high temperature ceramics melting temperature prediction via machine learning

Melting temperature has great influence on the high temperature properties and working temperature limits of ultra-high temperature ceramics (UHTCs) In order to bypass the challenge in the measurement of ultra-high melting points, this paper proposed a novel method to predict UHTCs melting temperature via machine learning. A dataset including more than ten thousand melting temperature data has been established, which covers 8 elements and most of the known non-oxide UHTCs. We built up an element to ceramic system framework by back propagation artificial neural network (BPANN) with the accuracy approaching to 90% and the correlation coefficients approaching to 0.95. Our work provides a probability to get the high accuracy melting temperature of UHTCs, and a more convenient way to develop novel materials with higher working temperature. The given case of melting temperature prediction of Hf-C-N ceramics proves the generality of the artificial neural network (ANN). An inter-validation of melting temperature prediction using our network with materials thermodynamics and density functional theory (DFT) has been demonstrated, indicating that our network is of powerful prediction ability.     

SOFT COMPUTING METHOD FOR PREDICTION OF CO2 CORROSION IN FLOW LINES BASED ON NEURAL NETWORK APPROACH

An important aspect of corrosion prediction for oil/gas wells and pipelines is to obtain a realistic estimate of the corrosion rate. Corrosion rate prediction involves developing a predictive model that utilizes commonly available operational parameters, existing lab/field data, and theoretical models to obtain realistic assessments of corrosion rates. This study presents a new model to predict corrosion rates by using artificial neural network (ANN) systems. The values of pH, velocity, temperature, and partial pressure of the CO₂ are input variables of the network and the rate of corrosion has been set as the network output. Among the 718 data sets, 503 of the data were implemented to find the best ANN structure, and 108 of the data that were not used in the development of the model were used to examine the reliability of this method. Statistical error analysis was used to evaluate the performance and the accuracy of the ANN system for predicting the rate of corrosion. It is shown that the predictions of this method are in acceptable agreement with experimental data, indicating the capability of the ANN for prediction of CO₂ corrosion rate in production flow lines.     

Artificial intelligence density model for oxide glasses

A comprehensive study to perform glass density prediction employing artificial intelligence using a dataset of 6630 oxide glass samples. The prediction is done based on Ionic packing ratio as the independent variable and experimental densities from the dataset as the dependent variable. Random forest regression and artificial neural networks were observed as the best models training the density datasets. The random forest regression had the least average R² score for large datasets. Artificial neural networks employing sigmoid and ReLU activation functions dominate in predicting the glass density as compared to tanh and identity activation functions. Based on this study we can theoretically predict the density of any oxide glass to an extent of maximum accuracy for a known glass composition.     

Improved Artificial Neural Network for Data Analysis and Property Prediction in Slag Glass–Ceramic

The development of slag glass–ceramics has environmental and commercial value. However, new types of these materials are usually developed using the "trial and error" method because of little understanding of the relationship between the composition, processing, microstructure, and properties. In this paper, artificial neural network (ANN) technology was applied to investigate the relationship between the composition content and the properties of slag glass–ceramic. The investigation showed that the ANN model had an outstanding learning ability and was effective in complex data analysis. If the data set reflects the relationship of the composition and property, the trained network will learn the relationship and then give relatively accurate and stable prediction. A new "virtual sample" technology has also been created which improves the prediction performance of the network by providing greater accuracy and reliability. With this virtual sample technology, the ANN model can establish the exact relationship from a small-size-data set, and gives accurate predictions. This improved ANN model is a powerful and reliable tool for data analysis and property prediction, and will facilitate the material design and development of slag glass–ceramics.     

利用人工神经网络预测复相陶瓷材料组分含量的研究

根据人工神经网络（ANN）的BP(back propagation）算法,预测复相陶瓷各组分的体积分数的神经网络模型,模型由三层神经元组成,分别为输入层、隐含层和输出层用以模拟人脑的结构,输入层参数由两部分组成,一部分为抗弯强度、硬度和断裂韧性等力学性能,另一部分包括相应各组分的弹性模量和热膨胀系数,以用来辨识不同的材料系统,输出层参数是复相陶瓷中各组分的体积分数,只要训练样本值足够精确,预测模型就能够预测已有的陶瓷系统的组分含量,同时,模型能够预估未知材料系统的组分含量。计算证明,模型的容错性较好,因此对开发新型复相陶瓷非常有益。     

ZrO2-SiC材料中原位SiC生成量预报的神经网络模型

研究了基于神经网络的ZrO2-SiC材料中原位SiC生成量预报模型,运用材料制备过程中的工艺参数,实现了SiC生成量的预报.结果表明:本模型具有良好的预报效果,人工神经网络是材料性能定量预报的一种有效方法.