Determination of Drying Characteristics of Timber by Using Artificial Neural Networks and Mathematical Models

In this research, poplar and pine timbers have been dried in heat pump dryer functioning on the basis of 24-h operation. The change in weight in all of the timbers was followed in the drying chamber and drying stopped when the desired weight was achieved. Initial moisture content of the poplar timbers was 1.28 kg water/kg dry matter, and the moisture content was reduced to 0.15 kg water/kg dry matter moisture content in 70 h; the moisture content of the pine timbers, which was 0.60 kg water/kg dry matter, was reduced to the same amount in 50 h. Drying air temperature, relative humidity, and stack weight were measured and collected during drying and saved on a computer and analyzed afterwards. The moisture ratios were analyzed with Statgraphic computer program by using semitheoretical models and empirical values. Correlation and standard error of estimation (SEE) and R ² values were achieved.     

High-Performance Nanocatalyst for Adsorptive and Photo-Assisted Fenton-Like Degradation of Phenol: Modeling Using Artificial Neural Networks

High-performance activated carbon-zinc oxide (Ac–ZnO) nanocatalyst was fabricated via the microwave-assisted technique. Ac–ZnO was characterized and the results indicated that Ac–ZnO is stable, had a band gap of 3.26?eV and a surface area of 603.5?m²g^?1, and exhibited excellent adsorptive and degrading potentials. About 93% phenol was adsorbed within 550?min of reaction by Ac–ZnO. Impressively, a complete degradation was achieved in 90?min via a photo-Fenton/Ac–ZnO system under optimum conditions. An artificial neural network (ANN) model was developed and applied to study the relative significance of input variables affecting the degradation of phenol in a photo-Fenton process. The ANN results indicate that increases in both H₂O₂ and Ac–ZnO dosage enhanced the rate of phenol degradation. The highest rate constant at the optimum conditions was 0.093?min^?1 and it was found to be consistent with the ANN-predicted rate constant (0.095?min^?1).     

Prediction of Microwave Drying Behavior of Pharmaceutical Powders Using Thin-Layer Models

Common pharmaceutical excipients and active ingredients, wetted with specific solvents, were dried under selected continuous power microwave and pulsed power microwave-vacuum conditions in an experimental system. Irrespective of the drying technique, a typical drying profile, with a constant drying rate stage followed by two falling rate periods, was exhibited. The experimental moisture loss data were fitted to semi-theoretical and empirical thin-layer drying equations and the models compared on the basis of three statistical parameters. The drying characteristics were satisfactorily described by the Lewis, Page, Logarithmic, Chavez-Mendez et al., and Midilli et al. models, with the latter providing the best representation of the data.     

Prediction of Microwave Drying Behavior of Pharmaceutical Powders Using Thin-Layer Models

Common pharmaceutical excipients and active ingredients, wetted with specific solvents, were dried under selected continuous power microwave and pulsed power microwave-vacuum conditions in an experimental system. Irrespective of the drying technique, a typical drying profile, with a constant drying rate stage followed by two falling rate periods, was exhibited. The experimental moisture loss data were fitted to semi-theoretical and empirical thin-layer drying equations and the models compared on the basis of three statistical parameters. The drying characteristics were satisfactorily described by the Lewis, Page, Logarithmic, Chavez-Mendez et al., and Midilli et al. models, with the latter providing the best representation of the data.     

喷雾干燥的数学模型和技术进展

介绍了国外在计算机模型基础上发展起来的喷雾干燥技术的最新进展,由于数字模型回答了喷雾干燥过程中的许多问题,新的喷雾干燥设备（它们更多的是喷雾干燥塔,流化床一体化装置）可以提供较好的品质控制,耗能少,细粉少而效率更高。     

Drying Kinetics Prediction of Solid Waste Using Semi‐Empirical and Artificial Neural Network Models

The drying process of organic solid waste is investigated, based on an experimental study involving its drying kinetics. The experiments were conducted in a thin‐layer fixed‐bed dryer under various operational conditions. The problem of selecting the best fit for solid waste moisture content as a function of time is addressed as well, using artificial neural network (ANN) models and four well‐known drying kinetics correlations commonly applied to biological materials. According to the statistical analysis employed, the simulations showed good results for the ANN, and the Overhults model provided optimum agreement with experimental data among all other models evaluated. Empirical correlations between the Overhults model parameters and the drying operational conditions using nonlinear regression techniques were determined.     

Drying Models and Quality Analysis of Sun-Dried Ciku

Sun drying of ciku (Manilkara zapota) was carried out on different sample sizes to investigate the effects on drying kinetics. It was found that the maximum drying rates of sun-dried ciku decreased with larger product size. Three sunny days are needed to dry the ciku slabs to an average final moisture content of 0.2 g H₂O/g dry mass. The results showed that hardness and chewiness of the dried samples were significantly different (p < 0.05) compared to fresh ciku slabs and commercial dried fruit. The color measurement of dried product showed that L? and b? values significantly decreased (p < 0.05), whereas the a? value increase was not significantly different (p > 0.05) compared to fresh ciku slabs. In addition, sun-dried ciku retained a total polyphenol content (TPC) that was relatively low (p < 0.05) compared to fresh ciku.     

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 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.     

基于NNs模型的轻骨料混凝土梁抗剪分析

混凝土构件的抗剪问题始终未形成统一定论.优化多层前馈神经网络(NNs)模型使用反向传播算法及提前终止技术,能够合理考虑各层神经元几何与材料特性.基于神经网络建立了轻骨料混凝土梁的受剪承载力计算模型,并搜集国内外82组轻骨料混凝土梁受剪试验结果作为样本数据,分为训练组、验证组及测试组,通过与试验值对比分析验证了计算模型的合理性和准确性.研究表明:训练组、验证组及测试组的试验值与NNs模型计算值比值的平均值分别为0.953、1.064和1.124,方差为0.147、0.034和0.091,NNs模型的计算结果能很好的对轻骨料钢筋混凝土梁的抗剪承载力进行预测,并能充分考虑各影响因素的显著性.     

Moisture Content Prediction in the Switchgrass (Panicum virgatum) Drying Process Using Artificial Neural Networks

This article proposes two artificial neural network (ANN)-based models to characterize the switchgrass drying process: The first one models processes with constant air temperature and relative humidity and the second one models processes with variable air conditions and rainfall. The two ANN-based models proposed estimated the moisture content (MC) as a function of temperature, relative humidity, previous MC, time, and precipitation information. The first ANN-based model describes MC evolution data more accurately than six mathematical empirical equations typically proposed in the literature. The second ANN-based model estimated the MC with a correlation coefficient greater than 98.8%.     

利用神经网络动态模拟污水生物脱氮过程

用以活性污泥数学模型 (ASM)为基础的EFOR软件的模拟输入输出数据训练设计好的神经网络 ,然后同时变化输入数据 ,比较输出数据。结果表明神经网络用于污水生物脱氮过程的动态的模拟 ,预测出水COD的误差可控制在± 3%以下 ,出水TN的误差可控制在± 6 %以下 ,出水SS的误差可控制在± 10 %以下。     

基于Elman网络的动力配煤煤质预测模型的研究

动力配煤的多种煤质指标与各组分单一煤种的煤质指标之间具有典型的非线性映射特征。Elman回归神经网络是一种典型的动态神经元网络,具有映射动态特征的功能,尤其具有高度的非线性映射能力。笔者利用Elman网络建立了动力配煤煤质预测模型,并以较好的预测效果实现了动力配煤煤质预测,从而证实了该方案的可行性。     

香蕉片热泵干燥过程动力学模型研究

利用自制的热泵干燥设备,选择加热温度为45℃、风速为1．0m／s、物料厚度为3mm条件下的热泵干燥香蕉切片试验数据作为实测值样本。基于Matlab软件,利用高斯一牛顿算法,对传统干燥模型进行非线性最小二乘数据拟合求解,确定干燥系数。通过决定系数（R＇）、卡方差（x^2）、平均相对偏差（MBE）和均方根误差（RMSE）等拟合优度评价指标对7种干燥模型进行评价。结果表明,HendersonandPabiS模型的理论值和实测值吻合良好,能够很好地预测和控制香蕉切片热泵干燥过程的水分比变化规律。     

Thin-Layer Drying of Flax Fiber: II. Modeling Drying Process Using Semi-Theoretical and Empirical Models

Thin-layer drying experiments were performed for drying flax fiber under four different drying conditions. In all drying treatments the absolute humidity of drying air was 0.0065 kg of water per kg of dry air, but the drying temperature were 30, 50, 70, and 100°C. The drying process was modeled using the drying data and five semi-theoretical and empirical models cited in different literatures. From the five tested models, the Page model gave the best fitting for experimental data with R² equal to 0.99, for all treatments. The estimated drying constants at different drying temperatures were highly correlated with drying air temperature. The drying constants were also highly correlated with the calculated coefficient of diffusions.     

Thin-Layer Drying of Flax Fiber: II. Modeling Drying Process Using Semi-Theoretical and Empirical Models

Thin-layer drying experiments were performed for drying flax fiber under four different drying conditions. In all drying treatments the absolute humidity of drying air was 0.0065 kg of water per kg of dry air, but the drying temperature were 30, 50, 70, and 100°C. The drying process was modeled using the drying data and five semi?theoretical and empirical models cited in different literatures. From the five tested models, the Page model gave the best fitting for experimental data with R ² equal to 0.99, for all treatments. The estimated drying constants at different drying temperatures were highly correlated with drying air temperature. The drying constants were also highly correlated with the calculated coefficient of diffusions.     

Drying Characteristics and Quality of Restructured Wild Cabbage Chips Processed Using Different Drying Methods

The drying characteristics of restructured wild cabbage chips dried using microwave vacuum (MVD), hot air (AD), and microwave freeze drying (MFD) were compared. Some of the key quality parameters of restructured wild cabbage chips such as fracturability and color and sensory characteristics were measured. Results showed that the drying time was reduced with the increase of microwave power (MVD/MFD) and in the case of air drying by the temperature (AD). Drying time was the shortest in the MVD process. Optimal quality of dried chips was obtained with the MFD process at a microwave power level 2.0 W/g.     

一种分布式模糊神经网络在熔融指数软测量中的应用

采用Mamdani模型作为模糊分类器 ,利用神经网络建立非线性模型 ,构造一种分布式神经网络。采用多组样本数据建模 ,根据各输入模糊子集和隶属度函数 ,将输入样本空间模糊分割成多个子空间 ,对每个子空间用一个神经网络模型建立映射关系。对每一组输入向量在确定归属类后 ,自动切换至对应的子网络作为输入 ,该子网络的输出值则作为分布式网络的输出。仿真结果表明 ,该方法与用单个神经元网络相比 ,明显提高了模型的精度和泛化能力。