人工神经网络在材料科学与加工中的应用

综述了人工神经网络在材料科学基础理论研究、材料检测以及其在材料工业中的应用研究。认为随着人工神经网络理论本身及其相关理论、相关技术的不断发展 ,其在材料科学与加工中的应用定将更加深入和广泛 ,特别是在材料加工中的应用具有良好的发展前景     

BP网络预测H_2在煤液化油混合组分中的溶解度

为满足煤制油工业化过程中设计和操作需要,以H_2在神华煤液化油模型组分混合溶剂中实测溶解度为基础,考察利用人工神经网络法预测H_2在该系统中溶解度的能力。结果表明,神经网络的计算精度随着循环次数的增加而提高;对于不同种类的混合溶剂,随着隐藏层个数的增加,计算值与试验值之间的相对误差呈现逐渐减小的趋势,从减小计算量的角度考虑,选定为4个隐藏层;3-4-1网络结构对于H_2在不同混合溶剂中溶解度的计算值与试验值最大相对误差为4.48%,这表明该模型能够满足H_2在该系统中溶解度的预测需要。     

Predicting the properties of needlepunched nonwovens using artificial neural network

Needlepunching is a well‐known nonwoven process of converting fibrous webs into self‐locking or coherent structures using barbed needles. In this study, Artificial Neural Network (ANN) modeling technique has been used to predict the bulk density and tensile properties of needlepunched nonwoven structures by relating them with the main process parameters, namely, web area density, punch density, and depth of needle penetration. The simultaneous effect of more than one parameter on bulk density and tensile properties of needlepunched nonwoven structures have been investigated based upon the results of trained ANN models. A comparison is also made between the experimental and predicted values of fabric bulk density and tensile strength in the machine and crossmachine directions in unseen or test data sets. It has been inferred that the ANN models have achieved good level of generalization that is further ascertained by the acceptable level of mean absolute error obtained between predicted and experimental results. © 2009 Wiley Periodicals, Inc. J Appl Polym Sci, 2009     

煤种成浆性的人工神经网络预测模型研究

为更好地预测煤的成浆性,以大量煤种成浆浓度试验数据为基础,建立了3个输出因子的神经网络成浆浓度预测模型,模型采用L-M算法,对输入数据进行数据预处理,最后对比分析了神经网络预测模型与回归分析模型的预测结果。结果表明,以A_d、哈氏可磨性指数HGI和氧含量O为输入因子的模型预测结果平均绝对误差为0.63%,以M_(ad)、HGI和O为输入因子的模型预测结果平均绝对误差为0.60%,以M_(ad)、HGI和氧碳比O/C为输入因子的模型预测结果平均绝对误差为0.40%,3种组合的模型结果均小于回归分析模型的平均绝对误差1.15%。因此神经网络模型比回归分析模型有更好的预测能力,其中以M_(ad)、HGI和O/C为输入因子的神经网络模型预测结果最好。     

Application of artificial neural network optimization for resilient ceramic parts fabricated by direct ink writing

Geometries of ceramic parts for high-temperature sealing have great influence on their compression-resilience behaviors. In this work, an accurate and large-scale artificial neural network (ANN) was established to match the relationship between structural parameters and mechanical properties of ZrO₂ parts fabricated by 3D printing. Four geometry parameters of the designed ZrO₂ parts were imported as input and apparent Young's modulus and maximum deformation simulated by finite element method (FEM) were imported as output. FEM calculation provided 400 groups of data for the training of ANN, which greatly improved the predicted accuracy of the network. The predicted results show the mechanical performance of the parts with a range of modulus from 9.24 × 10⁻³ GPa to 100.35 × 10⁻³ GPa and a range of maximum deformation from 2.32% to 5.80% can be forecasted with error less than 8%. Based on the optimized structural parameters, the designed ZrO₂ parts were fabricated by Direct Ink Writing (DIW) technique. The experimental compression-rebound property is comparable to that of ANN prediction. It demonstrates that the combined method of ANN and FEM is a preferable way to optimize the structure and guide the fabrication of complex ceramic parts by 3D printing method.     

红外光谱法结合K⁃均值聚类与神经网络对饮料瓶的检验研究

利用傅里叶变换红外光谱法对41个不同品牌的塑料饮料瓶进行快速无损检测.谱图数据在经过预处理后可将样品分为聚对苯二甲酸乙二醇酯和聚乙烯两类.每一类内部的各个样品红外特征峰存在差异.对于数量最多的一类样品,通过主成分分析将样品光谱数据降维并提取主成分,然后结合K-均值聚类对样品进一步分组.最后以聚类结果作为因变量,构建神经...     

Polyurethanes synthetized with polyols of distinct molar masses: Use of the artificial neural network for prediction of degree of polymerization

The molar mass of the polyurethanes (PUs)' reagents directly influences their thermal response, affecting both the polymerization process and the enthalpy and the degree of reaction. This study reports applying an artificial neural network (ANN), associated with surface response methodology (SRM) models, to predict the calorimetric behavior of certain PU's bulk polymerizations. A noncatalyzed reaction between an aliphatic hexamethylene diisocyanate (HDI) and a polycarbonate diol (PCD) with distinct molar masses (500, 1000, and 2000 g/mol) was proposed. A high level of reliability of the predicted calorimetric curves was obtained due to an excellent agreement between theoretical and modeled results, enabling creating a 3D surface response to predict the reaction kinetics. Also, it was possible to observe that the polymerization kinetics is affected by the  OH group's association phenomena. The applied methodology can be extended for other materials or properties of interest.     

Artificial neural network for the prediction of physical properties of organic compounds based on the group contribution method

In the development and optimization of chemical processes involving the selection of organic fluids, knowledge of the physical properties of compounds is vital. In many cases, it is complex to find experimental measurements for all substances, so it becomes necessary to have a tool to predict properties based on the characteristics of the molecule. One of the most extensively used methods in the literature is the estimation by contribution of functional groups, where properties are calculated using the constituent elements of the molecule. There are several models published in the literature, but they fail to represent a wide variety of compounds with high accuracy and simultaneously maintain a low computational complexity. The aim of this work is to develop a prediction model for eight thermodynamic properties (melting temperature, boiling temperature, critical pressure, critical temperature, critical volume, enthalpy of vaporization, enthalpy of fusion, and enthalpy of gas formation) based on the group contribution methodology by implementing a multilayer perceptron. Here, 2736 substances were used to train the neural network, whose prediction capacity was compared with other reference models available in the literature. The proposed model presents errors ranging from 1% to 5% for the different properties (except for the melting point), which improves the reference models with errors in the range of 3%–30%. Nevertheless, a difficulty in the prediction of the melting point is detected, which could represent an inherent hindrance to this methodology.     

基于模式分类的油水混合物含水率测量方法

为了提高原油脱水过程中含水率测量的精度和量程,提出了油水混合物多模态的电特性计算方法。通过分析油水混合物的不同存在模式,采用有限元法计算不同模态油水混合物的介电常数、电导率与原油含水率之间的关系,并通过自组织人工神经网络实现了油水混合物的模式分类。实验结果表明,通过计算介电常数和电导率可以识别油水混合物的不同模态,及时修正含水分析仪的设置参数,有效地提高了原油含水率在线测量的精确度。     

人工神经网络用于三苯基丙烯腈衍生物的定量结构-活性关系模型

采用人工神经网络(ANN)BP算法探讨了24个三苯基丙烯睛衍生物的lg1/C(C为半致死浓度)与X位羟基指示数I、分子表面积SA和B环上原子净电荷之和QB之间的关系,以20个样本为训练集建立了定量结构-活性关系(QSAR)模型,其相关系数和标准偏差分别为R=0.9969和SD=0.0164,其余4个样本为测试集,得到R=0.9913和SD=0.1533;用多元线性回归(MLR)方法建立的QSAR模型R=0.9360,SD=0.3779。结果表明,ANN方法具有良好的预测能力,比MLR方法更精密。     

BP神经网络计算乙醇-环己烷-水体系汽-液平衡

基于带动量因子的 BP神经网络 ,以实验测定的乙醇 (1) -环己烷 (2 ) -水 (3)体系在 35℃、5 0℃、6 5℃的汽液平衡数据为训练和预测样本进行了计算 ,选择温度、X1 和 X2 3个参数作为输入 ,Y1 、Y2 和 Y3作为输出 ,隐层单元数为 9,学习速率为 0 .5 ,动量因子为 0 .12 8。对 Y1 ,Y2 ,Y3,神经网络计算的训练平均误差分别为 :0 .0 0 71,0 .0 101,0 .0 0 6 0 ,预测平均误差分别为 :0 .0 0 6 5 ,0 .0 12 4 ,0 .0 0 6 0 ,小于 NRTL 模型计算的相应误差。为相平衡计算提供了新的有效的工具。     

人工神经网络-基团键贡献耦合模型预测煤液化油的偏心因子

为探索预测煤直接液化油窄馏分的偏心因子的新方法,建立了基于人工神经网络-基团键贡献耦合模型(ANN-GBC),以煤直接液化油包含的45个基团键和常压沸点(T_b)共46个参数作为该模型的输入参数,研究了煤直接液化油15个窄馏分的偏心因子与分子结构之间的相关性。结果表明,通过计算20个模型化合物的偏心因子,表明ANN-GBC模型具有较好的模拟推算功能,计算值与理论值平均相对误差均在2.5%以下。偏心因子ω随蒸馏切割馏分温度的升高而增大,ANN-GBC模型预测值普遍高于Watanasiri、NEDOL关联式的计算值。380℃馏分ω小于1,相对偏差较小;380℃馏分ω偏差较大;针对420℃馏分,因仅能定性定量分析其中20%物质,不同物质的含量差异导致个别结果的跳跃,ω偏差较大。     

Tribological behavior prediction of friction materials for ultrasonic motors using Monte Carlo-based artificial neural network

In this article, the relationship of complexity, diversity, and uncertainty between components and tribological properties of friction materials based on a Monte Carlo-based artificial neural network (MC-ANN) model was predicted precisely. Meanwhile, the grey relational analysis was applied to figure out weight of factors, optimize formulation design, and calculate nonlinear dependency of ingredients. The accuracy of model was studied by comparing experimental and simulated values on the basis of statistical methods (root-mean-squared error). It was found that the model exhibited an excellent performance in predicting and fitting effect. Moreover, comprehensive analysis of weight indicated that nano-SiO₂ and mica exerted a significant role in improving the friction stability and wear resistance. According to different contents of each ingredient, the corresponding friction coefficient and specific wear rate could be obtained by virtue of a well-trained MC-ANN model without experiments, which saved a lot of time and money. It can be expected that the results of this work will extend the current research and pave a route for further in-depth studies of friction materials. © 2018 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2019 , 136, 47157.     

人工神经网络在膜生物反应器膜污染预测中的应用前景

近年来,膜污染逐渐成为膜生物反应器研究的热点问题,并面临着突破性进展.人工神经网络为膜生物反应器膜污染预测的研究提供了新的思路,是膜生物反应器优化控制的有效工具.作者对人工神经网络在膜污染中的应用进行了较为全面的综述,并指出了其在膜生物反应器膜污染研究中的应用前景.     

降凝降黏剂在原油开采集输中的应用

降凝降黏剂已成为钻高难度的高温深井、大斜度定向井、水平井和各种复杂地层的重要手段,并且还可广泛地用作解卡液、射孔完井液、修井液和取心液等。由于稠油的黏度以及凝点低,防止在开采过程中出现困难,降凝降黏剂的应用需要进行一定的关注,解决其发展困难。     

应用人工神经网络模拟腈纶五效减压蒸发系统

利用Matlab所提供的人工神经网络模拟五效蒸发系统的非线性过程。模拟采用在生产过程中采集的数据,生成模拟五效减压蒸发系统中进料量、各效阀位等参数、各效蒸发器壳程压力关系的人工神经网络。用此网络处理相关操作参数,得到模拟的生产效果。将模拟效果与实际生产过程中的数据对比发现,两者十分接近。     

Development of an artificial neural network correlation for prediction of hold-up of slurry transport in pipelines

In the literature, very few correlations have been proposed for hold-up prediction in slurry pipelines. However, these correlations fail to predict hold-up over a wide range of conditions. Based on a databank of around 220 measurements collected from the open literature, a correlation for hold-up was derived using artificial neural network (ANN) modeling. The hold-up for slurry was found to be a function of nine parameters such as solids concentration, particle dia, slurry velocity, pressure drop and solid and liquid properties. Statistical analysis showed that the proposed correlation has an average absolute relative error (AARE) of 2.5% and a standard deviation of 3.0%. A comparison with selected correlations in the literature showed that the developed ANN correlation noticeably improved prediction of hold-up over a wide range of operating conditions, physical properties and pipe diameters. This correlation also predicts properly the trend of the effect of the operating and design parameters on hold-up.     

原油常减压蒸馏装置的模拟

用石油馏分的蒸馏曲线(ASTM或TBP)和整体密度进行虚拟组分切割，以单元模块组合法严格求解常减压蒸馏塔，建立原油减压蒸馏装置的流程模拟系统。     

分布式并行算法在长周期原油混输调度中的应用

为了有效求解长周期原油混输调度问题,提出了基于事件树的分布式并行算法。该方法把原油混输调度问题分解为码头调度子问题和厂区调度子问题,采用基于事件树的建模方法,并根据两个子问题的求解顺序提出了原油混输调度问题的分布式并行算法。本方法采用主从式并行结构,主节点把求解码头调度子问题所需的原油质量要求信息发送到各从节点,然后各从节点把与质量要求信息对应的码头调度最优解返回给主节点,通过综合比较两个子问题的解,从而得出最优的调度方案。实例计算表明,该并行算法可以有效减少问题的求解时间,特别是对不同常减压对原油质量要求不同时的长周期调度（如4周）问题,采用串行算法在48 h内都无法得到可行解,而采用此算法用3台计算机可以在25 h内得到最优解。     

基于BP人工神经网络的生化处理水水质预测

神经网络具有强大的非线性映射能力和并行处理能力,近年来在水处理领域中被广泛地应用.利用神经网络算法对某污水处理厂的污水处理系统进行了出水水质预测.结果表明,基于BP神经网络的水质预测模型拟合效果较好,模拟出来的化学需氧量(COD)、pH、固体悬浮物(SS)及生物需氧量(BOD)的数值范围均较接近于实际值,其平均相对标准差分别为6.96%、1.31%、12.09%、15.18%.