Synthesis,characterization and application of a dispersant based on rosin for coal-water slurry

A rosin derivative and maleopimaric acid diethanolamide (MAD), was synthesized, characterized by FTIR and ¹H NMR, and applied as dispersant for the coal-water slurry (CWS) prepared from Chinese Shenfu coal. The CWS application performance investigation shows that the MAD dispersant has better abilities in reducing CWS viscosity and stabilizing the slurry than a commercial dispersant—sulfonated naphthalene-formaldehyde condensate (SNF). The physicochemical property investigation of the two tested dispersants shows that the adsorption amount of the MAD at coal-water interface is much larger than that of SNF, and the MAD has better wetting property than the SNF on the coal surface. It indicated that the excellent capabilities of MAD are related to the adsorption mode of standing upright on the coal surface. Based on the above, the mechanism of dispersion and stabilization of the CWS prepared from MAD dispersant is presented.     

Performance prediction of gravity concentrator by using artificial neural network-a case study

In conventional chromite beneficiation plant, huge quantity of chromite is used to loss in the form of tailing. For recovery these valuable mineral, a gravity concentrator viz. wet shaking table was used. Optimisation along with performance prediction of the unit operation is necessary for efficient recovery. So, in this present study, an artificial neural network (ANN) modeling approach was attempted for predicting the performance of wet shaking table in terms of grade (%) and recovery (%). A three layer feed forward neural network (3:3–11–2:2) was developed by varying the major operating parameters such as wash water flow rate (L/min), deck tilt angle (degree) and slurry feed rate (L/h). The predicted value obtained by the neural network model shows excellent agreement with the experimental values.     

多子群粒子群集成神经网络

为了使参加神经网络集成的个体差异度较大,从而提高网络集成的泛化能力,本文提出一种新的基于多子群粒子群算法的神经网络集成方法.每个子群通过补充差异度独立训练出一批神经网络,从每个子群中选择一个最优个体参加网络集成,实验使用了UCI标准数据集.实验证明,该算法的识别能力要好于Boosting、Bagging等传统方法.     

基于神经网络的被测量重构方法研究

提出了基于神经网络的被测量重构方法 ;针对神经网络中误差反向传播算法收敛速度慢的问题对目标函数等三方面进行了改进 ,将改进的多层前向网络、误差反向传播算法用于被测量重构。在实际的测量系统中 ,进行了仿真研究 ,结果表明 ,神经网络用于被测量重构 ,方法是可行的 ;解决了重构之前建立数学模型问题和多影响量情况下的被测量重构问题。     

水环境质量评价的人工神经网络模型及应用

基于人工神经网络理论建立了一种新的水质评价模型．实例分析表明,该模型具有较强的处理矛盾样本的能力,用于水环境质量评价简便而实用,预测精度高,应用前景广泛     

Effect of the benzene ring of the dispersant on the rheological characteristics of coal-water slurry: Experiments and theoretical calculations

In this study,low-rank coal-water slurry(LCWS) was prepared using polyoxyethylene dodecylphenol ether(PDPE) and polyoxyethylene lauryl ether(PLE),respectively.A combination of experiments and simulations was used to investigate the pulping properties and microscopic mechanism of the LCWS samples prepared using the two agents,so as to explore the influence of benzene ring on the performance of dispersant.The results of the LCWS preparation experiments revealed that the pulp-forming performance of PDPE exceeded that of PLE.When LCWS concentration is 62%,64%,and 66%,the apparent viscosity corresponding to PDPE is 247.80,504.17,and 653.10 mPa·s,and the apparent viscosity corresponding to PLE is 548.10,1470.61,and 1549.98 mPa·s,respectively.The C_(1000)(When the apparent viscosity is 1000 mPa·s,the corresponding concentration of LCWS is defined as C_(1000)) values of PDPE and PLE are 67.60% and 62.95%,respectively.In addition to the van der Waals forces and hydrogen bonds between the PDPE and/or PLE molecules and coal,the benzene rings of PDPE present π-π stacking effect with the aromatic rings of coal.That could facilitate and strengthen the adsorption of PDPE on coal,which would be conducive to further improving the dispersion of coal particles.The two dispersants have no significant difference in effect on the pyrolysis of LCWS.The simulation results indicated that the times for PDPE and PLE molecules to reach flat adsorption state on coal are approximately 290 and 565 ps,respectively.The self-diffusion coefficient(D) of the PDPE and PLE on coal is 3.16 x 10~(-6) and6.57×10~(-6) m~2/s,respectively,and their interaction energies with coal are 785.71 and 648.60 kcal/mol,respectively.The results of the simulation calculations demonstrated that PDPE adsorbed on coal easier than PLE,and its binding is more stable than that of PLE owing to the π-π stacking effect,which is conducive to uniform dispersion of coal in solution.The simulation results confirmed the experimental results.     

基于遗传神经网络的汽轮发电机振动故障诊断的研究

汽轮发电机的故障诊断对电力系统的安全运行有着十分重要的意义.文章介绍了基于遗传优化的神经网络在汽轮发电机故障诊断中的应用.     

基于PSO算法的神经网络集成构造方法

为合理选择组成神经网络集成的个体,使各个体间保持较大的差异度,从而提高集成所建模型的仿真精度,提出一种新的神经网络集成构造方法.独立训练出一批神经网络,采用离散粒子群优化(PSO)算法,用多维空间中0或1取值的粒子描述所有可能的神经网络集成.网络集成预测误差的估计值用组成集成的个体网络之间的相关度表示,并作为优化过程中的适应度函数.优选得到参与构成神经网络集成的部分差异度较大网络个体.对8个典型数据集回归问题的实验结果表明,该方法构造的神经网络集成普遍使用了较少的网络个体,而预测精度均好于Bagging方法等传统方法.     

BP神经网络在醋酸乙烯生产中的应用研究

介绍了醋酸乙烯合成反主应器BP神经网络模型的建立及有关参数的选取;提出了采用LevenbergMarquart优化法来训练BP神经网络,通过将BP神经网络用于醋酸乙烯合成反应器操作优化的研究表明,对于机理不明确或精确模型难于建立的过程,人工神经网络是一种有效的方法。     

BP神经网络法预测水泵全性能曲线的研究

采用BP神经网络方法 ,进行任意比转速水泵全特性曲线的预测 ,从而可得到一种实用的任意比转速Suter水泵全特性曲线     

基于BP神经网络的车型分类器

针对车型特征,提出了一种基于BP神经网络的识别方法．从图像中提取车型特征向量,用BP神经网络设计分类器,并进行有效的训练与测试．应用改进的BP算法（尺度化共轭梯度法）对网络进行训练,使网络很快得到收敛,解决了一般算法收敛慢的缺陷．     

前馈式神经网络的最小二乘学习算法

通过对 Sigmoid 函数求逆,把非线性极值问题转化为线性方程组来处理,巧妙地避开了梯度,从而可以克服 BP 算法的一些缺点,提高了算法的收敛速度.同时采用最小二乘法来求解方程组,进一步提高了收敛速度.算法的计算过程为每次处理一个节点的所有前一层连接权,轮换处理,直到收敛到最小点.     

快速收敛的BP神经网络算法

以标准BP算法为基础,应用Levenberg Marquardt最优化方法,提出了一种快速收敛的BP算法———LMBP算法。经实验验证并与标准BP算法及其它改进形式比较,LMBP算法大大提高了收敛速度,而且性能稳定。这为BP神经网络应用于实时性要求高的场合(如在线检测)提供了算法基础。该算法的缺点是计算量大,所需计算机内存大,不适合大型网络的计算。     

前馈式神经网络的最小二乘学习算法

通过对Sigmoid函数求逆，把非线性极值问题转化为线性方程组来处理，巧妙地避开了梯度，从而可以克服BP算法的一些缺点，提高了算法的收敛速度．同时采用最小二乘法来求解方程组，进一步提高了收敛速度．算法的计算过程为每次处理一个节点的所有前一层连接权，轮换处理，直到收敛到最小点．     

A novel artificial intelligent model for predicting air overpressure using brain inspired emotional neural network

Blasting is the live wire of mining and its operations, with air overpressure(AOp) recognised as an end product of blasting. AOp is known to be one of the most important environmental hazards of mining.Further research in this area of mining is required to help improve on safety of the working environment.Review of previous studies has shown that many empirical and artificial intelligence(AI) methods have been proposed as a forecasting model. As an alternative to the previous methods, this study proposes a new class of advanced artificial neural network known as brain inspired emotional neural network(BIENN) to predict AOp. The proposed BI-ENN approach is compared with two classical AOp predictors(generalised predictor and McKenzie formula) and three established AI methods of backpropagation neural network(BPNN), group method of data handling(GMDH), and support vector machine(SVM). From the analysis of the results, BI-ENN is the best by achieving the least RMSE, MAPE, NRMSE and highest R, VAF and PI values of 1.0941, 0.8339%, 0.1243%, 0.8249, 68.0512% and 1.2367 respectively and thus can be used for monitoring and controlling AOp.     

动态递归模糊神经网络及其BP学习算法

提出了一种新型的动态递归模糊神经网络，并根据动态递归神经网络的数学模型推导出其动态反向传播学习算法，仿真结果表明对于动态系统的辨识，动态递归模糊神经网络较传统模糊神经网络在辨识精度和稳定性方面具有更好的效果。     

Artificial neural network based inverse design method for circular sliding slopes

Current design method for circular sliding slopes is not so reasonable that it often results in slope sliding. As a result, artificial neural network (ANN) is used to establish an artificial neural network based inverse design method for circular sliding slopes. A sample set containing 21 successful circular sliding slopes excavated in the past is used to train the network. A test sample of 3 successful circular sliding slopes excavated in the past is used to test the trained network. The test results show that the ANN based inverse design method is valid and can be applied to the design of circular sliding slopes.     

基于萤火虫算法优化BP神经网络的目标威胁估计

在萤火虫优化算法和BP神经网络的基础上,建立了萤火虫算法优化BP神经网络的目标威胁估计模型,并提出了基于该模型的算法。该模型和算法采用萤火虫算法优化BP神经网络的初始权值和阈值,优化后的BP神经网络能对测试集进行更好的预测。实验结果表明,萤火虫算法优化BP神经网络的预测误差明显小于BP和PSO_SVM。该模型和算法具有很好的预测能力,可以快速、准确地完成目标威胁估计。     

基于遗传算法与神经网络的VRP求解

为求解配送货物过程中车辆路径安排问题(VRP),融合神经网络与遗传算法,在标准遗传算法基础上,将并行进化思想与阶段性进化思想相结合,提出了一种新型遗传算法--并行阶段性遗传算法(PPGA).实际应用表明,与标准遗传算法相比,新的混合遗传算法收敛速度更快、收敛精度更高.     

干旱内陆河流域月径流的神经网络模拟

针对干旱内陆河流域地表径流形成、消耗的特点,采用1956~2003年的水文气象、灌溉用水等资料建立了用于模拟出山口月径流量、下游径流月径流量的分布式神经网络(ANN)模型。模型的输入为各子流域及中游本月降水、潜在蒸发蒸腾量、上月降水、潜在蒸发蒸腾量、中游灌溉面积、灌溉定额,输出为月径流量.检验结果表明,本文所建立的分布式ANN模型可以有效模拟干旱内陆河流域月径流,模型用于模拟子流域出山口径流的误差为0.18×107~0.42×107m3,用于模拟下游径流的误差为0.52×107m3.与单一ANN相比,尽管分布式ANN的输入不需实测出山口径流,但模型的精度没有明显减小.分布式ANN为研究干旱内陆河流域气候变化及农业活动对地表径流过程的影响提供了有效的工具.