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.     

A highly stable and efficient catalyst for direct synthesis of LPG from syngas

Liquefied petroleum gas (LPG) fuel was directly synthesized from syngas over a hybrid catalyst which contained a methanol synthesis catalyst and zeolite. The new hybrid catalyst composed of (Pd–Ca/SiO₂) and β-zeolite, showed a high activity and selectivity for LPG production. X-ray diffraction (XRD) characterization of the catalyst was used to analyze the deactivation of (Pd–Ca/SiO₂)/β-zeolite.     

基于重标极差法和神经网络的隧道变形趋势判断

为准确、科学及全面地对隧道变形进行趋势判断和预测分析,将隧道的变形过程划分为中期阶段和长期阶段,利用R/S分析对其位移序列和速率序列进行趋势判断研究,再利用PSO-BP神经网络对各阶段的变形进行预测,将预测结果与R/S分析结果进行对比,验证两者的一致性。利用两个工程实例进行检验,得出各序列的Hurst指数均大于0.5,说明各序列均具有持续变形的长期性,且位移序列的趋势性均大于速率序列的趋势性;同时,变形预测结果也显示隧道后期变形将持续增加,验证了R/S分析的准确性。     

基于BPNN-PID的风电机组桨距控制分析

变桨控制技术是风力发电机组的核心技术之一,开展对风力发电机组变桨控制方面的研究具有重要的理论和应用价值。根据风力发电机组在额定风速以上如何保持输出功率稳定和降低风轮转速波动的控制技术进行研究,在传统的变桨距控制策略基础上,提出了基于BP神经网络(Neural Network,NN)整定PID的控制策略,并在Matlab/simulink环境下对PID控制和BP神经网络控制相结合的复合控制系统进行建模与分析。对1.5MW风电机组的仿真验证了BPNN-PID算法的有效性,提出算法不仅能够解决传统PID控制器参数整定困难的问题,而且优化效率更高,可以得到优良的控制性能。     

基于神经网络的轮胎胎号字符识别

介绍了采用BP神经网络来进行轮胎胎号字符识别的一种尝试性方法。用Matlab来模拟用神经网络进行胎号数字识别这一过程，用投影—变换系数法进行特征提取，确定特征输入、隐含层的神经元和输出后，经训练后可识别胎号，识别率尚可。     

三乙胺对丙烯酸酯-聚氨酯复合乳液的影响研究

采用原位乳液聚合法，合成聚氨酯-丙烯酸酯(PUA)复合乳液。通过粒径分析、黏度测定、力学测试等手段，研究了三乙胺对乳液性能和相行为变化等的影响。实验结果表明：随着中和度提高，乳液外观改善，贮存稳定性提高，吸水率增大，耐水性降低，拉伸剪切强度增大，而断裂伸长率降低，相转变点后延。     

工业PTA氧化过程4-CBA浓度的模糊神经网络模型

A fuzzy neural network (FNN) model is developed to predict the 4-CBA concentration of the oxidation unit in purified terephthalic acid process. Several technologies are used to deal with the process data before modeling.First,a set of preliminary input variables is selected according to prior knowledge and experience. Secondly,a method based on the maximum correlation coefficient is proposed to detect the dead time between the process variables and response variables. Finally, the fuzzy curve method is used to reduce the unimportant input variables.The simulation results based on industrial data show that the relative error range of the FNN model is narrower than that of the American Oil Company (AMOCO) model. Furthermore, the FNN model can predict the trend of the 4-CBA concentration more accurately.     

质量交换网络集成的状态空间法

State space approach is an effective method to mass-exchange network (MEN) synthesis. By decomposing the network into two interactive parts, a distribution network and a process operator, the synthesis problem can be formulated into a mixed integer nonlinear programming (MINLP) model. In this article, a generalized state space model based on typical MEN is established and verified in two cases. A new asymmetrical operator and cost index are also adopted to speed up the solution process. The results demonstrate the efficiency of the proposed approach.     

Large deformation and ultimate properties of biopolymer gels: 2. Mixed gel systems

Biphasic, mixed gels of agarose and gelatin were prepared, and their mechanical behaviour in tensile tests was determined, up to failure, utilising four decades of (constant) strain rate. The behaviour of pure agarose and pure gelatin in such tests has been determined previously. Suitable ‘blending-laws’ relating the small deformation shear modulus of the composite to the moduli of the component phases have also been discussed elsewhere. This report extends the latter treatment to the more aggressive large deformation regime, deriving bounds for modulus and break stress which closely model observed behaviour.     

Multirate control with incomplete information over Profibus-DP network

When a process field bus-decentralized peripherals (Profibus-DP) network is used in an industrial environment, a deterministic behaviour is usually claimed. However, due to some concerns such as bandwidth limitations, lack of synchronisation among different clocks and existence of time-varying delays, a more complex problem must be faced. This problem implies the transmission of irregular and, even, random sequences of incomplete information. The main consequence of this issue is the appearance of different sampling periods at different network devices. In this paper, this aspect is checked by means of a detailed Profibus-DP timescale study. In addition, in order to deal with the different periods, a delay-dependent dual-rate proportional-integral-derivative control is introduced. Stability for the proposed control system is analysed in terms of linear matrix inequalities.