Prediction of process parameters of water-assisted injection molding based on inverse radial basis function neural network

Because of the introduction of new processing parameters in water-assisted injection molding (WAIM), processes control has become more difficult. First, design of experiment (DOE) was carried out by using optimized Latin hypercubes (Opt LHS). On the basis of this, computational fluid dynamics (CFD) method was used to simulate and calculate hollowed core ratios and wall thickness differences of cooling water pipe at different positions. Then inverse radial basis function (RBF) neural network model reflecting the fitting relationship between processing parameters and molding quality was established, and accuracy of the model was detected by cross validation. Finally, expected molding quality was applied to predict processing parameters, and the obtained molding quality under the predicted processing parameters was verified by computer aided engineering (CAE) simulation and experimental methods. The results showed that mean relative precisions of processing parameters such as melt temperature, delay time, short shot size, water pressure, and mold temperature for inverse RBF model were 98.6%, 93.6%, 98.5%, 93.9%, and 97.9%, respectively, which met the accuracy requirements. Furthermore, compared with expected values of hollowed core ratios and wall thickness differences, the average errors of CAE and experiment were 2.3% and 4.9%, respectively.     

基于DEM的振动筛筛孔形状对潮湿原煤筛分效果影响的研究

随着原煤含水量的增加,引起原煤颗粒间相互粘聚,影响振动筛筛分效率。基于离散元法,运用EDEM软件模拟了潮湿原煤颗粒在圆形筛孔、方形筛孔和矩形筛孔的筛分过程,并且以筛分效率和阻碍粒排出率为衡量指标,对振动筛筛孔形状影响潮湿煤筛分效果进行了研究。结果表明:在筛孔名义尺寸相同的情况下,潮湿煤在矩形筛孔筛面上的筛分效果最好,方形筛孔次之,圆形筛孔最差。     

基于投影寻踪的径向基函数网络在参考腾发量预测中的应用

径向基函数网络(RBFN)已广泛应用于参考腾发量预测等领域，但常用的K均值聚类和自组织特征映射等方法在求取径向基函数网络隐层节点中心时存在较大不足。针对这一问题，本文引入投影寻踪方法，在投影降维的基础上实现对大量高维数据的聚类，建立了基于投影寻踪的径向基函数网络模型，并将该模型应用于山西潇河灌区参考腾发量的预测，研究了不同气象因子输入对参考腾发量预测精度的影响。结果表明，基于投影寻踪的径向基函数网络具有较强的适用性，只需使用最高温度、最低温度、日照时数和旬序数作为输入因子，就能以较高的精度预测参考腾发量。     

A note on the value function for constrained control problems

We consider the Mayer optimal control problem with dynamics given by a nonconvex differential inclusion, whose trajectories are constrained to a given set and we obtain a relation between the costate function that appears in the maximum principle and the value function. This relation extends the known conditions existing in the literature for unconstrained problems to those for problems under state constraints.     

Experimental and modeling approaches of MR behaviors under large step strains

Rheological properties of MR fluids under large step strain shear are presented in this paper. The experiments were carried out using a rheometer with parallel-plate geometry. Under the large step strain shear, MR fluids behave as nonlinear viscoelastic properties, where the stress relaxation modulus, G(t, γ), shows a decreasing trend with step strain. The experimental results indicate that G(t, γ) obeys time-strain separability. Thus, a mathematical form based on finite exponential serials is proposed to predict MR behavior. In this model, G(t, γ) is represented as the product of a linear stress relaxation, G(t), and the damping function, h(γ), i.e. G(t, γ)=G(t) h(γ). G(t) is simply represented as a three-parameter exponential serial and h(γ) has a sigmoidal form with two parameters. The parameters are identified by adopting an efficient optimization method proposed by Stango et al. The comparison between the experimental results and the model-predicted values indicates that this mathematical model can accurately predict MR behavior.     

住宅设计的分析与研究

总结了住宅设计的发展,概括了住宅各个功能区的特点。通过设计的实例说明了各不同功能区的设计,成果可供进一步的研究参考。     

个性化公开密钥系统的设计

论文提出利用用户提供的个性化信息来随机产生关联大素数,保证了素数选取的随机化、个性化,提高了RSA算法的安全性。     

径向基函数神经网络的再学习算法及其应用

为了应用径向基函数神经网络逐步地识别待研究系统,文章针对径向基函数神经网络的再学习算法开展了深入的研究.应用严格的数学推理方法,将径向基函数神经网络的再学习问题转化为矩阵求逆的附加运算.详细给出了径向基函数神经网络再学习算法中增加新训练样本和增加新基函数的数学公式,同时对如何获取新的训练样本进行了研究.     

利用整合区域特性约束提高孔隙率模拟精度

本文将空间结构变化的要求与动态资料确定的储量共同作为约束,建立了包含两个约束条件的目标函数, 应用模拟退火算法对孔隙率的空间分布进行预测。在实现过程中,通过初始控制参数的给定及目标函数修改提高了运算效率。由于目标函数有效地整合了静、动态信息,从而降低了模拟结果的不确定性．提高了模拟的精度。合成数据及实际数据的模拟试验表明,整合区域特性约束不仅提高了孔隙率模拟精度,而且算法收敛快、稳定性高。     

柴油蜡晶的理论形态预测与显微实际形态的比较

采用BFDH模型和AE模型预测柴油中蜡晶的理论形态，与通过相衬光学显微镜在冷环境平台上观察柴油蜡晶在低温下析出的实际形态。以及加入低温流动性改进剂T1804的柴油蜡晶形态进行比较研究。以十八烷晶体和二十三烷晶体作为柴油蜡晶中偶数正构烷烃和奇数正构烷烃的模型化合物，得到它们的晶体理论形态为六面体薄片状晶体。不同降温速率下得到的蜡晶的实际形态与大小均不同。快速降温条件下得到的晶体形态主要为六边形、菱形和其它少数不规则多边形薄片状集合体；慢速降温条件下得到的柴油蜡晶的形态比较完整，为六边形片状，与通过BFDH和AE模型得到的十八烷即偶数正构烷烃的形态比较接近。柴油加T1804后，快速降温时，出现更多细小的无规则晶体，且很快聚集成片状晶体；慢速降温时，出现晶体的数目要多于未加剂柴油，形状不规则，且尺寸小于未加剂柴油。