改进的BP神经网络在多裂纹柱体扭转中的应用

提出一种基于BP神经网络的多裂纹柱体扭转问题的数据新处理方法。以多裂纹柱体扭转问题为例,以MATLAB中的神经网络工具箱为工具,采用了改进的BP神经网络,并对其设计方案进行了详细的分析说明,发现动量参数对训练次数影响很大,而学习率对它的影响很小;采用双隐含层比单隐含层训练更稳定,收敛的也更快,同时给出了理想的学习方案。最后对柱体的抗扭刚度实验值进行快速拟合,得到了裂纹尖端的应力强度因子K3。结果证明这种设计方案计算的更精确、收敛速度更快。     

基于BP神经网络的变速箱故障诊断方法研究

针对变速箱的工作时间不能真实反映实际健康状况的问题,通过提取变速箱的振动信号作为状态参数,建立了基于BP神经网络的变速箱故障诊断模型。该模型首先提取振动信号中对故障反映灵敏的成分作为特征值,获得BP神经网络的训练数据,并通过对比确定最优的隐含层节点数,确定BP神经网络的结构参数。模型训练结束后,以验证数据为例进行故障诊断研究,并对诊断结果进行评估。评估结果表明,该模型准确度高,具有较好的应用和推广价值。     

一种混合入侵检测模型

为了提高入侵检测模型的准确率,提出一种基于K-均值算法、朴素贝叶斯分类算法和反向传播神经网络的混合入侵检测模型。首先,采用基于分区、无监督式聚类分析的K-均值算法进行数据的聚类处理,得到易于被机器处理和学习的数据集。为了进一步获取必要的数据属性,将聚类处理的结果输入到贝叶斯分类器进行分类。然后,具有较短学习周期的反向传播神经网络负责训练数据分类样本。最后,基于KDD CUP99数据集,对混合入侵检测模型进行了仿真实验,实验结果表明,通过混合入侵检测模型,DoS、U2R、R2L和Probe等入侵数据被精准地检测出。相比其它入侵检测模型,混合入侵检测模型取得了较高的准确率和召回率,以及较低的误报率,具有一定的实用价值。     

Neural networks for predicting air gap membrane distillation performance

The hollow fiber air gap membrane distillation (AGMD) has recently attracted tremendous attention for desalination and wastewater treatment due to its high packing density, low conductive heat loss, and latent heat recovery capability. Utilizing fast and accurate modeling tools to predict MD performance can result in the further development of desalination technologies. However, simple and time-saving prediction models to assess the AGMD performance were not abundant. Herein, AGMD performance, including permeate flux (J) and gained output ratio (GOR) was predicted through multiple linear regression (MLR) model, back propagation neural network (BP ANN) and radial basis function neural network (RBF ANN) under different hot temperatures (T_h), coolant temperatures (T_c), feed flow rates (F), and feed concentration (c). A total of 30 sets of data were used to train the proposed models, the other 10 external validation datasets not used for training the models were applied to validate the prediction accuracy. The results depicted that RBF ANN (SPREAD = 30, N = 30) showed greatest prediction performance (R² = 0.99–1) compared with BP ANN and MLR models (R² = 0.98–0.99; R² = 0.89–0.97). The computing time consumption of RBF ANN was higher than BP ANN. According to the Mean impact value (MIV) analysis, T_h had the strongest effect on J and GOR. Increasing T_h and decreasing c both had positive impacts on J and GOR, but increasing T_c or F resulted in a trade-off influence. A genetic algorithm (GA) was employed to optimize J and GOR simultaneously, the optimum J and GOR could reach 6.00 kg/m²·h and 7.70 respectively. In this study, the three prediction models proved their abilities to predict AGMD performance and further provide guidance in the actual membrane distillation water treatment process.