用人工神经网络预测摩擦学系统磨损趋势

人工神经网络具有高度的并行分布式、联想记忆、自组织及自学习能力和极强的非线性映射能力，在许多领域显示了广阔的应用前景．但是，将神经网络用于摩擦学行为预测的研究报道却还鲜见．在对基于神经网络的单变量时间序列预测方法与过程进行分析之后，提出了摩擦学系统磨损趋势神经网络预测模型．采用定量铁谱参数中的总磨损Ｑ作为预测磨损趋势的特征参数，讨论了磨损趋势神经网络预测的单步预测法和多步预测法，并用其对ＣＤ４０齿轮泵的磨损趋势进行了预测，预测值与实测值吻合较好     

The Use of Fractal Geostatistics and Artificial Neural Networks for Carbonate Reservoir Characterization

In this study, a carbonate oil reservoir located in the southeast part of Turkey was characterized by the use of kriging and the fractal geometry. The three-dimensional porosity and permeability distributions were generated by both aforementioned methods by using the wireline porosity logs and core plug permeability measurements taken from six wells of the field. Since classical regression (lognormal or polynomial) and geostatistical techniques (cross variograms) fail to estimate permeability from wireline log-porosity data, the use of artificial neural networks (ANNs) is proposed in this study to generate permeability data at uncored intervals of porosity logs. For both of the methods, kriging and fractal techniques, the validation of the estimated/simulated data with known wellbore data resulted with acceptable agreements, especially for porosity. Also the comparison of both methods at unsampled locations show better agreements for porosity than permeability.     

基于神经网络的结构变形估计和形状控制

准确的变形估计是智能结构形状控制的前提。本文基于人工神经网络（ＡＮＮ）方法设计了智能桁架结构的变形估计器和形状控制器，根据结构系统有限数目的测量值可以估计结构变形并用于形状控制。该方法同时适于处理结构非线性问题。算例表明方法的可行性与有效性。     

Nondestructive Evaluation of Crack Depth in Concrete Using PCA-compressed Wave Transmission Function and Neural Networks

Cracks in concrete are common defects that may enable rapid deterioration and failure of structures. Determination of a crack’s depth using surface wave transmission measurement and the cut-off frequency in the transmission function (TRF) is difficult, in part due to variability of the measurement data. In this study, use of complete TRF data as features for crack depth assessment is proposed. A principal component analysis (PCA) is employed to generate a basis for the measured TRFs for various simulated crack (notch) cases in concrete. The measured TRFs are represented by their projections onto the most significant PCs. Then neural networks (NN), using the PCA-compressed TRFs, are applied to estimate the crack depth. An experimental study is carried out for five different artificial crack (notch) cases to investigate the effectiveness of the proposed method. Results reveal that the proposed method can effectively estimate the artificial crack depth in concrete structures, even with incomplete NN training.     

Al_2O_(3f)+C_f/ZL109干摩擦磨损行为及其人工神经网络分析

采用挤压铸造法制备了氧化铝及碳短纤维混杂增强 Ｚ Ｌ１０９ 合金复合材料,考察了该复合材料的干摩擦磨损行为．结果表明：该复合材料的摩擦磨损性能随纤维总体积分数的增加而降低;当纤维总体积分数一定时,随碳纤维含量的增加复合材料摩擦磨损性能降低．采用人工神经网络技术对该复合材料的干摩擦磨损试验结果进行了综合分析,其结果与试验值吻合较好．分析表明：纤维总体积分数较小时,碳纤维含量对复合材料耐磨性的影响较大,随纤维总体积分数的增大其影响减弱;无论纤维总体积分数如何变化,碳纤维含量对复合材料摩擦系数均有较大影响,这是其自润滑作用的结果;载荷较小时,该复合材料摩擦磨损的跑合时间较长;随载荷的增大摩擦系数减小;磨损达到稳态后载荷对复合材料摩擦系数的影响不大