论文部分内容阅读
为探究拱坝施工期横缝的工作性态,采用SOM神经网络对监测数据进行模糊聚合分类,依据分类结果标识输入样本,进而利用Elman神经网络诊断分析测试样本,并以溪洛渡高拱坝横缝监测数据为例进行实例验证。结果表明,在误差分析过程和诊断结果精度等方面该方法具有良好的适应性和稳定性。
In order to explore the working behavior of transverse joints during the construction period of arch dam, SOM neural network was used to classify the monitoring data by fuzzy aggregation. The input samples were identified according to the classification results. Then the Elman neural network was used to diagnose and analyze the test samples. Example of monitoring data for instance verification. The results show that this method has good adaptability and stability in error analysis process and diagnostic accuracy.