论文部分内容阅读
为解决利用混凝土坝安全监测全序列数据建立的支持向量机(SVM)模型存在结构复杂、计算工作量大等问题,提出利用熵理论选择具有代表性样本代替全序列样本进行建模,即通过建立外部档案,根据外部档案更新算法选择具有代表性的样本,然后将外部档案的样本用作支持向量机的训练样本。将该方法用于某蓄水初期的混凝土坝变形模型的构建中,结果表明,该组合算法在保证模型精度的同时有效降低了模型的复杂程度,减少了模型的训练时间,且使模型的泛化能力得到一定的提升。
In order to solve the problems of complex structure and large workload, the support vector machine (SVM) model established by using full sequence data of safety monitoring of concrete dams is proposed to select representative samples instead of full sequence samples by using entropy theory, that is, External files, according to external file update algorithm to select a representative sample, and then use the external file samples as support vector machine training samples. The method is applied to the construction of a concrete dam deformation model of an early impoundment. The results show that the combination algorithm can effectively reduce the complexity of the model and reduce the training time of the model, Ability to get some improvement.