论文部分内容阅读
针对高速铁路桥梁架梁后许多沉降变形点沉降量级较小,变形曲线呈现“小量级,大波动”特点,观测数据中可能存在大量的随机噪声,对沉降变形分析产生干扰,影响预测结果的可信度,本文将Kalman滤波引入到高速铁路桥梁变形分析数据预处理中,建立基于Kalman滤波的动态模糊神经网络模型。通过应用实例分析表明,基于Kalman滤波的动态模糊神经网络模型的预测精度有所改善,具有一定的优势。
For the settlement of many settlement points of high-speed railway bridges, the settlement magnitude is small and the deformation curve shows the characteristics of “small order and large fluctuation”. There may be a large amount of random noise in the observation data, which may interfere with the settlement deformation analysis The credibility of the prediction results, the introduction of Kalman filtering high-speed railway bridge deformation analysis data preprocessing, the establishment of dynamic fuzzy neural network model based on Kalman filtering. The application examples show that the prediction accuracy of the dynamic fuzzy neural network model based on Kalman filter is improved, which has some advantages.