基于BP神经网络的土石填料压实质量控制

BP neural network based quality control on compaction of earth-rock fill material

现行的土石填料压实质量检测方法由于自动化程度低、效率低、采样密度小等缺点,很难满足工程建设质量实时控制的需要。开发新的检测技术,实现填料高质、快速、无损和动态的检测已成为亟待解决的重要任务之一。本文阐述了BP神经网络原理,并结合PFWD时程曲线的动态参数,建立了基于BP神经网络的土石填料预测模型。实际数据对比分析表明,该方法能够满足压实质量的快速检测。

Since the current methods for the detecting the compaction quality of earth-rock fill material have some defects such as lower automatic level, lower efficiency, less sampling density, etc. , they are difficult to meet the demand of the real-time control on the quality the actual construction; for which developing a new detection technology for realization of the high precision, quick, non-destructive and dynamic detection of the fill material becomes an important task to be urgently solved. The principle of BP neural network is described herein and a prediction model for detecting the quality of the earth-rock fill material is established in combination with the dynamic parameters of the time-curve of PFWD （ portable falling weight deflectometer） based on the BP neural network. The comparative analysis on the actual data shows that the method can satisfy the quick detection of the compaction quality concerned.