本文已被:浏览 107次 下载 0次
投稿时间:2019-06-19 修订日期:2019-07-16
投稿时间:2019-06-19 修订日期:2019-07-16
中文摘要: 为准确地预测爆破结果、减少爆破振动对建筑的损伤和保障工人的安全,利用具有处理非线性问题能力的BP神经网络预测爆破结果。选取合格的爆破结果作为网络模型的学习样本,经过一定次数的训练学习后通过神经网络的前馈特性确定各层阈值和误差,完成对BP神经网络的建立,发现预测结果与真实结果相比的误差在10%以内,误差符合工程要求。再结合例如PAC算法、POS算法或者MATLAB软件等优化网络后甚至可以将误差控制在5%以内。通过建立BP神经网络预测可以减少爆破作业带来的危害,降低安全成本,指导爆破作业的施工。
中文关键词: BP神经网络,非线性,爆破预测,误差
Abstract:In order to accurately predict the blasting results, reduce the damage of blasting vibration to the building and ensure the safety of workers, BP neural network with the ability to deal with nonlinear problems is used to predict the blasting results. Qualified blasting results were selected as the learning samples of the network model, after a certain number of times of training and learning, the feedforward characteristics of the neural network were used to determine the thresholds and errors of each layer, then the establishment of BP neural network was completed. It is found that the error between the prediction result and the real result is within 10%, which conforms to the engineering requirements. By combining PAC algorithm, POS algorithm or MATLAB to optimize the network, the error can even be controlled within 5%. By establishing BP neural network prediction can reduce the damage caused by blasting operation, reduce safety cost and guide the construction of blasting operation.
文章编号:20190619001 中图分类号: 文献标志码:
基金项目:国家自然科学基金资助(No.51564027);北京理工大学开放基金项目(KFJJ15-14M)。
Author Name | Affiliation | Postcode |
Lengzhigao | Kunming University of Science and Technology | 650093 |
Li xionglong | Kunming University of Science and Technology | 650093 |
引用文本: