基于多信息融合的深基坑安全预警方法及应用

Deep foundation pit safety warning method based on multi-information fusion and it’s application

提出了一种基于多信息融合的深基坑安全预警方法。验证了T-S模糊神经网络是适用于处理非线性、大量数学分析的多信息融合模型,并利用MATLAB软件实现了该模型的构建。通过大量样本对模型训练与检测,实现对应空间区位与事故警情的各组多信息融合模型的准确性与泛化能力,提升现有深基坑安全预警信息分析处理的智能化。最后,以黄浦新城地铁车站深基坑工程为研究实例,实地采取各信息源相应预警信息,并代入已训练好的各组多信息融合模型。结果表明,融合结果与现场实际情况相吻合,验证了该方法的可行性。可为深基坑安全预警方法提供参考。

A method based on multi-information fusion for deep foundation pit safety warning was proposed.The T-S fuzzy neural network is a multi-information fusion model which is suitable for nonlinear and massive mathematical analysis,and the model was constructed by MATLAB software.Through the training and detection of a large number of samples,the accuracy and generalization ability of each group of multi-information fusion models corresponding to spatial location and accident alert were realized,and the intelligent analysis and processing of existing deep foundation pit safety warning information were intelligently improved.Finally,taking the deep foundation pit project of Huangpu New Town subway station as the research object,the corresponding information of each information source was taken in the field,and put into the trained multi-information fusion model.The results show that,the fusion result is consistent with the actual situation on the site,and the feasibility of the method is verified.It can provide reference for the safety warning method of deep foundation pit.