传感器信息融合在滑坡预报中的应用  

Application of Sensor Information Fusion in Landslide Prediction

作　　者：陈紫妍 赵佳睿 高仕奇 李丽敏[1] 梁聪 喻远佳 CHEN Ziyan;ZHAO Jiarui;GAO Shiqi;LI Limin;LIANG Cong;YU Yuanjia(School of Electronics and Information,Xi an Polytechnic University,Xi an 710600,China)

机构地区：[1]西安工程大学电子信息学院,西安710600

出　　处：《微处理机》2021年第6期56-58,共3页Microprocessors

基　　金：陕西省技术创新引导专项-科技成果转移与推广计划资助项目(2020CGXNG-009);陕西省自然科学基础研究计划资助项目(2019JQ-206);陕西省教育厅科学研究资助项目(17JK0346)。

摘　　要：为解决传统的滑坡预报准确率低、预警不及时的问题,采用信息融合与RBF神经网络相结合的方式,提出一种滑坡地质灾害预报模型,对多传感器参数进行全面综合分析。将多传感器采集到的历史数据和对应发生概率作为RBF神经网络的输入进行模型训练,通过将实时采集的数据输入给训练好的预报模型,计算出滑坡发生的概率。基于模糊规则建立滑坡发生等级表,用以更为准确直观的查询。通过仿真实验,结果表明,模型可有效提高灾害预报准确率。In order to solve the problems of low accuracy and untimely warning of traditional landslide prediction,a landslide geological disaster prediction model is proposed by combining information fusion with RBF neural network,and multi-sensor parameters are comprehensively analyzed.The historical data collected by multiple sensors and the corresponding probability of occurrence are used as the input of RBF neural network for model training.By inputting the real-time data into the trained prediction model,the probability of landslide occurrence is calculated.Based on fuzzy rules,the landslide occurrence grade table is established for more accurate and intuitive inquiry.The simulation results show that the model can effectively improve the accuracy of disaster prediction.

关 键 词：多传感器信息融合 RBF神经网络 滑坡概率 预报模型 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]