计算机工程与应用 ›› 2019, Vol. 55 ›› Issue (10): 250-255.DOI: 10.3778/j.issn.1002-8331.1808-0183

• 工程与应用 • 上一篇    下一篇

优化GD-模糊规则的滑坡预报模型研究

温宗周,李  璐,李丽敏,高园平,程少康,刘德阳   

  1. 西安工程大学 电子信息学院,西安 710048
  • 出版日期:2019-05-15 发布日期:2019-05-13

Study on Landslide Prediction Model Based on Optimized GD-Fuzzy Rule

WEN Zongzhou, LI Lu, LI Limin, GAO Yuanping, CHENG Shaokang, LIU Deyang   

  1. School of Electronic Information, Xi’an Polytechnic University, Xi’an 710048, China
  • Online:2019-05-15 Published:2019-05-13

摘要: 为了提高滑坡灾害预报准确率,改善传统的滑坡监测和预报中存在的参数选取困难及模糊控制系统作为预报模型精确度不高的问题,首先采用山体结构稳定性分析法进行滑坡灾害参数的选取,得出降雨量、含水率、土压力及岩土表面位移增量作为预报参数的结论;其次将选取的参数作为模糊系统的输入,建立滑坡灾害发生概率模型,并引入优化的GD算法修正预报模型中的动态参数,使模糊控制模型具有自适应性;同时与未优化的模糊控制模型以及单独模糊控制模型进行仿真对比,仿真结果表明,该控制算法收敛速度快,具有很好的收敛性;最后将该模型在某滑坡重点灾区实验区进行实验测试,实验结果显示该模型具有较好的收敛性,且预报精度达到90%。

关键词: 滑坡, 山体结构稳定性, 优化GD-模糊规则, 动态修正

Abstract: In order to improve the accuracy of landslide disaster prediction and the problem of difficult parameter selection in traditional monitoring and forecasting, firtly, the influence factors of landslide are extracted by using the analysis method of mountain structure stability. Rainfall, water content, soil pressure and displacement increment of rock and soil surface are obtained as the prediction parameters. Secondly, the selected parameters are used as the input of the fuzzy system to establish the probability model of landslide disaster. And the optimized GD algorithm is introduced to correct the dynamic parameters in the prediction model. It makes the fuzzy control model self-adaptive. At the same time, the results are compared with the unoptimized fuzzy control model and the separate fuzzy control model, the simulation results show that the proposed control algorithm has the advantages of fast convergence speed and good convergence. Moreover the model is tested in the experimental area of the key landslide disaster area, which shows that the model has good convergence and the forecast accuracy reaches 90%.

Key words: landslide disasters, mountain structure stability, optimized GD-fuzzy rule, dynamic correction