首页|SSA-BP神经网络模型在地震伤亡人数预测中的应用

SSA-BP神经网络模型在地震伤亡人数预测中的应用

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
  • 维普
为快速准确地预测地震伤亡人数,提高地震应急救援效率,基于皮尔逊相关系数法定量刻画地震伤亡人数与影响因素之间的关联程度,挖掘地震伤亡人数的有效影响因素,并通过多元回归分析法检验有效影响因素的可靠性;采用麻雀搜索算法(SSA)优化BP神经网络,构建SSA-BP神经网络模型对地震伤亡人数进行预测,并将该模型与SVM、RBF、BP模型的预测数据和实际值进行对比.结果表明:与地震伤亡人数相关程度从高到低的有效影响因素依次为震中烈度、震级、房屋受损情况、发震时间、震源深度;SSA-BP神经网络模型较SVM、RBF、BP预测模型的均方误差分别降低93.3％、91.4％、85.2％,平均绝对误差分别降低69.3％、64.9％、54.7％,均方根误差分别降低74.1％、70.8％、61.6％,预测结果与实际地震伤亡人数接近,该模型可用于地震伤亡人数预测.
Application of SSA-BP Neural Network Model in Predicting Earthquake Casualties
In order to quickly and accurately predict the number of earthquake casualties,improve the efficiency of earthquake emergency rescue,the correlation degree between the number of earthquake casualties and the influencing factors was quanti-tatively described based on Pearson correlation coefficient method,and the effective influencing factors of the number of earthquake casualties were explored,and the reliability of the effective influencing factors was tested by multiple regression analysis.The sparrow search algorithm(SSA)is used to optimize the BP neural network,and the SSA-BP neural network model is constructed to predict the number of casualties in the earthquake.Compare the predicted data and actual values of SSA-BP neural network model with SVM,RBF,BP models.The results show that the effective influencing factors related to the number of earthquake casualties from high to low are as follows:epicentral intensity,magnitude,building damage,earthquake occurrence time and focal depth.Compared with SVM,RBF and BP prediction models,the mean square error of SSA-BP neural network model is reduced by 93.3％,91.4％and 85.2％respectively,the average absolute error is reduced by 69.3％,64.9％and 54.7％respectively,and the root mean square error is reduced by 74.1％,70.8％and 61.6％respectively.The forecast results are close to the actual earthquake casualties,and the model can be used to predict the earthquake casualties.

earthquake disastersnumber of casualtiessparrow search algorithm(SSA)BP neural networkprediction

李洪兵、唐成浩、韩咪、李超、刘可、刘琴

展开 >

四川师范大学工学院,四川成都 610101

西南石油大学经济管理学院,四川成都 610500

四川省泰达建设工程有限公司,四川成都 610041,China

地震灾害 伤亡人数 麻雀搜索算法(SSA) BP神经网络 预测

国家民委"一带一路"国别和区域研究中心日本应急管理研究中心项目四川省哲学社会科学重点实验室"智慧应急管理重点实验室"项目四川应急管理知识普及基地项目四川省科技计划四川师范大学实验技术项目四川省大学生创新创业训练计划(2023)

2023RBYJGL-42023ZHYJGL-6SCYJ2023-072023NSFSC1038SYJS2022008S202310636103

2024

10.19737/j.cnki.issn1002-3631.2024.04.014

安全
北京市劳动保护科学研究所 中国职业安全健康协会

安全

影响因子：0.186
ISSN：1002-3631
年,卷(期)：2024.45(4)
  • 25