摘要
安全状态下的大坝工程可以带来显著的经济效益和社会效益,一旦大坝溃决,将会给下游人民的生命和财产安全造成严重危害。为此,文章提出利用改进的鸡群算法优化SVM参数,利用丰满大坝水平位移实例监测资料,分析水平位移的影响因子,分别建立了改进鸡群算法优化的SVM预测模型、基本鸡群算法优化的SVM预测模型和遗传算法优化的BP神经网络预测模型。分析结果表明,文章所提的预测模型误差波动范围、平均绝对误差和均方根误差更小,是一种预测精度更高的模型,具有很高的实际应用价值。
Dam engineering under safe conditions can bring significant economic and social benefits.Once the dam breaks,it will cause serious harm to the life and property safety of downstream people.Therefore,this paper proposes to use the improved chicken swarm algorithm to optimize the SVM parameters.Using the monitoring data of horizontal displacement of Fengman dam,the influence factors of horizontal displacement are analyzed.The SVM prediction model optimized by improved chicken swarm algorithm,the SVM prediction model optimized by basic chicken swarm algorithm and the BP neural network prediction model optimized by genetic algorithm are established respectively.The analysis results show that the prediction model proposed in this paper has smaller error fluctuation range,mean absolute deviation and root mean squared error.It is a model with higher prediction accuracy and has high practical application value.
作者
蔡东健
岳顺
CAI Dongjian;YUE Shun(Yuance Information Technology Co.,Ltd.,Suzhou 215027,Jiangsu,China)
出处
《工程技术研究》
2023年第24期44-46,共3页
Engineering and Technological Research
关键词
大坝
SVM
变形监测
鸡群算法
dam
SVM
deformation monitoring
chicken swarm algorithm