摘要
为了及时掌握黄河水沙通量的动态变化情况,最大程度地减少黄河水沙监测成本,本文基于黄河小浪底水库下游的某水文站水沙通量的实时监测数据,首先建立了决策树模型预测该水文站未来两年水沙通量的变化趋势,然后利用遗传算法制订了未来两年的最优监测方案。研究结果表明,运用遗传算法求解制定的监测方案能在减少监测次数的同时有效监测水沙通量的突变点和变化趋势,平均降低69.77%的监测成本。
In order to grasp the dynamic changes of water and sediment flux in the Yellow River in a timely manner and minimize the cost of water and sediment monitoring in the Yellow River,this paper first established a decision tree model to predict the trend of water and sediment flux at hydrological stations in the next two years based on the real-time monitoring data of a hydrological station downstream of the Xiaolangdi Reservoir on the Yellow River.Then the genetic algorithm was used to formulate the optimal monitoring plan for the next two years.The research results show that the monitoring plan developed using genetic algorithms can effectively monitor the mutation points and changing trends of water and sediment flux while reducing the number of monitoring times,reducing monitoring costs by an average of 69.77%.
作者
崔春林
李博
皮滨滨
唐玉铭
李华平
Cui Chunlin;Li Bo;Pi Binbin;Tang Yuming;Li Huaping(Chongqing City Management College,Chongqing,China;Yangtze Normal University,Chongqing,China;Chongqing University of Posts and Telecommunications,Chongqing,China)
出处
《科学技术创新》
2024年第22期17-20,共4页
Scientific and Technological Innovation
基金
重庆市高等职业教育教学改革研究项目“数学建模提升高等数学教育教学的研究与实践”(编号:Z213102)。
关键词
小浪底水库
水沙监测
遗传算法
智能预测
Xiaolangdi reservoir
water and sediment monitoring
genetic algorithm
intelligent prediction