摘要
通过分析与溢油污染程度有关的影响因素,首次构建了海上石油平台溢油污染程度评价指标体系。针对模型无样本的难题,对评价指标进行分级,利用Rand函数在各分级标准内随机生成足够数量的训练和测试样本,建立了较合理的网络结构,构建了石油平台溢油污染等级BP网络模型。研究结果表明BP网络模型具有很强的泛化能力,能够用于评判未知样本,具有较强的实用性。
Assessment index system of oil spill for the offshore oil platform was established for the first time by analyzing the influenced factors related to the degree of oil pollution.To solve the problem of non-samples,every assessment index was divided into several grades and the Rand function was used to generate enough training samples and test samples.A more reasonable network structure was established and a BP neural network model of the degree of oil pollution was finally set up.The results showed that the model had good generalization,and it not only could be used to evaluate unknown samples but also had a strong practical value.
出处
《海洋湖沼通报》
CSCD
北大核心
2011年第1期115-121,共7页
Transactions of Oceanology and Limnology
基金
海洋公益性行业科研专项经费项目"渤海石油平台及邻近海域环境污染实时监控预警及应急支持技术研究与示范"(200805013)
关键词
BP网络
溢油
评价指标体系
污染等级
训练样本
BP network
oil spill
assessment index system
pollution level
training sample
