摘要
在简要介绍BP神经网络和遗传算法基本理论的基础上,针对BP算法易陷入局部极小的缺点,将具有全局寻优的特点的遗传算法融入其中,以胶州湾东北部海域的海水水质评价为例,阐明了该方法在海水水质评价中的应用,并与其他水质评价算法进行的比较,结果表明该算法具有较好的客观性和实用性,丰富了海水水质评价的方法体系,为近岸海域的环境管理与决策的提供依据。
The principle of BP algorithm and genetic algorithm is introduced briefly. In order to overcome the shortcomings of BP algorithm that is usually trapped to a local optimum, according to the advantage of the globe optimal searching of genetic algorithm, a combining algorithm for neural network training is formed by combining BP algorithm and genetic algorithm in the seawater quality assessment of Jiaozhou bay＇s northeast. This algorithm is tested and compared with other algorithms. The comparison results of cases showed that the genetic neural network algorithm was objective and could be a new method in seawater assessment, further more provide evidence for marine environment protection.
出处
《海洋湖沼通报》
CSCD
北大核心
2009年第3期167-173,共7页
Transactions of Oceanology and Limnology
关键词
BP神经网络
遗传算法
海水水质评价
BP neural network
genetic algorithm
seawater quality assessment
