基于BP神经网络的火电厂大气环境评价研究  

Evaluation on Atmosphere Environmental of Thermal Power Plant Base on BP Neural Network

作　　者：苏波[1] 武祥波[1] 白玉娥[1] 

机构地区：[1]内蒙古电力勘测设计院,内蒙古呼和浩特010020

出　　处：《电力勘测设计》2008年第1期62-65,共4页Electric Power Survey & Design

摘　　要：利用附加动量法对传统的BP神经网络算法改进,建立了基于改进BP神经网络的评价模型,并将其应用到火电厂大气环境评价研究中去。动量系数的引入减少了学习次数,有效防止了网络陷入局部极小值,同时能保证评价结果的准确性,通过火电厂的实例验证,结果表明:神经网络法进行火电厂环境评价不仅计算简便,而且评价结果具有较高的可靠性。This paper, making use of the traditional BP neural network algorithm which is improved by the law of additional momentum, establish an evaluation model based on the improved BP neural network. This model is applied to the research on the evaluation for atmosphere environmental of thermal power plant. The introduction of momentum coefficient cuts down the times of learning, and efficiently prevents the network trap into the local optimum and the same time ; ensures the veracity of the evaluation result. Example verification of thermal power plant shows that the method presented in this paper is simple to calculate, but also practical and effective.

关 键 词：火电厂 大气环境 BP神经网络 动量系数 

分 类 号：X820[环境科学与工程—环境工程]