人工鱼群算法在气固流化床流型识别中的应用  

Application of artificial fish-swarm algorithm in gas-solid fluidized bed flow regime identification

作　　者：周云龙[1] 何强勇[2] 许明飞[1] 

机构地区：[1]东北电力大学能源与机械工程学院,吉林吉林132012 [2]东北电力大学自动化工程学院,吉林吉林132012

出　　处：《化学工程》2010年第7期39-42,50,共5页Chemical Engineering(China)

摘　　要：准确识别流型是流化床气固二相流参数检测的一项重要内容,实验是在流化床气固二相流实验系统上进行的。首先,采集5种典型流型的压力波动信号,并以信号的统计参量作为流型特征。然后,将样本送入经过人工鱼群优化的BP神经网络进行训练。人工鱼群(AFSA)是一种新型的智能优化算法,具有全局收敛性好,鲁棒性强,对初值不敏感等特点,通过优化神经网络的权值使识别率得到明显提高,实现了气固流化床典型流型的快速、准确识别。实验结果表明,该方法对气固流化床5种典型流型的识别率达到97%,为在线识别气固流化床流型提供了一种新的有效方法。The exact identification of flow regime is an important content to detect the parameters of gas-solid two-phase flow fluidized bed.The experiments were conducted on gas-solid fluidized bed system in the following steps： collect pressure fluctuation signals of 5 kinds of typical flow regimes,take statistical parameters of those signals as characteristics of flow regimes,and send those training samples to BP neural network optimized by artificial fish-swarm algorithm（AFSA）,which is a new kind of intelligence optimization algorithm,and has advantages of good global astringency,robustness and insensitive to initial value.The optimized weights of neural network can improve identification rate obviously.Thus,it can identify 5 typical flow regimes of gas-solid fluidized bed successfully,rapidly and accurately.The test results show that identification rate of this method can reach 97% and it provides a new effective way to identify the gas-solid flow regime of fluidized bed online.

关 键 词：BP神经网络 人工鱼群算法 气固流化床 统计参数 

分 类 号：O359.2[理学—流体力学]