摘要
为提高BP神经网络对水工钢闸门安全等级识别的速度和精度,构建基于信息增益(IG)和混沌粒子群优化(CPSO)算法优化BP神经网络的水工钢闸门安全等级评估模型。该模型利用IG算法精简水工钢闸门安全等级评估的特征指标,避免冗余变量干扰,提升模型的训练速度;利用CPSO算法优化BP神经网络的初始权重,提高模型的收敛性及对水工钢闸门安全等级的分类能力。经过验证分析,基于IG-CPSO-BP的水工钢闸门安全等级评估模型的评估结果与实际的水工钢闸门安全等级基本吻合,识别精度明显优于IG-BP、IG-GA-BP、IG-PSO-BP模型。
In order to improve the speed and accuracy of BP neural network in the identification of safety grade of hydraulic steel gates,a safety grade evaluation model of hydraulic steel gates based on information gain(IG)and chaotic particle swarm optimization(CPSO)opti⁃mized BP neural network was constructed.In this model,IG algorithm was used to simplify the characteristic index of safety grade evaluation of hydraulic steel gates,eliminate the interference of redundant feature vectors,and improve the training speed of the model.The model used CPSO algorithm to optimize the initial weight system of BP neural network to improve the convergence of the model and the classification abil⁃ity of the safety grade of hydraulic steel gates.After verification and analysis,the evaluation results of the safety grade evaluation model of hy⁃draulic steel gates based on IG⁃CPSO⁃BP are basically consistent with the actual safety grade of hydraulic steel gates,and the identification accuracy is significantly better than that of IG⁃BP,IG⁃GA⁃BP and IG⁃PSO⁃BP models.
作者
周伦钢
赵松波
仝戈
许亮
ZHOU Lungang;ZHAO Songbo;TONG Ge;XU Liang(Henan Industrial School,Zhengzhou 450002,China;South-to-North Water Diversion Middle Route Information Technology Co.,Ltd.,Beijing 100053,China;Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems,School of Electrical Engineering and Automation,Tianjin University of Technology,Tianjin 300384,China)
出处
《人民黄河》
CAS
北大核心
2023年第7期130-133,162,共5页
Yellow River
基金
国家自然科学基金资助项目(61308120)。
关键词
信息增益
混沌粒子群优化算法
BP神经网络
安全等级识别
水工钢闸门
information gain
chaotic particle swarm optimization algorithm
BP neural network
safety grade identification
hydraulic steel gate
