摘要
针对造纸企业生产过程中的能源消耗预测问题,提出一种基于改进粒子群算法优化的BP神经网络能耗预测模型。在耗电量预测方面对该模型进行了预测分析,对某造纸厂生产车间的视觉耗电量数据进行预测和对比;得出结果比传统BP神经网络预测模型预测误差小,表明预测效果良好。因此,改进PSO-BP网络预测模型能为企业源供需稳定和平衡提供保障,可以促进企业的长久发展与经济效益。
A BP neural network energy consumption prediction model based on improved particle swarm optimization(PSO) was proposed to predict the energy consumption in paper enterprises. In the aspect of power consumption prediction, the model was analyzed, and the visual power consumption data of a paper mill workshop was predicted and compared. The results showed that the prediction error was smaller than that of the traditional BP neural network prediction model. Therefore, the improved PSO-BP network prediction model can guarantee the stability and balance of supply and demand of enterprise sources, and promote the long-term development and economic benefits of enterprises.
作者
王淼
WANG Miao(Xi'an Peiliua University,Xi'an 710125,China)
出处
《造纸科学与技术》
2020年第6期57-60,共4页
Paper Science & Technology
关键词
PSO-BP网络
能耗预测
粒子群算法
造纸
PSO-BP network
energy consumption prediction
particle swarm optimization
papermaking
