摘要
分析了影响水泵机组性能变化的主要因素;根据泵性能与各因素之间的关系,利用BP人工神经网络构建了水泵性能的预测模型;以某轴流泵试验数据为样本,BP人工神经网络为工具,对轴流泵模型进行了泵扬程及效率性能指标与流量、叶片角度等相关因素间的性能预测研究.预测结果表明,将该模型用于轴流泵性能参数预测,不仅可以提高预测精度,而且可以缩短试验时间,降低试验成本.
The main factors influencing the performance of pumping units were analyzed. Based on the relationships between the pump performance and each factor, a prediction model for pump performance was constructed by using artificial neural network, and the model was trained with the test data of an axial-flow pump. Then, the BP neural network was employed for prediction of the relationship of lift head and effficiency-performance index with the flow rate, the angle of blade installation, etc. of an axial-flow pump model. The results show that the BP neural network can improve the accuracy in performance prediction, and it can shorten the time and reduce the cost of experiments.
出处
《河海大学学报(自然科学版)》
CAS
CSCD
北大核心
2007年第1期22-25,共4页
Journal of Hohai University(Natural Sciences)
基金
国家自然科学基金资助项目(50279045)
水利部科技创新资助项目(SCX2003-12)
关键词
人工神经网络
水泵机组
性能预测
artificial neural network
pumping unit
performaance prediction