Cheng-ping Yen,Jen-hun Chen.The Prediction of Flow Using Neural Network Model[J].Research of Soil and Water Conservation,1995,2(03):62-67.
神经网路模式在流量之预测
- Title:
- The Prediction of Flow Using Neural Network Model
- Keywords:
- back-propagation neural network model; the gradient steepest descent method; sigmoid function; flow prediction
- 摘要:
- 本文以倒传递神经网路模式，进行长期流量预测之应用研究，并以台湾中部德基水库上游松茂流量站历年观测资料进行探讨。初步得到预测结果与实测值比较尚有一倍以上的误差。但以神经网路之潜在应用潜力，寻找系统化网路参数值建立方法以得到更精确预测结果之经验，为寻人相当值得继续研究之课题。
- Abstract:
- This paper uses Back-Propagation Neural Network Model to proceed the research of long-term flow prediction.The observed flow data of Son-Mao station on the upstream of De-Ji Reservoir of central Taiwan are used.The primer result is the over prediction nearly 100% with observed data.But for future potential of Neural Network application, the experience of searching the systematized method of network parameters construction, and to get more accurate prediction results, is worth to study.
参考文献/References:
[1] 焦李成.神经网路系统理论.儒林图书有限公司, 1991, P14
[2] 曾仁宏、颜正平.介入时度间数列在坡地开发之应用.1994年农业工程研讨会论文集.1994, P38~400.
[3] 萧国鑫等.德基水库集水区土地利用变迁分析及资讯系统之建立总报告.工研院能资所, 1994, P78
[4] Using Neural Works-A Tutorial for Neural Works Professional I/PLUS and Neural Works Explorer.Neural Ware, Inc., 1993
[5] Reference Guide-Software Reference for Professional I/PLUS and Neural Works Explorer.Neural Ware, Inc., 1993
[6] 王进德、萧大全.类神经网路与模糊控制理论入门:全华科技图书股份有限公司, 1994, P15~58
[7] 叶怡成.类神经网路模式应用与实作.儒林图书有限公司, 1993, P69~110
[8] 叶怡成.类神经网路系统Professional I Plus训练教材:中纲科技股份有限公司, 1993
[9] 林茂文.时间数列分析与预测:华泰书局, 1992.p321
[10] Nachimuthu Karunanithi etc. NEURAL NETWORKS FOR RIVER FLOWPREDICTION. ournal of Computing in Civil Engineering, Vol. 8, No. 2.ASCE, 1994.P201~220
备注/Memo
收稿日期:1995-5-10。
作者简介:颜正平，中兴大学水土保持学研究所所长兼系主任。