摘要： 鉴于训练后的人工神经网络可以精确逼近任意非线性函数,建立了引黄灌渠斗口流量BP网络和RBF网络软测量模型,精选水工试验数据构成训练样本集,在MATLAB6.5环境下进行了仿真训练。检验表明,基于人工神经网络的软测量模型的输出值与标准三角量水堰的测量结果(期望值)吻合情况良好,水流量测量精度大为改善。

关键词: 引黄灌渠, 斗口流量, 软测量, ANN

Abstract: Because ANN trained can exactly approach to any nonlinear function, ANN-based soft-sensing models (BP and RBF) are established and trained by sample-set selected from experiment-data under MATLAB6.5. The examination shows that output of the ANN-based models approaches to result from standard triangular weir (expectation) well. The precision of water-flow measurement is improved largely.

中图分类号: 

• S274.4