RBFE人工神经网络在四组分络合滴定中的应用

本文用非线性的方法来解决多组分金属离子体系同时测定的问题。在此我们用MATLABv5 .3编写了BP网络和RBFE网络并比较了它们在校正时的情况 ,发现在此体系中RBFE网络优于BP网络。络合滴定是在不加缓冲液的情况下直接滴加入EGTA ,并讨论了滴定体积V与溶液的pH值和溶液中金属离子的初始浓度C0M之间的关系 .最后 ,我们将RBFE网络应用于四组分金属离子CuZnPbCd的同时测定

The application of an exact neural network based on radial basis functions(RBFE) in the four cent metalses of the complexometric titration

This paper uses non-linearity method to resolve the problem for simultaneous measurement of the concentrations of mixtures of metal ions. Here we wrote a multilayer feedforword net with the backpropagation learning algorithm (BP) and a neural network based on radial basis functions with MATLAB v5.3, and compared the circumstance for them to correct, and discovered it is better than BP network of RBFE network of system inside. The complexometric titration that we use, with ethylene glycol-bis(2-aminoethylether)-N,N,N',N'-tetraacetic acid (EGTA)is not added the buffer liquid, and we discuss the relation of the volume of titration V ,the value of pH and the ionic original solution C0M . Finally RBFE network apply to simultaneous measurement of four cent metals leaving the son CuZnPb such as Cu, Zn , Cd and Pb .