基于自适应模糊神经网络预测金属——EDTA配合物稳定常数

Prediction of the Stabilities of Metal -EDTA Complex with Adaptive Fuzzy Neural Network

中文关键词:  自适应模糊神经网络  金属离子  EDTA配合物  稳定常数

英文关键词:Adaptive Fuzzy Neural Network  Metallic ions  EDTA complexes  Stability constants

中文摘要:

      采用自适应模糊神经网络的方法，以金属离子外层主量子数（n）、电荷（Z）、半径（r）、适配价轨道数因子（w）及价电子结构因子（S）等为参数，关联金属——EDTA配合物稳定常数。利用减法聚类算法确定模糊神经网络的结构，并结合模糊推理系统进行该网络参数的调整，网络仿真的结果是满意的。在此基础上，预测了13种金属——EDTA配合物稳定常数。

英文摘要:

      An adaptive fuzzy neural network was applied to study the relationships between the structural parameters of metal ions and their stability constants of EDTA complexes, associated with the structural parameters such as principal quantum number in the outer-shell （n） , electric charges （Z） , ionic radii （r）, the factor of adaptive valence orbit number （w） and the structural factor in the valence layer（S）. Subtractive clustering algorithm was used to confirm the structure of fuzzy neural network, and combined fuzzy inference systems to process regulation of the network parameters. The simulation results were satisfactory, and stability constants data of 13 metallic ions without experimental data were predicted.