Research and prediction of coordination reactions between CPA-mA and some metal ions using artificial neural networks

The complex relationship between maximum absorption wavelength (lambda (max )), molar absorptivity (epsilon) of the coordination compounds formed from m-acetyl-chlorophosphonazo (CPA-mA) and the metal ions, the acidity of coor dination reaction, some properties of metal ions and the properties of more than 20 coordination compounds were studied using artificial neural networ ks with extended delta-bar-delta EDBD back learning algorithms in this pape r. Six parameters: the pH of coordination reactions, metal ion radius (R), relative atomic weight (Wt), ionic electronic energy (E), metal ion standar d Gibbs' free energy (DeltaG(0)) and hard-soft acid-base dual scale (f) wer e used as input parameters, to predict the lambda (max) and epsilon of the coordination compounds. The structures of networks and the learning times w ere optimized. The best networks structure is 6-7-2. The optimum number of learning times is about 160 196. It is shown that the maximum relative erro r is no more than 6% in the testing set. The trained networks are used to s imulate the complicated relations between the metal ion properties, coordin ation reaction conditions and the properties of coordination compounds. Thi s optimized networks have been used for the prediction of the lambda (max) and epsilon of coordination compounds formed from Tb3+ , Ho3+ with CPA-mA s eparately and with satisfactory results. 2001 Elsevier Science Ltd. All rig hts reserved.