Orthogonal design has been applied to the optimization of separation and determination of dauricine and daurisoline in Rhizoma Menispermi and its herbal medicine by micellar electrokinetic capillary chromatography. Operational variables, such as the voltage, micelle concentration, buffer concentration and pH were optimized. Their different effects on peak resolution were studied by the experimental design method. Optimized separation conditions were obtained and successfully applied to the separation and determination of dauricine and daurisoline in real samples. The proposed method allows alkaloids in real samples to be determined within 15 min using a buffer system composed of 25 mM HAc, 25 mM NaAc and 2% polyoxyethylene sorbitan monolaurate (Tween-20) (pH 4.5). In addition, a radial basis function neural network with a “4-18-1” structure was developed based on the experimental results of orthogonal design and uniform design, and applied to the prediction of peak resolution of dauricine and daurisoline under the optimum separation conditions given by orthogonal design. The predicted results were in good agreement with the experimental values, indicating that radial basis function neural network may be a potential method for the selection of separation conditions in capillary electrophoresis.
