In the paper,the chemometric methods,such as classical least square(CLS),principal component regression(PCR),partial least square(PLS) and radial basis function-artificial neural network(RBF-ANN) were applied to the simultaneous determination of three compounds of synthetic samples in a Britton-Robinson(B-R) buffer solution(pH1.81).The results showed that RBF-ANN had advantages for the prediction of the analytes over other chemometric methods(CLS,PCR and PLS).Norfloxacin,ofloxacin and lomefloxacin have ultrariolet absorption and their absorption spectra are severely overlapped.So they can be determined individually by spectrophotometry without prior separation.Following the validation of the proposed method,it was successfully applied to the determination of norfloxacin,ofloxacin and lomefloxacin in pig feedstuffs.Besides,linear calibration graphs were obtained in the concentration range of 0.6~13.8 mg/L,0.5~15.0 mg/L and 0.5~15.0 mg/L,respectively,and limit of detections were 0.14,0.24 and,0.06 mg/L,respectively.