Building method for rhubarb medicinal material trueness/falseness and species prediction model

The invention provides a building method for a rhubarb medicinal material trueness/falseness and species prediction model. According to the model, category identification of quality rhubarb, fake rhubarb and three rhubarb species is realized on the basis of a gas chromatography-mass spectrum technology in combination with partial least square discriminant analysis. The building method comprises the following steps: (1) collecting samples; (2) preparing the samples; (3) acquiring GC-MS data; (4) performing data processing and multivariate analysis, wherein cluster analysis and principal component analysis are performed by comparing the differences of chromatographic behaviors of rhubarb of different sources; (5) building the prediction model; and (6) verifying the model. Two built category prediction models are proved to have 100 percent identification accuracy and prediction accuracy. Through adoption of the method, trueness/falseness and species identification of rhubarb are realized by modeling, so that a reliable conclusion and high integrity are achieved; the defects of an existing method are overcome; and a more feasible and reliable new thought is provided for the trueness/falseness and species identification of rhubarb medicinal materials and decoction pieces.