Аннотация:The TAIGA experiment in Tunka Valley is expanding the present scintillation detector array with new TAIGA-Muon detector stations. A simulation model was developed to optimise the layout of the new stations and study the identification performance of the array. The extensive air showers (EASs) were simulated with the CORSIKA simulation tool, and the detector response was simulated with the GEANT4 package. The EASs induced by gamma quanta or proton, Helium, Carbon, Nitrogen, Oxygen, Iron in the energy range of 1 PeV and the zenith angle range from 0°to 45°, are used for these studies. For the identification of high-energy extensive air showers, a method based on a neural network was suggested. With this method, the proton identification efficiency is more than 99.9%, while the gamma dentification efficiency is not less than 50%.