The Dark Matter Particle Explorer (DAMPE) is a space-borne particle detector and cosmic ray observatory in operation since 2015, equipped with alongside other instruments a deep calorimeter able to detect electrons up to an energy of 10 TeV and cosmic hadrons up to 100 TeV. The large proton and ion background in orbit requires a powerful electron identification method. In recent years, the field of machine learning has provided such tools. We explore here a neural network based approach to an on-orbit particle identification problem. We present the issues that arise from the constraints of particle physics, notably the difference between training set based on simulated data, and the application set based on real unlabeled data, leading to a trade-off between performances and general usability. We finally compare the neural network discrimination power with the more traditional cut-based analysis.