Electroacoustic music on analog magnetic tape is characterized by several carrier-related specificities that must be considered when creating a copy for digital preservation. The tape recorder needs to be set to the correct speed and equalization, and the magnetic tape could have some intentional or unintentional alterations. During both the creation and the musicological analysis of a digital preservation copy, the quality of the work may be affected by human inattention. This article presents a methodology based on neural networks to recognize and classify the alterations of a magnetic tape from the video of the tape as it passes in front of the tape recorder's playback head. Furthermore, some machine-learning techniques have been tested to recognize a tape's equalization from its background noise. The encouraging results open the way to innovative tools able to unburden audio technicians and musicologists from repetitive tasks and to improve the quality of their work.