The proposal presented in this paper focuses on the process of classification of electrical faults in a transformer environment. Although the application is very specific in a very concrete field, the scope of the research has a wider scope since it is a multivariate time series classification system. It is based on two already known proposals such as the InceptionTime and Gated Transformer models, in which an attempt is made to extract the benefits provided by each of them. From the first one we extract its optimal computation time, and from the second one the way in which it handles multivariability. Although in the latter case, better results are obtained by modifying and changing the gating proposal for a linear double layer in its output, and the elimination of one of the bottleneck layers in charge of the relationships between the different time variables used. The study focuses on a potential future practical application in which processing time is prioritized together with a high percentage of classification accuracy. Finally, a comparative study is presented between the four models studied or proposed on a proprietary database created for the development of this and future work.