The approach of continuous evaluation is an important tool in the learning process. However, only recently it was applied in training based on virtual reality. This paper presents a methodology of evaluation that uses a fuzzy continuous evaluation approach to provide a user profile from his several training. This information can be used to improve the user performance in the real execution of a task. The methodology proposed is given by the union of fuzzy statistical measures, fuzzy statistics and fuzzy parameters (fuzzy testing of hypothesis and fuzzy regression models) as input for a fuzzy rule based expert system (FRBES). The FRBES is able to construct an individual profile for each trainee. This new approach is a diagnostic tool that enables a trainee to understand the areas in which he presents difficulties, allowing him to concentrate on improving skills related to them. Keywords-- Continuous evaluation, fuzzy rule based expert system, fuzzy statistics, fuzzy testing of hypothesi...