In this paper, an intelligent fault diagnosis scheme based on big data analysis method and adaptive neuro-fuzzy inference system (ANFIS) is proposed. An experimental study is given on the example of an electric drive of a stirrer of a hydrogenator reactor to illustrate the effectiveness of the proposed method and algorithmic solutions. Numerical experiments demonstrated the possibility of scaling proposed methodology for a wide class of similar process objects with the achievement of accuracy not less than 96.5%. The residual life calculation based on the ANFIS model have been carried out.