Adaptive neuro-fuzzy inference system with analytic hierarchy process: an application for drawworks’ failure mode and effect analysis

Abstract

ABSTRACT Maintenance-significant equipment malfunctions impose coetaneous consideration of the economic, environmental, and social safety in the Oil and Gas industry. Moreover, to overcome the conventional drawbacks of risk evaluation analysis regarding the multi-level impact factors and computational inaccuracy, this study proposes a modified failure mode and effect analysis model. The proposed model incorporates a combination of quantitative intelligent-based technique and qualitative objective accuracy-oriented analyses. First, experts’ judgment was evaluated by spherical fuzzy sets represented by support, opposition, and hesitation toward the risk assessment of a system failure. Second, an analysis was performed to establish the pairwise importance of influencing factors using the analytic hierarchy process. Third, an adaptive neuro-fuzzy inference system was incorporated to address the fluctuation of risk prioritization by imitating the experts’ judgment to predict the future possibilities of failure modes. Then, Taguchi’s design of experiment was implemented to optimize the precision of the predictive analysis. The applicability of the proposed model was validated by a case study of a drawworks system on an offshore production and drilling platform. The results indicated that the model is accurate and acceptable for use in the evaluation of sustainable maintenance processes. The study culminated with directions for future studies.