New prognosis approach for preventive and predictive maintenance - Application to a distillation column

The maintenance, repair, and rehabilitation of industrial reactors are expensive and time-consuming. Sudden interruptions may adversely affect the production process and may lead to harmful effects and disastrous results. Therefore, lifetime prediction is extremely important to prevent catastrophic breakdowns leading to complete cessation of production. This paper aims to propose a prognosis reliable method that can be used to estimate the degradation path of a distillation column and calculate the lifetime percentage of this system. The work presents a direct monitoring approach based on the technique of adaptive neuro-fuzzy inference system (ANFIS) combined with fuzzy C-means algorithm (FCM). At the beginning, ANFIS is used to detect the small variations in the signal over time. Secondly, a new strategy is proposed to find the system degradation path. Thirdly, ANFIS is combined with FCM to predict the future path and calculate the lifetime percentage of the system. The methodology is tested on real experimental data obtained from a distillation column. Results demonstrate the validity of the proposed technique to achieve the needed objectives with a high-level accuracy, especially the ability to determine a more accurate Remaining Useful Life (RUL) when it applied on the automated distillation process in the chemical industry. (C) 2019 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.