Maintenance of industrial equipment: Degree of certainty with fuzzy modelling using predictive maintenance

Abstract

Purpose

The purpose of this paper is to ascertain overall system health and maintenance needs with degree of certainty using condition‐monitoring data with hierarchical fuzzy inference system.

Design/methodology/approach

In process plants, equipment condition is ascertained using condition‐monitoring data for each condition indicator. For large systems with multiple condition indicators, estimating the overall system health becomes cumbersome. The decision of selecting the equipment for an overhaul is mostly determined by generic guidelines, and seldom backed up by condition‐monitoring data. The proposed approach uses a hierarchical system health assessment using fuzzy inference on condition‐monitoring data collected over a period. Each subsystem health is ascertained with degree of certainty using degree of match operation performed on fuzzy sets of condition‐monitoring data and expert opinion. Fuzzy sets and approximate reasoning are used to handle the uncertainty/imprecision in data and subjectivity/vagueness of expert domain knowledge.

Findings

The proposed approach has been applied to a large electric motor (> 500kW), which is treated as four subsystems i.e. power transmission system, electromagnetic system, ventilation system and support system. Fuzzy set of condition‐monitoring data of each condition indicator on each subsystem is used to ascertain the degree of match with the expert opinion fuzzy set, thus inferring the need for periodical overhaul. Subjective expert opinion and quantitative condition‐monitoring data have been evaluated using hierarchical fuzzy inference system with a rule base. It is found that the certainty of each subsystem's health is not the same at the end of 600 days of monitoring and can be classified as “very good”, “good”, “marginal” and “sick”. Degree of certainty has helped in taking a managerial decision to avoid “over‐maintenance” and to ensure reliability. Large volumes of condition‐monitoring data not only helped in assessing motor overhaul health, but also guide the maintenance engineer to suitably review maintenance/monitoring strategy on similar systems to achieve desired reliability goals.

Practical implications

Condition‐monitoring data collected for long periods can be utilized to understand the degree of certainty of degradation pattern in the longer time frame with reference to domain knowledge to improve effectiveness of predictive maintenance towards reliability.

Originality/value

The paper gives an opportunity to evaluate quantitative condition‐monitoring data and subjective/qualitative domain expertise using fuzzy sets. The predictive maintenance cycle “Monitor‐analyse‐plan‐repair‐restore‐operate” is scientifically regulated with a degree of certainty. Approach is generic and can be applied to a variety of process equipment to ensure reliability through effective predictive maintenance.

Citation

Vijay Kumar, E., Chaturvedi, S.K. and Deshpandé, A.W. (2009), "Maintenance of industrial equipment: Degree of certainty with fuzzy modelling using predictive maintenance", International Journal of Quality & Reliability Management, Vol. 26 No. 2, pp. 196-211. https://doi.org/10.1108/02656710910928824