Adaptive decision support for suggesting a machine tool maintenance strategy: From reactive to preventative

Abstract

Purpose

The purpose of this paper is to produce a decision support aid for machine tool owners to utilise while deciding upon a maintenance strategy. Furthermore, the decision support tool is adaptive and capable of suggesting different strategies by monitoring for any change in machine tool manufacturing accuracy.

Design/methodology/approach

A maintenance cost estimation model is utilised within the research and development of this decision support system (DSS). An empirical-based methodology is pursued and validated through case study analysis.

Findings

A case study is provided where a schedule of preventative maintenance actions is produced to reduce the need for the future occurrences of reactive maintenance actions based on historical machine tool accuracy information. In the case study, a 28 per cent reduction in predicted accuracy-related expenditure is presented, equating to a saving of £14k per machine over a five year period.

Research limitations/implications

The emphasis on improving machine tool accuracy and reducing production costs is increasing. The presented research is pioneering in the development of a software-based tool to help reduce the requirement on domain-specific expert knowledge.

Originality/value

The paper presents an adaptive DSS to assist with maintenance strategy selection. This is the first of its kind and is able to suggest a preventative strategy for those undertaking only reactive maintenance. This is of value for both manufacturers and researchers alike. Manufacturers will benefit from reducing maintenance costs, and researchers will benefit from the development and application of a novel decision support technique.

Citation

Shagluf, A., Parkinson, S., Longstaff, A.P. and Fletcher, S. (2018), "Adaptive decision support for suggesting a machine tool maintenance strategy: From reactive to preventative", Journal of Quality in Maintenance Engineering, Vol. 24 No. 3, pp. 376-399. https://doi.org/10.1108/JQME-02-2017-0008