A fuzzy-logic advisory system for lean manufacturing within SMEs

Abstract

This research article presents the development of a fuzzy-logic advisory system to assist small-medium sized enterprises (SMEs) as a decision support tool for implementing lean manufacturing. The system is developed using fuzzy logic rules, with a combination of research methodology approaches employed in the research study that included data collection from 10 manufacturing SMEs through documentation analysis, observation of companies’ practices and semi-structured interviews. The overall system comprises three fuzzy-logic advisory sub-systems that feed into a main system. These outputs are relative cost of lean implementation, a company lean readiness status and the level of value-add to be achieved (impact/benefits). The three sub-systems were validated with hard data that enabled the assignment of a number of input variables whose membership functions aided the definition of the linguistic variables used. The main system yielded heuristic rules that enable the postulation of scenarios of lean implementation (Do it, Probably do it, Possibly do it and Do not do it). This was also validated with a number of firms based within the UK. Moreover, expert opinions encompassed those in both academic and industrial settings. The developed system has the capability to assess the impact of implementing lean manufacturing within small-to-medium sized manufacturers. Hence, a major contribution of the developed system is its provision of the heuristic rules that aid decision-making process for lean implementation at the early implementation stage. The visualisation facility of the developed system is also a useful tool in enabling potential lean users to forecast the relative cost of the lean project upfront, anticipate lean benefits, and realise the degree of lean readiness.

Keywords:

• fuzzy logic
• impact assessment
• lean manufacturing
• SMEs

Acknowledgements

The authors thank the Engineering Physical Science Research Council (EPSRC), the Manufacturing Advisory Service in the East of England (MAS-East) and Cranfield University for sponsoring this research project.