An ANN‐based DSS system for quality assurance in production network

Abstract

Purpose

The purpose of this paper is to propose an integrated model of decision support system (DSS), artificial neural network, information and communication technologies and statistical process control (SPC) to facilitate agreement by different stakeholders with special interests to commit to the decision that will be taken to stop the production line when something goes wrong somewhere in a supplier network environment.

Design/methodology/approach

A DSS is proposed to capture exceptional signals from source on deterioration of product quality to alert preventive actions needed before the problems are getting out of hand. The supervisors are given a set of guidelines to support making the decision. Real‐time SPC and rule‐based decision support procedures are used to trigger pre‐defined exceptional signals for forwarding to the most appropriate person (the knowledge holder in the problem domain) to make a decision to stop the line. All servers in all remote sites are internet‐connected and provide real‐time quality data to the regional supply chain manager. A case study is described to show how this is implemented in a lens manufacturing company.

Findings

A significant improvement in quality level can be achieved by holding the knowledge worker accountable for making the decision to stop the production line rather than made by default as is with most traditional operations.

Practical implications

To provide a concept to structure activities for decision support so that the persons responsible for making the decision to stop the production line is held accountable by all stakeholders.

Originality/value

Practitioners can replicate the approach used in this paper to their own situations involving decisions to be made to address un‐structured problems and unclear responsibilities.

Citation

Chung, W.W.C., Wong, K.C.M. and Soon, P.T.K. (2007), "An ANN‐based DSS system for quality assurance in production network", Journal of Manufacturing Technology Management, Vol. 18 No. 7, pp. 836-857. https://doi.org/10.1108/17410380710817282

Download as .RIS