An application of integrated EPC–SPC methodology for simultaneously monitoring multiple output characteristics

Abstract

Purpose

The purpose of this paper is to develop an integrated engineering process control (EPC)–statistical process control (SPC) methodology for simultaneously monitoring and controlling autocorrelated multiple responses, namely, brightness and viscosity of the pulp bleaching process.

Design/methodology/approach

The pulp bleaching is a process of separating cellulose from impurities present in cooked wood chips through chemical treatment. More chemical dosage or process adjustments may result in better brightness but adversely affect viscosity. Hence, the optimum chemical dosage that would simultaneously minimize the deviation of pulp brightness and viscosity from their respective targets needs to be determined. Since the responses are autocorrelated, dynamic regression is used to model the responses. Then, the optimum chemical dosage that would simultaneously optimize the pulp brightness and viscosity is determined by fuzzy optimization methodology.

Findings

The suggested methodology is validated in 12 cases. The validation results showed that the optimum dosage simultaneously minimized the variation in brightness and viscosity around their respective targets. Moreover, suggested solution has been found to be superior to the one obtained by optimizing the responses independently.

Practical implications

This study provides valuable information on how to identify the optimum process adjustments to simultaneously ensure autocorrelated multiple responses on or close to their respective targets.

Originality/value

To the best of the authors’ knowledge, this paper is the first to provide application of the integrated EPC–SPC methodology for simultaneously monitoring multiple responses. The study also demonstrates the application of dynamic regression to model autocorrelated responses.

Citation

John, B. and Singhal, S. (2019), "An application of integrated EPC–SPC methodology for simultaneously monitoring multiple output characteristics", International Journal of Quality & Reliability Management, Vol. 36 No. 5, pp. 669-685. https://doi.org/10.1108/IJQRM-04-2018-0104