A moving average denoise operator and grey discrete production process quality prediction model
Grey Systems: Theory and Application
ISSN: 2043-9377
Article publication date: 31 May 2022
Issue publication date: 25 January 2023
Abstract
Purpose
The purpose of this paper is to solve the problem of quality prediction in the equipment production process and provide a method to deal with abnormal data and solve the problem of data fluctuation.
Design/methodology/approach
The analytic hierarchy process-process failure mode and effect analysis (AHP-PFMEA) structure tree is established based on the analytic hierarchy process (AHP) and process failure mode and effect analysis (PFMEA). Through the failure mode analysis table of the production process, the weight of the failure process and stations is determined, and the ranking of risk failure stations is obtained so as to find out the serious failure process and stations. The spectrum analysis method is used to identify the fault data and judge the “abnormal” value in the fault data. Based on the analysis of the impact, an “offset operator” is designed to eliminate the impact. A new moving average denoise operator is constructed to eliminate the “noise” in the original random fluctuation data. Then, DGM (1,1) model is constructed to predict the production process quality.
Findings
It is discovered the “offset operator” can eliminate the impact of specific shocks effectively, moving average denoise operator can eliminate the “noise” in the original random fluctuation data and the practical application of the shown model is very effective for quality predicting in the equipment production process.
Practical implications
The proposed approach can help provide a good guidance and reference for enterprises to strengthen onsite equipment management and product quality management. The application on a real-world case showed that the DGM (1,1) grey discrete model is very effective for quality predicting in the equipment production process.
Originality/value
The offset operators, including an offset operator for a multiplicative effect and an offset operator for an additive effect, are proposed to eliminate the impact of specific shocks, and a new moving average denoise operator is constructed to eliminate the “noise” in the original random fluctuation data. Both the concepts of offset operator and denoise operator with their calculation formulas were first proposed in this paper.
Keywords
Acknowledgements
This work was supported by a long term project of national major talent plan of China (YQR20024), projects of the National Natural Science Foundation of China (72071111, 71671091). It is also supported by a joint project of both the NSFC and the RS of the UK (71811530338), a project of Intelligence Introduction base of the Ministry of Science and Technology (G2021181014L). At the same time, the authors would like to acknowledge the partial support of the Fundamental Research Funds for the Central Universities of China (NC2019003).
Citation
Li, Q., Liu, S. and Lin, C. (2023), "A moving average denoise operator and grey discrete production process quality prediction model", Grey Systems: Theory and Application, Vol. 13 No. 1, pp. 34-57. https://doi.org/10.1108/GS-09-2021-0143
Publisher
:Emerald Publishing Limited
Copyright © 2022, Emerald Publishing Limited