Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter November 2, 2023

Quality Control Using Convolutional Neural Networks Applied to Samples of Very Small Size

  • Rallou A. Chatzimichail ORCID logo and Aristides T. Hatjimihail ORCID logo EMAIL logo

Abstract

Artificial neural networks (NNs) have been extensively studied for their application to quality control (QC) to monitor the conformity of processes to quality specifications. However, the requirement of at least five QC measurements increases the associated costs. This study explores the potential of using NNs on samples of QC measurements of very small size. To achieve this, three one-dimensional (1-D) convolutional NNs (CNNs) were designed, trained, and tested on datasets of n-tuples of simulated, standardized, normally distributed QC measurements, where 2 n 4 .

The performance of the designed CNNs was compared to that of statistical QC functions applied to samples of equal sizes, maintaining equal probabilities for false rejection. The results demonstrated that for n-tuples of QC measurements distributed as 𝒩 ( 0 , s 2 ) , where 1.2 < s 9.0 , the designed CNNs outperformed their statistical QC functions counterparts. Therefore, the use of 1-D CNNs applied to samples of two to four QC measurements can effectively enhance the detection of nonconformity of a process to quality specifications. This approach has the potential to significantly reduce the costs of QC measurements and improve the overall efficiency of the QC process.

MSC 2020: 62P30; 68T07

References

[1] A. C. Atkinson, M. Riani and A. Corbellini, The Box-Cox transformation: review and extensions, Statist. Sci. 36 (2021), no. 2, 239–255. 10.1214/20-STS778Search in Google Scholar

[2] G. E. P. Box and D. R. Cox, An analysis of transformations. (With discussion), J. Roy. Statist. Soc. Ser. B 26 (1964), 211–252. 10.1111/j.2517-6161.1964.tb00553.xSearch in Google Scholar

[3] S. I. Chang and C. A. Aw, A neural fuzzy control chart for detecting and classifying process mean shifts, Int. J. Production Res. 34 (1996), no. 8, 2265–2278. 10.1080/00207549608905024Search in Google Scholar

[4] C.-S. Cheng, A multi-layer neural network model for detecting changes in the process mean, Comput. Indust. Eng. 28 (1995), no. 1, 51–61. 10.1016/0360-8352(94)00024-HSearch in Google Scholar

[5] H. A. David and H. N. Ngaraja, Order statistics, Encyclopedia of Statistical Sciences, John Wiley & Sons, New York (2014), 5829–5838. Search in Google Scholar

[6] S. Ding, H. Li, C. Su, J. Yu and F. Jin, Evolutionary artificial neural networks: A review, Artificial Intelligence Rev. 39 (2013), no. 3, 251–260. 10.1007/s10462-011-9270-6Search in Google Scholar

[7] A. J. Duncan, Quality Control and Industrial Statistics, 5th ed. Richard D. Irwin, Homewood, 1986. Search in Google Scholar

[8] C. G. Fraser, P. Hyltoft Petersen, J. C. Libeer and C. Ricos, Proposals for setting generally applicable quality goals solely based on biology, Ann. Clinical Biochemistry 34 (1997), 8–12. 10.1177/000456329703400103Search in Google Scholar PubMed

[9] J. Gillard, A generalised Box-Cox transformation for the parametric estimation of clinical reference intervals, J. Appl. Stat. 39 (2012), no. 10, 2231–2245. 10.1080/02664763.2012.706266Search in Google Scholar

[10] W. Hachicha and A. Ghorbel, A survey of control-chart pattern-recognition literature (1991–2010) based on a new conceptual classification scheme, Comput. Indust. Eng. 63 (2012), no. 1, 204–222. 10.1016/j.cie.2012.03.002Search in Google Scholar

[11] A. T. Hatjimihail, A tool for the design and evaluation of alternative quality-control procedures, Clinical Chem. 38 (1992), no. 2, 204–210. 10.1093/clinchem/38.2.204Search in Google Scholar

[12] A. T. Hatjimihail, Genetic algorithms-based design and optimization of statistical quality-control procedures, Clinical Chem. 39 (1993), no. 9, 1972–1978. 10.1093/clinchem/39.9.1972Search in Google Scholar

[13] A. T. Hatjimihail, Estimation of the optimal statistical quality control sampling time intervals using a residual risk measure, PloS One 4 (2009), no. 6, Paper No. e5770. 10.1371/journal.pone.0005770Search in Google Scholar PubMed PubMed Central

[14] Z. Hong, Y. Li and Z. Zeng, Convolutional neural network for control chart patterns recognition, Proceedings of the 3rd International Conference on Computer Science and Application Engineering—CSAE 2019, Association for Computing Machinery, New York (2019), 1–9. 10.1145/3331453.3360974Search in Google Scholar

[15] H. B. Hwarng and N. F. Hubele, X control chart pattern identification through efficient off-line neural network training, IIE Trans. 25 (1993), no. 3, 27–40. 10.1080/07408179308964288Search in Google Scholar

[16] A. Khan, A. Sohail, U. Zahoora and A. Saeed Qureshi, A survey of the recent architectures of deep convolutional neural networks, Artificial Intelligence Rev. 53 (2020), no. 8, 5455–5516. 10.1007/s10462-020-09825-6Search in Google Scholar

[17] S. Kiranyaz, O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj and D. J. Inman, 1D convolutional neural networks and applications: A survey, Mech. Syst. Signal Process. 151 (2021), Article ID 107398. 10.1016/j.ymssp.2020.107398Search in Google Scholar

[18] S. Kiranyaz, T. Ince and M. Gabbouj, Real-time patient-specific ecg classification by 1-D convolutional neural networks, IEEE Trans. Biomed. Eng. 63 (2016), no. 3, 664–675. 10.1109/TBME.2015.2468589Search in Google Scholar PubMed

[19] S. Leijnen and F. van Veen, The neural network zoo, Proceedings 47 (2020), no. 1, 10.3390/proceedings2020047009. 10.3390/proceedings2020047009Search in Google Scholar

[20] Q. Li and H. Sompolinsky, Statistical mechanics of deep linear neural networks: the backpropagating kernel renormalization, Phys. Review X 11 (2021), no. 3, Article ID 031059. 10.1103/PhysRevX.11.031059Search in Google Scholar

[21] K. Linnet, Choosing quality-control systems to detect maximum clinically allowable analytical errors, Clinical Chemistry 35 (1989), no. 2, 284–288. 10.1093/clinchem/35.2.284Search in Google Scholar

[22] W. S. McCulloch and W. Pitts, A logical calculus of the ideas immanent in nervous activity, Bull. Math. Biophys. 5 (1943), 115–133. 10.1007/BF02478259Search in Google Scholar

[23] D. C. Montgomery, Introduction to Statistical Quality Control, 8th ed., John Wiley & Sons, New York, 2019. Search in Google Scholar

[24] S. Psarakis, The use of neural networks in statistical process control charts, Quality Reliab. Eng. Int. 27 (2011), no. 5, 641–650. 10.1002/qre.1227Search in Google Scholar

[25] G. A. Pugh, Synthetic neural networks for process control, Comput. Indust. Eng. 17 (1989), no. 1, 24–26. 10.1016/0360-8352(89)90030-2Search in Google Scholar

[26] B. C. Read, Folded distributions, Encyclopedia of Statistical Sciences, John Wiley & Sons, New York (2014), 2421–2421. 10.1002/9781118445112.stat00985Search in Google Scholar

[27] R. M. Sakia, The Box–Cox transformation technique: A review, Statist. J. Inst. Statist. 41 (1992), no. 2, 169–178. 10.2307/2348250Search in Google Scholar

[28] W. A. Shewhart, Economic Quality Control of Manufactured Product, D. Van Nostrand Company, New York, 1930. 10.1002/j.1538-7305.1930.tb00373.xSearch in Google Scholar

[29] A. E. Smith, X-bar and R control chart interpretation using neural computing, Int. J. Prod. Res. 32 (1994), no. 2, 309–320. 10.1080/00207549408956935Search in Google Scholar

[30] H. Solomon and A. M. Stephens, Variance, sample, Encyclopedia of Statistical Sciences, John Wiley & Sons, New York (2014), 8973–8975. 10.1002/9781118445112.stat01904Search in Google Scholar

[31] T. Stützle, A neural network approach to quality control charts, From Natural to Artificial Neural Computation, Springer, Berlin (1995), 1135–1141. 10.1007/3-540-59497-3_295Search in Google Scholar

[32] J. Xia, S.-F. Chen, F. Xu and Y.-L. Zhou, Quality specifications of routine clinical chemistry methods based on sigma metrics in performance evaluation, J. Clinical Laboratory Anal. 32 (2018), no. 3, Article ID e22284. 10.1002/jcla.22284Search in Google Scholar PubMed PubMed Central

[33] J. Xu, H. Lv, Z. Zhuang, Z. Lu, D. Zou and W. Qin, Control chart pattern recognition method based on improved one-dimensional convolutional neural network, IFAC-PapersOnLine 52 (2019), no. 13, 1537–1542. 10.1016/j.ifacol.2019.11.418Search in Google Scholar

[34] F. Zorriassatine and J. D. T. Tannock, A review of neural networks for statistical process control, J. Intell. Manufact. 9 (1998), no. 3, 209–224. 10.1023/A:1008818817588Search in Google Scholar

Received: 2023-01-03
Revised: 2023-08-30
Accepted: 2023-09-21
Published Online: 2023-11-02
Published in Print: 2023-12-01

© 2023 Walter de Gruyter GmbH, Berlin/Boston

Downloaded on 24.2.2024 from https://www.degruyter.com/document/doi/10.1515/eqc-2023-0001/html
Scroll to top button