Abstract
Quality has become one of the most important factors in the success of manufacturing companies. In this paper, the use of machine learning algorithms in quality control is compared to the use of statistical process monitoring, a classical quality management technique. The test dataset has a large number of features, which requires the use of principal component analysis and clustering to isolate the data into potential process groups. A Random Forest, Support Vector Machine and Naive Bayes algorithms were used to predict when the manufacturing process is out of control. The Random Forest algorithm performed significantly better than both the Naive Bayes and SVM algorithms in all 3 clusters of the dataset. The results were benchmarked against Hotelling’s \(T^2\) control charts which were trained using 80% of each cluster dataset and tested on the remaining 20%. In comparison with Hotelling’s \(T^2\) multivariate statistical process monitoring charts, the Random Forest algorithm still emerges as the better quality control method.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ahsan, M., Mashuri, M., Kuswanto, H., Prastyo, D.D., et al.: Intrusion detection system using multivariate control chart Hotelling’s T2 based on PCA. Int. J. Adv. Sci. Eng. Inf. Technol. 8(5), 1905–1911 (2018)
Bekkar, M., Djemaa, H.K., Alitouche, T.A.: Evaluation measures for models assessment over imbalanced data sets. J. Inf. Eng. Appl. 3(10) (2013)
Bersimis, S., Panaretos, J., Psarakis, S.: Multivariate statistical process control charts and the problem of interpretation: a short overview and some applications in industry. In: Proceedings of the 7th Hellenic European Conference on Computer Mathematics and its Applications, Athens, Greece (2005)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees, vol. 37, no. 15, pp. 237–251. Wadsworth International Group (1984)
Chiang, L.H., Kotanchek, M.E., Kordon, A.K.: Fault diagnosis based on fisher discriminant analysis and support vector machines. Comput. Chem. Eng. 28(8), 1389–1401 (2004)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Escobar, C.A., Morales-Menendez, R.: Machine learning techniques for quality control in high conformance manufacturing environment. Adv. Mech. Eng. 10(2), 1687814018755519 (2018)
Evans, J.R., Lindsay, W.M.C.: The management and control of quality. Technical report, South Western (2002)
Gao, X., Hou, J.: An improved SVM integrated GS-PCA fault diagnosis approach of tennessee eastman process. Neurocomputing 174, 906–911 (2016)
Hand, D.J., Yu, K.: Idiot’s bayes–not so stupid after all? Int. stat. Rev. 69(3), 385–398 (2001)
Hotelling, H.: Multivariate Quality Control. Techniques of Statistical Analysis. McGraw-Hill, New York (1947)
Kourti, T., Macgregor, J.F.: Multivariate SPC methods for process and product monitoring. J. Qual. Technol. 28(4), 409–428 (1996)
Lieber, D., Stolpe, M., Konrad, B., Deuse, J., Morik, K.: Quality prediction in interlinked manufacturing processes based on supervised and unsupervised machine learning. Proc. Cirp 7, 193–198 (2013)
MacGregor, J.F., Kourti, T.: Statistical process control of multivariate processes. Control Eng. Pract. 3(3), 403–414 (1995)
Madanhire, I., Mbohwa, C.: Application of statistical process control (SPC) in manufacturing industry in a developing country. Proc. Cirp 40, 580–583 (2016)
International Organization for Standardization: ISO 9000. Technical report, International Organization for Standardization (1995)
Sánchez-Fernádez, A.: Fault detection based on time series modelling and multivariate statistical process control. Chemom. Intell. Lab. Syst. 182, 57–69 (2018)
Wuest, T., Irgens, C., Thoben, K.D.: An approach to monitoring quality in manufacturing using supervised machine learning on product state data. J. Intell. Manuf. 25(5), 1167–1180 (2014)
Yu, J., Xi, L., Zhou, X.: Identifying source(s) of out of control signals in multivariate manufacturing process using selective network ensemble. Eng. Appl. Artif. Intell. 22, 141–152 (2009)
Yu, J., Zheng, X., Wang, S.: Stacked denoising autoencoder-based feature learning for out-of-control source recognition in multivariate manufacturing process. Qual. Reliabi. Eng. Int. 35, 204–223 (2018)
Zhang, D., Xu, B., Wood, J.: Predict failures in production lines: a two-stage approach with clustering and supervised learning. In: 2016 IEEE International Conference on Big Data (Big Data), pp. 2070–2074. IEEE (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Khoza, S.C., Grobler, J. (2019). Comparing Machine Learning and Statistical Process Control for Predicting Manufacturing Performance. In: Moura Oliveira, P., Novais, P., Reis, L. (eds) Progress in Artificial Intelligence. EPIA 2019. Lecture Notes in Computer Science(), vol 11805. Springer, Cham. https://doi.org/10.1007/978-3-030-30244-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-30244-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30243-6
Online ISBN: 978-3-030-30244-3
eBook Packages: Computer ScienceComputer Science (R0)