Pattern recognition of control chart with variable chain length based on recurrent neural network

Tao Zan; JiaWei Chen; ZhiLue Sun; ZhiHao Liu; Min Wang; XiangSheng Gao; Peng Gao

doi:10.55092/am20240003

Article

Open Access

Pattern recognition of control chart with variable chain length based on recurrent neural network

Tao Zan¹^,∗JiaWei Chen¹^,∗ZhiLue Sun²ZhiHao Liu²Min Wang²XiangSheng Gao²Peng Gao²

¹ Beijing Key Laboratory of Advanced Manufacturing Technology, Faculty of Materials and Manufacturing, Beijing 100124, China

² Beijing University of Technology, Chaoyang District, Beijing 100124, China

* zantao@bjut.edu.cn; chenjiawei@emails.bjut.edu.cn

Volume
Volume 1 Issue 1, 2024
Citation
Zan T, Chen J, Sun Z, Liu Z, Wang M, et al. Pattern recognition of control chart with variable chain length based on recurrent neural network . Adv. Manuf. 2024(1):0003, https://doi.org/10.55092/am20240003.
DOI
10.55092/am20240003
Copyright
Copyright2024 by the authors. Published by ELSP.
Special Issue
Artificial Intelligence in Manufacturing Processes and Systems

Abstract

The existing control chart pattern recognition method exhibits limitations in discriminating control charts with variable chain lengths, and it demonstrates poor generalization. This study introduces an innovative Recurrent Neural Network (RNN) control chart pattern recognition method designed to enable intelligent recognition of control charts with varying chain lengths and different patterns. In this study, control charts with six different chain lengths are generated through the Monte Carlo simulation method. Prior to processing the raw data, expected values are introduced as padding. Subsequently, an RNN model is established. The trained network model is then deployed to discriminate patterns in control chart data characterized by variable chain lengths. Simulation experiments and engineering applications show that the proposed method achieves a remarkable recognition accuracy of 99.06% and demonstrates robust generalization capabilities. The outcomes of this study bear direct practical relevance to the manufacturing industry and advanced manufacturing technologies. By enhancing pattern recognition accuracy under variable chain lengths, we can more effectively monitor the production process, reduce defect rates, and elevate production efficiency.

Keywords

Control chart; pattern recognition; variable chain lengths; recurrent neural networks; deep learning

Preview

view pdf

References

[1]Zhu B. Research on quality control methods for automatic machining processes based on support vector machines. Chongqing University.
[2]Saghir A. Flexible and robust control charts in statistical process monitoring. Zhejiang University, 2014
[3]Evans JR, Lindsay WM. A framework for Expert System development in statistical quality control. Comput. Ind. Eng. 1988, 14(3):335-343
[4]Roberts SW. Properties of Control Chart Zone Tests. Bell Syst. Tech. J 2012, 37(1):115-134
[5]Nelson LS. Interpreting Shewhart X‐bar control charts. Qual Technol Quant M. 1985, 17:114-116.
[6]Klingst A. Quality Control and Industrial Statistics - Duncan, Acheson 1959.
[7]Shewhart M. Interpreting statistical process control (SPC) charts using machine learning and expert system techniques. Aerospace; Electronics Conference. IEEE Xplore,1992.
[8]Pham DT, Wani MA. Feature-based control chart pattern recognition. Int. J. Prod. Res. 1997, 35(7):1875-1890.
[9]Yue QH, Gao XH, Hao J, Zhu MQ. A novel neural network for pattern recognition. Comp Engineering 2004 (17):17-18+35.
[10]Chen P, Huai CJ, Luo J. Improved BP algorithm for control chart pattern recognition. M&E 2005 (03):42-44.
[11]Wang M, Zan T, Fei R. Intelligent Statistical Process Control Using Fuzzy ART Neural Networks. Front. Mech. Eng. in China 2010, 5149-156.
[12]Zan T, Wang H, Liu ZH, Wang M, Gao XS. Rolling bearing fault diagnosis model based on multi input layer convolutional neural network. Vib. Shock 2020, 39(12):142-149+163.
[13]Ebrahimzadeh A, Ranaee V. Control chart pattern recognition using an optimized neural network and efficient features. ISA Trans. 2010, 3(49):387-393.
[14]Hou SW, Zhu HM, Li R. Pattern recognition of uncertain anomalies in quality control charts based on Simulink simulation. CA 2012, 32(10):2940-2943.
[15]Li C, Zhang HL, Zhao X. Simulation research on control diagram pattern recognition of hybrid intelligent algorithm. Computer Simulation 2013, 30(10): 345-349+437.
[16]Zhang YB, Lin XN. Pattern recognition method of SPC control chart combined with improved sequence forward selection method (ISFS) and extreme learning machine (ELM). Journal of Qingdao University of Science and Technology (Natural Science Edition), 2015, 36(03): 322-326.
[17]Wang H. Research on mixed abnormal pattern recognition of control charts based on wavelet analysis. Central North University 2017.
[18]Hou SW, Zhu HM. Quality control chart anomaly pattern recognition based on Bayesian theory. Stats and Decision 2017 (10):18-21.
[19]Liu YM, Zhao ZY. Quality anomaly pattern recognition based on Feature selection and SVM. Stats and Decision 2018(10):5.
[20]Wang HY, Zhuo YJ. Pattern recognition method of statistical process control chart based on principal component analysis. Stats and Decision 2020, 36(24):20-24.
[21]El-Midany TT, El-Baz MA, Abd-Elwahed MS. A proposed framework for control chart pattern recognition in multivariate process using artificial neural networks. Expert Syst Appl 2010, 2(37):1035-1042.
[22]Medhat HA, Awadalla M, Abdellatif Sadek. Spiking neural network-based control chart pattern recognition. Alex. Eng. J. 2012, 1(51):27-25.
[23]De la Torre-Gutiérrez H, Pham DT. A control chart pattern recognition system for feedback-control processes. Expert Syst Appl 2019, 138:112826.
[24]Zan T, Liu Z, Wang H, et al. Control chart pattern recognition using the convolutional neural network. J. Intell. Manuf. 2020, 31:703–716.
[25]Miao Z, Yang M. Control chart pattern recognition based on convolution neural network. In: Panigrahi, B., Trivedi, M., Mishra, K., Tiwari, S., Singh, P. (eds) Smart Innovations in Communication and Computational Sciences. Adv. Intell. Syst. Comput 2019, 670.
[26]Zan T, Liu Z, Su Z, Wang M, Gao X, Chen D. Statistical process control with intelligence based on the deep learning model. Appl. Sci. 2020, 10(1):308.
[27]Wu CL. Research and development of LSTM based quality control chartical model pattern recognition. Kunming University of Science and Technology 2020.
[28]Chen S, Yu J. Deep recurrent neural network‐based residual control chart for autocorrelated processes. QREI 2019, 35(8):2687-2708.
[29]Janssens O, Slavkovikj V, Vervisch B, Stockman K, Loccufer M, et al. Convolutional neural network based fault detection for rotating machinery. JSV 2016, 377:331–345.
[30]Cheng Z, Ma YZ. A Research about pattern recognition of control chart using probability Neural Network. In Proceedings of the Isecs International Colloquium on Computing, Communication, Control & Management, Guangzhou, China, 3–4 August 2008; IEEE: Piscatway, NJ, USA.
[31]Awadalla MHA, Sadek MA. Spiking neural network‐based control chart pattern recognition. Alex. Eng. J. 2012, 51:27–35.
[32]Gauri SK. Control chart pattern recognition using feature‐based learning vector quantization. Int. J. Adv. Manuf. Technol. 2010, 48:1061–1073.
[33]Guh RS. Real‐time recognition of control chart patterns in autocorrelated processes using a learning vector quantization network‐based approach. Int. J. Prod. Res. 2008, 46:3959–3991.
[34]Yang WA, Zhou W. Autoregressive coefficient‐invariant control chart pattern recognition in autocorrelated manufacturing processes using neural network ensemble. J. Intell. Manuf. 2015, 26:1161–1180.
[35]Shi Y. Technical research on spc based data collection and quality monitoring system. Shenyang University of Technology 2017.
[36]Wang K, Yang H, Tian J, et al. Comparison of the effectiveness of completely random missing data processing methods based on Monte Carlo simulation. China Health Statistics 2020, 37(2):4.
[37]Liu C, Liu C. A topic trend prediction method combining recurrent neural networks and convolutional neural networks. Industrial Control Computer 2022, 35(08):102-104.
[38]Zhao R, Yan R, Wang J, Mao K. Learning to monitor machine health with convolutional Bi-directional LSTM networks. Sens. (Basel, Switzerland). 2017, 17(2):273.
[39]Al‐Assaf Y. Recognition of control chart patterns using multiresolution wavelets analysis and neural networks. CAIE 2004, 47:17–29.
[40]Ranaee V, Ebrahimzadeh A. Control chart pattern recognition using a novel hybrid intelligent method. Appl. Soft Comput. 2011, 11:2676-2686.