Abstract
Manufacturers are increasingly applying machine and deep learning to automate production quality monitoring to save time and costs. The most widely used approach is Convolutional Neural Network (CNN) trained to detect quality issues in production output images. While the approach achieves high accuracy, many companies face challenges implementing it. Many manufacturers lack both the big data sets required for machine and deep learning model training and the data scientists having the domain knowledge to build and run complex models. Today manufacturers have implemented lean manufacturing and six sigma quality controls which result in small defect samples that are not sufficient for modeling. Some manufacturers also change the production outputs frequently which does not permit enough time for data collection for model building. In this paper, we propose two motif discovery based approaches that work within the constraints of modern manufacturing. The first approach is programmatic motif discovery learning patterns from small data samples. The second approach is a self-service visual motif discovery that is simple and intuitive for engineers not versed in data science. We compare the proposed approaches with a CNN and conclude that our proposed methods achieve higher accuracy, have significantly lower computational costs, and empower engineers to do it themselves.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of data and material
The data will be released online after confirmed by the industry provider.
Code availability Source codes will be released online after acceptance.
References
Aguiar, P. R., Da Silva, R. B., Gerônimo, T. M., Franchin, M. N., & Bianchi, E. C. (2017). Estimating high precision hole diameters of aerospace alloys using artificial intelligence systems: a comparative analysis of different techniques. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 39(1), 127–153. https://doi.org/10.1007/s40430-016-0525-7.
Al-Kharaz, M., Ananou, B., Ouladsine, M., Combal, M., & Pinaton, J., (2019, October). Quality Prediction in Semiconductor Manufacturing processes using multilayer perceptron feedforward artificial neural network. In 2019 8th international conference on systems and control (ICSC) (pp. 423–428). IEEE https://doi.org/10.1109/ICSC47195.2019.8950664.
Arnheiter, E. D., & Maleyeff, J. (2005). The integration of lean management and Six Sigma. The TQM magazine. https://doi.org/10.1108/09544780510573020.
Baker, N., Lu, H., Erlikhman, G., & Kellman, P. J. (2018). Deep convolutional networks do not classify based on global object shape. PLoS Computational Biology, 14(12), e1006613. https://doi.org/10.1371/journal.pcbi.1006613.
Banadaki, Y., Razaviarab, N., Fekrmandi, H., & Sharifi, S. (2020). Toward Enabling a reliable quality monitoring system for additive manufacturing process using deep convolutional neural networks. arXiv:2003.08749.
Chi, L., Feng, Y., Chi, H., & Huang, Y. (2012, August). Face image recognition based on time series motif discovery. In 2012 IEEE international conference on granular computing (pp. 72–77). IEEE. http://hdl.handle.net/10453/22962.
Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21, 6. https://doi.org/10.1186/s12864-019-6413-7.
Chi, L. H., Chi, H. H., Feng, Y. C., Wang, S. L., & Cao, Z. S. (2011). Comprehensive and efficient discovery of time series motifs. Journal of Zhejiang University SCIENCE C, 12(12), 1000–1009. https://doi.org/10.1631/jzus.C1100037.
Ding, L., & Goshtasby, A. (2001). On the Canny edge detector. Pattern Recognition, 34(3), 721–725. https://doi.org/10.1016/S0031-3203(00)00023-6.
Feng, S., Zhou, H., & Dong, H. (2019). Using deep neural networks with small datasets to predict material defects. Materials & Design, 162, 300–310. https://doi.org/10.1016/j.matdes.2018.11.060.
Goutte, C., & Gaussier, E. (2005). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In Losada, D. E., Fernández-Luna, J. M. (eds) Advances in information retrieval. ECIR 2005. Lecture Notes in Computer Science (Vol. 3408). Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-31865-1_25.
Hassan, M., (2020). Resnet (34, 50, 101): Residual cnns for image classification tasks. [online] Neurohive.io. Available at: https://neurohive.io/en/popular-networks/resnet/.
He, K., Zhang, X., Ren, S., & Sun, J., (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770–778). https://doi.org/10.1109/CVPR.2016.90.
Heaven, W. (2020, November). AI is wrestling with a replication crisis, MIT technology review. https://www.technologyreview.com/2020/11/12/1011944/artificial-intelligence-replication-crisis-science-big-tech-google-deepmind-facebook-openai/.
Heaven, W. (2020, November). The way we train AI is fundamentally flawed, MIT technology review. https://www.technologyreview.com/2020/11/18/1012234/training-machine-learning-broken-realworld-heath-nlp-computer-vision/.
https://pillow.readthedocs.io/en/5.1.x/reference/Image.html#PIL.Image.Image.Getdata.
Imoto, K., Nakai, T., Ike, T., Haruki, K., & Sato, Y. (2019, November). A CNN-based transfer learning method for defect classification in semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing, 32(4), 455-459, https://doi.org/10.1109/TSM.2019.2941752. https://doi.org/10.1109/issm.2018.8651174.
Kantesaria, N., Vaghasia, P., Hirpara, J. & Bhoraniya, R., (2020). Casting product imagedata for quality inspection. [online] https://www.kaggle.com. Available at: https://www.kaggle.com/ravirajsinh45/real-life-industrial-dataset-of-casting-product.
Kim, C., Lee, J., Kim, R., Park, Y., & Kang, J. (2018). DeepNAP: Deep neural anomaly pre-detection in a semiconductor fab. Information Sciences, 457, 1–11. https://doi.org/10.1016/j.ins.2018.05.020.
Kotorov, R., Chi, L., & Shen, M. (2020). Personalized monitoring model for electrocardiogram signals: Diagnostic accuracy study. JMIR Biomedical Engineering, 5(1), e24388. https://doi.org/10.2196/24388.
Lin, Y., McCool, M. D., & Ghorbani, A. A. (2010). Time series motif discovery and anomaly detection based on subseries join. IAENG International Journal of Computer Science, 37(3), 259–271.
Lonardi, J. L. E. K. S., & Patel, P. (2002). Finding motifs in time series. In Proceedings of the 2nd workshop on temporal data mining (pp. 53–68).
Lones, M. A., & Tyrrell, A. M. (2005, June). The evolutionary computation approach to motif discovery in biological sequences. In Proceedings of the 7th annual workshop on genetic and evolutionary computation (pp. 1–11). https://doi.org/10.1145/1102256.1102258.
Luckow, A., Kennedy, K., Ziolkowski, M., Djerekarov, E., Cook, M., Duffy, E., Schleiss,M., Vorster, B., Weill, E., Kulshrestha, A., & Smith, M. C. (2018, December). Artificial intelligence and deep learning applications for automotive manufacturing. In 2018 IEEE international conference on Big Data (Big Data) (pp. 3144–3152). IEEE https://doi.org/10.1109/BigData.2018.8622357.
Mateus, B. C., Mendes, M., Farinha, J. T., & Cardoso, A. M. (2021). Anticipating future behavior of an industrial press using LSTM networks. Applied Sciences, 11(13), 6101. https://doi.org/10.3390/app11136101.
Matplotlib.org. (2020). Matplotlib.Pyplot.Hist—Matplotlib 3.1.2 Documentation. [online] Available at: https://matplotlib.org/3.1.1/api/_as_gen/matplotlib.pyplot.hist.html.
McGovern, A., Rosendahl, D. H., Brown, R. A., & Droegemeier, K. K. (2011). Identifying predictive multi-dimensional time series motifs: an application to severe weather prediction. Data Mining and Knowledge Discovery, 22(1–2), 232–258. https://doi.org/10.1007/s10618-010-0193-7.
Medus, L. D., Saban, M., Francés-Víllora, J. V., Bataller-Mompeńn, M., & Rosado-Muñoz, A. (2021). Hyperspectral image classification using CNN: Application to industrial food packaging. Food Control, 125, 107962. https://doi.org/10.1016/j.foodcont.2021.107962.
Melhem, M., Ananou, B., Ouladsine, M., & Pinaton, J. (2016). Regression methods for predicting the products quality in the semiconductor manufacturing process. IFACPapersOnLine, 49(12), 83–88. https://doi.org/10.1016/j.ifacol.2016.07.554.
Midgley, A. R., Jr., Niswender, G. D., & Rebar, R. W. (1969). Principles for the assessment of the reliability of radioimmunoassay methods (precision, accuracy, sensitivity, specificity). Acta Endocrinologica, 62(1_Suppl), S163-S184. Retrieved Jul 22, 2021, from https://eje.bioscientifica.com/view/journals/eje/62/1_Suppl/acta_62_Suppl_142_011.xml.
Montgomery, D. C. (2012). Statistical quality control. Wiley Global Education. https://www.wiley.com/en-us/Introduction+to+Statistical+Quality+Control.
Rosebrock, A. (2020). Imagenet: Vggnet, Resnet, Inception, And Xception With Keras- Pyimagesearch. [online] PyImageSearch. https://www.pyimagesearch.com/2017/03/20/imagenet-vggnet-resnet-inception-xception-keras/.
Sagheer, A., & Kotb, M. (2019). Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing, 323, 203–213. https://doi.org/10.1016/j.neucom.2018.09.082.
Song, R., Xiao, Z., Lin, J., & Liu, M. (2020). CIES: Cloud-based Intelligent EvaluationService for video homework using CNN-LSTM network. Journal of Cloud Computing, 9(1), 7. https://doi.org/10.1186/s13677-020-0156-5.
Srinath, R., et al. (2020). Early emergence of solid shape coding in natural and deep NetworkVision. Current Biology. https://doi.org/10.1016/j.cub.2020.09.076.
Sucholutsky, I., & Schonlau, M. (2020). Less than one-shot learning: learning NClasses From \( M\le N \) samples. arXiv:2009.08449.
Thoben, K. D., Wiesner, S., & Wuest, T. (2017). Industrie 4.0 and smart manufacturing review of research issues and application examples. International Journal of Automation Technology,11(1), 4–16. https://doi.org/10.20965/IJAT.2017.P0004
Wang, T., Zhu, J. Y., Torralba, A., & Efros, A. A. (2018). Dataset distillation. arXiv:1811.10959.
Williams, J. D., Woodall, W. H., & Birch, J. B. (2007). Statistical monitoring of nonlinear product and process quality profiles. Quality and Reliability Engineering International, 23(8), 925–941. https://doi.org/10.1002/qre.858.
Wilson, H., & Daugherty, P. (2020). Small Data Can Play A Big Role In AI. [online] Harvard Business Review. https://hbr.org/2020/02/small-data-can-play-a-big-role-in-ai.
Wuest, T., Weimer, D., Irgens, C., & Thoben, K. D. (2016). Machine learning in manufacturing: advantages, challenges, and applications. Production & Manufacturing Research, 4(1), 23–45. https://doi.org/10.1080/21693277.2016.1192517.
Zhang, B., Jaiswal, P., Rai, R., Guerrier, P., & Baggs, G. (2019). Convolutional neural network-based inspection of metal additive manufacturing parts. Rapid Prototyping Journal, 25(3), 530–540. https://doi.org/10.1108/RPJ-04-2018-0096.
Zhao, Q. J., Cao, P., & Tu, D. W. (2014). Toward intelligent manufacturing: label characters marking and recognition method for steel products with machine vision. Advances in Manufacturing, 2(1), 3–12. https://doi.org/10.1007/s40436-014-0057-2.
Funding
Not applicable.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Bhatia, A.S., Kotorov, R. & Chi, L. Casting plate defect detection using motif discovery with minimal model training and small data sets. J Intell Manuf 34, 1731–1742 (2023). https://doi.org/10.1007/s10845-021-01880-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10845-021-01880-2