Abstract
Data-driven systems have been increasingly applied in industries to improve process production and pattern analysis. To enhance an industrial vacuum metallization process, we propose advanced machine learning (ML) technologies to extract information, make predictions, and elaborate prescription scenarios. We also implemented visual tools to promote robustness, interpretability, and reliability based on visual interaction between models and operators. The random forest algorithm demonstrated the best classification performance in most analyzed metrics throughout an automatic ML implementation, with 85.4% of accuracy and 0.76 of area under curve (AUC). Media optical density is the most critical product feature for quality analysis with a positive impact on higher values, followed by the warm-up time of ceramic boats, which present better stability to extended warming times. Moreover, specific ranges of operating conditions were identified, such as wire speed and warm-up time, enabling higher values for optical density variables and offering the best conditions for film approval. Finally, visualization techniques allowed us to interpret feature importance, correlation, and patterns that directly interfere with product classification. A product summary enables observing this interference and predicting the probability of approval of a specific product manufactured. The results showed that visual tools and ML algorithms are promising for industrial automation, monitoring, and process improvement. The proposed approach can support analysts and operators in quality analysis and process management.
Similar content being viewed by others
Data Availability
The industrial dataset used in this manuscript can not be published due to confidentiality requests.
References
Arnold F, King R (2021) State–space modeling for control based on physics-informed neural networks. Eng Appl Artif Intell 101:104,195. https://doi.org/10.1016/j.engappai.2021.104195
Bhosekar A, Ierapetritou M (2018) Advances in surrogate based modeling, feasibility analysis, and optimization: a review. Comput Chem Eng 108:250–267. https://doi.org/10.1016/j.compchemeng.2017.09.017
Biji KB, Ravishankar CN, Mohan CO, et al. (2015) Smart packaging systems for food applications: a review. J Food Sci Technol 52(10):6125–6135
Bikmukhametov T, Jäschke J (2020) Combining machine learning and process engineering physics towards enhanced accuracy and explainability of data-driven models. Comput Chem Eng 138: 106,834. https://doi.org/10.1016/j.compchemeng.2020.106834
Bishop CA (2007) Vacuum deposition onto webs, films, and foils. Second Edition 91(2)
Bradley W, Kim J, Kilwein Z, et al. (2022) Perspectives on the integration between first-principles and data-driven modeling. Comput Chem Eng 166:107,898. https://doi.org/10.1016/j.compchemeng.2022.107898
Chen Y, Meng G, Zhang Q et al (2018) Reinforced evolutionary neural architecture search. https://doi.org/10.48550/ARXIV.1808.00193
Daoutidis P, Lee JH, Harjunkoski I, et al. (2018) Integrating operations and control: a perspective and roadmap for future research. Comput Chem Eng 115:179–184
Davis J, Edgar T, Porter J, et al. (2012) Smart manufacturing, manufacturing intelligence and demand-dynamic performance. Comput Chem Eng 47:145–156
Gavitt IF (1994) Vacuum coating applications for snack food packaging
Grossmann IE, Harjunkoski I (2019) Process systems engineering: academic and industrial perspectives. Comput Chem Eng 126:474–484
He X, Zhao K, Chu X (2020) Automl: a survey of the state-of-the-art. Preprint - Knowledge-Based Systems. arXiv:1908.00709v5
Hutter F, Hoos H H, Leyton-Brown K (2011) Sequential model-based optimization for general algorithm configuration. In: Coello CAC (ed) Learning and intelligent optimization. Berlin, Springer, pp 507–523
Jin H, Song Q, Hu X (2018) Auto-keras: an efficient neural architecture search system. https://doi.org/10.48550/ARXIV.1806.10282
Joshi AV (2020) Machine learning and artificial intelligence. Springer, Cham
Kahng M, Andrews PY, Kalro A, et al. (2018) Activis: visual exploration of industry-scale deep neural network models. IEEE Trans Vis Comput Graph 24(1):88–97
Lee G, Kim W, Oh H, et al. (2019) Review of statistical model calibration and validation—from the perspective of uncertainty structures. Struct Multidiscip Optim 60(4):1619–1644
Lee JH, Shin J, Realff MJ (2018) Machine learning: overview of the recent progresses and implications for the process systems engineering field. Comput Chem Eng 114:111–121
Ma K, Sahinidis NV, Amaran S, et al. (2022a) Data-driven strategies for optimization of integrated chemical plants. Comput Chem Eng 166:107,961. https://doi.org/10.1016/j.compchemeng.2022.107961
Ma K, Sahinidis N V, Bindlish R, et al. (2022b) Data-driven strategies for extractive distillation unit optimization. Comput Chem Eng 167:107,970. https://doi.org/10.1016/j.compchemeng.2022.107970
Mann V, Venkatasubramanian V (2021) Predicting chemical reaction outcomes: a grammar ontology-based transformer framework. AIChE J 67(3):e17,190. https://doi.org/10.1002/aic.17190
Ono J P, Castelo S, Lopez R, et al. (2020) Pipelineprofiler: a visual analytics tool for the exploration of automl pipelines. https://doi.org/10.48550/ARXIV.2005.00160
Overcash M R (2019) Perspective on advanced manufacturing and progress on improvement in societal well-being. J Adv Manuf Process 1(3):2–3
Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12(85):2825–2830. http://jmlr.org/papers/v12/pedregosa11a.html
Perry M, Lentz R (2009) 9 - susceptors in microwave packaging. In: Lorence MW, Pesheck PS (eds) Development of packaging and products for use in microwave ovens. Woodhead Publishing, p 207–236. https://doi.org/10.1533/9781845696573.2.207
Pistikopoulos EN, Barbosa-Povoa A, Lee JH, et al. (2021) Process systems engineering – the generation next?. Comput Chem Eng 147:107,252. https://doi.org/10.1016/j.compchemeng.2021.107252
Quaghebeur W, Torfs E, De Baets B, et al. (2022) Hybrid differential equations: Integrating mechanistic and data-driven techniques for modelling of water systems. Water Res 213:118,166. https://doi.org/10.1016/j.watres.2022.118166
Radhakrishnan R (2021) A survey of multiscale modeling: foundations, historical milestones, current status, and future prospects. AIChE J e17(3):026. https://doi.org/10.1002/aic.17026
Rasmussen CE, Williams CKI (2005) Gaussian processes for machine learning (adaptive computation and machine learning). The MIT Press
Remolona MFM, Conway MF, Balasubramanian S et al (2017) Hybrid ontology-learning materials engineering system for pharmaceutical products: multi-label entity recognition and concept detection. Comput Chem Eng 107:49–60. https://doi.org/10.1016/j.compchemeng.2017.03.012. in honor of Professor Rafiqul Gani
Ren D, Amershi S, Lee B, et al. (2017) Squares: supporting interactive performance analysis for multiclass classifiers. IEEE Trans Vis Comput Graph 23(1):61–70
Rendall R, Reis MS (2018) Which regression method to use? making informed decisions in “data-rich/knowledge poor” scenarios – the predictive analytics comparison framework (pac). Chemometr Intell Lab Syst 181:52–63. https://doi.org/10.1016/j.chemolab.2018.08.004
Sansana J, Joswiak MN, Castillo I, et al. (2021) Recent trends on hybrid modeling for industry 4.0. Comput Chem Eng 151: 107,365. https://doi.org/10.1016/j.compchemeng.2021.107365
Shahriari B, Swersky K, Wang Z, et al. (2016) Taking the human out of the loop: a review of bayesian optimization. Proc IEEE 104(1):148–175. https://doi.org/10.1109/JPROC.2015.2494218
Thornton C, Hutter F, Hoos H H, et al. (2012) Auto-weka: combined selection and hyperparameter optimization of classification algorithms. https://doi.org/10.48550/ARXIV.1208.3719
Tuggener L, Amirian M, Rombach K, et al. (2019) Automated machine learning in practice: state of the art and recent results. In: Proc - 6th Swiss Conf Data Sci SDS, 2019, 31–36
Xie J, Xu X, Dubljevic S (2019) Long range pipeline leak detection and localization using discrete observer and support vector machine. AIChE J 65(7):e16,532. https://doi.org/10.1002/aic.16532
Xu P, Mei H, Ren L, et al. (2017) Vidx: visual diagnostics of assembly line performance in smart factories. IEEE Trans Vis Comput Graph 23(1):291–300
Yang C, Fan J, Wu Z et al (2020) Efficient automl pipeline search with matrix and tensor factorization. https://doi.org/10.48550/ARXIV.2006.04216
Zhang K, Zhang Y, Wang M (2012) A unified approach to interpreting model predictions scott. Neural Inf Proc Syst 16(3):426–430
Zhou X, Zhuo J, Krähenbühl P (2019) Bottom-up object detection by grouping extreme and center points. https://doi.org/10.48550/ARXIV.1901.08043
Zimmer L, Lindauer M, Hutter F (2020) Auto-pytorch tabular:, multi-fidelity metalearning for efficient and robust autodl, 2006, 13799
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and approval of the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bastos, T.M.R., Stragevitch, L. & Zanchettin, C. On machine learning and visual analysis for quality prediction of film metallization process. Int J Adv Manuf Technol 124, 315–327 (2023). https://doi.org/10.1007/s00170-022-10520-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-10520-9