Automated evaluation of Cr-III coated parts using Mask RCNN and ML methods

• Published in: Surface & coatings technology Vol. 422; p. 127571
• Main Authors: Katırcı, Ramazan, Yılmaz, Esra Kavalcı, Kaynar, Oğuz, Zontul, Metin
• Format: Journal Article
• Language: English
• Published: Lausanne Elsevier B.V 25.09.2021; Elsevier BV
• Subjects: Accuracy; Algorithms; Artificial intelligence; Classification; Classifiers; Convolutional neural networks; Cr-III electroplating; Deep learning; Electroplating; Gaussian process; Machine learning; Mask RCNN; Multilayer perceptrons; Plating; Plating baths; Process parameters; Surface detection; Deep learning; Surface detection; Convolutional neural networks; Cr-III electroplating; Mask RCNN; Machine learning
• ISSN: 0257-8972; 1879-3347
• DOI: 10.1016/j.surfcoat.2021.127571

In this study, chrome coatings were carried out using a Cr-III electroplating bath. The coated parts were classified depending on their appearance. A new approach was developed to classify the coated parts automatically using artificial intelligence methods. Mask RCNN and machine learning (ML) methods such as Multilayer Perceptron (MLP), Support Vector Classifier (SVC), Gaussian Process (GP), K-nearest Neighbors (KNN), XGBoost, and Random Forest Classifier (RFC) were used together. Mask RCNN was used to clean the coated parts from the redundant data. The extracted data were flattened and converted to the row vectors for use as input in ML methods. ML algorithms were used to classify the coated parts as “Pass” and “Fail”. The classification accuracy was checked with the leave one out (loo) cross-validation method. RFC method gave the highest accuracy, 0.83, and F1 score, 0.88. The accuracy of Mask RCNN was checked using a dataset of separated validation images. It was observed that extracting the unnecessary data from the images increased the accuracy exceedingly. Moreover, the method exhibits a high potential to keep the parameters of the electroplating process under control. •The quality of coating was classified using artificial intelligence methods.•Mask R-CNN algorithm was used to clean the data.•The hyperparameters of MLP, SVC, GP, KNN, XGBoost, and RFC methods were optimized.•RF method indicated the best performance (F1 score = 0.88)•Mask RCNN and ML methods were compared in terms of classification performance.