AI Landing for Sheet Metal-Based Drawer Box Defect Detection Using Deep Learning (ALDB-DL)

Sheet metal-based products serve as a major portion of the furniture market and maintain higher quality standards by being competitive. During industrial processes, while converting a sheet metal to an end product, new defects are observed and thus need to be identified carefully. Recent studies have shown scratches, bumps, and pollution/dust are identified, but orange peel defects present overall a new challenge. So our model identifies scratches, bumps, and dust by using computer vision algorithms, whereas orange peel defect detection with deep learning have a better performance. The goal of this paper was to resolve artificial intelligence (AI) as an AI landing challenge faced in identifying various kinds of sheet metal-based product defects by ALDB-DL process automation. Therefore, our system model consists of multiple cameras from two different angles to capture the defects of the sheet metal-based drawer box. The aim of this paper was to solve multiple defects detection as design and implementation of Industrial process integration with AI by Automated Optical Inspection (AOI) for sheet metal-based drawer box defect detection, stated as AI Landing for sheet metal-based Drawer Box defect detection using Deep Learning (ALDB-DL). Therefore, the scope was given as achieving higher accuracy using multi-camera-based image feature extraction using computer vision and deep learning algorithm for defect classification in AOI. We used SHapley Additive exPlanations (SHAP) values for pre-processing, LeNet with a (1 × 1) convolution filter, and a Global Average Pooling (GAP) Convolutional Neural Network (CNN) algorithm to achieve the best results. It has applications for sheet metal-based product industries with improvised quality control for edge and surface detection. The results were competitive as the precision, recall, and area under the curve were 1.00, 0.99, and 0.98, respectively. Successively, the discussion section presents a detailed insight view about the industrial functioning with ALDB-DL experience sharing.

[1]  Xiao Fu,et al.  Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network , 2020, Sensors.

[2]  Prashant Kumar,et al.  Deep convolutional neural network based on adaptive gradient optimizer for fault detection in SCIM. , 2020, ISA transactions.

[3]  Shashi Phoha,et al.  Application of supervised machine learning for defect detection during metallic powder bed fusion additive manufacturing using high resolution imaging. , 2018 .

[4]  Nikhil Ketkar,et al.  Introduction to Keras , 2017 .

[5]  Liqiang Nie,et al.  Genetic algorithm and mathematical morphology based binarization method for strip steel defect image with non-uniform illumination , 2016, J. Vis. Commun. Image Represent..

[6]  Siu Kai Choy,et al.  Fuzzy model-based clustering and its application in image segmentation , 2017, Pattern Recognit..

[7]  Chang-hou Lu,et al.  A local annular contrast based real-time inspection algorithm for steel bar surface defects , 2012 .

[8]  Yi Jiang,et al.  Fast classification for rail defect depths using a hybrid intelligent method , 2019, Optik.

[9]  J. Tomas,et al.  A deep learning-based model for defect detection in laser-powder bed fusion using in-situ thermographic monitoring , 2020, Progress in Additive Manufacturing.

[10]  Geok Soon Hong,et al.  Defect detection in selective laser melting technology by acoustic signals with deep belief networks , 2018, The International Journal of Advanced Manufacturing Technology.

[11]  Alexej Jerschow,et al.  Rechargeable lithium-ion cell state of charge and defect detection by in-situ inside-out magnetic resonance imaging , 2018, Nature Communications.

[12]  Qipeng Chen,et al.  Research on a Surface Defect Detection Algorithm Based on MobileNet-SSD , 2018, Applied Sciences.

[13]  P. Groche,et al.  Defect detection in thread rolling processes – Experimental study and numerical investigation of driving parameters , 2018, International Journal of Machine Tools and Manufacture.

[14]  Xiaofeng He,et al.  Geometric calibration algorithm of polarization camera using planar patterns , 2017 .

[15]  Yunhui Yan,et al.  A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects , 2013 .

[16]  Mingyu Liu,et al.  On-machine surface defect detection using light scattering and deep learning. , 2020, Journal of the Optical Society of America. A, Optics, image science, and vision.

[17]  Ming Du,et al.  Computer vision algorithms and hardware implementations: A survey , 2019, Integr..

[18]  Lu Tian,et al.  Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials , 2020, Sensors.

[19]  De Xu,et al.  Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks , 2018, Applied Sciences.

[20]  Min Liu,et al.  A mobile vision inspection system for tiny defect detection on smooth car-body surfaces based on deep ensemble learning , 2019, Measurement Science and Technology.

[21]  Di He,et al.  Defect detection of hot rolled steels with a new object detection framework called classification priority network , 2019, Comput. Ind. Eng..

[22]  Yu Wang,et al.  Real-time defect detection of high-speed train wheels by using Bayesian forecasting and dynamic model , 2020, Mechanical Systems and Signal Processing.

[23]  Yichuang Sun,et al.  Automated Visual Defect Detection for Flat Steel Surface: A Survey , 2020, IEEE Transactions on Instrumentation and Measurement.

[24]  Yu Yao,et al.  Detection of a casting defect tracked by deep convolution neural network , 2018, The International Journal of Advanced Manufacturing Technology.

[25]  Olatomiwa Badmos,et al.  Image-based defect detection in lithium-ion battery electrode using convolutional neural networks , 2020, J. Intell. Manuf..

[26]  Xuebin Xu,et al.  Magnetic Ring Multi-Defect Stereo Detection System Based on Multi-Camera Vision Technology † , 2020, Sensors.

[27]  Yunhui Yan,et al.  Vision-based automatic detection of steel surface defects in the cold rolling process: considering the influence of industrial liquids and surface textures , 2017 .

[28]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[29]  Qinggang Meng,et al.  An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features , 2020, IEEE Transactions on Instrumentation and Measurement.

[30]  Paolo Tripicchio,et al.  Welding defect detection: coping with artifacts in the production line , 2020, The International Journal of Advanced Manufacturing Technology.

[31]  Ke Xu,et al.  Surface Detection of Continuous Casting Slabs Based on Curvelet Transform and Kernel Locality Preserving Projections , 2013 .

[32]  Jie Zhao,et al.  Steel surface defects recognition based on multi-type statistical features and enhanced twin support vector machine , 2017 .

[33]  Hichem Snoussi,et al.  A fast and robust convolutional neural network-based defect detection model in product quality control , 2017, The International Journal of Advanced Manufacturing Technology.

[34]  Jure Skvarč,et al.  Segmentation-based deep-learning approach for surface-defect detection , 2019, Journal of Intelligent Manufacturing.

[35]  Guangzhong Cao,et al.  Large-Complex-Surface Defect Detection by Hybrid Gradient Threshold Segmentation and Image Registration , 2018, IEEE Access.

[36]  Stefano Roccella,et al.  Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY , 2020, Sensors.

[37]  Shibin Gao,et al.  Deep Architecture for High-Speed Railway Insulator Surface Defect Detection: Denoising Autoencoder With Multitask Learning , 2019, IEEE Transactions on Instrumentation and Measurement.

[38]  Chao Li,et al.  An Effective Method of Weld Defect Detection and Classification Based on Machine Vision , 2019, IEEE Transactions on Industrial Informatics.

[39]  Yujie Li,et al.  Railway track fastener defect detection based on image processing and deep learning techniques: A comparative study , 2019, Eng. Appl. Artif. Intell..

[40]  Ruben Usamentiaga,et al.  Multi-camera calibration for accurate geometric measurements in industrial environments , 2019, Measurement.

[41]  Leyza Baldo Dorini,et al.  Inspection of Imprint Defects in Stamped Metal Surfaces Using Deep Learning and Tracking , 2021, IEEE Transactions on Industrial Electronics.

[42]  Donatella Cerniglia,et al.  Defect Detection in Additively Manufactured Components: Laser Ultrasound and Laser Thermography Comparison , 2018 .

[43]  Qiang Chen,et al.  Network In Network , 2013, ICLR.