Optimization of Wire Arc Additive Manufacturing Process Parameters for Low‐Carbon Steel and Properties Prediction by Support Vector Regression Model

Barik, Sougata; Bhandari, Rahul; Mondal, Manas Kumar

doi:10.1002/srin.202300369

Cited by 6 publications

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, Ma et al [23] used the popular Deeplab-based segmentation network considering binary mask image patches to evaluate the Al alloy defect identification. Besides, Barik et al [24] study aimed to optimize the process parameters of wire arc AM for ER70S6 steel and to build a machine-learning (ML)-based support vector regression (SVR) model with tensile testing and metallography to predict the defect properties like porosity of deposited specimens. Moreover, the research articles [22,25] provide a clear insight into this domain with relatively simpler but effective methodologies.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning-Based Automatic Defect Detection of Additive Manufactured Stainless Steel

Zubayer,

Zhang,

Wang

2023

Metals

View full text Add to dashboard Cite

Accumulating interest from academia and industry, the part of quality assurance in metal additive manufacturing (AM) is achieving incremental recognition owing to its distinct advantages over conventional manufacturing methods. In this paper, we introduced a convolutional neural network, YOLOv8 approach toward robust metallographic image quality inspection. Metallographic images accommodate key information relating to metal properties, such as structural strength, ductility, toughness, and defects, which are employed to select suitable materials for multiple engineering execution. Therefore, by comprehending the microstructures, one can understand insights into the behavior of a metal component and make predictive assessments of failure under specific conditions. Deep learning-based image segmentation is a robust technique for the detection of microstructural defects like cracks, inclusion, and gas porosity. Therefore, we improvise the YOLOv8 with dilated convolution mechanisms to acquire automatic micro-structure defect characterization. More specifically, for the first time, the YOLOv8 algorithm was proposed in the metallography dataset from additive manufacturing of steels (Metal DAM) to identify defects like cracks and porosity as a novel approach. A total of 414 images from ArcelorMittal engineers were used as an open-access database. The experimental results demonstrated that the YOLOv8 model successfully detected and identified cracks and porosity in the metal AM dataset, achieving an improved defect detection accuracy of up to 96% within just 0.5 h compared to previous automatic defect recognition processes.

show abstract