Deep Learning and Image data-based surface cracks recognition of laser nitrided Titanium alloy

Abstract

Laser nitriding, a high-precision surface modification process, enhances the hardness, wear resistance and corrosion resistance of the materials. However, laser nitriding process is prone to appearance of cracks when the process is performed at high laser energy levels. Traditional techniques to detect the cracks are time consuming, costly and lack standardization. Thus, this research aims to put forth deep learning-based crack recognition for the laser nitriding of Ti–6Al–4V alloy. The process of laser nitriding has been performed by varying duty cycles, and other process parameters. The laser nitrided sample has then been processed through optical 3D surface measurements (Alicona Infinite Focus G5), creating high resolution images. The images were then pre-processed which included 2D conversion, patchification, image augmentation and subsequent removal of anomalies. After preprocessing, the investigation focused on employing robust binary classification method based on CNN models and its variants, including ResNet-50, VGG-19, VGG-16, GoogLeNet (Inception V3), and DenseNet-121, to recognize surface cracks. The performance of these models has been optimized by fine tuning different hyper parameters and it is found that CNN base model along with models having less trainable parameters like VGG-19, VGG-16 exhibit better performance with accuracy of more than 98% to recognize cracks. Through the achieved results, it is found that VGG-19 is the most preferable model for this crack recognition problem to effectively recognize the surface cracks on laser nitrided Ti–6Al–4V material, owing to its best accuracy and lesser parameters compared to complex models like ResNet-50 and Inception-V3.

Keywords

• Laser nitriding
• Crack recognition
• Deep learning
• Transfer learning
• Anomalies
• Binary classification