Search results for: Nandhini

Authors: Nandhini Ravi, Muthukumaran Shanmugam

Abstract:

Metals are being replaced by thermoplastic polymer composites in automotive industries because of their low density, easiness to fabricate, low cost and good wear resistance. Complex polymer components consist of assemblies of smaller parts which can be joined by friction stir welding. This study deals with the additive friction stir welding of 15 wt.% glass fiber reinforced polyamide 66 composite which is a modified technique of the conventional friction stir welding by the addition of a filler plate for the heating of the composite work piece through the tool during the welding process. Welding at different combinations of tool rotational speed, travel speed and tool plunge depth was done after which the tensile strength of the respective experiments was determined. The maximum tensile strength obtained was 77 MPa which was 80% of the strength of the base material. The process parameters were optimized using the L9 orthogonal array and also the effect of individual welding parameter on the tensile strength was studied. The optimum parameter combination was determined with the help of ANOVA studies. The hardness of the welded joints was studied with the help of Shore Durometer which yielded the maximum of D 75.

Keywords: additive friction stir welding, polyamide 66, process parameters, thermoplastic polymer composite

Procedia PDF Downloads 157

Authors: Nandhini, Gaurab mudbhari

Abstract:

Ranging from the field of health care to self-driving cars, machine learning and deep learning algorithms have revolutionized the field with the proper utilization of images and visual-oriented data. Segmentation, regression, classification, clustering, dimensionality reduction, etc., are some of the Machine Learning tasks that helped Machine Learning and Deep Learning models to become state-of-the-art models for the field where images are key datasets. Among these tasks, classification and clustering are essential but difficult because of the intricate and high-dimensional characteristics of image data. This finding examines and assesses advanced techniques in supervised classification and unsupervised clustering for image datasets, emphasizing the relative efficiency of Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Deep Embedded Clustering (DEC), and self-supervised learning approaches. Due to the distinctive structural attributes present in images, conventional methods often fail to effectively capture spatial patterns, resulting in the development of models that utilize more advanced architectures and attention mechanisms. In image classification, we investigated both CNNs and ViTs. One of the most promising models, which is very much known for its ability to detect spatial hierarchies, is CNN, and it serves as a core model in our study. On the other hand, ViT is another model that also serves as a core model, reflecting a modern classification method that uses a self-attention mechanism which makes them more robust as this self-attention mechanism allows them to lean global dependencies in images without relying on convolutional layers. This paper evaluates the performance of these two architectures based on accuracy, precision, recall, and F1-score across different image datasets, analyzing their appropriateness for various categories of images. In the domain of clustering, we assess DEC, Variational Autoencoders (VAEs), and conventional clustering techniques like k-means, which are used on embeddings derived from CNN models. DEC, a prominent model in the field of clustering, has gained the attention of many ML engineers because of its ability to combine feature learning and clustering into a single framework and its main goal is to improve clustering quality through better feature representation. VAEs, on the other hand, are pretty well known for using latent embeddings for grouping similar images without requiring for prior label by utilizing the probabilistic clustering method.

Keywords: machine learning, deep learning, image classification, image clustering

Procedia PDF Downloads 0