Session: 03-16-01: AI Integration in Mechanical Engineering and Smart Manufacturing

Paper Number: 142963

142963 - "Enhancing Defective Casting Classification in Manufacturing Using Deep Learning: A Case Study With Vgg16" 

Abstract:

In the manufacturing industry, the detection of defective products, such as castings, is crucial for ensuring product quality and preventing potential safety hazards. Deep learning techniques, particularly convolutional neural networks (CNNs), have emerged as powerful tools for automating the detection and classification of defects in manufacturing processes. This study explores the application of deep learning, specifically utilizing the VGG16 model, for classifying defective castings from normal castings in the manufacturing field.

The dataset comprises a collection of images depicting both normal and defective castings. Initially, the VGG16 model was trained on a dataset consisting of 5000 training images, 1600 validation images, and 525 testing images. The model achieved a moderate accuracy of approximately 60% on the testing set, indicating its ability to classify defective castings to some extent. However, the model's performance in terms of precision, recall, and F1 score was suboptimal.

To enhance the model's performance, several strategies were employed. First, the VGG16 layers were fine-tuned by selectively unfreezing and training certain layers of the pre-trained model. This process allowed the model to adapt more effectively to the nuances of the specific dataset. Additionally, regularization techniques, such as dropout and L2 regularization, were incorporated to prevent overfitting and improve generalization performance.

Moreover, the learning rate of the model was adjusted and different values were experimented with to optimize its performance. Learning rate schedules and adaptive optimizers, such as the Adam optimizer, were utilized to dynamically adjust the learning rate during training.

Furthermore, the training dataset was augmented by applying various data augmentation techniques, such as rotation, flipping, and zooming, to increase the diversity of the images. By balancing the dataset to include an equal number of training, validation, and testing images, consisting of 4100, 1200, and 500 samples respectively, a significant improvement in the model's performance was observed.

After implementing these enhancements, the model achieved impressive results, with an accuracy of 89.6%, precision of 91.4%, recall of 89.6%, and F1 score of 89.5% on the testing set. These findings underscore the effectiveness of deep learning approaches, particularly when combined with fine-tuning, regularization, and data augmentation techniques, in accurately detecting and classifying defective castings in the manufacturing industry. Such advancements have the potential to streamline quality control processes, reduce production costs, and enhance overall product reliability and safety in manufacturing operations.

Presenting Author: Sathish Kumar Gurupatham Kennesaw State University

Presenting Author Biography: I am Dr. Sathish Gurupatham, an associate professor at Kennesaw State University with a diverse background in mechanical engineering and a growing expertise in artificial intelligence (AI). My academic journey began with a doctoral degree in Mechanical Engineering from the New Jersey Institute of Technology, which I earned in August 2011. Over the past eighteen years, I have dedicated myself to teaching and research across various engineering disciplines, including Thermodynamics, Heat Transfer, Fluid Mechanics, and Renewable Energy, at both the undergraduate and graduate levels.

Despite my roots in mechanical engineering, I have always been captivated by the transformative potential of AI in solving complex problems and improving systems. This fascination has driven me to pursue self-education in AI, focusing particularly on Machine Learning, Deep Learning, and Natural Language Processing. My current research interests lie at the intersection of AI and engineering, where I am exploring the application of AI in Predictive Maintenance, Process Optimization, Quality Control, Robotics, and Autonomous systems.

I have also conducted experimental research in micro-fluidics, self-assembly of micro-nano particles, and thermal imaging, which has further fueled my interest in integrating AI into these domains. My academic and industrial experience, coupled with my passion for AI, positions me uniquely to contribute to innovative research and education at the intersection of engineering and artificial intelligence.

Authors:

Sathish Kumar Gurupatham Kennesaw State University
Chandana Palreddy Kennesaw State University
Harshith Vijayakumar Kennesaw State University
Tyler Loignon Kennesaw State University