Satish Sonwane

Visvesvaraya National Institute of Technology

Papers

Total Citations

H-Index

About

Satish Sonwane is a researcher specializing in the intersection of computer vision and manufacturing, with a particular focus on automated inspection and quality control. His work centers on developing intelligent systems for industrial applications, notably through the integration of deep learning and classical machine learning techniques. His most cited paper, "Pre-trained CNN Based SVM Classifier for Weld Joint Type Recognition" (2022), demonstrates a novel approach that leverages pre-trained convolutional neural networks for feature extraction, combined with support vector machines for classification. This work addresses a critical need in automated welding processes, where accurate joint type recognition is essential for ensuring structural integrity and production efficiency. While his citation count is currently modest, Sonwane's research contributes to the growing field of Industry 4.0, offering practical solutions that bridge the gap between advanced AI models and real-world manufacturing challenges. His methodology—using transfer learning to reduce computational demands while maintaining high accuracy—is particularly valuable for resource-constrained industrial environments. As automated quality inspection becomes increasingly vital across sectors, Sonwane's work provides a foundation for more robust and efficient manufacturing systems.