FURI | Spring 2023

Multi-Conditional cGAN Model for Resistance Spot Welding Dataset

Data icon, disabled. Four grey bars arranged like a vertical bar chart.

The Resistance Spot Welding technique has been widely employed in automotive and aeronautical industries. The advantages of utilizing this technique are that it is low cost, employs a high amount of current at low voltage, has high speed, and is reliable. RSW reduces weight while preserving strength. Defects commonly occur in the process, limiting its utilization in industry. Deep Learning has proven to be an effective tool for analyzing images in many applications. The proposal for this project is a multi-conditional GAN that can analyze images obtained from thermal videos of the RSW process and detect defects.

Student researcher

Srinidhi Budhiraju

Computer science

Hometown: Tempe, Arizona, United States

Graduation date: Spring 2024