Continuous Real Time Weld Quality Inspection in Friction Stir Welding
- 0 Collaborators
Friction stir welding is a solid-state joining process that uses a non-consumable tool to join two facing workpieces without melting the workpiece material. Continuous Quality Inspection of the weld can be used as a feedback for changing the weld parameters and hence improve the welding process. ...learn more
Project status: Concept
Internet of Things, Artificial Intelligence
Groups
Student Developers for AI
Intel Technologies
Intel Opt ML/DL Framework,
Intel Python,
Intel FPGA
Overview / Usage
Welding is one of the most used metal joining process. Friction stir welding is a non conventional welding process used to join metals and alloys together. Determining the quality of a weld continuously in real time can bring some real benefits such as deciding the parameters of welding such as tool rotation and tool traversal speeds. In addition it removes the necessity for a human visual inspection and hence can help reduce time, cost and improve efficiency in the process of weld inspection. This can be achieved by training a deep Convolutional Neural Networks.
Technologies Used
Python
Tensorflow
Keras
Matplotlib
Numpy
Scipy
Fast AI
Jupyter Notebook