Papers

[1] Fault Classification of FDM 3D Printer in Virtual Environment(Thesis)
[2] Efficient CNN-based Fault Classification for FDM 3D Printer using Embedded Device (KICS Fall 2022)

Last Week's Progress

[1] - Thesis presentation (in NSL)

- Performance metrics:
1. Accuracy
2. Loss
3. Trainable parameter
4. File size of embedded file
5. Training time
6. Time for one prediction (inference time?)
7. Latency
8. System overhead (is it needed?)

This Week Todo's

- Title:
1. Digital-Twin Assisted Fault Detection in Smart Additive Manufacturing
2. Fault Detection on Metaverse Environment for FDM 3D Printer

short clip: <a href='https://drive.google.com/file/d/1G-_aYFnFGchZuBZ8RIkVNJsa_mRvrFVn/view?usp=share_link'> Click Here</a>;

- Book and journal writing
- Fix thesis presentation based on NSL member suggestion
- Prepare for KICS Fall

Project Progress

3D Printer Monitoring

Last Week's Project

- Waiting for the new dataset for validation

This Week's Project

- Waiting for the new dataset for validation

Monthly Goals

- Finish thesis book
- Finish PPT for Thesis Defense
- Present thesis presentation in NSL
- Finish all the simulation and implementation part
- KICS Fall 2022

Annual Goals

- Submit domestic and international conferences (Done with KICS Summer 2022 and ICTC 2022)
- Submit journal
- Graduate