Predictive Maintenance from Vacuum Pumps
Use time series Data to label normal sensor data, outlier sensor data and develop a model for Outlier Detection.
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
I have more than 13 years of experience in ML Project for Defect Image Classification in the semiconductor manufacturing. I have worked and technically supervised projects for Object Detection, Spatial Pattern Recognition, ChipCode Identification, Image Outlier Detection, Classic Defect Classification). Also, I have established CI/CD Pipelines to support ML Applications in the manufacturing.
Use time series Data to label normal sensor data, outlier sensor data and develop a model for Outlier Detection.
Each Wafer in the Manufacturing has printed certain Chip Codes from the Lithography mask used for the pattern printing. I created a fined tuned AWS Recognition model to recognise the Chip Codes and compared them with the Design Database. If there was a Code mismatch then the material would be stopped in real time.
Label, Train and Deploy ML Models in production to classify different defect patterns visible in semiconductor wafers (e.g. Scratches, Cluster Defects, Edge Defects, Cracks) on Wafers.
Classify, Train and Deploy Defect Classification models for different steps in the semiconductor manufacturing. Around 12 Models for different steps (e.g. Inspection after Lithography, CMP, Etching, etc), using images from the Scanning Electron Microscope after Review
Executive MBA, Executive MBA
Master of Science, Production Engineering
Senior Staff Engineer
Staff Manager