Skip to content

jtian123/CERN-Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 

Repository files navigation

CERN-Project

Jinyao Tian

This project is one of major projects I accomplished at Utrecht University cooperated with The European Organization for Nuclear Research (CERN), Netherlands. The main goal is the devise a predictive system to warn the operators beforehand that the beam might decay, as well as to get better insight into what causes these dacays.

In this project, I am mainly focused on building and testing XGBoost model. My main jobs are:

• Improved Neural Network model performance by 20% of using Exponential Rolling Average method to remove stochastic noise from sensor data.

• Increased prediction accuracy by 40% of applying XGBoost (Extreme Gradient Boosting) to devise predictive system to warn operators beforehand beam current might decay.

• Captured change trend of beam current focusing on three sensitive regions and provided actual possible solutions for operators to highly reduce beam decay.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published