A sparse autoencoder based denosing the spectrum signal in LIBS
- Resource Type
- Conference
- Authors
- Ye, Shibing; Niu, Zhixing; Yang, Peng; Sun, Junqing
- Source
- 2018 Chinese Control And Decision Conference (CCDC) Chinese Control And Decision Conference (CCDC), 2018. :3572-3577 Jun, 2018
- Subject
- General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Surface emitting lasers
Steel
Spectroscopy
Plasmas
Free electron lasers
Electric breakdown
LIBS
sparse autoencoder
spectral data
denosing
- Language
- ISSN
- 1948-9447
Based on laser induced breakdown spectroscopy (LIBS) technique, the content of the main elements in the liquid steel of carbon steel alloy can be detected in real time during melting process. In order to detect the liquid alloy steel and forecast the content of the main elements in the alloy steel more accurately, we use the method of sparse autoencoder to reduce noise in the spectral data which were collected in the detecting process. The experimental results show that the sparse autoencoder method can effectively improve the accuracy and precision of the spectral data.