Combination of data rectification techniques and soft sensor model for robust prediction of sulfur content in HDS process
详细信息 查看全文
- 作者：Saeid Shokria ; Mahdi Ahmadi Marvasta ; ahmadim@ripi.ir" class="auth_mail" title="E-mail the corresponding author ; marvast@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Mohammad Taghi Sadeghib ; Shankar Narasimhanc
- 关键词：Gas oil hydrodesulfurization ; Outlier detection ; Wavelet transforms (WT) ; Soft sensor ; Support vector regression (SVR)
- 刊名：Journal of the Taiwan Institute of Chemical Engineers
- 出版年：2016
- 出版时间：January 2016
- 年：2016
- 卷：58
- 期：Complete
- 页码：117-126
- 全文大小：3418 K
文摘
- •
Designing an accurate and robust data-driven soft sensor to predict sulfur content in Hydrodesulfurization (HDS) Process.
- •
Developing a novel hybrid approach for data-preprocessing.
- •
Investigating the effects of outlier detection and noise reduction on prediction accuracy of the SVR model.
- •
Improving prediction performance and computation time (CT) by integration of vector quantization (VQ) and SVR.