Petroleum Science >2015,??Issue 1:??177-188 DOI: https://doi.org/10.1007/s12182-014-0010-9
Improvement of the prediction performance of a soft sensor modelbased on support vector regression for production of ultra-lowsulfur diesel Open?Access
文章信息
作者：Saeid Shokri,Mohammad Taghi Sadeghi,Mahdi Ahmadi Marvast and Shankar Narasimhan
作者單位：
Department of Chemical Engineering, Iran University of Science and Technology (IUST), Tehran, Iran e-mail: [email protected];Department of Chemical Engineering, Iran University of Science and Technology (IUST), Tehran, Iran e-mail: [email protected];Process and Equipment Technology Development Division, Research Institute of Petroleum Industry (RIPI), Tehran, Iran;Department of Chemical Engineering, IIT Madras, Chennai, India
投稿時(shí)間：2015-01-13
引用方式：Shokri, S., Sadeghi, M.T., Marvast, M.A. et al. Pet. Sci. (2015) 12: 177. https://doi.org/10.1007/s12182-014-0010-9
文章摘要
A novel data-driven, soft sensor based on support
vector regression (SVR) integrated with a data compression
technique was developed to predict the product quality for the
hydrodesulfurization (HDS) process. A wide range of experimental
data was taken from a HDS setup to train and test the
SVR model. Hyper-parameter tuning is one of the main
challenges to improve predictive accuracy of the SVRmodel.
Therefore, a hybrid approach using a combination of genetic
algorithm(GA) and sequential quadratic programming (SQP)
methods (GA–SQP) was developed. Performance of different
optimization algorithms including GA–SQP, GA, pattern
search (PS), and grid search (GS) indicated that the best
average absolute relative error (AARE), squared correlation
coefficient (R2), and computation time (CT)
(AARE = 0.0745, R2 = 0.997 and CT = 56 s) was accomplished
by the hybrid algorithm. Moreover, to reduce the CT
and improve the accuracy of the SVR model, the vector
quantization (VQ) technique was used. The results also
showed that the VQ technique can decrease the training time
and improve prediction performance of the SVR model. The
proposed method can provide a robust, soft sensor in a wide
range of sulfur contents with good accuracy.
vector regression (SVR) integrated with a data compression
technique was developed to predict the product quality for the
hydrodesulfurization (HDS) process. A wide range of experimental
data was taken from a HDS setup to train and test the
SVR model. Hyper-parameter tuning is one of the main
challenges to improve predictive accuracy of the SVRmodel.
Therefore, a hybrid approach using a combination of genetic
algorithm(GA) and sequential quadratic programming (SQP)
methods (GA–SQP) was developed. Performance of different
optimization algorithms including GA–SQP, GA, pattern
search (PS), and grid search (GS) indicated that the best
average absolute relative error (AARE), squared correlation
coefficient (R2), and computation time (CT)
(AARE = 0.0745, R2 = 0.997 and CT = 56 s) was accomplished
by the hybrid algorithm. Moreover, to reduce the CT
and improve the accuracy of the SVR model, the vector
quantization (VQ) technique was used. The results also
showed that the VQ technique can decrease the training time
and improve prediction performance of the SVR model. The
proposed method can provide a robust, soft sensor in a wide
range of sulfur contents with good accuracy.
關(guān)鍵詞
-
Soft sensor Support vector regression Hybrid optimization method Vector quantization Petroleum refinery Hydrodesulfurization process Gas oil