Bayesian Regularized Gaussian Mixture Regression with Application to Soft Sensor Modeling for Multi-Mode Industrial Processes

2018 ◽  
Author(s):  
Jingbo Wang ◽  
Weiming Shao ◽  
Zhihuan Song
Keyword(s):  
Gaussian Mixture ◽  
Soft Sensor ◽  
Industrial Processes ◽  
Mixture Regression ◽  
Sensor Modeling ◽  
Multi Mode

Soft Sensor for Multiphase and Multimode Processes Based on Gaussian Mixture Regression

2014 ◽  
Vol 47 (3) ◽  
pp. 1067-1072
Author(s):  
Xiaofeng Yuan ◽  
Zhiqiang Ge ◽  
Hongwei Zhang ◽  
Zhihuan Song ◽  
Peiliang Wang
Keyword(s):  
Gaussian Mixture ◽  
Soft Sensor ◽  
Mixture Regression

scholarly journals Student’s-t Mixture Regression-Based Robust Soft Sensor Development for Multimode Industrial Processes

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3968 ◽  
Author(s):  
Jingbo Wang ◽  
Weiming Shao ◽  
Zhihuan Song
Keyword(s):  
Learning Algorithm ◽  
Real Life ◽  
Industrial Process ◽  
Soft Sensor ◽  
Operating Conditions ◽  
Industrial Processes ◽  
Computationally Efficient ◽  
Mixture Regression ◽  
Student’S T ◽  
T Distribution

Because of multiple manufacturing phases or operating conditions, a great many industrial processes work with multiple modes. In addition, it is inevitable that some measurements of industrial variables obtained through hardware sensors are incorrectly observed, recorded or imported into databases, resulting in the dataset available for statistic analysis being contaminated by outliers. Unfortunately, these outliers are difficult to recognize and remove completely. These process characteristics and dataset imperfections impose challenges on developing high-accuracy soft sensors. To resolve this problem, the Student’s-t mixture regression (SMR) is proposed to develop a robust soft sensor for multimode industrial processes. In the SMR, for each mixing component, the Student’s-t distribution is used instead of the Gaussian distribution to model secondary variables, and the functional relationship between secondary and primary variables is explicitly considered. Based on the model structure of the SMR, a computationally efficient parameter-learning algorithm is also developed for SMR. Results conducted on two cases including a numerical example and a real-life industrial process demonstrate the effectiveness and feasibility of the proposed approach.

Dynamic soft sensor development based on Gaussian mixture regression for fermentation processes

2017 ◽  
Vol 25 (1) ◽  
pp. 116-122 ◽  
Author(s):  
Congli Mei ◽  
Yong Su ◽  
Guohai Liu ◽  
Yuhan Ding ◽  
Zhiling Liao
Keyword(s):  
Gaussian Mixture ◽  
Soft Sensor ◽  
Fermentation Processes ◽  
Mixture Regression ◽  
Sensor Development

SOFT SENSOR MODELING FOR VACUUM OIL PURIFICATION MACHINE BASED ON LSSVM

2008 ◽  
Vol 07 (01) ◽  
pp. 141-144 ◽  
Author(s):  
CHUAN LI ◽  
SHILONG WANG ◽  
XIANMING ZHANG ◽  
LING KANG ◽  
JIANJUN MIN
Keyword(s):  
Rough Sets ◽  
Soft Sensor ◽  
Industrial Processes ◽  
Support Vector ◽  
Rough Sets Theory ◽  
Sensor Model ◽  
Oil Purification ◽  
Sets Theory ◽  
Primary Variable ◽  
Sensor Modeling

According to the secondary variables acquired from industrial processes, a Least Squares Support Vector Machine (LSSVM) based model is proposed for the primary variable soft sensing. The Rough Sets Theory is firstly employed to compress values and attributes of the secondary variables. Then the LSSVM is delivered for the primary variable nonlinear estimating. The method is applied for the vacuum oil purification machine. The moisture content in oil, a hard-to-be-measured primary variable, is computed from the soft sensor model. The result shows that the proposed method features a faster and more precise approximation ability.

Sign in / Sign up

Export Citation Format

Share Document