Virtual Sensing Technology in Process Industries: Trends and Challenges Revealed by Recent Industrial Applications

被引：156

作者：

Kano, Manabu ^{[1
]}

Fujiwara, Koichi ^{[1
]}

机构：

[1] Kyoto Univ, Dept Syst Sci, Sakyo Ku, Kyoto 6068501, Japan

来源：

JOURNAL OF CHEMICAL ENGINEERING OF JAPAN | 2013年 / 46卷 / 01期

关键词：

Softsensor; Input Variable Selection; Just-in-Time Modeling; Model Maintenance; Partial Least Squares; Industrial Application; LOCALLY WEIGHTED REGRESSION; PARTIAL-LEAST-SQUARES; INDEPENDENT COMPONENT ANALYSIS; SOFT-SENSOR DEVELOPMENT; SUPPORT VECTOR MACHINE; INFERENTIAL CONTROL; DISTILLATION COMPOSITIONS; SECONDARY MEASUREMENTS; SUBSPACE IDENTIFICATION; VARIABLE SELECTION;

D O I：

10.1252/jcej.12we167

中图分类号：

TQ [化学工业];

学科分类号：

0817 ;

摘要：

Virtual sensing technology is crucial for high product quality and productivity in any industry. This review aims to clarify the trend of research and application of virtual sensing technology in process industries. After a brief survey, practical issues are clarified by introducing recent questionnaire survey results: 1) changes in process characteristics and operating conditions, 2) individual difference of equipment, and 3) reliability of soft-sensors. Since input variable selection is crucial for high estimation performance, conventional methods and new group-wise variable selection methods are introduced, and the usefulness of the group-wise variable selection methods is demonstrated through industrial case studies. Just-in-time (JIT) modeling is dealt with as a promising virtual sensing technology that can cope with changes in process characteristics as well as nonlinearity. Recent developments leading to successful industrial applications are introduced: correlation-based JIT (CoJIT) modeling and locally weighted regression (LWR), especially LW-PLS, with modified similarity measures. Manufacturing processes in different industries are quite different in appearance, but they have very similar problems from the viewpoint of quality issue. There remain practical issues requiring further research efforts to realize high-performance, maintenance-free virtual sensing technology.

引用

页码：1 / 17

页数：17

共 100 条

[11]

Bontempi G, 1999, INT J CONTROL, V72, P643, DOI 10.1080/002071799220830

[12]

Boser B. E., 1992, Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, P144, DOI 10.1145/130385.130401

[13]

BOZENHARDT HF, 1988, HYDROCARB PROCESS, V67, P47

[14] Optimization in locally weighted regression [J].

Centner, V ;

Massart, DL .

ANALYTICAL CHEMISTRY, 1998, 70 (19) :4206-4211

[15] Implementation of locally weighted regression to maintain calibrations on FT-NIR analyzers for industrial processes [J].

Chang, SY ;

Baughman, EH ;

McIntosh, BC .

APPLIED SPECTROSCOPY, 2001, 55 (09) :1199-1206

[16] A new data-based methodology for nonlinear process modeling [J].

Cheng, C ;

Chiu, MS .

CHEMICAL ENGINEERING SCIENCE, 2004, 59 (13) :2801-2810

[17] Performance of some variable selection methods when multicollinearity is present [J].

Chong, IG ;

Jun, CH .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2005, 78 (1-2) :103-112

[18] ROBUST LOCALLY WEIGHTED REGRESSION AND SMOOTHING SCATTERPLOTS [J].

CLEVELAND, WS .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1979, 74 (368) :829-836

[19] LOCALLY WEIGHTED REGRESSION - AN APPROACH TO REGRESSION-ANALYSIS BY LOCAL FITTING [J].

CLEVELAND, WS ;

DEVLIN, SJ .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1988, 83 (403) :596-610

[20] SUPPORT-VECTOR NETWORKS [J].

CORTES, C ;

VAPNIK, V .

MACHINE LEARNING, 1995, 20 (03) :273-297

← 1 2 3 4 5 6 7 8 9 10 →