Soft Measurement Technology and Implementation Based on PSO-SVR

Lin Zhu; Tian Cai

doi:10.4028/www.scientific.net/AMM.392.774

Paper Titles

The Transformer Tangled Winding Joints Open Welding Diagnostic Methods
p.755

A Harmonic Detecting Scheme Based on BP Neural Network
p.759

Research on the Relationship between the Anchor Pattern Characteristics and Adhesion Based on Neural Network
p.765

The Simultaneous Acquisition of the Mixed Vehicle-Carrying Signals Based on the CompactRIO
p.770

Soft Measurement Technology and Implementation Based on PSO-SVR
p.774

Research the Measurement Method of Software Aging in Cloud
p.779

Application of Multi-Sensors Data Fusion Technology in the Theodolite Tracking System
p.783

Application of GPR in Measurement of Kunming Lake
p.787

Application of WSN in the Remote Monitoring for Heating Network
p.791

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 392Soft Measurement Technology and Implementation...

Soft Measurement Technology and Implementation Based on PSO-SVR

Abstract:

Aiming at the important parameters of industrial process can not be online measured by sensors, this paper proposes a soft sensor modeling method based on PSO-SVR, and analyzes the technical bottleneck of the soft measurement model applied in engineering, designs the online application system of soft-sensing model with OPC technology. This paper discusses in detail the implementation steps of exchanging data between MATLAB algorithm model and WinCC industrial control configuration platform with OPC technology. The method has the advantages of simple integration and easy to implement, has certain application value.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 392)

Pages:

774-778

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.392.774

Citation:

Cite this paper

Online since:

September 2013

Authors:

Lin Zhu, Tian Cai

Keywords:

OPC Technology, Particle Swarm Optimization Algorithm, Soft Measurement Technology, Support Vector Machine Regression, WinCC

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Deng Naiyang, Tian Yingjie. New data mining methods-support vector machine [M]. Beijing: Science Press, (2004).

Google Scholar

[2] Zhang Xuegong. On the statistical learning theory and support vector machines[J]. Journal of Automation, 2000, 26(1): 32-42.

Google Scholar

[3] Xiong Weili, Xu Baoguo. Study on PSO for the optimization of SVR parameters selection [C]. Proceedings of 2007 Chinese Controland Decision Conference: 447-452.

Google Scholar

[4] LiH X. A comparative design and tuning for conventional fuzzy control [J]. IEEE Trans System Man Cybernet PB: Cybernetics, 1997, 27 (5): 884-889.

DOI: 10.1109/3477.623242

Google Scholar

[5] HAMalk. i . New design and stability analysis of fuzzy proportion-derivative control systems [J]. IEEE Trans. Fuzzy Syst, 1994, 2(3): 245-254.

DOI: 10.1109/91.324804

Google Scholar

[6] Ming Liu. Decentralized control of robot manipulators nonlinear and adaptive approaches [J]. IEEE Transactions on Automatic contro, l999, 44 (2): 357-363.

DOI: 10.1109/9.746266

Google Scholar

[7] Xue Fuzhen, Xu Lei, Tian Guishi. Design and implementation of OPC based advanced control algorithm platform [J]. Process Automation Instrumentation, 2005, 9: 26-28.

Google Scholar