Modeling the Performance of an Industrial Process Based on Neural Networks and Data Mining

S. Sara Aghvami; Heidar T. Shandiz; M.R. Jahed Motlagh

doi:10.4028/www.scientific.net/AMR.403-408.3544

Paper Titles

A New Approach in Digital Image Watermarking Using Fractal Model in DWT Domain
p.3510

A Hybrid FCM Clustering- Neural Network Model for Intrusion Detection
p.3519

Simulation and Analysis of Nonlinear System Identification Using the LMS Volterra Filter
p.3528

Application of Artificial Neural Network in the Modeling of Skidding Time Prediction
p.3538

Modeling the Performance of an Industrial Process Based on Neural Networks and Data Mining
p.3544

A Novel Flow Meter Selection Method Based on Fuzzy Multiple Criteria Decision-Making
p.3548

RoboGenius Team Description Paper Review and Develop a War Simulation Agent from AI Vision
p.3555

Collision Avoidance in Unstructured Environments for Autonomous Robots: A Behavioural Modelling Approach
p.3559

Comparison of Artificial Neural Network Models and Multiple Linear Regression Models in Cargo Port Performance Prediction
p.3570

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 403-408Modeling the Performance of an Industrial Process...

Modeling the Performance of an Industrial Process Based on Neural Networks and Data Mining

Abstract:

Data Mining has been applied to the world of industrial process. Through this paper, modeling of such a process, a boiler, is discussed focusing on the two methods of Partial Least Square (PLS) Regression and Neural Networks. In modeling the system behavior, the former has the capability of reducing the database dimension and taking to account the latent relations between data, while the later handles the nonlinearity of the process in order to predict the system response through the database of observed boiler operation data.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 403-408)

Pages:

3544-3547

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.403-408.3544

Citation:

Cite this paper

Online since:

November 2011

Authors:

S. Sara Aghvami, Heidar T. Shandiz, M.R. Jahed Motlagh

Keywords:

Boiler, Data Mining (DM), Modeling, Neural Network (NN), PLS

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Martin Andersson, A Comparison of nine PLS1 Algorithms, Journal of Chemometrics, 23: 518-529, (2009).

DOI: 10.1002/cem.1248

Google Scholar

[2] ASME Power Test Code. PTC 4-1998. Fired Steam Generators, New York, (1998).

Google Scholar

[3] R.C. Booth and W.B. Roland. Neural, Network-Based Combustion Optimization Reduces NOx Emissions while Improving Performance, Proc. IEEE Industry applications Dynamic modeling Control applications Industry Workshop, pp.1-6, (1998).

DOI: 10.1109/dmca.1998.703475

Google Scholar

[4] Madan M. Gupta, Liang Jin, and Noriyasu Homma, Static and Dynamic Neural Networks, John Wiely & Sons Ltd., (2003).

Google Scholar

[5] Tao Jin and Zhongguang Fu., Data Mining for Complex Thermal System Modeling, , Fifth International Conference on Fuzzy Systems and Knowledge Discovery, (2008).

DOI: 10.1109/fskd.2008.201

Google Scholar

[6] Harald Martens and Tormod Næs, Multivariate Calibration, John Wiely & Sons Ltd., (1994).

Google Scholar

[7] Zhe Song and Andrew Kusiak, Constraint-Based Control of Boiler Efficiency: A Data Mining Approach., IEEE Transactions on Industrial Informatics, Vol. 3, No. 1, Feb. (2007).

DOI: 10.1109/tii.2006.890530

Google Scholar

[8] Ian H. Witten, Data Mining, Practical Machine Learning Tools and Techniques, Elsevier, (2005).

Google Scholar