Soft Measurement Technique of Sewage Treatment Parameters Based on Wavelet Neural Networks

Abstract:

There are certain nonlinearity, time variability, randomness and uncertainty in the process of using sequencing batch sludge method in sewage treatment. Therefore, propose a soft measurement technique for sewage treatment parameters basing on the model of Kernel Principal Component Analysis and Wavelet Neural Network. Use Kernel Principal Component Analysis as concise as possible in the case of the input variables can ensure that a smaller amount of loss and combine WNN soft-measurement model and on-line measuring instruments together, do real-time detection for redox potential, dissolved oxygen, PH, COD and so on parameter control information .PLC controller outputs control signals to control the entire system equipment operation. The simulation results show that compared with traditional methods, there is good dynamic performance, fewer error, which is with good robustness and stability.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 3168-3171
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.3168
• Online since: May 2014
• Authors: Wen Cheng Wang*, Ke Li, Zhong Xue Chen, Qin Zhou Niu
• Keywords: Kernel Principal Component Analysis, Learning Algorithm, Wavelet Neural Network

References

[1] Olsson G, Nielsen M and Yuan. Z. G. e. al, Instrumentation, Control and Automation in Wastewater Systems [M]. London: Hove, IWA, 2005: 33-38.

[2] Lee M. W., et al., Real-time remote monitoring of small-scaled biological wastewater treatment plants by a multivariate statistical process control and neural network-based software sensors [J]. Process Biochemistry, 2008, 43(10): 1107-1113.

DOI: 10.1016/j.procbio.2008.06.002

[3] Aguado D., et al., Comparison of different predictive models for nutrient estimation in a sequencing batch reactor for wastewater treatment [J]. Chemometrics and Intelligent Laboratory Systems, 2006, 84(1-2): 75-81.

DOI: 10.1016/j.chemolab.2006.03.009

[4] Edakunni N. U., Bayesian Locally Weighted Online Learning [D]. Edinburgh: School of Informatics, University of Edinburgh, (2009).

[5] Liu J., Chen D. S. and Shen J. F., Development of Self-Validating Soft Sensors Using Fast Moving Window Partial Least Squares [J]. Industrial & Engineering Chemistry Research, 2010, 49(2): 11530-11546.

DOI: 10.1021/ie101356c