Ball Mill Load State Recognition Based on Kernel PCA and Probabilistic PLS-ELM

Abstract:

Operating condition recognition of ball mill load is important to improve product quality, decrease energy consumption and ensure the safety of grinding process. A probabilistic one-against-one (OAO) multi-classification method using partial least square-based extreme learning machine algorithm (PLS-ELM) is proposed to identify the operating state of ball mill. The feature of shell vibration spectrum is extracted using KPCA. PLS-ELM model is applied to enhance the reliability and accuracy of the operating conditions identification of the ball mill load. Posterior probability of each class using Bayesian decision theory is defined as a measure as classification reliability. Classification results of the experimental ball mill shown that the accuracy and stability of the proposed method outperform ELM, PLS-ELM and KPCA-ELM model.

• Periodical: Applied Mechanics and Materials (Volumes 263-266)
• Pages: 398-401
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.263-266.398
• Online since: December 2012
• Authors: Li Jie Zhao, De Cheng Yuan, Jian Tang
• Keywords: Ball Mill, Extreme Learning Machine, Mill Load, Partial Least Square (PLS), State Recognition

References

[1] Ning Xu, Junwu Zhou and Qing Wang: Copper Engineering, Vol. 107, No. 1, (2011), pp.54-60.(In Chinese).

[2] Jian Tang, Lijie Zhao, Junwu Zhou, Heng Yue and Tianyou Chai: Minerals Engineering, Vol. 23, No. 9, (2010), pp.720-730.

[3] Ping Zhou and Tianyou Chai: Control Theory & Applications, Vol.25, No.6, (2008), pp.1095-1099. (In Chinese).

[4] Jian Tang. Soft Sensing of Ball Mill Load for Grinding Process, PhD, Northeastern University, 2012. (In Chinese)

[5] Guangbin Huang, Qinyu Zhu and Chee khong Siew: Neurocomputing, Vol. 70, No.1-3, (2006), pp.489-501.

[6] Guangbin Huang, Dianhui Wang and Yuan Lan: International Journal of Machine Learning and Cybernetics, Vol. 2, No.2, (2011), pp.107-122.

[7] Néstor F. Pérez, Joan Ferré, Ricard Boqué: Chemometrics and Intelligent Laboratory Systems, Vol. 95, No. 2, (2009), pp.122-128.

DOI: 10.1016/j.chemolab.2008.09.005

[8] Lijie Zhao, Xiaokun Diao, Decheng Yuan and Wei Tang: Procedia Engineering, Vol. 15, No. 1, (2011), pp.5563-5567.

[9] Néstor F. Pérez, Joan Ferrér and Ricard Boqué : Analytical Chemical Acts, Vol.664, No.1, (2010), pp.27-33.

[10] Lijie Zhao, Dianhui Wang and Tianyou Chai: Neural Computing and Applications, Vol. 21, No.1, (2012), pp.1-11.

[11] Scholkopf B., Smola A. and Muller K. R: Neural Computation, Vol.10, (1998), pp.1299-1319.