Abstract
Online prediction of mill load is useful to control system design in the grinding process. It is a challenging problem to estimate the parameters of the load inside the ball mill using measurable signals. This paper aims to develop a computational intelligence approach for predicting the mill load. Extreme learning machines (ELMs) are employed as learner models to implement the map between frequency spectral features and the mill load parameters. The inputs of the ELM model are reduced features, which are extracted and selected from the vibration frequency spectrum of the mill shell using partial least squares (PLS) algorithm. Experiments are carried out in the laboratory with comparisons on the well-known back-propagation learning algorithm, the original ELM and an optimization-based ELM (OELM). Results indicate that the reduced feature-based OELM can perform reasonably well at mill load parameter estimation, and it outperforms other learner models in terms of generalization capability.
Similar content being viewed by others
References
Bai R, Chai TY (2009) Optimization control of ball mill load in blending process with data fusion and case-based reasoning. J Chem Ind Eng 60(7):1746–1751
Behera B, Mishra BK, Murty CVR (2007) Experimental analysis of charge dynamics in tumbling mills by vibration signature technique. Miner Eng 20(1):84–91
Boehm O, Hardoon DR, Manevitz LM (2011) Classifying cognitive states of brain activity via one-class neural networks with feature selection by genetic algorithms. Int J Mach Learn Cybern 2(3):125–134
Chacko BP, Krishnan VR, Raju G, Anto PB (2011) Handwritten character recognition using wavelet energy and extreme learning machine. Int J Mach Learn Cybern. doi:10.1007/s13042-011-0049-5
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
Dai JJ, Lieu L, Rocke D (2006) Dimension reduction for classification with gene expression microarray data. Stat Appl Genet Mol Biol 5(1):Article 6
Dhanjal C, Gunn SR, Shawe-Taylor J (2009) Efficient sparse kernel feature extraction based on partial least squares. IEEE Trans Pattern Anal Mach Intell 31(8):1347–1361
Frnay B, Verleysen M (2010) Using SVMs with randomized feature spaces: an extreme learning approach. In: Proceedings of the 18th European symposium on artificial neural networks (ESANN). Bruges, Belgium, pp 315–320
Fukunaga K (1989) Effects of sample size in classifier design. IEEE Trans Pattern Anal Mach Intell 11(1):873–885
Gugel K, Palcios G,Ramirez J, Parra M (2003) Improving ball mill control with modern tools based on digital signal processing (DSP) technology. In: IEEE cement industry technical conference. Dalas, America, pp 311–318
Hoskuldsson A (1988) PLS regression methods. J Chemom 2(3):211–228
Hu G, Otaki H, Watanuki K (2000) Motion analysis of a tumbling ball mill based on non-linear optimization. Miner Eng 13(8–9):933–947
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501
Huang GB, Ding X, Zhou H (2010) Optimization method based extreme learning machine for classification. Neurocomputing 74(1-3):155–163
Huang GB, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2(2):107–122
Jain AK, Duin RPW, Mao JC (2000) Statistical pattern recognition: a review. IEEE Trans Pattern Anal Mach Intell 22(1):4–38
Jimnez-Rodrguez LO, Arzuaga-Cruz E, Vlez-Reyes M (2007) Unsupervised linear feature-extraction methods and their effects in the classification of high-dimensional data. IEEE Trans Geosci Remote Sens 45(2):469–483
Jolliffe IT (2002) Principal component analysis. Springer Press, Berlin
Kadlec P, Gabrys B, Strand S (2009) Data-driven soft-sensors in the process industry. Comput Chem Eng 33(4):795–814
Liu JL (2007) On-line soft sensor for polyethylene process with multiple production grades. Control Eng Pract 15(7):769–778
Li GZ, Bu HL, Yang MQ, Zeng XQ, Yang JY (2008) Selecting subsets of newly extracted features from PCA and PLS in microarray data analysis. BMC Genomics 9(s-2):1–15
Liu Q, He Q, Shi Z (2008) Extreme support vector machine classifier. Lect Notes Comput Sci 5012:222–233
Li WT, Mao KZ, Zhou XJ, Chai TY, Zhang H (2009) Eigen-flame image-based robust recognition of burning states for sintering process control of rotary kiln. In: Joint 48th IEEE conference on decision and control (CDC) and 28th Chinese control conference (CCC 2009), Shanghai, China, pp 398–403
Nguyen DV, Rocke DM (2002) Tumor classification by partial least squares using microarray gene expression data. Bioinformatics 18(1):39–50
Ramrez J, Grriz JM, Segovia F, Chaves R, Salas-Gonzalez D, Lpez M, lvarez I, Padilla P (2010) Computer aided diagnosis system for the Alzheimer’s disease based on partial least squares and random forest SPECT image classification. Neurosci Lett 472(2):99–103
Sharma A, Imoto S, Miyano S, Sharma V (2011) Null space based feature selection method for gene expression data. Int J Mach Learn Cybern. doi:10.1007/s13042-011-0061-9
Tang J, Zhao LJ, Yue H, Chai TY (2010) Present status and future developments of detection method for mill load. Control Eng China 17(5):565–570
Tang J, Zhao LJ, Zhou JW, Yue H, Chai TY (2010) Experimental analysis of wet mill load based on vibration signals of laboratory-scale ball mill shell. Miner Eng 23(9):720–730
Tang J, Zhao LJ, Yu W, Yue H, Chai TY (2010) Soft sensor modeling of ball mill load via principal component analysis and support vector machines. Lect Notes Electr Eng 67:803–810
Tong DL, Mintram R (2010) Genetic algorithm-neural network (GANN): a study of neural network activation functions and depth of genetic algorithm search applied to feature selection. Int J Mach Learn Cybern 1(1–4):75–87
Wang L (2008) Feature selection with kernel class separability. IEEE Trans Pattern Anal Mach Intell 30(9):1534–1546
Wang ZH, Chen BC (2001) Present state and development trend for ball mill load measurement. Chin Powder Sci Technol (Chinese) 7(1):19–23
Wang XZ, Chen AX, Feng HM (2011) Upper integral network with extreme learning mechanism. Neurocomputing 74(16):2520–2525
Wang XZ, Dong CR (2009) Improving generalization of fuzzy if-then rules by maximizing fuzzy entropy. IEEE Trans Fuzzy Syst 17(3):556–567
Wang XZ, Dong LC, and Yan JH (2011) Maximum ambiguity based sample selection in fuzzy decision tree induction. IEEE Trans Knowl Data Eng. doi:10.1109/TKDE.2011.67
Wu J, Wang ST, Chung FL (2011) Positive and negative fuzzy rule system, extreme learning machine and image classification. Int J Mach Learn Cybern 2(4):261–271
Yu W, Li XO (2008) On-line fuzzy modeling via clustering and support vector machines. Inf Sci 178(22):4264–4279
Zeng Y, Forssberg E (1993) Monitoring grinding parameters by signal measurements for an industrial ball mill. Int J Miner Process 40(1):1–16
Zeng Y, Forssberg E (1994) Monitoring grinding parameters by vibration signal measurement-a primary application. Miner Eng 7(4):495–501
Zeng XQ, Li GZ, Wu G (2007) On the number of partial least squares components in dimension reduction for tumor classification. Lect Notes Bioinforma 4819:206–217
Zhou P, Chai TY (2008) Intelligent monitoring and control of mill load for grinding processes. Chin Control Theory Appl 25(66):1095–1099
Zhou P, Chai TY, Wang H (2009) Intelligent optimal-setting control for grinding circuits of mineral processing. IEEE Trans Autom Sci Eng 6(4):730–743
Acknowledgments
The authors would like to express their thanks to Mr. Weitao Li from Northeastern University, who helped in word processing and proof reading. The second author thanks the support from the matching grant for 1000 Talent Program under Grant No. P201100020.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tang, J., Wang, D. & Chai, T. Predicting mill load using partial least squares and extreme learning machines. Soft Comput 16, 1585–1594 (2012). https://doi.org/10.1007/s00500-012-0819-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-012-0819-3