Feature extraction and selection based on vibration spectrum with application to estimating the load parameters of ball mill in grinding process

Feature extraction and selection are important issues in soft sensing and complex nonlinear system modeling. In this paper, a new feature extraction and selection approach based on the vibration frequency spectrum is proposed to estimate the load parameters of wet ball mill in grinding process. This approach can simplify the modeling process. In this study, the vibration acceleration signals are first transformed into the frequency spectrum by fast Fourier transform (FFT). Then the candidate features are extracted and selected from the frequency spectrum, which include characteristic frequency sub-bands, spectral principal components, and features of local peaks. Mutual information, spectral segment clustering and kernel principal component analysis are used to obtain these candidate features. Finally, a combinatorial optimization method based on adaptive genetic algorithm selects the input sub-set and parameters of the soft sensor model simultaneously. This approach is successfully applied in a laboratory scale wet ball mill. The test results show that the proposed approach is effective for modeling the parameters of mill load.

[1]  Richard E. Grandy,et al.  Orlando, Florida, USA , 2011 .

[2]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[3]  T. O. Olsen,et al.  Automatic Control of Continuous Autogenous Grinding , 1976 .

[4]  I. Iwasaki,et al.  Nature of corrosive and abrasive wear in ball mill grinding , 1988 .

[5]  Tianyou Chai,et al.  Modeling of operating parameters for wet ball mill by modified GA-KPLS , 2010, Third International Workshop on Advanced Computational Intelligence.

[6]  Gangquan Si,et al.  Experimental investigation of load behaviour of an industrial scale tumbling mill using noise and vibration signature techniques , 2009 .

[7]  Yigen Zeng,et al.  Monitoring grinding parameters by signal measurements for an industrial ball mill , 1993 .

[8]  Xiaowei Yang,et al.  An efficient gene selection algorithm based on mutual information , 2009, Neurocomputing.

[9]  Wang Ze.  Present State and Development Trend for Ball Mill Load Measurement , 2001 .

[10]  Tianyou Chai,et al.  The intelligent setting control of the mill load in pulverizing system for an alumina sintering process , 2009, Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference.

[11]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[12]  Michel Verleysen,et al.  Spectrophotometric variable selection by mutual information , 2004 .

[13]  I. Jolliffe.  Principal Component Analysis , 2002 .

[14]  Lalit M. Patnaik,et al.  Adaptive probabilities of crossover and mutation in genetic algorithms , 1994, IEEE Trans. Syst. Man Cybern..

[15]  Biao Huang,et al.  Spectral principal component analysis of dynamic process data , 2002 .

[16]  Keinosuke Fukunaga,et al.  Effects of Sample Size in Classifier Design , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Yigen Zeng,et al.  Monitoring grinding parameters by vibration signal measurement - a primary application , 1994 .

[18]  J. Tang,et al.  Feature extraction and selection based on vibration spectrum with application to mill load modeling , 2011, 2011 International Symposium on Advanced Control of Industrial Processes (ADCONIP).

[19]  S. Qin,et al.  Selection of the Number of Principal Components: The Variance of the Reconstruction Error Criterion with a Comparison to Other Methods† , 1999 .

[20]  Sheng Liu,et al.  Stereo vision camera calibration based on AGA-LS-SVM algorithm , 2010, 2010 8th World Congress on Intelligent Control and Automation.

[21]  Chai Tianyou.  Intelligent monitoring and control of mill load for grinding processes , 2008 .

[22]  Debi Prasad Das,et al.  Interpretation of mill vibration signal via wireless sensing , 2011 .

[23]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Luis O. Jimenez-Rodriguez,et al.  Unsupervised Linear Feature-Extraction Methods and Their Effects in the Classification of High-Dimensional Data , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Wen Yu,et al.  Soft Sensor Modeling of Ball Mill Load via Principal Component Analysis and Support Vector Machines , 2010 .

[26]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[27]  Douglas M. Hawkins,et al.  The Problem of Overfitting , 2004, J. Chem. Inf. Model..

[28]  Jialin Liu,et al.  On-line soft sensor for polyethylene process with multiple production grades , 2007 .

[29]  Lei Wang,et al.  Feature Selection with Kernel Class Separability , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Junya Kano,et al.  Ball mill simulation in wet grinding using a tumbling mill and its correlation to grinding rate , 2004 .

[31]  Jian Tang,et al.  Experimental analysis of wet mill load based on vibration signals of laboratory-scale ball mill shell , 2010 .

[32]  Tianyou Chai,et al.  Intelligent Optimal-Setting Control for Grinding Circuits of Mineral Processing Process , 2009, IEEE Transactions on Automation Science and Engineering.

[33]  Chai Tianyou.  Intelligent mill-load control for pulverizing system in alumina sintering process , 2010 .

[34]  Bogdan Gabrys,et al.  Data-driven Soft Sensors in the process industry , 2009, Comput. Chem. Eng..

[35]  Chai Tianyou.  Optimization control of ball mill load in blending process with data fusion and case-based reasoning , 2009 .

[36]  Yigen Zeng,et al.  Effects of operating parameters on vibration signal under laboratory scale ball grinding conditions , 1992 .

[37]  R. Leardi,et al.  Variable selection for multivariate calibration using a genetic algorithm: prediction of additive concentrations in polymer films from Fourier transform-infrared spectral data , 2002 .

[38]  Hideyuki Otaki,et al.  Motion analysis of a tumbling ball mill based on non-linear optimization , 2000 .

[39]  K. Gugel,et al.  Improving ball mill control with modern tools based on digital signal processing (DSP) technology , 2003, Cement Industry Technical Conference, 2003. Conference Record. IEEE-IAS/PCA 2003.

[40]  Steven J. Spencer,et al.  Acoustic emissions monitoring of SAG mill performance , 1999, Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296).

[41]  Jian Tang,et al.  KPCA based multi-spectral segments feature extraction and GA based Combinatorial optimization for frequency spectrum data modeling , 2011, IEEE Conference on Decision and Control and European Control Conference.

[42]  C. V. R. Murty,et al.  Experimental analysis of charge dynamics in tumbling mills by vibration signature technique , 2007 .

[43]  Lei Tian,et al.  A genetic-algorithm-based selective principal component analysis (GA-SPCA) method for high-dimensional data feature extraction , 2003, IEEE Trans. Geosci. Remote. Sens..

[44]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .