Abstract: Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volumeratio. Latent features are first extracted fromdifferent vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposedmodeling approach has better prediction performance than previous ones.

Key words: Nonlinear latent feature extraction, Kernel partial least squares, Selective ensemble modeling, Least squares support vector machines, Material to ball volume ratio

摘要： Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volumeratio. Latent features are first extracted fromdifferent vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposedmodeling approach has better prediction performance than previous ones.

关键词: Nonlinear latent feature extraction, Kernel partial least squares, Selective ensemble modeling, Least squares support vector machines, Material to ball volume ratio