Abstract
In cement plant and power plant, ball mills remain in current and widespread use. The load parameter inside a ball mill directly impacts the stability of the production process, the grinding production rate, and the quality of the product in the grinding process. Accurately predicting the load from acoustic signals remains a challenging problem because of the nonlinearity and high dimensions of spectral data. In this paper, the application of fractional Fourier transforms on acoustic signals for estimating mill load parameter was researched. A fractional Fourier transform can give intermediate time-frequency representations by controlling an additional order, and the acoustical frequency spectra in the fractional Fourier domain can provide more information about the load parameters. According to the distribution of acoustic frequency spectra in the fractional Fourier domain, the strategies of predicting ball mill loads were divided into three segments, namely feature extraction, offline modeling, and online monitoring. These techniques included an acoustic signal analysis in different fractional orders, feature extracted based on mutual information and kernel principal component analysis, offline soft measuring modeling compared with other regression models, and online adaptive monitoring based on the optimal fractional order. The experimental investigation of the proposed method demonstrates its effectiveness for estimating mill loads in the fractional Fourier domain by comparing with the result in the Fourier domain.
Highlights
Large tumbling coal ball consumes 40% of their energy in their pulverizing system
In this paper, we propose a series of measurement methods in the fractional Fourier domain for predicting the loads of tumbling ball mills
The performance of the least squares support vector machine (LSSVM), partial least squares (PLS), support vector machines (SVMs), and radial basis function (RBF) were demonstrated for a series of training data sets
Summary
Large tumbling coal ball consumes 40% of their energy in their pulverizing system. most of the energy is wasted in rotating the heavy mill shell and balls. The main characteristics are non-stationary, nonlinear, and multiple components since the complexity of powder mechanism in pulverizing, and finding mill load information in the time domain from it have proved difficult. The relation between mill load information and acoustic signals can be obtained in Fourier frequency domain. J. Shi et al.: Application of Fractional Fourier Transform for Prediction of Ball Mill Loads Using Acoustic Signals duration disturbances and short duration disturbances, they are used to monitor and diagnose working conditions [8]. Since the acoustic spectrum has the dimensionality problem, multi-scale, and multiple component characteristics [2], there are still many challenges on soft sensing mill load parameters, such as how to extract the candidate features from acoustic spectrums, how to select the modeling technology, and how to achieve the online monitoring. Where F(f0) is the impact force caused by the crack of the balls and the coal in the cylinder, He(f0) is the mill shell-response function, a is the weighting coefficient of the A sound level, σrad is the sonic amplitude coefficient, ηs is the damping coefficient, d is the thickness of mill, and B is a constant
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call