Multi-classification of Ball Mill Load Status Using Vibration Frequency Spectrum
نویسندگان
چکیده
On-line monitoring and recognition of mill load status has significant effect on the operating efficiency, product quality and energy consumption for the milling circuit. Due to low reliability to recognize the operating states near the boundary region, a multiclassification model is built to identify the operating status of ball mill load. Spectrum features of shell vibration signals are extracted using kernel principal component analysis as input of the multi-classification model. Partial least square-based extreme learning machine model predicts the output coding of ball mill load status. Bayesian decision theory further enhances the reliability and accuracy of the classification model. The proposed method is compared with one-against-one multi-classification strategy and verified with the experimental ball mill. Experimental results show the accuracy and stability of the proposed multi-classification model of ball mill load status outperforms multi-classification with one-against-one strategy.
منابع مشابه
Soft Sensor Modeling of Mill Load Based on Feature Selection Using Synergy Interval Pls
Mill load is an important equipment index which is closely related to operating efficiency, product quality and energy consumption of grinding process. Due to high dimension and collinearity of spectral data, mill load model has high complexity, poor interpretability and generalization. A soft sensor modeling method of mill load parameters is proposed based on frequency spectrum feature using S...
متن کاملEnsemble Modeling of Mill Load Based on Empirical Mode Decomposition and Partial Least Squares
Reliable measurements of ball mill load parameters and reorganization of the operating statuses are the key factors for saving energy and optimization control. Empirical mode decomposition (EMD) and partial least squares (PLS) are used to analyze shell vibration signal and monitor mill load parameters of ball mill. The shell vibration signal is decomposed into several intrinsic mode functions (...
متن کاملMulti-Channel Vibration Feature Extraction of Ball Mill Using Synchronized Wavelet Based Multi-Scale Principal Component Analysis
The trait of the ball mill is chaotic in nature due its complex dynamics associated during grinding. Grinding in ball mill generates high-intensity vibration and is too complex on account dependency of multiple variables. In this paper, the vibration signal is acquired using a low power ZigBee based three axes wireless MEMS accelerometer sensor mounted onto the mill shell. Firstly, the exact fr...
متن کاملKPCA Based Multi-Spectral Segments Feature Extraction and GA Based Compound Optimization for Frequency Spectrum Data Modeling
Mill load (ML) estimation plays a major role in improving the grinding production rate (GPR) and the product quality of the grinding process. The ML parameters, such as mineral to ball volume ratio (MBVR), pulp density (PD) and charge volume ratio (CVR), reflect the load inside the ball mill accurately. The relative amplitudes of the high-dimensional frequency spectrum of shell vibration signal...
متن کاملSoft sensor for parameters of mill load based on multi-spectral segments PLS sub-models and on-line adaptive weighted fusion algorithm
The parameters of mill load (ML) not only represent the load of the ball mill, but also determine the grinding production ratio (GPR) of the grinding process. In this paper, a novel soft sensor approach based on multi-spectral segments partial least square (PLS) model and on-line adaptive weighted fusion algorithm is proposed to estimate the ML parameters. At first, frequency spectrums of the s...
متن کامل