Assessing load in ball mill using instrumented grinding media

Abstract Monitoring mill load is vital for the optimization and control of grinding process. This study proposed the use of an instrumented grinding media to assess solid loading inside a ball mill, with size and density of the instrumented ball comparable to that of the ordinary grinding media. The acceleration signal was captured by an embedded triaxial accelerometer. The signal was first detrended by a complete ensemble empirical mode decomposition and then reconstructed using a correlation coefficient method. The filling ratio, particle to ball ratio, time domain features and sample entropy are features extracted from the signal, providing input to a support vector machine (SVM) learning model. Grinding experiments with different loads were conducted. The typical loading level was classified according to grinding efficiency index and associated power consumption. Different methods were adopted to determine the optimal values of parameters in the SVM model, including particle swarm optimizer (PSO), genetic algorithm (GA), and grid search (GS). The results showed that the accuracy of particle swarm optimizer can reach 96.67%. This study demonstrates the potential of using instrumented grinding media for real-time characterization of mill feed and operation monitoring.

[1]  Zhencai Zhu,et al.  Effect of mill speed and slurry filling on the charge dynamics by an instrumented ball , 2019, Advanced Powder Technology.

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

[3]  Measurement of impact forces in ball mills: a reanalysis , 2001 .

[4]  Yaqun He,et al.  Liberation characteristics of coal middlings comminuted by jaw crusher and ball mill , 2013 .

[5]  Jiacheng Cai,et al.  Integrated approach for ball mill load forecasting based on improved EWT, refined composite multi-scale dispersion entropy and fireworks algorithm optimized SVM , 2021 .

[6]  Peter Radziszewski,et al.  Experimental and simulated instrumented ball in a tumbling mill—A comparison , 2013 .

[7]  Lei Wang,et al.  Multi-information online detection of coal quality based on machine vision , 2020 .

[8]  Zelin Zhang.  Particle overlapping error correction for coal size distribution estimation by image analysis , 2016 .

[9]  Malcolm Powell,et al.  A three-dimensional analysis of media motion and grinding regions in mills , 2004 .

[10]  Gangquan Si,et al.  Feature extraction based on the fractional Fourier transform for vibration signals with application to measuring the load of a tumbling mill , 2019, Control Engineering Practice.

[11]  Tan Jianping,et al.  Rope Tension Fault Diagnosis in Hoisting Systems Based on Vibration Signals Using EEMD, Improved Permutation Entropy, and PSO-SVM. , 2020 .

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

[14]  R. X. Gao,et al.  Sensor-Integrated Grinding Balls for on-Line Load Distribution Measurement in Ball Mills , 1994 .

[15]  Qian Zhang,et al.  Short-Term Load Forecasting Method Based on EWT and IDBSCAN , 2020, Journal of Electrical Engineering & Technology.

[16]  Norden E. Huang,et al.  Complementary Ensemble Empirical Mode Decomposition: a Novel Noise Enhanced Data Analysis Method , 2010, Adv. Data Sci. Adapt. Anal..

[17]  Luo,et al.  Load State Identification Method for Ball Mills Based on Improved EWT, Multiscale Fuzzy Entropy and AEPSO_PNN Classification , 2019, Processes.

[18]  Bin Wang,et al.  Classification of spot‐welded joint strength using ultrasonic signal time‐frequency features and PSO‐SVM method , 2019, Ultrasonics.

[19]  Jian Tang,et al.  Ball Mill Load State Recognition Based on Kernel PCA and Probabilistic PLS-ELM , 2012 .

[20]  V. Kreinovich,et al.  Why 70/30 or 80/20 Relation Between Training and Testing Sets: A Pedagogical Explanation , 2018 .

[21]  Peter Radziszewski,et al.  Validating the instrumented ball outputs with simple trajectories , 2008 .

[22]  Junfei Qiao,et al.  Mechanism characteristic analysis and soft measuring method review for ball mill load based on mechanical vibration and acoustic signals in the grinding process , 2018, Minerals Engineering.

[23]  Gaowei Yan,et al.  Experimental analysis of wet mill load parameter based on multiple channel mechanical signals under multiple grinding conditions , 2020 .

[24]  R. A. Pax.  Non contact acoustic measurement in mill variables of SAG mills , 2001 .

[26]  Li Zhang,et al.  Prediction of Rolling Load in Hot Strip Mill by Innovations Feedback Neural Networks , 2007 .

[27]  A method to identify wet ball mill’s load based on CEEMDAN, RCMDE and SRNN classification , 2021 .

[28]  Yanbin Zhang,et al.  Ball Mill Load Measurement Using Self-adaptive Feature Extraction Method and LS-SVM Model , 2008, ICIC.

[29]  He Zhang,et al.  Hand Gesture Recognition of Double-Channel EMG Signals Based on Sample Entropy and PSO-SVM , 2020 .

[30]  Chai Tian-you.  Present Status and Future Developments of Detection Method for Mill Load , 2010 .

[31]  Carlos A. Carballo-Monsivais,et al.  Vibration analysis in bearings for failure prevention using CNN , 2020, Journal of the Brazilian Society of Mechanical Sciences and Engineering.

[32]  Cong Wu,et al.  Feature Extraction Method of Ball Mill Load Based on Adaptive Variational Mode Decomposition and Improved Power Spectrum Analysis , 2020 .

[33]  Jian Tang,et al.  Mill Load Parameter Forecasting Based on Multi-source Single-scale Mechanical Frequency Spectral Multiple feature Subsets , 2018 .

[34]  Xiaopeng Guo,et al.  Improved Support Vector Machine Oil Price Forecast Model Based on Genetic Algorithm Optimization Parameters , 2012 .

[35]  Michael H. Moys,et al.  Optimisation of the secondary ball mill using an on-line ball and pulp load sensor – The Sensomag , 2011 .

[36]  M. Valyrakis,et al.  A Sensory Instrumented Particle for Environmental Monitoring Applications: Development and Calibration , 2021, IEEE Sensors Journal.