ORIGINAL PAPER
Load identification method of ball mill based on the CEEMDAN-wavelet threshold-PMMFE
1
Jiangxi Mining and Metallurgical Engineering Research Center, China
2
School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi Province, China
Submission date: 2023-11-11
Final revision date: 2023-12-26
Acceptance date: 2024-04-25
Publication date: 2024-06-24
Corresponding author
Gospodarka Surowcami Mineralnymi – Mineral Resources Management 2024;40(2):163-180
KEYWORDS
TOPICS
Scientific background of mineral resource managementOptimization of resources and reserves managementPreparation and processing of mineral raw materialsRational use of mineral raw materials
ABSTRACT
In order to address the difficult problem of ball mill load identification during milling operation, the multi-scale fuzzy entropy algorithm is introduced into ball mill load identification and an innovative ball mill load identification method is proposed- the complete integrated empirical decomposition based on adaptive noise (CEEMDAN)-joint denoising with wavelet thresholding-multi-scale fuzzy entropy biased mean value (PMMFE) ball mill load identification method. Firstly, the vibration signals of ball mill bearings are denoised by the CEEMDAN-wavelet threshold joint denoising method and the analysis reveals that this method has obvious advantages over other denoising methods; secondly, the fuzzy entropy, multi-scale fuzzy entropy, and multi-scale fuzzy entropy deviation of denoised vibration signals are computed, the relationship between each entropy feature and the mill load is analysed in-depth and in an information-rich manner. Finally, the least squares support vector algorithm is used to identify the load of the feature vector. The analysis of the measured vibration signals reveals that the overall recognition rate of this method is 84.4%, which is significantly higher than that of other denoising methods and the combination of feature parameters, and the experiments show that the mill load recognition method based on CEEMDAN-wavelet thresholding-PMMFE is able to effectively identify the different loading states of ball mills.
ACKNOWLEDGEMENTS
This work was supported by the General Project of Ganzhou Key R&D Programme (grant number 20210112411).
METADATA IN OTHER LANGUAGES:
Polish
Metoda identyfikacji obciążenia młyna kulowego w oparciu o CEEMDAN – próg falkowy – PMMFE
obciążenie młyna, sygnał drgań łożyska, próg CEEMDAN-fala, PMMFE, identyfikacja obciążenia
W celu rozwiązania trudnego problemu identyfikacji obciążenia młyna kulowego podczas operacji mielenia, do identyfikacji obciążenia młyna kulowego wprowadzono wieloskalowy algorytm entropii rozmytej oraz zaproponowano innowacyjną metodę identyfikacji obciążenia młyna kulowego – pełną zintegrowaną dekompozycję empiryczną opartą na szumie adaptacyjnym (CEEMDAN) – wspólne odszumianie z progowaniem falkowym – wieloskalowa metoda identyfikacji obciążenia młyna kulowego metodą rozmytej entropii z odchyleniem wartości średniej (PMMFE). Po pierwsze, sygnały wibracyjne łożysk młyna kulowego są odszumiane za pomocą wspólnej metody odszumiania CEEMDAN z progowaniem falkowym, a analiza pokazuje, że metoda ta ma oczywiste zalety w porównaniu z innymi metodami odszumiania; po drugie, obliczana jest rozmyta entropia, wieloskalowa rozmyta entropia i wieloskalowe rozmyte odchylenie entropii odszumionych sygnałów wibracyjnych, a związek między każdą cechą entropii a obciążeniem młyna jest analizowany dogłębnie i w sposób bogaty w informacje. Na koniec, algorytm wektora wsparcia najmniejszych kwadratów jest wykorzystywany do identyfikacji obciążenia wektora cech. Analiza zmierzonych sygnałów wibracyjnych pokazuje, że ogólny wskaźnik rozpoznawania tej metody wynosi 84,4%, co jest znacznie wyższe niż w przypadku innych metod odszumiania i kombinacji parametrów cech, a eksperymenty pokazują, że metoda rozpoznawania obciążenia młyna oparta na progowaniu falkowym CEEMDAN-PMMFE jest w stanie skutecznie identyfikować różne stany obciążenia młynów kulowych.
REFERENCES (21)
1.
Cai et al. 2017 – Cai, G., Zhao, X., Hu, X., Huang, X. and Chen, H. 2020. Denoising Method of Vibration Signal of Ball Mill based on CEEMDAN-wavelet Threshold Combination. Mechanical Science and Technology for Aerospace Engineering 39(7), pp. 1077–1085, DOI: 10.13433/j.cnki.1003-8728.20190241.
2.
Chang et al. 2023 – Chang, Y., Zhu, Z., Tang, Y., et al. 2023. Wind power prediction model based on CEEMD and improved SSA-LSSVM. Sensors and Microsystems 42(10), pp. 130–134.
3.
Chen et al. 2009 – Chen W., Jun, Z., Yu, W. and Wang, Z. 2009. Measuring complexity using FuzzyEn, ApEn, and SampEn. Medical Engineering and Physics 31(1), pp. 61–68, DOI: 10.1016/j.medengphy.2008.04.005.
4.
Donoho, D.L. and Johnstone, I.M. 1994. Ideal Spatial Adaptation by Wavelet Shrinkage. Biometrika 81(3), pp. 425–455, DOI: 10.1093/biomet/81.3.425.
5.
Kononerko, I. 1994. Estimating attributes: analysis and extension of Relief. [In:] Proceedings of European conference on machine learing, Springer-Verlag New York, pp. 171–182.
6.
Li et al. 2016 – Li, B., Cheng, J., Wu, Z., et al. 2016. Gear fault diagnosis method based on the adaptive and sparsest time-frequency analysis method and partial mean multi-scale fuzzy entropy. Journal of Vibration Engineering 29(5), pp. 928–935.
7.
Luo et al 2016 – Luo, X., Lu, X., Yang, X., et al. 2016. Feature Extraction Method for Ball-mill Bearing’s Vibration Signals Using Wavelet Analysis. Noise and Vibration Control 36(1), pp. 148–152.
8.
Ren et al 2023 – Ren, W., Zan, L. and Li, X. 2023. Coherent orthogonal frequency division multiplexing passive optical network system based on eigenvector construction. Laser Journal 44(3), pp. 195–199.
9.
Tang et al. 2011 – Tang, J., Zhao, L.J., Yue, H., Yu, W. and Chai, T. 2011. Vibration analysis based on empirical mode decomposition and partial least squares. Procedia Engineering 16(1), pp. 646–652, DOI: 10.1016/j.proeng.2011.08.1136.
10.
Tang et al. 2012 – Tang, J., Chai, T., Zhao L.J., Yue, H. and Zheng, X.P. 2012. Ensemble modeling for parameters of ball-mill load in grinding process based on frequency spectrum of shell vibration. Control Theory and Application 29(2), pp. 183–191.
11.
Tang et al. 2013 – Tang, J., Chai, T., Yu, W. and Zhao, L.J. 2013. Modeling load paramters of ball mill in grinding process based on selective ensemble multi sensor information. IEE, Transactions on Automation Science and Engineering 10(3), pp. 726–740, DOI: 10.1109/TASE.2012.2225142.
12.
Tang et al 2014 – Tang, J., Chai, T., Cong, Q. Yuan, M., Zhao, L., Liu, Z. and Yu, W. 2014. Soft measurement of mill load parameters based on EMD and selective integrated learning algorithm. Acta Automatica Sinica 40(9), pp. 1853–1866, DOI: 10.3724/SP.J.1004.2014.01853.
13.
Torres et al. 2011 – Torres M.E., Colominas, M.A., Schlotthauer, G. and Flandrin, P. 2011. A complete ensemble empirical mode decomposition with adaptive noise. IEEE International Conference on Speech and Signal Processing ICASSP, Prague, Czech, pp. 4144–4147, DOI: 10.1109/ICASSP.2011.5947265.
14.
Wang et al. 2019 – Wang, H., Zhao, Y., Zhaohui, et al. 2019. Fault Diagnosis of Wind Turbine Gearbox based on EEMD Wavelet Threshold Denoising and CS-BP Neural Network. Journal of Mechanical Transmission 43(1), pp. 100–106.
15.
Wang et al. 2023 – Wang, R., Wang, Y.Z. and Lu, J. 2023. Photovoltaic power prediction based on ICEEMDAN--DTW and ISMA-WLSSVM. Thermal Power Engineering 38(9), pp. 131–140.
16.
Yang et al. 2015 – Yang, W., Zhang, P., Wang, H., et al. 2015. Gear fault diagnosis based on multiscale fuzzy entropy of EEMD. Journal of Vibration and Shock 34(14), pp. 163–167+187.
17.
Zhao, L. 2014. Integrated modeling method for ball mill load parameters based on EEMD and PLS. Process Control Committee of Chinese Society of Automation. Committee of Process Control, Chinese Society of Automation. Proceedings of the 25th China Process Control Conference. Proceedings of the 25th China Process Control Conference. Process Control Committee of the Chinese Society of Automation: Chinese Society of Automation, pp. 8.
18.
Zhao et al 2017 – Zhao, L.J., Li, B., Wang, Y., et al. 2017. Mill Load Parameter Model Using Fast Decorrelated Neural Network Ensemble. Control Engineering of China 24(09), pp. 1952–1957.
19.
Zheng et al. 2014 – Zheng, J., Chen, M., Cheng, J. and Yang, Y. 2014. Multiscale fuzzy entropy and its application in rolling bearing fault diagnosis. Journal of Vibration Engineering 27(1), pp. 145–15.
20.
Zheng et al. 2016 – Zheng, J., Pan, H., Cheng, J., et al. 2016. Composite multi-scale fuzzy entropy based rolling bearing fault diagnosis method. Journal of Vibration and Shock 35(8), pp. 116–123.
21.
Zhu et al 2023 – Zhu, J., Liu, W., Gao, L. 2023. Exploration and practice of intelligent mineral processing plant. Nonferrous Metals (Mineral Processing Section) 1, pp. 121–126.
| eISSN: | 2299-2324 |
| ISSN: | 0860-0953 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
