ORIGINAL PAPER
Method of vibration signal processing and load-type identification of a mill based on ACMD-SVD
1
Jiangxi University of Science and Technology
Submission date: 2022-09-05
Final revision date: 2022-10-30
Acceptance date: 2022-12-08
Publication date: 2023-03-22
Gospodarka Surowcami Mineralnymi – Mineral Resources Management 2023;39(1):217-233
KEYWORDS
TOPICS
ABSTRACT
Green mine construction is the main melody of mining development and problems such as safe production, energy saving and consumption reduction need to be solved urgently. The working conditions of the mill are complex in the process of grinding. Aiming at the problems existing in the feature extraction and load prediction of the mill, a signal-processing method based on adaptive chirp mode decomposition (ACMD) and a standardized variable distance classifier (SVD) is proposed. Firstly, the recursive framework of the ACMD method is used to obtain the initial frequency of mill vibration signals. Secondly, the initial frequency is used to reconstruct the high-resolution component of the mill vibration signal through the iterative frame in the ACMD method. The frequency corresponding to the frequency domain peak of the reconstructed signal is then selected as the mill load feature vector. Finally, with consideration to the influence of standard deviation and standardized variable factors on the feature vectors, a standardized variable distance classifier is proposed. The feature vectors of the mill load are input into the SVD model for training, and the state types of the mill load are obtained. The method is applied to the grinding experiment and the results show that the frequency-domain features obtained by the mill vibration signal-processing method based on ACMD-SVD are obvious, which has high accuracy in the identification of mill load types, and provides a new idea for the extraction of mill load features and prediction of the mill load.
ACKNOWLEDGEMENTS
This work was supported by the key R&D project of Jiangxi Provincial Science and Technology Department (No. 20181ACE50034), in part by the Science and Technology project of Jiangxi Provincial Education Department (No. 200827). The authors are very grateful for this generous support.
METADATA IN OTHER LANGUAGES:
Polish
Metoda przetwarzania sygnału drganiowego i identyfikacji typu obciążenia młyna na podstawie ACMD-SVD
informacja o cechach, obciążenie młyna, ACMD, SVD, wektor cech
Budowa zielonej kopalni jest główną melodią rozwoju górnictwa, a problemy takie jak: bezpieczna produkcja, oszczędność energii i redukcja zużycia wymagają pilnego rozwiązania. Warunki pracy młyna w procesie mielenia są złożone. Mając na celu rozwiązanie problemów występujących w ekstrakcji cech i przewidywaniu obciążenia młyna, zaproponowano metodę przetwarzania sygnału opartą na dekompozycji w trybie adaptacyjnym ACMD (Adaptive Chirp Made Decomposition) i znormalizowanym klasyfikatorze zmiennej odległości SVD (Variable Distance Classifier). Po pierwsze, rekurencyjna struktura metody ACMD jest wykorzystywana do uzyskania początkowej częstotliwości sygnałów drgań młyna. Po drugie, częstotliwość początkowa jest wykorzystywana do rekonstrukcji wysokorozdzielczej składowej sygnału drgań młyna poprzez ramkę iteracyjną w metodzie ACMD. Częstotliwość odpowiadająca pikowi w dziedzinie częstotliwości rekonstruowanego sygnału jest następnie wybierana jako wektor cech obciążenia młyna. Na koniec, biorąc pod uwagę wpływ odchylenia standardowego i standaryzowanych czynników zmiennych na wektory cech, zaproponowano standaryzowany klasyfikator odległości o zmiennej długości. Wektory cech obciążenia młyna są wprowadzane do modelu SVD w celu uczenia i uzyskiwane są typy stanu obciążenia młyna. Metodę zastosowano w eksperymencie mielenia, a wyniki pokazują, że cechy w dziedzinie częstotliwości uzyskane za pomocą metody przetwarzania sygnału drgań młyna opartej na ACMD-SVD są oczywiste, co ma wysoką dokładność w identyfikacji typów obciążeń młyna i zapewnia nowy pomysł na ekstrakcję cech obciążenia młyna i predykcję obciążenia młyna.
REFERENCES (27)
1.
Cai et al. 2019 – Cai, G., Zong, L., Luo, X. and Hu, X. 2019. Research on mill load prediction based on characteristic entropy of CEEMDAN- cloud model and LSSVM. Vibration and Impact 38(07), pp. 128–133.
2.
Cai et al. 2020 – Cai, G., Zhao, X., et al. 2020. Soft-sensing method of wet mill load based on ASOS-ELM. Vibration. Testing and Diagnosis 40(01), pp. 184–192+211.
3.
Chen et al. 2019 – Chen, S., Yang, Y., Peng, Z., Wang, S., Zhang, W. and Chen, X. 2019. Detection of rub-impact fault for rotor-stator systems: A novel method based on adaptive chirp mode decomposition. Journal of Sound and Vibration 440.
4.
Elen et al. 2021 – Elen, A. and Emre, A. 2021. Standardized Variable Distances: A distance-based machine learning method. Applied Soft Computing Journal 98, DOI: 10.1016/j.asoc.2020.106855.
5.
Gao et al. 2020 – Gao, C., Zhou, X. and Huang, X. 2020. Mill load identification based on CEEMDAN- multiscale fuzzy entropy and ISRNN. Mining Research and Development 40(04), pp. 141–146.
6.
He et al. 2019 – He, M., Zhi, E., Cheng, L. and Yan, G. 2019. Soft-sensing of mill load parameters based on multi--load transfer learning. Control Engineering 26(11), pp. 1994–1999.
7.
Li, J. 2020. Research on mill load detection method based on audio analysis. Chongqing University of Posts and Telecommunications.
8.
Liao et al. 2008 – Liao, T.W., Tang, F., Qu, J. and Blau, P.J. 2008. Grinding wheel condition monitoring with boosted minimum distance classifiers. Mechanical Systems and Signal Processing 22(1), pp. 217–232, DOI: 10.1016/j.ymssp.2007.06.005.
9.
Liu et al. 2015 – Liu, Z., Chai, T.Y., Yu, W. and Tang, J. 2015. Multi-frequency signal modeling using empirical mode decomposition and PCA with application to mill load estimation. Neurocomputing 169, pp. 392–402, DOI: 10.1016/j.neucom.2014.08.087.
10.
Lu, X. 2017. Research on mill load forecasting method based on multi-source signal fusion technology. Jiangxi University of Science and Technology.
11.
Luo et al. 2019 – Luo, X., Lu Wenhai, et al. 2019. Random noise suppression of mill vibration signal based on VMD and SVD joint noise reduction method. Noise and Vibration Control 39(06), pp. 169–175+216.
12.
Luo et al. 2019 – Luo, X., Shao, F., Wai, M.C. and Lu, X. 2019. Research on mill load forecasting method based on multi-source signal fusion. Vibration and Impact 38(08), pp. 232–237.
13.
Ma et al. 2005 – Ma, P., Du, H.-L. and Feng Lv. 2005. Coal mass estimation of the coal mill based on two-step multi-sensor fusion. International Conference on Machine Learning and Cybernetics, pp. 1307–1311, DOI: 10.1109/ICMLC.2005.1527145.
14.
Ma et al. 2021 – Ma, Z., Lu, F., Liu, S.et al. 2021. A parameter-adaptive ACMD method based on particle swarm optimization algorithm for rolling bearing fault diagnosis under variable speed. Journal of Mechanical Science and Technology 35, pp. 1851–1865, DOI: 10.1007/s12206-021-0405-7.
15.
Qing et al. 2020 – Qing, Z., Gao, Y., Wu, C., Yang, J. and Wang, Q. 2020. Feature extraction of mill load based on adaptive VMD and improved power spectrum estimation. Chinese journal of scientific instrument 41(05), pp. 234–241.
16.
Tang et al. 2010 – Tang, J., Zhao, L., Yue, H. and Chai, T. 2010. Vibration signal analysis and load soft measurement of wet mill barrel. Journal of Northeastern University (Natural Science Edition) 31(11), pp. 1521–1524.
17.
Tang et al. 2014 – Tang, J., Chai, T., et al. 2014. Soft sensor of mill load parameters based on EMD and selective ensemble learning algorithm. Acta automatica sinica 40(09), pp. 1853–1866, DOI: 10.3724/SP.J.1004.2014.01853.
18.
Wang et al. 2015 – Wang, H., Hua, G., Jia, M., et al. 2015. Dynamic soft sensing of ball mill level based on LS-SVM and GM. Thermal Power Generation 44(1), pp. 77–81.
19.
Wang et al. 2021 – Wang, T., Zou, W., Xu, R., Xu, H., Tao, L., Zhao, J. and He, Y. 2021. Assessing load in ball mill using instrumented grinding media. Minerals Engineering 173, DOI: 10.1016/j.mineng.2021.107198.
20.
Wang et al. 2021 – Wang, X., Sun, K., Zhang, H., Xiong, W. and Yang, C. 2021. Mill Load Identification Method for Ball milling Process Based on Grinding Signal. IFAC-PapersOnLine 54(21), pp. 7–12, DOI: 10.1016/j.ifacol.2021.12.002.
21.
Wang et al. 2022 – Wang, J., Li, F., Du, W. and Wang, Z. 2022. Rolling bearing diagnosis method based on improved standardized variable distance fusion hierarchical state space correlation entropy. Measurement Science and Technology 33(1), DOI: 10.1088/1361-6501/ac2bc2.
22.
Xu et al. 2022 – Xu, H., Wang, T., Zou, W., Zhao, J., Tao, L. and Zhijun, Z. 2022. Ball mill load identification method based on intelligent grinding medium and CNN and optimized SVM model. Journal of Engineering Science 44(11), pp. 1821–1831.
23.
Yang, L. and Cai, J. 2021. A method to identify wet ball mill’s load based on CEEMDAN, RCMDE and SRNN classification. Minerals Engineering 165, DOI: 10.1016/j.mineng.2021.106852.
24.
Yang et al. 2020 – Yang, Q., Ruan, J. and Zhuang, Z. 2020. Fault diagnosis for circuit-breakers using adaptive chirp mode decomposition and attractor’s morphological characteristics. Mechanical Systems and Signal Processing 145, DOI: 10.1016/j.ymssp.2020.106921.
25.
Yun Y. 2020. Assessing the criticality of minerals used in emerging technologies in China. Gospodarka Surowcami Mineralnymi – Mineral Resources Management 36(2), pp. 5–20, DOI: 10.24425/gsm.2020.132559.
26.
Yao et al. 2022 – Yao, H., Li, C., Zheng, X. and Yang, P. 2022. A combined short-term load forecasting model integrating adaptive chirped modal decomposition and Bi LSTM. Power System Protection and Control 50(19), pp. 58–66.
27.
Zhao et al. 2014 – Zhao, L., Yang, H., Feng, X., Tang, J. and Yuan, D. 2014. Integrated modeling method of mill load parameters based on EEMD and iPLS. Process Control Committee of China Automation Society. Proceedings of 25th China Process Control Conference. Process Control Committee of China Automation Society: China Automation Society 8.
| 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.
