Abstract
Wear is an inevitable problem in abrasive belt grinding, and the material removal rate decreases with continuous wear of the abrasive belt. This indicates that the grinding control force is affected by two dynamic factors, namely the actual material removal and abrasive belt wear state. To obtain an accurate force-control model to achieve uniform material removal, a new method for online monitoring of abrasive belt material removal rates and their corresponding wear statuses is proposed herein using only the grinding sound signals. By performing material removal rate and abrasive belt wear experiments, the grinding sound signals during processing are obtained. The wear states of the abrasive belt are quantified using the newly defined gray-mean values of the topographical images of the belt into different levels. The grinding sound signals are quantitatively described via the statistical features of their sound wavelet signals. The statistical features related to material removal rates or belt wear states are selected on the basis of the Pearson correlation coefficients. The prediction models for material removal rate and wear levels of the abrasive based on the selected features are then established using the LightGBM learning algorithm. Experimental datasets are used to train and validate the established model. The test results show that the evaluation parameters of the prediction model of the material removal rate are all within 5%. Further, the accuracy of the wear levels of the abrasive belt can exceed 91%. Compared with other prediction models, the new LightGBM models exhibit superiority in terms of time factor without loss of accuracy of the model. It is thus proved that the proposed method can provide a good basis for monitoring the material removal rate and belt wear in the abrasive belt grinding process.
Similar content being viewed by others
References
Wang YJ, Huang Y, Chen YX, Yang ZS (2016) Model of an abrasive belt grinding surface removal contour and its application. Int J Adv Manuf Technol 82(9–12):2113–2122
Uhlmann E, Lypovka P, Hochschild L, Schröer N (2016) Influence of rail grinding process parameters on rail surface roughness and surface layer hardness. Wear 366–367:287–293
Wang RQ, Li JY, Liu YM, Wang WX (2016) Modeling material removal rate of heavy belt-grinding in manufacturing of U71Mn material. Key Eng Mater 693:1082–1089
Yang ZY, Xu XH, Zhu DH, Yan SJ, Ding H (2019) On energetic evaluation of robotic belt grinding mechanisms based on single spherical abrasive grain model. Int J Adv Manuf Technol 104(9–12):4539–4548
Wuest T, Irgens C, Thoben K (2014) An approach to monitoring quality in manufacturing using supervised machine learning on product state data. J Intell Manuf 25(5):1167–1180
Wang GL, Zhou XQ, Yang X, Zhou HB, Chen GG (2015) Material removal profile for large mould polishing with coated abrasives. Int J Adv Manuf Technol 80(1–4):625–635
Duan JH, Zhang YM, Shi YY (2016) Belt grinding process with force control system for blade of aero-engine. Proc Inst Mech eng 230(5):1–11
Wang YQ, Hou B, Wang FB, Ji ZC (2017) A controllable material removal strategy considering force-geometry model of belt grinding processes. Int J Adv Manuf Technol 93(1–4):241–251
Song YX, Liang W, Yang Y (2012) A method for grinding removal control of a robot belt grinding system. J Intell Manuf 23(5):1903–1913
Hamann G (1998) Modeling of the removal behavior of elastic robot-guided grinding tools. University Stuggart, Stuttgart
Cabaravdic B, Kuhlenköetter (2005) Belt grinding processes optimization. Mo Metal loberfläche 4:44–47
Ren X, Cabaravdic M, Zhang X, Kuhlenkötter B (2007) A local process model for simulation of robotic beltgrinding. Int J Mach Tool Manu 47(6):962–970
Wang W, Liu F, Liu Z, Yun C (2011) Prediction of depth of cut for robotic belt grinding. Int J Adv Manuf Technol 91(1–4):699–708
Ren X, Kuhlenkötter B (2008) Real-time simulation and visualization of robotic belt grinding processes. Int J Adv Manuf Technol 35:1090–1099
Gao KY, Chen HB, Zhang XQ, Ren XK, Chen XQ (2019) A novel material removal prediction method based on acoustic sensing and ensemble XGBoost learning algorithm for robotic belt grinding of Inconel 718. Int J Adv Manuf Technol 105(1–4):217–232
Ren LJ, Zhang GP, Wang Y, Zhang Q, Huang YM (2019) A new in-process material removal rate monitoring approach in abrasive belt grinding. Int J Adv Manuf Technol 104(2):2715–2726
Zhang XQ, Chen HB, Xu JJ, Song XF, Wang JW, Chen XQ (2018) A novel sound-based belt condition monitoring method for robotic grinding using optimally pruned extreme learning machine. J Mater Process Technol 260:9–19
Pandiyan V, Caesarendra W, Tjahjowidodo T, Praveen G (2017) Predictive modelling and analysis of process parameters on material removal characteristics in abrasive belt grinding process. Appl Sci 7(4):363
Cheng C, Li JY, Liu YM, Nie M, Wang WX (2019) Deep convolutional neural network-based in-process tool condition monitoring in abrasive belt grinding. Comput Ind 106:1–13
Cheng C, Li JY, Liu YM, Nie M, Wang WX (2020) An online belt wear monitoring method for abrasive belt grinding under varying grinding parameters. J Manuf Process 50:80–89
Pandiyan V, Caesarendra W, Tjahjowidodo T, Tan HH (2018) In-process tool condition monitoring in compliant abrasive belt grinding process using support vector machine and genetic algorithm. J Manuf Process 31:199–213
Salgado DR, Alonso FJ (2007) An approach based on current and sound signals for in-process tool wear monitoring. Int J Mach Tools Manuf 47:2140–2152
Khellouki A, Rech J, Zahouani H (2007) The effect of abrasive grain’s wear and contact conditions on surface texture in belt finishing. Wear 263(1):81–87
Li HZ, Zeng H, Chen XQ (2006) An experimental study of tool wear and cutting force variation in the end milling of inconel 718 with coated carbide inserts. J Mater Process Technol 180:296–304
Ke GL, Meng Q, Finley T, Wang TF, Chen W, Ma WD, Ye QW, Liu TY (2017) LightGBM: A Highly Efficient Gradient Boosting Decision Tree.
Availability of data and materials
The datasets used or analyzed during the current study are available from the corresponding author on reasonable request.
Funding
This work was supported by the Shaanxi Province key projects (grant number 2017ZDXM-GY-133).
Author information
Authors and Affiliations
Contributions
Nina Wang performed the analysis and summary of the experimental data and was a major contributor in writing the manuscript. Lijuan Ren, Nina Wang, and Wanjing Pang participate in carrying out grinding experiments. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethical approval
All data in this paper comes from machining grinding experiments and does not involve ethical issues.
Consent to participate
Not applicable.
Consent to publish
Not applicable.
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, N., Zhang, G., Pang, W. et al. Novel monitoring method for material removal rate considering quantitative wear of abrasive belts based on LightGBM learning algorithm. Int J Adv Manuf Technol 114, 3241–3253 (2021). https://doi.org/10.1007/s00170-021-06988-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-021-06988-6