A comprehensive analysis of an abrasive belt wear monitoring scheme for rail grinding was conducted, focusing on the generation mechanisms of sound and current signals during the sanding process. Initially, we establish a theoretical model linking the sound of belt grinding with its corresponding current generation mechanism. This model also integrates the patterns of abrasive belt wear, laying the groundwork for subsequent signal feature extraction and state recognition. Our approach not only guides the extraction and recognition processes but also ensures the general applicability of our findings, making them more relevant for real-world rail grinding scenarios. The study then delves into an empirical investigation of the characteristics of actual sound and current signals obtained during rail belt grinding. By analyzing these signals across time, frequency, and time-frequency domains, we extract multidimensional signal features. These extracted features serve as crucial inputs for identifying the wear state of the abrasive belt in subsequent chapters. Our methodical approach provides a robust framework for understanding and monitoring the condition of abrasive belts in rail grinding applications, with potential implications for improving efficiency and quality in industrial practices.

Haipeng Wang. Research on abrasive belt wear monitoring for the rail grinding. International Journal of Frontiers in Engineering Technology (2024), Vol. 6, Issue 1: 77-82. https://doi.org/10.25236/IJFET.2024.060113.

[1] XIAO G, HUANG Y. Experimental research and modelling of life-cycle material removal in belt finishing for titanium alloy[J]. Journal of Manufacturing Processes, 2017,30:255-267.

[2] XIAO G, HUANG Y. Adaptive belt precision grinding for the weak rigidity deformation of blisk leading and trailing edge[J]. Advances in Mechanical Engineering, 2017,9(10):1-12.

[3] SERPIN K, MEZGHANI S, EL MANSORI M. Wear study of structured coated belts in advanced abrasive belt finishing[J]. Surface & Coatings Technology, 2015,284:365-376.

[4] TSUWA H, NAMBA Y, YAMASAKI K. Studies on the Belt Grinding (1st Report): Grinding Performance[J]. Journal of the Japan Society of Precision Engineering, 1967,33(388):319-324.

[5] NAMBA Y, TSUWA H. Simulation of Grinding Process[J]. Journal of the Japan Society of Precision Engineering, 1974,40(479):1087-1092.

[6] NAMBA Y, TSUWA H. Studies on the Belt Grinding (2nd Report): Stress Distribution on the Interface between Abrasive Beltand Workpiece[J]. Journal of the Japan Society of Precision Engineering, 1970,36(426):478-483.

[7] NAMBA Y, TSUWA H. Wear Process of Abrasive Belt[J]. Journal of the Japan Society of Precision Engineering, 1972,38(445):202-208.

[8] PANDIYAN V, CAESARENDRA W, TJAHJOWIDODO T, et al. In-process tool condition monitoring in compliant abrasive belt grinding process using support vector machine and genetic algorithm[J]. Journal of Manufacturing Processes, 2018,31:199-213.

[9] ZHANG X, CHEN H, XU J, et al. A novel sound-based belt condition monitoring method for robotic grinding using optimally pruned extreme learning machine[J]. Journal of Materials Processing Technology, 2018,260:9-19.

[10] CHEN J, CHEN H, XU J, et al. Acoustic signal-based tool condition monitoring in belt grinding of nickel-based superalloys using RF classifier and MLR algorithm[J]. International Journal of Advanced Manufacturing Technology, 2018,98(1-4):859-872.

[11] ZHANG X, XU J, WANG J, et al. An intelligent method to monitor the abrasive belt condition based on sound signals[C]//Proceedings of the 2017 12th IEEE conference on industrial electronics and applications (ICIEA 2018). NEW YORK:IEEE,2018:58-63.

[12] MENG N, LIU Y, LI J. Feature extraction method of abrasive belt wear state for rail grinding[J]. Machining Science and Technology, 2019,23(6):1003-1021.