Wear Evaluation and Residual Life Prediction Method for Rail Grinding Wheels

doi:10.12141/j.issn.1000-565X.240173

Abstract

Abstract:

Rail grinding is a technology that removes the top fatigue layer of rails by applying high speed rotating grinding wheels. When the grinding wheels become abrasion, it typically leads to a decrease in material removal efficiency and an increase in grinding zone temperature. To prevent these issues from negatively affecting grinding operations, timely replacement of worn-out grinding wheels is necessary. This paper proposed a neural network-based method for predicting the wear level and residual life of rail grinding wheels, enabling the optimal timing for wheel replacement. The principle of this method is as follows: the axial acceleration signal of the motor spindle connected to the grinding wheel was collected, and based on this signal, characteristic parameters that describe the wear level of the grinding wheel were extracted. These characteristic parameters were then transformed using the Z-score method, which removes the dimensionality of the parameters and improves their comparability. After that, the XGBoost algorithm was employed to filter the most relevant features that are strongly correlated with the wheel’s service life. A fusion strategy integrating wear time and wheel wear volume was adopted as the criterion for assessing the wear and service life. Constructing a neural network model that mapped the filtered feature parameters to both the wear volume and the grinding wheel thickness. The experimental data along with the grinding wheels abrasion was obtained by using the experimental device. The data was divided into mutually independent training and validation sets, which were used to train and validate the constructed neural network, respectively. The results show that the method achieves comparable accuracy in both the training and validation sets. In the validation set, the accuracy for determining the wear level of the grinding wheel is 87.9%, with misclassified samples mainly concentrated in the transition zone of wear progression. The prediction accuracy for the grinding wheel life is -5.3%. Additionally, the method demonstrates a certain level of generalizability across different grinding process parameters.

Key words: rail grinding, grinding wheel wear, neural network, wear evaluation, residual life prediction

CLC Number:

TG74

HE Zhe, ZHANG Yuying, LIU Shangkun, GAO Chunlei. Wear Evaluation and Residual Life Prediction Method for Rail Grinding Wheels[J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(4): 72-80.

Figures/Tables 15

Fig.1

Fig.2

Table 1

Names and calculation formulas of the characteristic parameters"

名称	符号	计算公式
打磨功率	P
去除量	Δ
最大值	A_max	max（x（t））
最小值	A_min	min（x（t））
均值	A_mean	mean（x（t））
二阶矩	M_2nd	$1 n ∑ x (t) - A m e a n 2$
三阶矩	M_3rd	$1 n ∑ x (t) - A m e a n 3$
四阶矩	M_4th	$1 n ∑ x (t) - A m e a n 4$
衰减系数	α_c	$∑ f m i n f m a x l g (f) l g (p (f)) - n l g (f) ¯ l g (p (f)) ¯ ∑ f m i n f m a x l g (f) 2 - n l g (f) ¯ 2$
重心频率	f_g	$∑ f m i n f m a x f p (f) ∑ f m i n f m a x p (f)$

Table 1

Fig.3

Fig.4

Table 2

Table 3

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Fig.12

References 24

1	吴泽宇，李明航，王文斌，等．车轮踏面粗糙度对基于惯性基准法的钢轨波磨检测结果影响分析［J］．振动与冲击，2023，42（15）：241-249.
	WU Zeyu， LI Minghang， WANG Wenbin，et al ．Influence analysis of wheel tread roughness on rail corrugation detection results based on inertial reference method［J］．Journal of Vibration and Shock，2023，42（15）：241-249.
2	张胜，刘长宝，樊小强，等．固化工艺对树脂基高速打磨磨石性能影响［J］．铁道学报，2024，46（1）：137-144.
	ZHANG Sheng， LIU Changbao， FAN Xiaoqiang，et al ．Effect of curing process on properties of resin based high speed grinding wheel and its regulation mechanism［J］．Journal of the China Railway Society，2024，46（1）：137-144.
3	李江，樊文刚，吴志伟，等．基于槽型接触轮的钢轨砂带打磨材料去除特性［J］．中国铁道科学，2023，44（4）：75-83.
	LI Jiang， FAN Wengang， WU Zhiwei，et al ．Research on material removal characteristics of rail grinding by abrasive belt based on grooved contact wheel［J］．China Railway Science，2023，44（4）：75-83.
4	HE Z， LI J Y， LIU Y M，et al ．Investigation of conditions leading to critical transitions between abrasive belt wear modes for rail grinding［J］．Wear，2021，484/485：204048/1-9.
5	樊文刚，刘月明，李建勇．高速铁路钢轨打磨技术的发展现状与展望［J］．机械工程学报，2018，54（22）：184-195.
	FAN Wengang， LIU Yueming， LI Jianyong ．Development status and prospect of rail grinding technology for high speed railway［J］．Journal of Mechanical Engineering，2018，54（22）：184-195.
6	D’ADDONA D M， MATARAZZO D， TETI R，et al ．Prediction of dressing in grinding operation via neural networks［J］．Procedia CIRP，2017，62：305-310.
7	GONZÁLEZ D， ALVAREZ J， SÁNCHEZ J，et al ．Deep learning-based feature extraction of acoustic emission signals for monitoring wear of grinding wheels［J］．Sensors，2022，22：6911/1-14.
8	张诗语．SiC_f/SiC复合材料磨削中基于声发射信号的砂轮磨损识别［D］．长沙：湖南大学，2022.
9	胡天荣，郑红伟，戴士杰．基于异类信息融合的砂轮磨损状态监测［J］．工具技术，2023，57（2）：126 -131.
	HU Tianrong， ZHENG Hongwei， DAI Shijie ．Grinding wheel wear condition monitoring based on heterogeneous information fusion［J］．Tool Engineering，2023，57（2）：126 -131.
10	BI G， LIU S， SU S B，et al ．Diamond grinding wheel condition monitoring based on acoustic emission signals［J］．Sensors，2021，21（4）：1054/1-17.
11	于帅．基于钢轨打磨车的砂带磨损监测系统研究［D］．北京：北京交通大学，2021.
12	程灿，李建勇，刘月明，等．基于磨削声与电流的砂带磨损状态识别［J］．振动、测试与诊断，2020，40（2）：355-360，422.
	CHENG Can， LI Jianyong， LIU Yueming，et al ．Wear identification of abrasive belt based on grinding sound and current［J］．Journal of Vibration，Measurement and Diagnosis，2020，40（2）：355-360，422.
13	毛聪，孙鹏程，唐伟东，等．磨削白层特性及其与声发射信号的相关性［J］．机械工程学报，2023，59（9）：349-359.
	MAO Cong， SUN Pengcheng， TANG Weidong，et al ．Features of grinding white layer and its correlation with acoustic emission signal［J］．Journal of Mechanical Engineering，2023，59（9）：349-359.
14	赵华东，刘勇，朱振伟，等．金刚石砂轮与金刚石滚轮磨削接触的声发射监测［J］．机械设计与制造，2024（2）：174-178.
	ZHAO Hua-dong， LIU Yong， ZHU Zhen-wei，et al ．Acoustic emission monitoring of grinding contact between diamond wheel and diamond wheel［J］．Machi-nery Design & Manufacture，2024（2）：174-178.
15	何喆，李建勇，刘月明，等．砂带虚拟形貌的建模［J］．华南理工大学学报（自然科学版），2017，45（12）：85-91，105.
	HE Zhe， LI Jian-yong， LIU Yue-ming，et al ．Modeling of virtual topography of abrasive belt［J］．Journal of South China University of Technology （Natural Science Edition），2017，45（12）：85-91，105.
16	程灿．面向钢轨打磨的砂带磨损状态监测与剩余寿命预测研究［D］．北京：北京交通大学，2020.
17	聂磊，张吕凡，徐诗奕，等．基于相似度特征融合和CNN的滚动轴承剩余寿命预测［J］．噪声与振动控制，2023，43（5）：115-121.
	NIE Lei， ZHANG Lvfan， XU Shiyi，et al ．Remaining life prediction of rolling bearing based on similarity feature fusion and convolutional neural network［J］．Noise and Vibration Control，2023，43（5）：115-121.
18	刘岚，侯立群．基于改进一维残差网络的轴承故障诊断［J］．仪器仪表用户，2021，28（9）：45-50.
	LIU Lan， HOU Liqun ．Bearing fault diagnosis method based on improved 1D residual network［J］．Instrumentation，2021，28（9）：45-50.
19	张国文，贺春江，张静，等．钢轨打磨车砂轮技术标准［J］．金刚石与磨料磨具工程，2018，38（4）：83-86.
	ZHANG Guowen， HE Chunjiang， ZHANG Jing，et al ．Standard of grinding wheel used on rail grinding［J］．Diamond and Abrasives Engineering，2018，38（4）：83-86.
20	钢轨打磨车砂轮订货技术条件：［S］．
21	谭永敏，施展，迟玉伦，等．基于Shannon熵与声发射信号的CBN砂轮性能监测方法研究［J］．机械强度，2023，45（2）：321-330.
	TAN Yongmin， SHI Zhan， CHI Yulun，et al ．Research on CBN grinding wheel performance monitoring method based on Shannon entropy and acoustic emission signal［J］．Journal of Mechanical Strength，2023，45（2）：321-330.
22	赵书东，禹晓敏，王文玺，等．金字塔砂带磨损状态的声信号GA-BP识别方法［J］．表面技术，2024，53（3）：28-38.
	ZHAO Shudong， YU Xiaomin， WANG Wenxi，et al ．GA-BP identification of acoustic signals for wear states of pyramidal abrasive belts［J］．Surface Technology，2024，53（3）：28-38.
23	黄献聪，来悦，李常胜，等．超高分子量聚乙烯纤维及其复合材料的热氧老化行为［J］．兵工学报，2022，43（12）：3211-3220.
	HUANG Xiancong， LAI Yue， LI Changsheng，et al ．Thermo-oxidative aging behavior of ultra-high molecular weight polyethylene fiber and its composites［J］．Acta Armamentarh，2022，43（12）：3211-3220.
24	樊威，李嘉禄．热氧老化对碳纤维织物增强聚合物基复合材料弯曲性能的影响［J］．复合材料学报，2015，32（5）：1260-1270.
	FAN Wei， LI Jialu ．Effects of thermo-oxidative aging on flexural properties of carbon fiber fabric reinforced polymer matrix composites［J］．Acta Materiae Compositae Sinica，2015，32 （5）：1260-1270.

项目	参数		参数
第1层大小	100	迭代限制	1 000
第2层大小	50	正则化强度	0.005
第3层大小	10	激活函数	ReLU

序号	打磨功率/kW	去除量/mm	备注
1	7.5	0.02	训练
2	15.0	0.02	训练
3	15.0	0.05	训练
4	7.5	0.05	验证

[1]	CAO Ruifen, HU Weiling, LI Qiangsheng, BIN Yannan, ZHENG Chunhou. Prediction Method of IL-6 Inducing Peptides Based on Graph Neural Network [J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(5): 109-117.
[2]	DAI Zhou, LIU Yan, MAO Xianyin, GUO Tao, XU Lianggang, CHENG Guixian. Fusion Transformer Model-Based Segmentation Algorithm for Laser Point Cloud of Distribution Lines [J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(5): 139-146.
[3]	HU Guanghua, DAI Zhigang, WANG Qinghui. Machining Feature Recognition Method of B-Rep Model Based on Graph Neural Network [J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(5): 20-31.
[4]	JIA Huayu, ZHENG Huilong, ZHOU Hong, ZHANG Qian. Optimal Selection of UAV Launch Parameters Based on SSA-BP Neural Network [J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(4): 90-101.
[5]	BI Jun, WANG Jianing, WANG Yongxing. Short-Term Operation State Prediction of Charging Station Based on LSTM-FC Model [J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(2): 58-67.
[6]	DU Qiliang, WANG Yimin, TIAN Lianfang. Attention Module Based on Feature Similarity and Feature Normalization [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(7): 62-71.
[7]	LIU Weirong, ZHANG Zhiqiang, ZHANG Ning, et al. A TT-Tucker Decomposition-Based LC Convolutional Neural Network Compression Method Without Pre-Training [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(7): 29-38.
[8]	YUAN Renteng, WANG Chenzhu, XIANG Qiaojun, et al. Trajectory Data-Driven Model for Vehicle Lane Change Intention Recognition [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(6): 34-44.
[9]	CAI Xiaodong, ZHOU Qingsong, YE Qing. Social Recommendation Model Based on Dynamic Neighborhood Sampling [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(2): 32-41.
[10]	ZHU Rui, LIU Yu, LIANG Yuying, et al. BP Neural Network Prediction Model for Turbulent Noise Intensity in Gas/Water Medium [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(12): 119-126.
[11]	QIANG Xuhong, TIAN Weixiao, JIANG Xu, et al. Intelligent Method for Identifying Damage of Steel Members with Localized Random Pitting Based on Convolutional Neural Network [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(11): 43-54.
[12]	YANG Chunling, CHEN Wenjun, LIU Jiahui. Feature-Space Optimization-Inspired and Multi-Hypothesis Cross-Attention Reconstruction Neural Network for Video Compressive Sensing [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(10): 9-21.
[13]	FANG Gang, YUAN Longhua, WANG Xiaoming, et al. Soft-Sensor Modeling Method Based on Ensemble Kalman Filter-Elman Neural Network [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(8): 126-136.
[14]	MA Xiaoliang, AN Lingling, DENG Congjian, et al. Translation Optimization Technology of Automatic Speech Recognition Based on Industry-Specific Vocabulary [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(8): 118-125.
[15]	ZHU Zhengyu, LUO Chao, HE Qianhua, et al. Multi-View Lip Motion and Voice Consistency Judgment Based on Lip Reconstruction and Three-Dimensional Coupled CNN [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(5): 70-77.