Data-Driven Online Monitoring and System Development of Multi-scale Targets in the Grinding Process

doi:10.12382/bgxb.2022.0187

Abstract

Abstract:

Grinding is a key process in high value-added industries, such as national defense and military,aerospace,and automobiles.The realization of intelligent acquisition and monitoring of the grinding process is essentialto improve product quality and ensure safe production.Aiming at the problems in the data collection of the existing grinding process,such as the single target of the monitoring plan,insufficient integration,and difficulty in obtaining complete grinding information,a multi-scale target integrated monitoring system framework is established for the grinding process.A multi-scale target correlation monitoring model including quality,efficiency,status, and a green multi-scale is constructed,which maps monitoring variables and monitoring targets. The multi-sensor acquisition fusion and grinding result monitoring feature mapping method is proposed,and an intelligent acquisition and monitoring system for the grinding process is developed.The system is used for real-time data acquisition and monitoring of a high-speed electric spindle bearing grinding process.The measurement results show that the developed monitoring system can effectively and accurately predict the grinding time,grinding energy consumption,grinding state, and surface roughness during the grinding process.

Key words: multi-scale target, monitoring system framework, data driven, intelligent grinding monitoring system

LÜ Lishu, DENG Zhaohui, LIU Tao, TENG Hongzhao, ZHUO Rongjin. Data-Driven Online Monitoring and System Development of Multi-scale Targets in the Grinding Process[J]. Acta Armamentarii, 2023, 44(7): 2147-2161.

Figures/Tables 21

References 29

[1]	LÜ L S, DENG Z H, LIU T, et al. Intelligent technology in grinding process driven by data:a review[J]. Journal of Manufacturing Processes, 2020, 58:1039-1051. doi: 10.1016/j.jmapro.2020.09.018 URL
[2]	周昊飞, 刘玉敏. 基于深度置信网络的大数据制造过程实时智能监控[J]. 中国机械工程, 2018, 29(10):1201-1207,1213.
	ZHOU H F, LIU Y M. Real-time intelligent monitoring for manufacturing processes with big data based on deep belief networks[J]. China Mechanical Engineering, 2018, 29(10): 1201-1207,1213. (in Chinese)
[3]	TROMPT G M, KRASIL’NIKOV A Y. Improving the grinding precision by stable operation of an active monitoring system[J]. Russian Engineering Research, 2013, 33(1):36-38. doi: 10.3103/S1068798X13010115 URL
[4]	林峰, 焦慧锋, 傅建中. 基于贝叶斯网络的平面磨削状态智能监测技术研究[J]. 中国机械工程, 2011, 22(11): 1269-1273.
	LIN F, JIAO H F, FU J Z. Research on intelligent monitoring technique of machining state for surface grinder based on bayesian network[J]. China Mechanical Engineering, 2011, 22(11):1269-1273. (in Chinese)
[5]	THOMAZELLA R, LOPES W N, AGIAR P R, et al. Digital signal processing for self-vibration monitoring in grinding:a new approach based on the time-frequency analysis of vibration signals[J]. Measurement, 2019, 145:71-83. doi: 10.1016/j.measurement.2019.05.079 URL
[6]	姜晨, 李郝林. 基于声发射信号的精密外圆切入磨削时间评估算法及试验研究[J]. 机械工程学报, 2014, 50(5):194-200.
	JIANG C, LI H L. Algorithm and experiment of estimation of time of precision cylindrical plunge grinding based on acoustic emission signal[J]. Journal of Mechanical Engineering, 2014, 50(5):194-200. (in Chinese)
[7]	BOTCHA B, RAJAGOPAL V, BABU N R, et al. Process-machine interactions and a multi-sensor fusion approach to predict surface roughness in cylindrical plunge grinding process[J]. Procedia Manufacturing, 2018, 26:700-711. doi: 10.1016/j.promfg.2018.07.080 URL
[8]	朱欢欢, 迟玉伦, 闻章, 等. 断续磨削表面烧伤机理与在线监测方法研究[J]. 表面技术, 2021, 50(9):1-16.
	ZHU H H, CHI Y L, WEN Z, et al. Research on burn mechanism of intelligent grinding surface and online monitoring method[J]. Surface Technology, 2021, 50(9):1-16. (in Chinese)
[9]	OLIVEIRA J F G, BRAGA A P S, CARVALHO A C P L F. Development of a dressing monitoring system through artificial intelligence and acoustic maps for high performance grinding[J]. International Journal of Manufacturing Technology and Management, 2007, 12(1):171-183. doi: 10.1504/IJMTM.2007.014148 URL
[10]	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. doi: 10.1016/j.jmapro.2017.11.014 URL
[11]	TIAN Y B, LIU F, WANG Y, et al. Development of portable power monitoring system and grinding analytical tool[J]. Journal of Manufacturing Processes, 2017, 27:188-197. doi: 10.1016/j.jmapro.2017.05.002 URL
[12]	赵飞, 梅雪松, 李光东, 等. 数控成型磨齿机加工误差在线监测及补偿[J]. 机械工程学报, 2013, 49(1):171-177.
	ZHAO F, MEI X S, LI G D, et al. Machining error online monitoring and compensation of numerical control forming gear grinding machine[J]. Journal of Mechanical Engineering, 2013, 49(1):171-177. (in Chinese)
[13]	NGUYEN D, YIN S, TANG Q, et al. Online monitoring of surface roughness and grinding wheel wear when grinding Ti-6Al-4V titanium alloy using ANFIS-GPR hybrid algorithm and Taguchi analysis[J]. Precision Engineering, 2019, 55:275-292. doi: 10.1016/j.precisioneng.2018.09.018 URL
[14]	GAO Z Y, LIN J, WANG X F, et al. Grinding burn detection based on cross wavelet and wavelet coherence analysis by acoustic emission signal[J]. Chinese Journal of Mechanical Engineering, 2019, 32(4):104-113. doi: 10.1186/s10033-019-0420-0
[15]	FUKUHARA Y, SUZUKI S, SASAHARA H. Development of in-process monitoring system for grinding wheel surface temperature and grinding state[J]. Advanced Materials Research, 2016, 1136:624-629. doi: 10.4028/www.scientific.net/AMR.1136 URL
[16]	LLIO A D, PAOLETTI A, SFARRA S. Monitoring of MMCs grinding process by means of IR thermography[J]. Procedia Manufacturing, 2018, 19:95-102. doi: 10.1016/j.promfg.2018.01.014 URL
[17]	毕果, 汤期林, 王振忠, 等. 精密磨削机床智能监测系统开发与应用[J]. 航空制造技术, 2019, 62(6):32-40.
	BI G, TANG Q L, WANG Z Z, et al. Intelligent monitoring system of precision grinding machine[J]. Aeronautical Manufacturing Technology, 2019, 62(6):32-40. (in Chinese)
[18]	MAHATA S, SHAKYA P, BABU N R. A robust condition monitoring methodology for grinding wheel wear identification using Hilbert Huang transform[J]. Precision Engineering, 2021, 70:77-91. doi: 10.1016/j.precisioneng.2021.01.009 URL
[19]	GUO W C, LI B Z, ZHOU Q Z. An intelligent monitoring system of grinding wheel wear based on two-stage feature selection and long short-term memory network[J]. Proceedings of the Institution of Mechanical Engineers, 2019, 233(13):2436-2446.
[20]	郭维诚, 李蓓智, 杨建国, 等. 磨削过程信号监测与砂轮磨损预测模型构建[J]. 上海交通大学学报, 2019, 53(12):1475-1481.
	GUO W C, LI B Z, YANG J G, et al. Monitroing of grinding signals and development of wheel wear prediction model[J]. Journal of Shanghai Jiao Tong University, 2019, 53(12): 1475-1481. (in Chinese)
[21]	CHENG C, LI J Y, LIU Y M, et al. An online belt wear monitoring method for abrasive belt grinding under varying grinding parameters[J]. Journal of Manufacturing Processes, 2020, 50: 80-89. doi: 10.1016/j.jmapro.2019.12.034 URL
[22]	袁广超, 鲍劲松, 郑小虎, 等. 基于CNC实时监测数据驱动方法的钛合金高速铣削刀具寿命预测[J]. 中国机械工程, 2018, 29(4):457-462,470.
	YUAN G C, BAO J S, ZHENG X H, et al. Tool life prediction in titanium high speed milling processes based on CNC real time monitoring data driven[J]. China Mechanical Engineering, 2018, 29(4):457-462,470. (in Chinese)
[23]	DURO J A, PADGET J A, BOWEN C R, et al. Multi-sensor data fusion framework for CNC machining monitoring[J]. Mechanical Systems and Signal Processing, 2016, 66:505-520.
[24]	CHEN X Z, LI C, TANG Y,etal. A framework for energy monitoring of machining workshops based on IoT[J]. Procedia CIRP, 2018, 72:1386-1391. doi: 10.1016/j.procir.2018.03.085 URL
[25]	陈鹏, 刘飞, 宁俊锋. 机械加工自动生产线多目标监控集成模型及其应用[J] 计算机集成制造系统, 2017, 23(3):473-481.
	CHEN P, LIU F, NING J F. Integrated model for multi-objective monitoring on automatic machining line and its application[J]. Computer Integrated Manufacturing Systems, 2017, 23(3): 473-481. (in Chinese)
[26]	李恒, 叶祖坤, 查文彬, 等. 基于多传感器信息决策级融合的刀具磨损在线监测[J]. 兵工学报, 2021, 42(9):2024-2031. doi: 10.3969/j.issn.1000-1093.2021.09.023
	LI H, YE Z K, ZHA W B, et al. Tool wear online monitoring based on multi-sensor information decision-making level fusion[J]. Acta Armamentarii, 2021, 42(9):2024-2031. (in Chinese) doi: 10.3969/j.issn.1000-1093.2021.09.023
[27]	朱宏波. 基于多传感器信息融合的数控机床状态监测系统[D]. 北京: 北京邮电大学, 2019.
	ZHU H B. State monitoring system of CNC machine based on multi-sensor information fusion[D]. Beijing: Beijing University of Posts and Telecommunications, 2019. (in Chinese)
[28]	ZHANG Z Z, YAO P, WANG J, et al. Analytical modelling of surface roughness in precision grinding of particle reinforced metal matrix composites considering nanomechanical response of material[J]. International Journal of Mechanical Sciences, 2019,157-158:243-253.
[29]	吕黎曙, 邓朝晖, 刘涛, 等. 面向清洁生产的磨削工艺方案多层多目标优化模型及应用[J]. 中国机械工程, 2022, 33(5):589-599.
	LÜ L S, DENG Z H, LIU T, et al. Multi-layer and multi-objective optimization model and application of grinding process plan for cleaner production[J]. China Mechanical Engineering, 2022, 33(5):589-599. (in Chinese)

序号	砂轮线速度/ (m·s^-1)	工件转速/ (r·min^-1)	磨削深度/ mm	平均磨削功率/ W	粗糙度/μm	平均磨削温度/ ℃	磨削能耗 10^-3/(kW·h)
1	100	90	0.01	2112	0.374	276	77.96
2	100	90	0.02	2655	0.512	412	63.10
3	100	90	0.03	5211	0.605	664.5	58.22
4	100	90	0.04	7556	0.698	848.5	55.58
5	100	90	0.05	8499	0.952	906.5	53.44
6	100	30	0.03	2434	0.346	654	81.88
7	100	60	0.03	2644	0.431	660	63.77
8	100	120	0.03	6756	0.461	676	54.79
9	100	150	0.03	7914	0.544	687	52.78
10	60	90	0.03	3643	0.776	603.3	52.33
				……

序号	砂轮线速度/ (m·s^-1)	工件转速/ (r·min^-1)	磨削深度/ mm	平均磨削功率/ W	粗糙度/μm	平均磨削温度/ ℃	磨削能耗 10^-3/(kW·h)
1	100	90	0.01	2112	0.374	276	77.96
2	100	90	0.02	2655	0.512	412	63.10
3	100	90	0.03	5211	0.605	664.5	58.22
4	100	90	0.04	7556	0.698	848.5	55.58
5	100	90	0.05	8499	0.952	906.5	53.44
6	100	30	0.03	2434	0.346	654	81.88
7	100	60	0.03	2644	0.431	660	63.77
8	100	120	0.03	6756	0.461	676	54.79
9	100	150	0.03	7914	0.544	687	52.78
10	60	90	0.03	3643	0.776	603.3	52.33
				……

变量	特征参数值
变量	1	2	3	4	5	…
VAR01	0.048 7	0.252	0.432	0.389 5	0.571
VAR02	2.678 1	2.706	2.544 2	2.903 4	2.548 4
VAR03	3.359 1	2.898 5	2.702 1	2.845 3	2.651 4
VAR04	4.860 8	4.179 3	3.758 1	4.047 5	3.661 1
VAR05	806.3	969.7	969	888.8	969
VAR06	301	423	690	856	922
VAR07	251	401	639	841	891
VAR08	276	412	664.5	848.5	906.5	…
VAR09	2 212	2 755	5 311	7 656	8 599
VAR10	2 012	2 555	5 111	7 456	8 399
VAR11	2 112	2 655	5 211	7 556	8 499
VAR12	77.96	63.10	58.22	55.58	53.44
VAR13	100	100	100	100	100
VAR14	90	90	90	90	90
VAR15	0.01	0.02	0.03	0.04	0.05

变量	特征参数值
变量	1	2	3	4	5	…
VAR01	0.048 7	0.252	0.432	0.389 5	0.571
VAR02	2.678 1	2.706	2.544 2	2.903 4	2.548 4
VAR03	3.359 1	2.898 5	2.702 1	2.845 3	2.651 4
VAR04	4.860 8	4.179 3	3.758 1	4.047 5	3.661 1
VAR05	806.3	969.7	969	888.8	969
VAR06	301	423	690	856	922
VAR07	251	401	639	841	891
VAR08	276	412	664.5	848.5	906.5	…
VAR09	2 212	2 755	5 311	7 656	8 599
VAR10	2 012	2 555	5 111	7 456	8 399
VAR11	2 112	2 655	5 211	7 556	8 499
VAR12	77.96	63.10	58.22	55.58	53.44
VAR13	100	100	100	100	100
VAR14	90	90	90	90	90
VAR15	0.01	0.02	0.03	0.04	0.05

变量	主成分1	主成分2	主成分3
VAR01	0.796	0.183	-0.164
VAR02	-0.336	0.645	0.422
VAR03	-0.574	0.716	0.001
VAR04	-0.586	0.713	0.006
VAR05	0.328	-0.574	0.443
VAR06	0.893	0.152	0.392
VAR07	0.893	0.152	0.392
VAR08	0.893	0.152	0.392
VAR09	0.910	0.224	-0.290
VAR10	0.910	0.224	-0.290
VAR11	0.910	0.224	-0.290
VAR12	-0.778	0.095	0.168
VAR13	0.068	0.398	-0.552
VAR14	0.448	-0.200	-0.671
VAR15	0.861	0.238	0.397