Study on Single-point Dresser Wear Intelligent Prediction Method

doi:10.16182/j.issn1004731x.joss.201706007

Abstract

Abstract: In precision grinding process, grinding wheel should be dressed in time to keep the wheel sharpness and correct geometry. Now, it is still a difficult problem how to effectively predict the dresser wear in process. According to the single-point dresser wear mechanism, a method was proposed to predict the single-point dresser wear based on the acoustic emission signal and the sequential minimal optimization support vector machines (SMO-SVM) model. The wavelet packet algorithm was used to exact acoustic emission signal characteristic information. According to the large sample of acoustic emission signal, the sequential minimal optimization support vector machines (SMO-SVM) model was established to predict single-point dresser wear, and the signal characteristic information is as input for SMO-SVM model. The experiment result shows that the model's accuracy is above 95.257 1%.

Key words: single-point dresser wear, SMO-SVM, intelligent prediction, experiment

CLC Number:

TH123

Chi Yulun, Li Haolin, Yue Tai. Study on Single-point Dresser Wear Intelligent Prediction Method[J]. Journal of System Simulation, 2017, 29(6): 1210-1217.

References

[1] Arif Mohammed1, Janet Folkes1, Xun Chen. Detection of Grinding Temperatures Using Laser Irradiation and Acoustic Emission Sensing Technique, Materials and Manufacturing Processes (S1042-6914), 2012, 27(4): 395-400.
[2] María del Carmen Camacho, Oscar Galao, Francisco Javier Baeza, et al. Mechanical Properties and Durability of CNT Cement Composites[J]. Materials (S1996-1944), 2014, 7(3): 1640-1651.
[3] Berend Denkena, Tobias Ortmaier, Markus Ahrens, et al.Monitoring of grinding wheel defects using recursive estimation[J]. Int J Adv Manuf Technol (S0268-3768), 2014, 75(5): 1005-1015.
[4] Ander Arriandiaga, Eva Portillo, Jose A Sánchez, et al.Virtual Sensors for On-line Wheel Wear and Part Roughness Measurement in the Grinding Process[J]. Sensors (S1424-8220), 2014, 14(5): 8756-8778.
[5] Berend Denkena, Jens Köhler, Andreas Schindler, et al.Continuous generating grinding Material engagement in gear tooth machining[J]. Mechanism and Machine Theory (S0094-114X), 2014, 81(11): 11-20.
[6] D Gridhar, L Vijayaraghavan, R Krishnamurthy.Acoustic emission response of sintered alumina zirconia composite during grooving process[J]. NDT & E International (S1879-1174), 2012, 46(1): 55-62.
[7] T Warren Liao.Feature extraction and selection from acoustic emission signals with an application in grinding wheel condition monitoring[J]. Engineering Applications of Artificial Intelligence (S0952-1976), 2010, 23(1): 74-84.
[8] K Wegener, HW Hoffmeister,B Karpuschewski, et al. Conditioning and monitoring of grinding wheels, CIRP Annals-Manufacturing Technology (S0007-8506), 2011, 60(2): 757-777.
[9] Cesar H R Martins, Paulo R Aguiar, Arminio Frech. The condition monitoring of single-point dresser using acoustic emission and neural networks models[J]. IEEE Transactions on Instrumentation and Measurement (S 0018-9456), 2014, 63(3): 667-679.
[10] A Hassui, A E Diniz.Correlating surface roughness and vibration on plunge cylindrical grinding of steel[J]. International Journal of Machine Tools & Manufacture (S0890-6955), 2003, 43(8): 855-862.
[11] 王潜龙, 冯金科, 屈展, 等. 基于声发射与小波包理论的压力管道泄漏检测[J]. 西安交通大学学报, 2003, 37(5): 515-518.
(Wang Qianlong, Feng Jinke, Qu Zhan, et al.Pressure Pipe Leakage Detection Based on the Acoustic Emission and Wavelet Packet Theory[J]. JOURNAL OF XI'AN JIAOTONG UNIVERSITY, 2003, 37(5): 515-518.)
[12] S 马尔金. 磨削技术理论与应用 [M]. 沈阳: 东北大学出版社, 2002.
(S Malkin.Grinding technology theory and applications of machining with abrasives [M]. Shenyang, China: Northeastern university press, 2002.)
[13] 任敬心, 华定安. 磨削原理[M]. 北京: 电子工业出版社, 2011.
(Ren Jingxin, Hua Dingan.Grinding principle [M]. BeiJing, China: Publishing House of Electronics Industry, 2011.)
[14] 林伟青, 傅建中, 许亚洲, 等. 基于最小二乘支持向量机的数控机床热误差预测[J]. 浙江大学学报 (工学版), 2008, 46(2): 905-908.
(Lin Wei-qing, Fu Jian-zhong, Xu Ya-zhou, et al.Thermal error prediction of numerical control machine tools basedon least squares support vector machines[J]. Journal of Zhejiang University (Engineering Science), 2008, 46(2): 905-908.)
[15] Zhang M G, Li Z M, Li W H.Study on least squares support vector machines algorithm and its application[C]// Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence, Hong Kong, China. USA: IEEE, 2005: 1082-1085.