针对磨削过程中砂轮磨损难以直接监测的问题，提出了基于多特征优化融合的随机森林(MFOF-RF)算法，以实现砂轮磨损的准确预测.对外圆纵向磨削中采集的功率、加速度和声发射信号进行预处理和特征提取，获得平均值、有效值以及峰值频率等多个时域和频域信号特征.以统计学指标为评价标准，对预测模型的参数进行调优，确定了最佳的砂轮磨损信号特征组合.结果表明，相比于使用单一特征预测砂轮磨损，MFOF-RF模型提高了信号特征与砂轮磨损的相关程度，预测误差降低了30%以上.
Based on the issue that monitoring of wheel wear is difficult to be implemented directly during grinding process, a multi-feature optimization and fusion based random forest (MFOF-RF) algorithm was proposed to realize the accurate prediction of wheel wear. An experiment of cylindrical traverse grinding was performed and the power, acceleration and acoustic emission signals were collected and processed in order to extract a large amount of time-domain and frequency-domain signal features. Statistical criteria were used to adjust model parameters and choose best feature combination for the prediction of wheel wear. The results shown that the MFOF-RF model improved the prediction accuracy and diminished error more than 30% compared with the model with single feature.
［1］BRINKSMEIER E, WERNER F. Monitoring of grinding wheel wear［J］. CIRP Annals, 1992, 41(1): 373-376.
［2］ROWE W. Principles of modern grinding technology ［M］. New York: William Andrew, 2013: 113-122.
［3］MARINESCU I, HITCHINER M, UHLMANN E, et al. Handbook of machining with grinding wheels ［M］. Florida: CRC Press, 2006: 83-85.
［4］LI B Z, NI J M, YANG J G, et al. Study on high-speed grinding mechanisms for quality and process efficiency［J］. The International Journal of Advanced Manufacturing Technology, 2014, 70(5): 813-819.
［5］SU J, TARNG Y. Measuring wear of the grinding wheel using machine vision ［J］. The International Journal of Advanced Manufacturing Technology, 2006, 31(2): 50-60.
［6］ARUNACHALAM N, RAMAMOORTHY B. Texture analysis for grinding wheel wear assessment using machine vision ［J］. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 2007, 221(3): 419-430.
［7］SHEN J, WANG J, JIANG B, et al. Study on wear of diamond wheel in ultrasonic vibration-assisted grinding ceramic ［J］. Wear, 2015, 332: 788-793.
［8］HWANG T, WHITENTON E, HSU N, et al. Acoustic emission monitoring of high speed grinding of silicon nitride ［J］. Ultrasonics, 2000, 38(4): 614-619.
［9］LIAO T, TING C, QU J, et al. A wavelet-based methodology for grinding wheel condition monitoring［J］. International Journal of Machine Tools and Manufacture, 2007, 47(3): 580-592.
［10］FENG J, KIM B S, SHIH A, et al. Tool wear monitoring for micro-end grinding of ceramic materials［J］. Journal of Materials Processing Technology, 2009, 209(11): 5110-5116.
［11］XU L M, XU K Z, CHAI Y D. Identification of grinding wheel wear signature by a wavelet packet decomposition method［J］. Journal of Shanghai Jiao Tong University (Science), 2010, 15(3): 323-328.
［12］WANG J J, FENG P F, ZHA T J. Process monitoring in precision cylindrical traverse grinding of slender bar using acoustic emission technology［J］. Journal of Mechanical Science and Technology, 2017, 31(2): 859-864.
［13］YANG Z, YU Z. Grinding wheel wear monitoring based on wavelet analysis and support vector machine ［J］. The International Journal of Advanced Manufacturing Technology, 2012, 62(2): 107-121.
［14］石建, 丁宁. 基于声发射技术的砂轮磨损状况在线检测［J］. 长春大学学报, 2013, 23(8): 931-936.
SHI Jian, DING Ning. On-line detection of the state of grinding wheel wear based on acoustic emission technique［J］. Journal of Changchun University, 2013, 23(8): 931-936.
［15］ARRIANDIAGA A, PORTILLO E, SáNCHEZ J, et al. Virtual sensors for on-line wheel wear and part roughness measurement in the grinding process［J］. Sensors, 2014, 14(5): 8756-8778.
［16］MOIA D, THOMAZELLA I, AGUIAR P, et al. Tool condition monitoring of aluminum oxide grinding wheel in dressing operation using acoustic emission and neural networks ［J］. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2015, 37(2): 627-640.
［17］CHOI T, SUBRAHMANYA N, LI H, et al. Ge-neralized practical models of cylindrical plunge grinding processes ［J］. International Journal of Machine Tools and Manufacture, 2008, 48(1): 61-72.
［18］YAN L, ZHOU Z, JIANG F, et al. The application of three-dimensional surface parameters to characterizing grinding wheel topography ［J］. Advanced Materials Research, 2010, 126(1): 603-608.
［19］QIAO G, DONG G, ZHOU M. Simulation and assessment of diamond mill grinding wheel topography ［J］. The International Journal of Advanced Manufacturing Technology, 2013, 68(9): 2085-2093.
［20］PAN Y, ZHAO Q, GUO B. On-machine measurement of the grinding wheels’ 3D surface topography using a laser displacement sensor ［C］//7th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Advanced Optical Manufacturing Technologies. International Society for Optics and Photonics, Harbin, China: SPIE, 2014: 9281-9290.
［21］资嘉磊, 黄红武, 盛晓敏. 超高速平面磨削振动特性试验研究［J］. 机械与电子, 2006, 24(11): 10-12.
ZI Jialei, HUANG Hongwu, SHENG Xiaomin. Study on the vibration characteristic of ultra-high speed surface grinding［J］. Machinery & Electronics, 2006, 24(11): 10-12.
［22］JAMES G, WITTEN D, HASTIE T, et al. An introduction to statistical learning ［M］. New York: Springer, 2013: 68-71.
［23］BREIMAN L. Random forests ［J］. Machine Learn-ing, 2001, 45(1): 5-32.
［24］KUHN M, JOHNSON K. Applied predictive modeling ［M］. New York: Springer, 2013: 20-24.
