基于回归树和AdaBoost方法的刀具磨损评估
作者:
基金项目:

沈阳市2014年科学计划项目(F14-056-7-00)


Tool Wear Evaluation Based on Decision Tree Regression and AdaBoost Algorithm
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [16]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    本文利用高速数控铣刀铣削中不同侧面方向的切削力和振动信号以及声发射信号均方根值,以数据驱动的形式对刀具磨损进行了拟合评估. 在本次研究中,分别从时域、频域和时频联合域上探索与刀具磨损相关的敏感特征,具体特征提取方法包括时域统计分析、频域上的快速傅里叶变换(FFT)和时频联合分析的小波变换(WT). 本文中,决策树被用于回归问题而非分类问题,用于评估刀具磨损值. 同时,引入AdaBoost算法对回归树模型进行提升,并从模型的准确性、稳定性和适用性三个方面上综合对比了提升的决策树回归模型和原模型的性能. 研究表明,AdaBoost算法提升的回归决策树模型在预测的准确性和稳定性上都有一定程度上提高,并且在面向全新刀具磨损预测的适用性上也取得了不错的提升效果.

    Abstract:

    In this paper, the cutting force and vibration signals in different axial directions and the RMS of the acoustic emission signal in the milling of the high speed CNC cutters are fully utilized to evaluate the tool wear in the data-driven method. In this study, the sensitive features related to tool wear are explored from three aspects: time-domain, frequency-domain and joint time-frequency domain, and the feature extraction methods include time-domain statistical analysis, fast Fourier transform (FFT) between time-domain and frequency-domain, and wavelet transform (WT) in time-frequency domain. In this paper, the decision tree will be used for regression problems, rather than classification issues, to assess the tool wear value. And then, the AdaBoost algorithm is introduced to improve the performance of the decision tree regression (DTR), and the performance of the adaptive boosted decision tree regression (DTR-Ada) model and the original model are compared at the aspects of the accuracy, steadiness and applicability. The result shows the DTR-Ada model can improve the accuracy and stability of the fitting and prediction, and it also achieves a good effect on the applicability of the new tool wears prediction.

    参考文献
    [1] Huang S, Li X, Gan OP. Tool wear estimation using support vector machines in ball-nose end milling. Proc. of the 2010 Annual Conference of the Prognostics and Health Management Society. Portland, Oregon, USA. 2010.
    [2] Benkedjouh T, Medjaher K, Zerhouni N, et al. Health assessment and life prediction of cutting tools based on support vector regression. Journal of Intelligent Manufacturing, 2015, 26(2): 213-223. [DOI:10.1007/s10845-013-0774-6]
    [3] 韩玉辉. 基于粒子群优化SVM的刀具磨损量预测. 工具技术, 2016, 50(11): 109-112. [DOI:10.3969/j.issn.1000-7008.2016.11.031]
    [4] Li X, Lim BS, Zhou JH, et al. Fuzzy neural network modelling for tool wear estimation in dry milling operation. Proc. of 2009 International Conference of Prognostics and Health Management. San Diego, USA. 2009.
    [5] Tobon-Mejia DA, Medjaher K, Zerhouni N. CNC machine tool's wear diagnostic and prognostic by using dynamic Bayesian networks. Mechanical Systems and Signal Processing, 2012, 28: 167-182. [DOI:10.1016/j.ymssp.2011.10.018]
    [6] Chen HM. A multiple model prediction algorithm for cnc machine wear pHM. International Journal of Prognostics and Health Management, 2011, 2(2): 27. (请补全页码)
    [7] PHM Society. 2010 phm society conference data challenge. https://www.phmsociety.org/competition/phm/10. [2010].
    [8] MathWorks. Signal processing ToolBox. http://cn.mathworks.com/help/signal/ref/hampel.html. [2016].
    [9] 陈侃. 基于多模型决策融合的刀具磨损状态监测系统关键技术研究[博士学位论文]. 成都: 西南交通大学, 2012.
    [10] MathWorks. Wavelet ToolBox. http://cn.mathworks.com/help/wavelet/ref/wavedec.html. [2016].
    [11] Mallat SG. A theory for multiresolution signal decomposition: The wavelet representation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1989, 11(7): 674-693. [DOI:10.1109/34.192463]
    [12] Kraskov A, Stögbauer H, Grassberger P. Estimating mutual information. Physical Review E, 2004, 69(6 Pt 2): 066138.
    [13] Ross BC. Mutual information between discrete and continuous data sets. PLoS One, 2014, 9(2): e87357. [DOI:10.1371/journal.pone.0087357]
    [14] Wikipedia. Decision tree learning. https://en.wikipedia.org/wiki/Decision_tree_learning#Variance_reduction.
    [15] Breiman L, Friedman J, Stone CJ, et al. Classification and regression trees. Boca Raton: Chapman and Hall/CRC, 1984: 358.
    [16] 李航. 统计学习方法. 北京: 清华大学出版社, 2012: 137-151.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

陶耀东,曾广圣,李宁.基于回归树和AdaBoost方法的刀具磨损评估.计算机系统应用,2017,26(12):212-219

复制
分享
文章指标
  • 点击次数:1870
  • 下载次数: 3174
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2017-03-20
  • 最后修改日期:2017-04-10
  • 在线发布日期: 2017-12-07
文章二维码
您是第11202453位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号