特征选择是刀具模式识别的关键问题之一。笔者采用果蝇优化算法（FOA）将铣削力特征选择转换成果蝇寻优过程，得到了一种可用于铣刀磨损状态识别的适应度强的特征选择方法。该方法用力传感器提取铣削力特征，把特征选择过程模拟成果蝇觅食行为，采用Fisher辨别率作为特征寻优标准，将优选后的特征集输入BP神经网络，刀具磨损量为输出。实验证明，该方法易调节，寻优效果好，适应度强，BP神经网络表现好，可以快速有效地在线提取铣削加工过程的特征。
Abstract
Feature selection is one of the key processes in pattern recognition. To solve the problem of identification of tool wear condition, a feature selection method based on Improved Fruit Fly Optimization Algorithm was proposed. Feature selection of cutting force was converted to food finding process of the fruit fly. The experiment was conducted on a Makino CNC milling machine equipped with: milling cutter, EGD440R; and insert material was A30N. Cutting force was extracted using Kistler 9257B three-phase dynamometer, analyzed by wavelet packet theory to reduce noise and exact the energy feature of the signal as a basis for feature selection. Then, an Improved Fruit Fly Optimization Algorithm was established, in which Fisher discrimination was chosen as optimization criteria. The optimal feature subset is put into a BP neural network, which outputs the flank wear. The result of experiment indicates that the parameter of the model is easy to adjust, has good optimization result and BP network performance as shown in Table1, has ample potential for cutting feature selection.
关键词
果蝇优化算法 /
特征选择 /
模式识别 /
刀具磨损
{{custom_keyword}} /
Key words
Fruit Fly Optimization Algorithm /
Feature selection /
Pattern recognition /
Tool wear
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
1 Mei Wang , Jie Wang.CHMM for tool condition monitoring and remaining useful life prediction[J].The International Journal of Advanced Manufacturing Technology,2012,59(5):463-471.
2 Lin, J.T., Bhattacharyya, D., & Kecman, V. Multiple regression and neural networks analyses in composites machining[J]. Composites Science and Technology, 2003,63(3):539-548.
3 赵德滨，宋利利，闫纪红. 基于模糊聚类分析的特征识别方法及其应用[J].《计算机集成制造系统-CIMS》，2009.15(9)：2417-2423.
ZH AODe-bin, SONG Li-li, Y AN J i-hong.Feature recognition method based on fuzzy clustering analysis and its application[J].Computer Integr ated Manufacturing Systems,2009.15(9)：2417-2423.
4 Goldberg, D.E,Genetic algorithms in search, optimization, and machine learning[J]. Addison/Wesley, Reading,1988,3:95~99.
5 Wen-Tsao Pan,A new fruit fly optimization algorithm: Taking the financial distress model as an example[J].Knowledge-Based Systems,2012,26(6):69-74.
6 韩俊英，刘成忠. 自适应变异的果蝇优化算法[J].《计算机应用研究》，2013，30(9)：2641-2644.
HAN Junying，LIU Chengzhong.Fruit fly optimization algorithm with adaptive mutation[J].Application Research of Computer,2013,30(9)：2641-2644.
7 吴小文，李挚. 果蝇算法和5种群智能算法的寻优性能研究[J].火力与指挥控制，2013，38(4)：17-25.
WU Xiao-wen,LI Qing.Research of Optimizing Performance of Fruit Fly Optimization Algorithm and Five Kinds of Intelligent Algorithm,2013，38(4)：17-25.
8 Marko Mitic´,Chaotic fruit fly optimization algorithm[J].Knowledge-Based Systems,2015,89(13):446-458.
9 Lianghong Wu,A cloud model based fruit fly optimization algorithm[J].Knowledge-Based Systems,2015,89(15):603-617.
10 Wenchuan Wang,Improved fruit fly optimization algorithm optimized wavelet neural network for statistical data modeling for industrial polypropylene melt index prediction[J].Journal of chemometrics,2015,29(9):506-513.
11 Lin Wang,An improved fruit fly optimization algorithm and its application to joint replenishment problems[J].Expert Systems with Applications,2015,42(9):4310-4323.
12 刘路，王太勇，蒋永翔.基于超球面支持向量机的刀具磨损状态识别[J].农业机械学报，2011，42(1)：218-222.
Liu Lu,Wang Taiyong, Jiang Yongxiang.Tool Wear State Recognition Based on Hyper-sphere Support Vector Machine[J].Transaction of the Chinese Society For Agricultural Machinery,2011,42(1):218-222.
13 黄华，李爱平.基于小波神经网络的切削刀具磨损识别[J].农业机械学报，2008，39（8）：173-177．
Huang Hua,Li AiPing.Wear detection on cutting tools based on wavelet neural work[J].Transaction of the Chinese Society For Agricultural Machinery,2008,39(8):173-177.
14 Chien-Jen Huang,Using multi-stage data mining technique to build forecast model for Taiwan stocks[J].Neural Computing & Applications,2012, 21(8):2057-2063.
15 FUKUNAGA K. Introduction to statistical pattern recognition[M].San Diego:Academic Press Inc., 1992.
16 张军，陆森林，和卫星.基于小波包能量法的滚动轴承故障诊断[J].农业机械学报，2007，38(10)：178-181.
Zhang Jun,Lu Senlin,He Weixing.Vibrating Diagnosis of Roll ing Bearings Based on Wavelet Packet Energy Feature[J].Transaction of the Chinese Society For Agricultural Machinery,2007,38(10):178-181.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1424 KB)
