Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2020, Vol. 54 Issue (1): 40-47    DOI: 10.3785/j.issn.1008-973X.2020.01.005
机械工程     
基于GA-WPT-ELM的6061铝合金表面粗糙度预测
谭芳芳1(),朱俊江1,严天宏1,*(),高志强2,何岭松2
1. 中国计量大学 机电工程学院，浙江 杭州 310018
2. 华中科技大学 机械科学与工程学院，湖北 武汉 430074
Surface roughness prediction of 6061 aluminum alloy based on GA-WPT-ELM
Fang-fang TAN1(),Jun-jiang ZHU1,Tian-hong YAN1,*(),Zhi-qiang GAO2,Ling-song HE2
1. College of Mechanical and Electronic Engineering, China Jiliang University, Hangzhou 310018, China
2. School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
 全文: PDF(1170 KB)   HTML
摘要：

为了提高工件表面粗糙度预测的准确性，针对振动信号特征识别和表面粗糙度预测建模时多个参数难以同步优化和人工经验调优误差较大的问题，提出基于遗传算法（GA）的信号特征识别和表面粗糙度预测的优化算法. 对采集的6061铝合金铣削振动信号进行小波包变换（WPT）和多个特征提取，利用GA优化WPT母小波和特征向量；将信号特征向量和表面粗糙度分别作为极限学习机（ELM）的输入和输出，对预测模型训练的同时，利用GA优化ELM隐含层的神经元个数；对训练好的预测模型进行测试. 实验结果表明，通过GA对振动信号识别和表面粗糙度预测的3类参数同步优化，获得了最佳的信号特征和较高的表面粗糙度预测精度，节省了建模分析计算成本.
关键词： 在线振动信号;  遗传算法（GA）;  小波包变换;  极限学习机（ELM）;  表面粗糙度预测    
Abstract:

The problem of multi-parameter simultaneous optimization and large error of empirical tuning should be solved in the vibration signal feature recognition and surface roughness prediction processes in order to improve the on-line prediction accuracy of workpiece surface roughness. The optimization method of signal feature recognition and surface roughness prediction modeling was proposed based on genetic algorithm (GA). GA was used to choose mother wavelet and feature quantities when signal features of milling 6061 aluminum alloy was recognized based on wavelet packet transform (WPT). The number of neurons in hidden layer was selected by GA when signal features and surface roughness were used to train extreme learning machine (ELM). The prediction modeling which has been trained was tested. The experimental results show that the three types of parameters for signal recognition and surface roughness prediction were simultaneously optimized by GA. GA-WPT-ELM not only obtains the best features of signal and the higher prediction accuracy of surface roughness, but also reduces analytical-computational cost in the modeling processes.
Key words: on-line vibration signal    genetic algorithm (GA)    wavelet packet transform    extreme learning machine (ELM)    surface roughness predicting
收稿日期: 2018-12-03 出版日期: 2020-01-05
CLC:  TP 18  
基金资助: 国家自然科学基金资助项目（61801454，51379198，51075377）；浙江省自然科学基金资助项目（LQ18F010006）
通讯作者: 严天宏     E-mail: tff097443@yeah.net;thyan@163.com
作者简介: 谭芳芳（1993—），女，硕士生，从事信号处理的研究. orcid.org/0000-0003-2728-9476. E-mail： tff097443@yeah.net
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
谭芳芳
朱俊江
严天宏
高志强
何岭松

引用本文:

谭芳芳,朱俊江,严天宏,高志强,何岭松. 基于GA-WPT-ELM的6061铝合金表面粗糙度预测[J]. 浙江大学学报(工学版), 2020, 54(1): 40-47.

Fang-fang TAN,Jun-jiang ZHU,Tian-hong YAN,Zhi-qiang GAO,Ling-song HE. Surface roughness prediction of 6061 aluminum alloy based on GA-WPT-ELM. Journal of ZheJiang University (Engineering Science), 2020, 54(1): 40-47.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2020.01.005    或    http://www.zjujournals.com/eng/CN/Y2020/V54/I1/40

图 1  小波包分解结构图
图 2  极限学习机网络结构图
图 3  GA优化特征提取和预测模型的流程图
图 4  铣削振动信号采集与分析系统
n/（103 r·min?1） f/（103 mm·min?1） d/mm
6 1 1.0
9 1.65 0.7
12 2.3 0.5
15 3 0.3
18 — —
表 1  铣削加工参数
图 5  主轴铣削实验及传感器测量
类型 族系 Ψ
正交 Daubechies db2,db3,db4,db5,db6,db7,db8,db9,
db10,db11,db12,db13,db14
正交 Haar Haar
正交 Coiflets coif1,coif2,coif3,coif4,coif5
正交 Symmlets sym2,sym3,sym4,sym5,sym6,sym7, sym8
双正交 Biorthogonal bior1.3,bior1.5,bior2.2,bior2.4,bior2.6,
bior2.8,bior3.1,bior3.3,bior3.5,bior3.7,
bior3.9,bior4.4,bior5.5,bior6.8
表 2  小波包分解的母小波类型
特征 v 特征 v
均值 $J_{_{Gj}}^{{\lambda ^i}}$ 偏态 $P_{_{Gj}}^{{\lambda ^i}}$
标准差 $B_{_{Gj}}^{{\lambda ^i}}$ 峰态 $F_{_{Gj}}^{{\lambda ^i}}$
峰峰值 ${\rm{FF}}_{_{Gj}}^{{\lambda ^i}}$ 能量熵 $H_{_{Gj}}^{{\lambda ^i}}$
表 3  振动信号的统计特征量
图 6  母小波优化选取结果
图 7  bior5.5的尺度函数和小波函数
振动信号组别 Ψ v l σ/%
Gx bior5.5 $H_{G_{x}}^{\rm{DAAAA}}$ 76 88.95
Gx db8 $H_{G_{x}}^{\rm{DAAA}}$ 62 83.46
Gx Haar $P_{G_{x}}^{\rm{DAD}}$ 49 80.53
Gx coif3 $F_{G_{x}}^{\rm{DADAA}}$ 96 80.22
Gy db14 $H_{G_{y}}^{\rm{ADA}}$ 86 83.82
Gy db5 $H_{G_{y}}^{\rm{ADAA}}$ 64 82.22
Gy bior1.5 $H_{G_{y}}^{\rm{AAADA}}$ 31 81.24
Gz db6 $H_{G_{z}}^{\rm{AADAD}}$ 26 80.69
Gz sym6 $H_{G_{z}}^{\rm{DADA}}$ 38 82.92
表 4  GA优化算法训练结果
图 8  GA优化曲线及个体选择
图 9  表面粗糙度拟合曲线
组序号 n/（103
r·min?1） 		f/（103
mm·min?1） 		d/
mm 		$ \hat R_{\rm{a}} $/μm Ra/μm Δe/
μm
1 18 1.65 0.3 0.122 8 0.137 1 0.014 4
2 12 1.65 0.3 0.146 3 0.176 9 0.030 7
3 15 2.3 0.3 0.173 0 0.132 4 ?0.040 6
4 6 1 1.0 0.187 5 0.206 5 0.019 0
5 12 2.3 1.0 0.216 5 0.242 2 0.025 7
6 15 3 1.0 0.262 5 0.242 2 ?0.020 3
7 9 2.3 0.5 0.350 5 0.419 8 0.069 3
8 12 3 0.3 0.356 3 0.367 6 0.011 4
9 9 2.3 0.7 0.396 8 0.347 3 ?0.049 5
10 6 1.65 0.5 0.506 5 0.496 5 ?0.010 0
11 9 3 1.0 0.624 0 0.629 7 0.005 7
12 9 3 0.5 0.694 3 0.700 2 0.005 9
13 6 2.3 1.0 0.772 3 0.770 0 ?0.002 2
14 6 2.3 0.5 0.849 3 0.837 5 ?0.011 8
15 6 3 0.5 0.967 3 0.977 9 0.010 6
表 5  表面粗糙度预测结果
比较对象 信号源 样本数 方法 v σ/%
本文研究 振动信号 960 GA-WPT $H_{G_{x}}^{\rm{DAAAA}}$ 88.95
文献[14] 振动信号 360 SSA $a_y^{{\lambda _i}}$ 85.4
文献[13] 振动信号 20 TDA ax, v,f,d 80.0
文献[15] 切削力信号 360 G-WPT $X_{{F_X}}^{\rm{AAAA}}$ 88.1
表 6  不同研究方法的表面粗糙度预测结果对比
1 WANG H, TO S, CHAN C Y Investigation on the influence of tool-tip vibration on surface roughness and its representative measurement in ultra-precision diamond turning[J]. International Journal of Machine Tools and Manufacture, 2013, 69 (3): 20- 29
2 仲为武, 赵东标, 王希 航空铝合金7050-T7451干式铣削工艺参数对振动信号影响研究[J]. 中国机械工程, 2011, 22 (4): 458- 461
ZHONG Wei-wu, ZHAO Dong-biao, WANG Xi Effects of process parameters on vibration signals in dry milling of aeronautic aluminum alloy 7050-T7451[J]. China Mechanical Engineering, 2011, 22 (4): 458- 461
3 王政平, 张锡芳, 张艳娥 表面粗糙度光学测量方法研究进展[J]. 传感器与微系统, 2007, 26 (9): 4- 6
WANG Zheng-ping, ZHANG Xi-fang, ZHANG Yan-e Progress on optical measurement of surface roughness[J]. Transducer and Microsystem Technologies, 2007, 26 (9): 4- 6
doi: 10.3969/j.issn.1000-9787.2007.09.002
4 刘晨, 卢荣胜, 陈磊, 等 基于光学法表面粗糙度的测量研究进展[J]. 半导体光电, 2010, 31 (4): 495- 500
LIU Chen, LU Rong-sheng, CHEN Lei, et al Progress of surface roughness measurement based on optical method[J]. Semiconductor Optoelectronics, 2010, 31 (4): 495- 500
5 SALGADO D R, ALONSO F J, CAMBERO I, et al In-process surface roughness prediction system using cutting vibrations in turning[J]. The International Journal of Advanced Manufacturing Technology, 2009, 43 (1/2): 40- 51
6 LAURO C H, BRANDAO L C, BALDO D, et al Monitoring and processing signal applied in machining processes: a review[J]. Measurement, 2014, 58: 73- 86
doi: 10.1016/j.measurement.2014.08.035
7 OZEL T, KARPAT Y, LUíS FIGUEIRA, et al Modelling of surface finish and tool flank wear in turning of AISI D2 steel with ceramic wiper inserts[J]. Journal of Materials Processing Technology, 2007, 189 (1-3): 192- 198
doi: 10.1016/j.jmatprotec.2007.01.021
8 HESSAINIA Z, BELBAH A, YALLESE M A, et al On the prediction of surface roughness in the hard turning based on cutting parameters and tool vibrations[J]. Measurement, 2013, 46 (5): 1671- 1681
doi: 10.1016/j.measurement.2012.12.016
9 KIM D S, CHANG I C, KIM S W Microscopic topographical analysis of tool vibration effects on diamond turned optical surfaces[J]. Precision Engineering, 2002, 26 (2): 168- 174
doi: 10.1016/S0141-6359(01)00115-5
10 SEGRETO T, KARAM S, SIMEONE A, et al Residual stress assessment in Inconel 718 machining through wavelet sensor signal analysis and sensor fusion pattern recognition[J]. Procedia CIRP, 2013, 9: 103- 108
doi: 10.1016/j.procir.2013.06.176
11 迟军, 陈廉清, 杨超珍 基于小波包分析和Elman网络的切削表面粗糙度预测方法[J]. 中国机械工程, 2010, (7): 822- 826
CHI Jun, CHEN Lian-qing, YANG Chao-zhen Research on prediction of cutting surface roughness based on wavelet packet analysis and Elman network[J]. China Mechanical Engineering, 2010, (7): 822- 826
12 UPADHYAY V, JAIN P K, MEHTA N K In-process prediction of surface roughness in turning of Ti–6Al–4V alloy using cutting parameters and vibration signals[J]. Measurement, 2013, 46 (1): 154- 160
doi: 10.1016/j.measurement.2012.06.002
13 RISBOOD K A, DIXIT U S, SAHASRABUDHE A D Prediction of surface roughness and dimensional deviation by measuring cutting forces and vibrations in turning process[J]. Journal of Materials Processing Tech, 2003, 132 (1): 203- 214
14 PLAZA E G, LóPEZ P J N Surface roughness monitoring by singular spectrum analysis of vibration signals[J]. Mechanical Systems and Signal Processing, 2017, 84: 516- 530
doi: 10.1016/j.ymssp.2016.06.039
15 PLAZA E G, LóPEZ P J N Analysis of cutting force signals by wavelet packet transform for surface roughness monitoring in CNC turning[J]. Mechanical Systems and Signal Processing, 2018, 98: 634- 651
doi: 10.1016/j.ymssp.2017.05.006
16 钟崴, 彭梁, 周永刚, 等 基于小波包分析和支持向量机的锅炉结渣诊断[J]. 浙江大学学报: 工学版, 2016, 50 (8): 1499- 1506
ZHONG Wei, PENG Liang, ZHOU Yong-gang, et al Slagging diagnosis of boiler based on wavvelet packet analysis and support vector machine[J]. Journal of Zhejiang University: Engineering Science, 2016, 50 (8): 1499- 1506
17 李国宾, 关德林, 李廷举 基于小波包变换和奇异值分解的柴油机振动信号特征提取研究[J]. 振动与冲击, 2011, 30 (8): 149- 152
LI Guo-bin, GUAN De-lin, LI Ting-ju Study on feature extraction of diesel engine vibration signal based on wavelet packet transform and singularity value decomposition[J]. Journal of Vibration and Shock, 2011, 30 (8): 149- 152
doi: 10.3969/j.issn.1000-3835.2011.08.029
18 HUANG G B, ZHU Q Y, SIEW C K Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70 (1-3): 489- 501
doi: 10.1016/j.neucom.2005.12.126
19 HUANG G B, ZHOU H, DING X, et al Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 2012, 42 (2): 513- 529
doi: 10.1109/TSMCB.2011.2168604
20 段斌, 梁军, 费正顺, 等 基于GA-ANN的非线性半参数建模方法[J]. 浙江大学学报: 工学版, 2011, 45 (6): 977- 983
DUAN Bin, LIANG Jun, FEI Zheng-shun, et al Nonlinear semi-parametruc modeling mothed based on GA-ANN[J]. Journal of Zhejiang University: Engineering Science, 2011, 45 (6): 977- 983
21 刘浩然, 赵翠香, 李轩, 等 一种基于改进遗传算法的神经网络优化算法研究[J]. 仪器仪表学报, 2016, 37 (7): 1573- 1580
LIU Hao-ran, ZHAO Cui-xiang, LI Xuan, et al Study on a neural network optimization algorithm based on improved genetic algorithm[J]. Chinese Journal of Scientific Instrument, 2016, 37 (7): 1573- 1580
doi: 10.3969/j.issn.0254-3087.2016.07.017
22 杨阳, 李春, 缪维跑, 等 基于多目标遗传算法的风力机叶片全局优化设计[J]. 机械工程学报, 2015, 51 (14): 192- 198
YANG Yang, LI Chun, MIAO Wei-pao, et al Global optimal design of wind turbines blade based on multi-object genetic algorithm[J]. Journal of Mechanical Engineering, 2015, 51 (14): 192- 198
23 TABOADA H A, ESPIRITU J F, COIT D W MOMS-GA: a multi-objective multi-state genetic algorithm for system reliability optimization design problems[J]. IEEE Transactions on Reliability, 2008, 57 (1): 182- 191
doi: 10.1109/TR.2008.916874
24 刘守山, 杨辰龙, 李凌, 等 基于自适应小波阈值的超声信号消噪[J]. 浙江大学学报: 工学版, 2007, 41 (9): 1557- 1560
LIU Shou-shan, YANG Chen-long, LI Ling, et al Adaptive wavelet thresholding based ultrasonic signal denoising[J]. Journal of Zhejiang University: Engineering Science, 2007, 41 (9): 1557- 1560
25 覃柏英, 林贤坤, 张令弥, 等 基于整数编码遗传算法的传感器优化配置研究[J]. 振动与冲击, 2011, 30 (2): 252- 257
QIN Bo-ying, LIN Xian-kun, ZHANG Ling-mi, et al Research on optimal sensor placement based on integer-coded genetic algorithm[J]. Journal of Vibration and Shock, 2011, 30 (2): 252- 257
doi: 10.3969/j.issn.1000-3835.2011.02.051
[1] 商强, 林赐云, 杨兆升, 邴其春, 邢茹茹. 基于变量选择和核极限学习机的交通事件检测[J]. 浙江大学学报(工学版), 2017, 51(7): 1339-1346.
[2] 苏亮, 宋明亮, 董石麟, 罗尧治. 循环遗传聚类法稳定图自动分析[J]. 浙江大学学报(工学版), 2017, 51(3): 514-523.
[3] 谢罗峰, 徐慧宁, 黄沁元, 赵越, 殷国富. 应用双树复小波包和NCA-LSSVM检测磁瓦内部缺陷[J]. 浙江大学学报(工学版), 2017, 51(1): 184-191.
[4] 王树朋,黄凯,严晓浪. 基于遗传算法的覆盖率驱动测试产生器[J]. 浙江大学学报(工学版), 2016, 50(3): 580-588.
[5] 裘日辉, 刘康玲, 谭海龙, 梁军. 基于极限学习机的分类算法及在故障识别中的应用[J]. 浙江大学学报(工学版), 2016, 50(10): 1965-1972.
[6] 刘扬,鲁乃唯,蒋友宝. 结构体系可靠度分析的改进支持向量回归[J]. 浙江大学学报(工学版), 2015, 49(9): 1692-1699.
[7] 肖文生,崔俊国,刘健,吴晓东,黄红胜. 直驱采油用永磁同步电机削弱齿槽转矩优化[J]. 浙江大学学报(工学版), 2015, 49(1): 173-180.
[8] 肖文生,崔俊国,刘健,吴晓东,黄红胜. 直驱采油用永磁同步电机削弱齿槽转矩优化[J]. 浙江大学学报(工学版), 2014, 48(8): 1-8.
[9] 张鼎逆,刘毅. 基于改进遗传算法和序列二次规划的再入轨迹优化[J]. J4, 2014, 48(1): 161-167.
[10] 林震宇 李智勇 吴为麟. 基于嵌入式零树编码的电力系统数据压缩[J]. J4, 2007, 41(2): 291-293.