基于融合评价指标和神经网络的刀具磨损预测

doi:10.3969/j.issn.1000-1093.2021.09.022

兵工学报 ›› 2021, Vol. 42 ›› Issue (9): 2013-2023.doi: 10.3969/j.issn.1000-1093.2021.09.022

基于融合评价指标和神经网络的刀具磨损预测

秦国华¹，高杰¹，叶海潮¹，姜国杰²，黄帅¹，赖晓春³

(1.南昌航空大学航空制造工程学院，江西南昌 330063；2.北京航空材料研究院，北京 100095；3.江西省教育厅江西省教育国际合作与教师发展中心，江西南昌 330083)

上线日期:2021-10-20
通讯作者: 秦国华(1970—)，男，教授，博士生导师 E-mail:qghwzx@126.com
作者简介:高杰（1995—），男，硕士研究生。E-mail: 690849337@qq.com；
叶海潮（1979—），男，讲师，博士。E-mail: xxjy2000@163.com；
姜国杰（1985—），男，研究员，博士。E-mail: jieguo201@163.com；
黄帅（1995—），男，硕士研究生。E-mail: 1170019593@qq.com；
赖晓春（1981—），女，副教授，硕士。E-mail: springlet2002@sina.com
基金资助:
国家自然科学基金项目(51765047)；江西省主要学科学术和技术带头人计划项目(20172BCB22013)；江西省科技厅重点研发计划项目(20203BBE53049)

Tool Wear Prediction Based on Fusion Evaluation Index and Neural Network

QIN Guohua¹， GAO Jie¹， YE Haichao¹， JIANG Guojie²， HUANG Shuai¹， LAI Xiaochuun³

(1.School of Aeronautical Manufacturing Engineering， Nanchang Hangkong University，Nanchang 330063，Jiangxi，China；2.AECC Beijing Insititute of Aeronautical Materials，Beijing 100095，China；3.Jiangxi Education International Cooperation and Teacher Development Center，Jiangxi Provincial Department of Education，Nanchang 330083，Jiangxi，China)

Online:2021-10-20

摘要/Abstract

摘要： 机械加工过程中的刀具磨损状态对零件的加工质量、生产效率和成本影响极大。对刀具磨损的采集信号进行合理准确地降噪处理，是实现刀具磨损检测的核心技术。利用熵值法构造出信噪比、平滑度、均方根误差3个传统评价指标的权重，提出降噪质量的融合评价指标。对比仿真信号的去噪结果与真实信号发现，融合评价指标更具可行性和优越性。以最大融合评价指标为目标，提出降噪参数的优化方法。针对小波阈值去噪后的实际刀具磨损振动信号，与传统的单个评价指标相比，融合评价指标优选出来的降噪参数，不仅能够去除\[6 kHz，12 kHz\]高频部分的噪声信号，而且能够比较完整地保留\[0 kHz，6 kHz\]低频部分的真实信号。通过提取出刀具磨损特征值，建立切削工艺参数与刀具磨损之间的神经网络预测模型。刀具磨损试验结果表明，预测结果与试验测量值之间的最大误差不超出6.0%，进一步验证了基于多指标融合评价的最佳降噪参数能够准确地提取出刀具磨损信号的特征量。

关键词: 刀具磨损, 评价指标, 熵值法, 小波阈值去噪, 降噪参数

Abstract: Tool wear has a great influence on the machining quality，production efficiency and cost of parts in the process of machining. The reasonable and accurate noise reduction for collected tool wear signal is the core technology for tool wear detection. Based on the weights of the signal-to-noise ratio，the smoothness and the mean square root error which are constructed by the entropy method，the fusion evaluation index of noise reduction quality is proposed. Comparison of the denoised simulated signal with the real signal shows that the fusion evaluation index is of the feasibility and superiority. And then an optimization method of noise reduction parameters is presented with the objective of maximum fusion evaluation index. For the actual vibration signal of tool wear after wavelet threshold denoising，the noise reduction parameters optimized by the fusion evaluation index proposed in this paper can be used to remove the noise signals at high frequency \[6 kHz，12 kHz\] and also retain completely the real signals at low frequency \[0 kHz，6 kHz\] compared with the traditional single evaluation index. Finally，a neural network prediction model is established from the extracted feature values of tool wear for describing the relationship between the tool wear and the cutting parameters. Experimental results show that the tool wear signal features can be accurately extracted using the optimal noise reduction parameters based on multi-index fusion evaluation. The maximum error between the predicted values and the measured values is no more than 6.0%.

Key words: toolwear, noisereductionparameter, entropymethod, waveletthresholddenoising, evaluationindex

中图分类号:

TG702

秦国华，高杰，叶海潮，姜国杰，黄帅，赖晓春. 基于融合评价指标和神经网络的刀具磨损预测[J]. 兵工学报, 2021, 42(9): 2013-2023.

QIN Guohua， GAO Jie， YE Haichao， JIANG Guojie， HUANG Shuai， LAI Xiaochuun. Tool Wear Prediction Based on Fusion Evaluation Index and Neural Network[J]. Acta Armamentarii, 2021, 42(9): 2013-2023.

参考文献

［1］陈燕，杨树宝，傅玉灿，等.钛合金TC4高速切削刀具磨损的有限元仿真［J］.航空学报，2013，34(9):2230-2240.
CHEN Y，YANG S B，FU Y C，et al. FEM estimation of tool wear in high speed cutting of Ti6Al4V alloy［J］.Acta Aeronautica et Astronautica Sinica，2013，34(9):2230-2240.(in Chinese)
［2］梁伟云，郭井宽，陈晓波，等.基于影像视觉的立铣刀磨损状态检测技术研究与系统开发［J］.工具技术，2012，46(12): 59-64.
LIANG W Y，GUO J K，CHEN X B，et al. Research and application of end mill wear state measuring system based on shadow casting［J］.Tool Engineering，2012，46(12): 59-64. (in Chinese)
［3］钟建军，宋健，由长喜，等.基于信噪比评价的阈值优选小波去噪法［J］.清华大学学报(自然科学版)，2014， 54(2):259-263.
ZHONG J J，SONG J，YOU C X，et al.Wavelet denoising method with threshold selection rules based on SNR evaluations［J］.Journal of Tsinghua University (Science & Technology)，2014，54(2): 259-263. (in Chinese)

表7 网络测试集
Tab.7 Test set of network

序号
输入样本磨损量/mm
主轴转速/(r·mm^-1)进给量/(mm·r^-1)背吃刀量/mm特征量1特征量2预测值试验值相对误差/%
13200.030.11.277 30.792 50.058 20.058 70.86
28000.100.516.202 68.387 30.584 00.582 70.22
33200.030.12.308 41.872 60.096 90.096 00.93
45200.050.38.315 53.297 60.322 00.341 05.90
51 1200.151.05.283 62.058 40.113 00.113 00
68000.100.517.950 58.461 50.690 00.693 00.43
71 1200.151.08.171 52.993 70.298 00.301 31.11
85200.050.38.482 53.805 90.360 00.360 00
98200.050.815.730 09.790 00.488 00.471 03.60
108200.030.64.010 03.200 00.012 70.012 05.80
115600.041.07.250 06.010 00.447 00.429 04.20

［4］叶昊，王桂增，方崇智.小波变换在故障检测中的应用［J］.自动化学报，1997，23(6):736-741.
YE H，WANG G Z，FANG C Z.Application of wavelet transform to fault detection［J］.Acta Automatica Sinica，1997，23(6):736-741.(in Chinese)
［5］王普，李天垚，高学金，等.分层自适应小波阈值轴承故障信号降噪方法［J］.振动工程学报，2019，32(3): 548-556.
WANG P，LI T Y，GAO X J，et al.Bearing fault signal denoising method of hierarchical adaptive wavelet threshold function［J］.Journal of Vibration Engineering，2019，32(3):548-556. (in Chinese)
［6］杨恢先，王绪四，谢鹏鹤，等.改进阈值与尺度间相关的小波红外图像去噪［J］.自动化学报，2011，37(10):1167-1174.
YANG H X，WANG X S，XIE P H，et al. Infrared image denoising based on improved threshold and inter-scale correlations of wavelet transform［J］.Acta Automatica Sinica，2011，37(10):1167-1174.(in Chinese)
［7］黎锁平，周勇，周永强.自适应小波阈值去噪算法在低空飞行声目标的应用［J］.振动与冲击，2017，36(9): 153-158，230.
LI S P，ZHOU Y，ZHOU Y Q.An adaptive wavelet shrinkage de-noising algorithm for low altitude flying acoustic targets［J］.Journal of Vibration and Shock，2017，36(9):153-158，230. (in Chinese)
［8］ BONDA A G Y，NANDA B K，JONNALAGADDA S. Vibration signature based stability studies in internal turning with a wavelet denoising preprocessor［J］. Measurement，2020，154:107520.
［9］ GE J H，NIU T Y，XU D，et al.A rolling bearing fault diagnosis method based on EEMD-WSST signal reconstruction and multi-scale entropy［J］. Entropy，2020，22(3):290.
［10］ BEALE C，NIEZRECKI C，INALPOLAT M.An adaptive wavelet packet denoising algorithm for enhanced active acoustic damage detection from wind turbine blades［J］.Mechanical Systems and Signal Processing，2020，142:106754.
［11］李薇.基于联合去噪方法的MEMS矢量水听器信号去噪［D］.太原:中北大学，2019.
LI W. Signal denoising of MEMS vector hydrophone based on joint denoising method［D］.Taiyuan:North University of China，2019. (in Chinese)
［12］ LI Z C，WANG T Z，WANG Y D，et al.A wavelet threshold denoising-based imbalance fault detection method for marine current turbines［J］.IEEE Access，2020，8(1): 29815-29825.
［13］ LIU J C，GAO W X.Vibration signal analysis of water seal blasting based on wavelet threshold denoising and HHT transformation ［J］. Advances in Civil Engineering，2020 ［2020-07-01］. https:∥doi.org/10.1155/2020/4381480.
［14］杨秀芳，张伟，杨宇祥.基于提升小波变换的雷达生命信号去噪技术［J］.光学学报，2014，34(3): 0328003.
YANG X F，ZHANG W，YANG Y X. Denoising technology of radar life signal based on lifting wavelet transform［J］.Acta Optica Sinica，2014，34(3): 0328003. (in Chinese)
［15］叶海潮，范武林，秦国华，等.基于翘曲度阈值约束的铝合金板材热轧工艺优化与实验验证［J］.兵工学报，2020，41(8):1623-1632.
YE H C，FAN W L，QIN G H，et al. Optimization and experimental validation of aluminum alloy plate hot-rolling based on constraint of wrapage threshold ［J］. Acta Armamentarii，2020，41(8): 1623-1632. (in Chinese)
［16］秦国华，谢文斌，王华敏.基于神经网络与遗传算法的刀具磨损检测与控制［J］.光学精密工程，2015，23(5):1314-1321.
QIN G H，XIE W B，WANG H M.A detection and control technology for tool wear based on neural network and genetic algorithm［J］.Optics and Precision Engineering，2015，23(5): 1314-1321.(in Chinese)

[1]	马孟新，李蓉，牛兰杰. 侵彻引信加速度信号目标特征中干扰叠加程度的评价指标[J]. 兵工学报, 2022, 43(1): 20-28.
[2]	李恒, 叶祖坤, 查文彬, 王禹林. 基于多传感器信息决策级融合的刀具磨损在线监测[J]. 兵工学报, 2021, 42(9): 2024-2031.
[3]	傅斌贺，刘西侠，刘维平，张传清，宋海军. 不同任务需求下军用车辆乘员信息作业适宜性评价指标研究[J]. 兵工学报, 2020, 41(2): 239-245.
[4]	阎艳，郝佳，陈中明，王国新，沙金龙. 基于模糊决策图与灰色关联分析的枪械设计方案评价[J]. 兵工学报, 2016, 37(10): 1934-1940.
[5]	姜振喜，孙杰, 李国超，贾兴民，李剑峰. TC4铣削加工的刀具磨损与切削力和振动关系研究[J]. 兵工学报, 2015, 36(1): 144-150.
[6]	王展, 颜云辉, 焦学勇. 基于灰色理论的迷彩伪装多指标综合评价[J]. 兵工学报, 2013, 34(10): 1250-1257.
[7]	寇保华，杨涛,张晓今，张青斌. 单发末修子母弹对机场跑道毁伤能力的评价指标[J]. 兵工学报, 2007, 28(8): 934-938.
[8]	童中翔，李寿安，叶广强，惠晓滨. 基于协商定权的飞机生存カ评价体系研究[J]. 兵工学报, 2007, 28(4): 508-512.
[9]	金成哲，贯春德,庞思勤. 正交车铣高强度钢刀具磨损的研究[J]. 兵工学报, 2005, 26(3): 397-400.
[10]	骆清国，张永锋，袁伟. 履带车辆动力传动系统性能综合评价[J]. 兵工学报, 2005, 26(3): 413-417.
[11]	1:张健;2:张德智，吴玉斌,舒启林,郝永平. 论评价指标值的可公度性处理[J]. 兵工学报, 2004, 25(6): 746-751.
[12]	庞思勤. CVD涂层硬质合金刀具的耐磨性和破损特性[J]. 兵工学报, 1997, 18(2): 139-142.
[13]	王杰民、陈人亨、赵万镒、屈梁生. 铣刀磨损及表面粗糙度的超声监测[J]. 兵工学报, 1992, 13(3): 92-96.

基于融合评价指标和神经网络的刀具磨损预测

Tool Wear Prediction Based on Fusion Evaluation Index and Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价