基于灰度共生矩阵和神经网络的Si3N4陶瓷推挤加工表面纹理分析

doi:10.3969/j.issn.1000-1093.2015.08.020

兵工学报 ›› 2015, Vol. 36 ›› Issue (8): 1518-1524.doi: 10.3969/j.issn.1000-1093.2015.08.020

基于灰度共生矩阵和神经网络的Si3N4陶瓷推挤加工表面纹理分析

田欣利, 王龙, 王望龙, 唐修检, 吴志远

(装甲兵工程学院装备再制造技术国防科技重点实验室，北京 100072)

收稿日期:2014-07-02 修回日期:2014-07-02 上线日期:2015-10-16
作者简介:田欣利(1956—)，男，教授，博士生导师
基金资助:
国家自然科学基金项目（51475474、51105378）

Analysis of Surface Texture of Push-processed Si₃N₄ Ceramics Based on Gray Level Co-occurrence Matrix and Neural Network

TIAN Xin-li, WANG Long, WANG Wang-long, TANG Xiu-jian, WU Zhi-yuan

(National Defense Key Laboratory for Remanufacturing Technology, Academy of Armored Forces Engineering,Beijing 100072, China)

Received:2014-07-02 Revised:2014-07-02 Online:2015-10-16

摘要/Abstract

摘要： 基于边缘破碎效应驱动裂纹软推挤加工是一项新颖的加工技术。通过采集Si₃N₄陶瓷的软推挤加工表面形貌，运用灰度共生矩阵(GLCM)分析了对比度、熵、相关性3个特征参数与加工表面纹理分布的内在关系。通过径向基网络和竞争层网络两类神经网络的分工协作，对不同加工参数下已加工表面的纹理特征进行预测和分类，其预测结果的相对误差能控制在5%之内。随着对比度和熵越大，相关性越小；分类等级越大，表面平整程度越差。通过系统实验探讨了各加工参数对纹理特征的影响，可靠地评估了加工质量的优劣。随着车刀进给速度或槽深的增大，加工表面质量变差；随着凸缘厚度的增大，加工表面质量先逐渐变差，但经过凸缘厚度2.5 mm分界点后却又有所改善。

关键词: 材料表面与界面, Si3N4陶瓷, 纹理特征, 灰度共生矩阵, 神经网络

Abstract: Soft push processing based on the edge broken effect to drive crack is a novel processing technique. The surface texture of machined Si₃N₄ ceramic is collected, and the gray level co-occurrence matrix (GLCM) is used to analyze the relationship among contrast, entropy, correlation and machined surface texture. The radial basic network and competitive network are employed to predict and classify the texture characteristics in different processing parameters. The relative error value of the predicted results can be controlled within 5%. The larger the contrast and entropy are, the smaller the correlation is, and the greater the classification level is, the worse the surface roughness is. The processing quality is analyzed by exploring the effects of different process parameters on texture feature. With the increase in feed rate or groove depth, the machined surface quality is worse. With the increase in flange thickness, the machined surface quality is gradually poor. The machined surface quality can be improved when flange thickness is over 2.5 mm boundary point.

Key words: surface and interface of matterials, Si₃N₄ ceramics, texture characteristics, gray level co-occurrence matrix, neural network

田欣利, 王龙, 王望龙, 唐修检, 吴志远. 基于灰度共生矩阵和神经网络的Si3N4陶瓷推挤加工表面纹理分析[J]. 兵工学报, 2015, 36(8): 1518-1524.

TIAN Xin-li, WANG Long, WANG Wang-long, TANG Xiu-jian, WU Zhi-yuan. Analysis of Surface Texture of Push-processed Si₃N₄ Ceramics Based on Gray Level Co-occurrence Matrix and Neural Network[J]. Acta Armamentarii, 2015, 36(8): 1518-1524.

参考文献

［1］ Maizbender J, Steinbrech R W. Threshold fracture stress of thin ceramic components[J]. Journal of the European Ceramic Society, 2008,28(1): 247-252.
[2] 田欣利,于爱兵.工程陶瓷加工的理论与技术[M]. 北京:国防工业出版社,2006.
TIAN Xin-li,YU Ai-bing. Theory and technology of engineering ceramics processing[M]. Beijing: National Defense Industry Press, 2006.(in Chinese)
[3] 唐修检,田欣利,吴志远,等.工程陶瓷边缘碎裂行为与机理研究进展[J].中国机械工程,2010,21(1):114-119.
TANG Xiu-jian, TIAN Xin-li, WU Zhi-yuan,et al.Research progress of edge chipping behavior and mechanism of engineering ceramics[J]. China Mechanical Engineering, 2010,21(1):114-119.(in Chinese)
[4] 唐修检,田欣利,王望龙,等.基于能量的工程陶瓷边缘碎裂损伤规律与机理研究[J].人工晶体学报,2013,42(10):1-4.
TANG Xiu-jian, TIAN Xin-li, WANG Wang-long,et al. Study on fracture regulars and mechanisms of edge chipping for engineering ceramics based on energy[J]. Journal of Synthetic Crystals,2013,42(10):1-4.(in Chinese)
[5] 田欣利,王健全,张保国,等.基于纹理分析的Si₃N₄陶瓷表面粗糙度研究[J].材料工程,2012(9):56-63.
TIAN Xin-li, WANG Jian-quan, ZHANG Bao-guo, et al. Study of Si₃N₄ ceramic surface roughness based on texture analysis [J]. Materials Engineering, 2012(9):56-63.(in Chinese)
[6] 王波, 姚宏宇,李弼程.一种有效的基于灰度共生矩阵的图像检索方法[J].武汉大学学报：信息科学版,2006,31(9):761-764.
WANG Bo,YAO Hong-yu, LI Bi-cheng. An efficient image retrieval approach based on generalized image co-occurrence matrix [J]. Geomatics and Information Science of Wuhan University, 2006,31(9):761-764.(in Chinese)
[7] 孟广伟, 沙丽荣,李锋,等. 基于神经网络的结构疲劳可靠性优化设计[J].兵工学报,2010,31(6):765-769.
MENG Guang-wei, SHA Li-rong, LI Feng, et al. Design optimization for structural fatigue reliability based on artificial neural network[J].Acta Armamentarii, 2010,31(6):765-769. (in Chinese)
[8] 辛民,解丽静,王西彬, 等. 基于人工神经网络的铣削加工变形预测模型[J].兵工学报,2010,31(8):1130-1131.
XIN Min,XIE Li-jing,WANG Xi-bin,et al. Prediction model for milling deformation based on artificial neural network[J]. Acta Armamentarii, 2010,31(8):1130-1131.(in Chinese)
[9] 田欣利，王龙，王望龙，等.基于边缘破碎驱动裂纹推挤式加工的破碎模拟实验研究[J].人工晶体学报,2014,43(10):2726-2731.
TIAN Xin-li, WANG Long, WANG Wang-long,et al. Simulation experiments for push processing based on the edge effect to drive crack[J]. Journal of Synthetic Crystals, 2014,43(10):2726-2731.(in Chinese)
[10] Ulaby F T, Kouyate F, Brisco B, et al. Textural information in SAR images[J].IEEE Transactions on Geoscience and Remote Sensing, 1986, 24(2): 235-245.
[11] 田欣利，王健全，张保国，等. 工程陶瓷表面粗糙度与图像纹理特征关系[J].装甲兵工程学院学报, 2011,25(6): 77-82.
TIAN Xin-li, WANG Jian-quan, ZHANG Bao-guo, et al. Relationship between surface roughness and image texture features of engineering ceramics[J]. Journal of Academy of Armored Force Engineering, 2011,25(6): 77-82.(in Chinese)

[1]	梁志强，黄迪青，周天丰，李宏伟，乔治，王西彬，刘心藜. 齿轮钢18Cr2Ni4WA磨削烧伤实验及仿真预测研究[J]. 兵工学报, 2017, 38(10): 1995-2001.
[2]	朴钟宇，赵朦朦，徐滨士，王海斗，文东辉. 等离子喷涂铁基涂层疲劳磨损裂纹捕捉技术研究[J]. 兵工学报, 2016, 37(1): 109-113.
[3]	蒋清山，钱林方，徐亚栋，邹权. 考虑区间不确定性的某弹丸提升装置参数优化[J]. 兵工学报, 2015, 36(6): 1117-1122.
[4]	孔德军，谢春洋. Cr12MoV冷作模具钢渗硼层表面与界面分析[J]. 兵工学报, 2015, 36(3): 571-576.
[5]	齐烨，常秋英，王斌，李娟. 激光织构对干摩擦性能的影响及机理研究[J]. 兵工学报, 2015, 36(2): 200-205.
[6]	骆芳，赵兵，姚建华. 激光辅助冷喷涂Cu颗粒撞击45钢的数值模拟[J]. 兵工学报, 2015, 36(11): 2157-2163.
[7]	张鸿雁，王迎春，刘金旭，赵紫盈，郭文启，李树奎. 钨粉表面化学镀镍工艺研究[J]. 兵工学报, 2014, 35(9): 1481-1487.
[8]	王叶，陶刚，李德晴，马岳峰. 综合传动换挡品质的误差逆传播神经网络评价方法[J]. 兵工学报, 2014, 35(4): 495-500.
[9]	唐贤进，张丘，邹刚，吴松，刘维，尹锐. 基于径向基函数神经网络的高聚物粘结炸药切削表面粗糙度预测研究[J]. 兵工学报, 2014, 35(2): 200-206.
[10]	袁俊明，刘玉存，王建华，常双君，于雁武. 基于粒子群神经网络的黑索今基混合炸药大隔板试验冲击波感度预测[J]. 兵工学报, 2014, 35(2): 188-193.
[11]	张雪辉, 林晨光, 崔舜, 李增德, 胡晓康. 钨及其合金涂层的研究现状[J]. 兵工学报, 2013, 34(3): 365-372.
[12]	骆芳, 孔凡志, 威廉·欧尼尔，姚建华, 柴国钟. 激光加热温度对冷喷Stellite 6合金沉积层表面特性的影响[J]. 兵工学报, 2012, 33(7): 840-846.
[13]	葛培林，张海军，刘小萍，鲍明东，于磊，孙海林. 载荷对含Cr碳膜摩擦磨损性能影响研究[J]. 兵工学报, 2012, 33(3): 329-333.

基于灰度共生矩阵和神经网络的Si3N4陶瓷推挤加工表面纹理分析

Analysis of Surface Texture of Push-processed Si₃N₄ Ceramics Based on Gray Level Co-occurrence Matrix and Neural Network

PDF

可视化

被引次数

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

基于灰度共生矩阵和神经网络的Si3N4陶瓷推挤加工表面纹理分析

Analysis of Surface Texture of Push-processed Si3N4 Ceramics Based on Gray Level Co-occurrence Matrix and Neural Network

PDF

可视化

被引次数

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

Analysis of Surface Texture of Push-processed Si₃N₄ Ceramics Based on Gray Level Co-occurrence Matrix and Neural Network