基于BPNN的封严涂层孔隙分布均匀性超声表征

doi:10.7527/S1000-6893.2021.25294

材料工程与机械制造

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于BPNN的封严涂层孔隙分布均匀性超声表征

董珍一¹, 林莉¹, 雷明凯², 马志远¹

1. 大连理工大学无损检测研究所, 大连 116024;
2. 大连理工大学材料科学与工程学院, 大连 116024

收稿日期:2021-01-20 修回日期:2021-02-06 发布日期:2021-04-08
通讯作者: 马志远 E-mail:zhiyma@dlut.edu.cn
基金资助:
国家自然科学基金（52075078，51805072，51675083）；"兴辽英才计划"项目（XLYC1902082）

Ultrasonic quantitative characterization of pore distribution uniformity of seal coating based on BPNN

DONG Zhenyi¹, LIN Li¹, LEI Mingkai², MA Zhiyuan¹

1. Nondestructive Testing & Evaluation Laboratory, Dalian University of Technology, Dalian 116024, China;
2. School of Materials Science and Engineering, Dalian University of Technology, Dalian 116024, China

Received:2021-01-20 Revised:2021-02-06 Published:2021-04-08
Supported by:
National Natural Science Foundation of China (52075078, 51805072, 51675083); Program for Excellent Talents in Liaoning (XLYC1902082)

摘要/Abstract

摘要： 可磨耗封严涂层的多相非均质特性导致超声波在其中传播行为复杂，涂层组成相分布均匀性的超声表征在有效超声特征提取、特征与均匀性关系描述等方面存在困难。针对这一现状，提出了BP神经网络（BPNN）结合超声信号小波变换技术定量表征可磨耗封严涂层孔隙分布均匀性的方法。基于统计学思想与随机场理论建立铝硅聚苯酯（AlSi-PHB）封严涂层随机多相介质模型，通过调节自相关长度参数改变模型的孔隙分布状态。采用面积分数多尺度分析技术获得定量描述涂层孔隙分布均匀性的绝对斜率与均匀性长度，提取超声仿真信号的时域、频域及小波分解时频域衰减系数，探究其与绝对斜率及均匀性长度之间的相关性，并作为BPNN的输入对绝对斜率与均匀性长度进行预测。结果显示：在孔隙率5%时，随自相关长度从11 μm增大至26 μm，绝对斜率从0.86减小至0.76，均匀性长度从550 μm增大至6 785 μm，表明孔隙分布均匀性降低；时频域衰减系数与均匀性参数间的相关性最显著，绝对斜率与均匀性长度的BPNN预测结果决定系数分别为0.97和0.98，在3种衰减系数预测结果中最优。所提方法可为定量表征非均质涂层组织分布均匀性提供有效途径。

关键词: 封严涂层, 孔隙, 分布均匀性, 超声定量表征, BP神经网络

Abstract: The propagation behavior of ultrasonic wave is complex in multi-phase heterogeneous abradable seal coating, so it is difficult to extract effective ultrasonic characteristics and describe the relationship between the characteristics and microstructure distribution uniformity. The BP Neural Network (BPNN) combined with wavelet transform is proposed to quantitatively characterize pore distribution uniformity of abradable seal coating through the ultrasonic testing technique. Based on the statistical method and the random medium theory, random multiphase medium models for AlSi-Polyester (AlSi-PHB) seal coating were established, whose pore distributions were adjusted by varying autocorrelation lengths. Two uniformity parameters, absolute slope, and uniformity length were extracted to quantitatively describe pore distribution uniformity using the multi-scale analysis of area fraction. The time domain, frequency domain, and time-frequency domain attenuation coefficients were extracted from simulated ultrasonic signals. Correlations between absolute slope, uniformity length and the attenuation coefficients were explored. The BPNN with attenuation coefficients as the inputs was applied for training and prediction of absolute slope and uniformity length. The results show that when porosity was 5%, as autocorrelation lengths increased from 11 μm to 26 μm, absolute slope decreased from 0.86 to 0.76 and uniformity length increased from 550 μm to 6 785 μm, which indicates that the pore distribution uniformity gets worse. The time-frequency domain attenuation coefficients and the uniformity parameters were the most correlative, and the determination coefficients of the predicted absolute slope and uniformity length through BPNN were 0.97 and 0.98, respectively, which are the most accurate among the prediction results of three kinds of attenuation coefficients. The proposed method provides an effective way for quantitative characterization of distribution uniformity of multi-phase heterogeneous coatings.

Key words: seal coating, pore, distribution uniformity, ultrasonic quantitative characterization, BP neural network

中图分类号:

V257
TB553

董珍一, 林莉, 雷明凯, 马志远. 基于BPNN的封严涂层孔隙分布均匀性超声表征[J]. 航空学报, 2022, 43(5): 425294-425294.

DONG Zhenyi, LIN Li, LEI Mingkai, MA Zhiyuan. Ultrasonic quantitative characterization of pore distribution uniformity of seal coating based on BPNN[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(5): 425294-425294.

参考文献

[1] HARDWICKE C U, LAU Y C. Advances in thermal spray coatings for gas turbines and energy generation:A review[J]. Journal of Thermal Spray Technology, 2013, 22(5):564-576.
[2] 唐健江, 于方丽, 张海鸿, 等. 润滑相尺寸对镍-石墨可磨耗封严涂层性能的影响[J]. 航空材料学报, 2019, 39(2):42-48. TANG J J, YU F L, ZHANG H H, et al. Effect of size of lubrication phase on properties of Ni-graphite abradable seal coating[J]. Journal of Aeronautical Materials, 2019, 39(2):42-48(in Chinese).
[3] 张佳平, 高禩洋, 李浩宇, 等. 高速刮擦条件下两种铝基封严涂层的可刮削性[J]. 中国表面工程, 2018, 31(6):90-97. ZHANG J P, GAO S Y, LI H Y, et al. Investigation on abradability of two aluminum-based seal coatings under high-speed rubbing condition[J]. China Surface Engineering, 2018, 31(6):90-97(in Chinese).
[4] MA Z Y, ZHANG W, LUO Z B, et al. Ultrasonic characterization of thermal barrier coatings porosity through BP neural network optimizing Gaussian process regression algorithm[J]. Ultrasonics, 2020, 100:105981.
[5] DING S S, JIN S J, LUO Z B, et al. Researches on the ultrasonic scattering attenuation of carbon fibre reinforced plastics with 2D real morphology void model[J]. Acoustical Physics, 2017, 63(4):490-495.
[6] 董金龙, 陈昊, 陈曦, 等. 面向映射单调性的TC4初生α相晶粒尺寸超声评价方法[J]. 航空学报, 2018, 39(12):422360. DONG J L, CHEN H, CHEN X, et al. An ultrasonic method of evaluation of TC4 primary α-phase grain size towards mapping monotonicity[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(12):422360(in Chinese).
[7] 孙广开, 周正干. SiCp/Al复合材料增强体分布均匀性超声成像方法[J]. 北京航空航天大学学报, 2017, 43(3):417-423. SUN G K, ZHOU Z G. Ultrasonic imaging method fordistribution uniformity of reinforcement in SiCp/Al composites[J]. Journal of Beijing University of Aeronautics and Astronautics, 2017, 43(3):417-423(in Chinese).
[8] ZHU L B, XIANG X C, DU Y, et al. Uniformity assessment of TRISO fuel particle distribution in spherical HTGR fuel element using voronoi tessellation and delaunay triangulation[J]. Science and Technology of Nuclear Installations, 2018, 2018:7274261.
[9] SPOWART J E. Microstructural characterization and modeling of discontinuously-reinforced aluminum composites[J]. Materials Science and Engineering:A, 2006, 425(1-2):225-237.
[10] WILKS G B, TSCHOPP M A, SPOWART J E. Multi-scale characterization of inhomogeneous morphologically textured microstructures[J]. Materials Science and Engineering:A, 2010, 527(4-5):883-889.
[11] 李宗艺, 张伟, 林莉, 等. 基于面积分数多尺度分析的封严涂层孔隙分布均匀性定量表征[J]. 中国表面工程, 2020, 33(4):145-151. LI Z Y, ZHANG W, LIN L, et al. Quantitative characterization of pore distribution uniformity of seal coatings based on multi-scale analysis of area fraction[J]. China Surface Engineering, 2020, 33(4):145-151(in Chinese).
[12] CAGGIANO A, ZHANG J J, ALFIERI V, et al. Machine learning-based image processing for on-line defect recognition in additive manufacturing[J]. CIRP Annals, 2019, 68(1):451-454.
[13] 李萍, 宋波, 毛捷, 等. 深度学习在超声检测缺陷识别中的应用与发展[J]. 应用声学, 2019, 38(3):458-464. LI P, SONG B, MAO J, et al. Application and development of defect recognition using deep learning in ultrasonic testing[J]. Journal of Applied Acoustics, 2019, 38(3):458-464(in Chinese).
[14] ZHANG M X, LI M C, ZHANG J R, et al. Onset detection of ultrasonic signals for the testing of concrete foundation piles by coupled continuous wavelet transform and machine learning algorithms[J]. Advanced Engineering Informatics, 2020, 43:101034.
[15] 叶博嘉, 鲍序, 刘博, 等. 基于机器学习的航空器进近飞行时间预测[J]. 航空学报, 2020, 41(10):324136. YE B J, BAO X, LIU B, et al. Machine learning for aircraft approach time prediction[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(10):324136(in Chinese).
[16] 刘源, 庞宝君, 迟润强, 等. 基于声发射的铝蜂窝板超高速撞击损伤模式识别方法[J]. 航空学报, 2017, 38(5):220401. LIU Y, PANG B J, CHI R Q, et al. A damage pattern recognition method for hypervelocity impact on aluminum honeycomb core sandwich based on acoustic emission[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(5):220401(in Chinese).
[17] 骆志高, 张保刚, 何鑫. 基于BP神经网络的金属拉深件裂纹在线监测[J]. 振动与冲击, 2012, 31(10):102-105. LUO Z G, ZHANG B G, HE X. On-line crack monitoring of metal deep drawing parts based on BP neural network[J]. Journal of Vibration and Shock, 2012, 31(10):102-105(in Chinese).
[18] ZHANG R, WANG K, JIA R X, et al. Research on ultrasonic thermometry using maximum eigenvalue algorithm based on BP neural network[C]//2017 Chinese Automation Congress (CAC). Piscataway:IEEE Press, 2017:485-491.
[19] LI K S, MA Z Y, FU P, et al. Quantitative evaluation of surface crack depth with a scanning laser source based on particle swarm optimization-neural network[J]. NDT & E International, 2018, 98:208-214.
[20] ACCIANI G, BRUNETTI G, FORNARELLI G, et al. Angular and axial evaluation of superficial defects on non-accessible pipes by wavelet transform and neural network-based classification[J]. Ultrasonics, 2010, 50(1):13-25.
[21] LIN L, ZHANG W, MA Z Y, et al. Porosity estimation of abradable seal coating with an optimized support vector regression model based on multi-scale ultrasonic attenuation coefficient[J]. NDT & E International, 2020, 113:102272.
[22] 赵扬, 林莉, 马志远, 等. 基于随机介质理论的热障涂层随机孔隙模型构建[J]. 中国表面工程, 2010, 23(2):78-81. ZHAO Y, LIN L, MA Z Y, et al. Establishing TBC random pore model based on random media theory[J].China Surface Engineering, 2010, 23(2):78-81(in Chinese).
[23] LI L, WEI Z, ZHIYUAN M, et al. Random multi-phase medium model and its application in analysis of ultrasonic propagation characteristics for AlSi-polyester abradable seal coating[J]. NDT & E International, 2019, 108:102173.
[24] 饶颖, 符力耘, 吴玉, 等. 基于微结构-尺度双分解的页岩随机介质模拟和非均质特征分析[J]. 地球物理学报, 2020, 63(7):2800-2809. RAO Y, FU L Y, WU Y, et al. Heterogeneous characteristic analysis of shale based on multi-component and multi-scale random media method[J]. Chinese Journal of Geophysics, 2020, 63(7):2800-2809(in Chinese).

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于BPNN的封严涂层孔隙分布均匀性超声表征

Ultrasonic quantitative characterization of pore distribution uniformity of seal coating based on BPNN

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	马菲, 张琼, 赖培军, 岳一笛. 基于BP神经网络的试飞训练安全性量化模型[J]. 航空学报, 2024, 45(5): 529957-529957.
[2]	梁益铭, 李广宁, 徐敏. 基于机器学习的智能控制数值虚拟飞行方法[J]. 航空学报, 2023, 44(17): 128098-81280986.
[3]	骆俊廷, 赵静启, 杨哲懿, 刘卫鹏, 张春祥. 基于Deform软件二次开发和BP神经网络的TA15多向锻造微观组织预报[J]. 航空学报, 2021, 42(12): 424693-424693.
[4]	张禹, 董小野, 李东升, 曾奇峰, 杨树华, 巩亚东. 基于STEP和改进神经网络的STEP-NC制造特征识别方法[J]. 航空学报, 2019, 40(7): 422687-422687.
[5]	熊青春, 王家序, 周青华. 融合机床精度与工艺参数的铣削误差预测模型[J]. 航空学报, 2018, 39(8): 421713-421713.
[6]	陈浩然, 李勇, 还大军, 王鑫, 褚奇奕. T700/PEEK热塑性自动铺放预浸纱制备质量控制及性能研究[J]. 航空学报, 2018, 39(6): 421842-421842.
[7]	李伟斌, 魏东, 杜雁霞, 易贤, 杨肖峰. 动态结冰微观孔隙结构定量分析[J]. 航空学报, 2018, 39(2): 121536-121536.
[8]	姚裕盛, 徐开俊. 基于BP神经网络的飞行训练品质评估[J]. 航空学报, 2017, 38(S1): 721513-721513.
[9]	段玉岗, 闫晓丰, 李超, 张小辉. 压辊材料及形状对纤维铺放压紧效果的影响[J]. 航空学报, 2014, 35(4): 1173-1180.
[10]	黄江涛, 高正红, 白俊强, 赵轲, 李静, 许放. 基于任意空间属性FFD技术的融合式翼稍小翼稳健型气动优化设计[J]. 航空学报, 2013, 34(1): 37-45.
[11]	陈勇刚, 罗晓利. 航空公司机队设备可靠性非线性动态评估模型[J]. 航空学报, 2013, 34(1): 104-111.
[12]	蒙文巩;马东立;楚亮. 基于神经网络响应面的机翼气动稳健性优化设计[J]. 航空学报, 2010, 31(6): 1134-1140.
[13]	张慰;李晓阳;姜同敏;黄领才. 基于BP神经网络的多应力加速寿命试验预测方法[J]. 航空学报, 2009, 30(9): 1691-1696.
[14]	王雪明;谢富原;李敏;戴棣;王菲;张佐光. 热压罐成型复合材料复杂结构对制造缺陷的影响规律[J]. 航空学报, 2009, 30(4): 757-762.
[15]	沈以赴;吴鹏;顾冬冬;李玉芳. 激光烧结制备藕状316不锈钢多孔材料的微孔结构特征[J]. 航空学报, 2007, 28(5): 1236-1241.