Prediction of Contact Fatigue Life of Thermal Sprayed Coating Based on Support Vector Machine

doi:10.3969/j.issn.1000-1093.2021.12.022

Abstract

Abstract: For the contact fatigue life prediction of thermal sprayed coatings，a series of contact fatigue tests of the plasma sprayed Al₂O₃-40wt% TiO₂ composite coating (AT40 coating) were conducted on a multifunctional contact fatigue/wear testing machine (RM-1 tester) developed by National Key Laboratory for Remanufacturing of Army Academy of Armored Forces by using a central composite design scheme under the action of contact stress, rotation speed, coating thickness and slip ratio. The failure morphology of the coatings is observed by scanning electron microscopy. 3σ criterion is used to test the reliability of contact fatigue life test. The training set and test set are divided rationally by the combination of the golden section method and the information entropy theory. A life prediction model considering the contact stress， rotation speed， coating thickness and slip ratio is established based on the principle of support vector machine. The results show the main damage failure of the coatings is delamination failure and surface wear under the joint action of contact stress， rotation speed， coating thickness and slip ratio，the contact fatigue life obtained by using central composite design scheme is reliable， and the prediction model based on the support vector machine theory could be used to characterize the function relationship between the contact fatigue life of AT40 coating with contact stress， rotation speed， coating thickness and slip ratio. These results could provide theory support to the prediction of contact fatigue life of sprayed coatings.

Key words: thermalsprayedcoating, supportvectormachine, contactfatigue, lifeprediction, remanufacturing

CLC Number:

TG174.442⁺.1

MA Runbo， DONG Lihong， WANG Haidou. Prediction of Contact Fatigue Life of Thermal Sprayed Coating Based on Support Vector Machine[J]. Acta Armamentarii, 2021, 42(12): 2743-2752.

References

［1］朴钟宇.面向再制造的等离子喷涂层接触疲劳行为及寿命评估研究[D].秦皇岛:燕山大学，2010.
PIAO Z Y. Investigation of behavior and life evaluation of rolling contact fatigue of plasma sprayed coating for remanufacturing[D].Qinhuangdao:Yanshan University， 2010.(in Chinese)
[2］康嘉杰.等离子喷涂层的竞争性失效行为和寿命预测研究[D].北京:中国地质大学，2013.
KANG J J.Research on competing failure behavior and life prediction of plasma spraying coating[D].Beijing:China University of Geosciences，2013.(in Chinese)
[3］王韶云，李国禄，王海斗，等.超音速等离子NiCr /Cr₃C₂涂层的接触疲劳寿命[J]. 材料热处理学报，2012，33(5): 112-115.
WANG S Y，LI G L，WANG H D，et al.Connect fatigue life of supersonic plasma sprayed NiCr/Cr₃C₂ coatings[J].Transactions of Materials and Heat Treatment，2012，33(5):112-115. (in Chinese)
[4］马润波，董丽虹，王海斗，等. 基于统计学方法的热喷涂层滚动接触疲劳寿命研究现状[J].材料导报，2016，30(21):83-88.
MA R B，DONG L H，WANG H D，et al. Research status and prospect of rolling contact fatigue life of thermal sprayed coating based on statistics method[J].Materials Reports，2016，30(21):83-88. (in Chinese)
[5］许中林，董天顺，康嘉杰，等. 基于均匀设计的 NiCr-Cr₃C₂超声速等离子喷涂工艺参数优化[J].机械工程学报，2014，50(18): 43-49.
XU Z L,DONG T S，KANG J J，et al.Parameters optimizing of NiCr-Cr₃C₂ coating deposited by supersonic plasma spraying based on uniform design[J].Journal of Mechanical Engineering，2014，50(18):43-49. (in Chinese)
[6］ ZHANG X C，XU B S，XUAN F Z，et al. Failure mode and fatigue mechanism of laser-remelted plasma-sprayed Ni alloy coatings in rolling contact[J]. Surface and Coatings Technology，2011，205(10): 3119-3127.
[7］费晓瑜，李国禄，王海斗. 基于Weibull分布函数的等离子喷涂涂层接触疲劳寿命预测[J]. 航空材料学报，2018，28(5):102-107.
FEI X Y，LI G L，WANG H D.Predictipn for conect fatigue life of plasma sprayed coating based on weibull distribution[J].Journal of Aeronautical Materials，2018， 28(5):102-107. (in Chinese)
[8］ VAPNIK V N.统计学习理论的本质[M].张学工，译.北京:清华大学出版社，2000.
VAPNIK V N. The nature of statistical leaning theory[M].ZHANG X G, translated. Beijing: Tsinghua University Press，2000. (in Chinese)
[9］ SUYKENS J A K，VANEWALLEL J.Least square support vector machine classifiers[J].Neural Processing Letters，1999， 9(3):293-300.
[10］ CHAPELLE O，HAFFNER P，VAPNIK V N. Support vector machines for Histogram-based image classification[J].IEEE Transactions on Neural Networks，1999，10(5): 1055-1064.
[11］ FAN Z G，WANG K A，LU B L.Feature selection for fast image classification with support vector machines[C]∥Proceedings of the 11st International Conference on Neural Information Processing.Calcutta,India: Springer, 2004: 1026-1031.
[12］ GHOSH A，GUHA T，BHAR R B.Classification of yarn interlacement pattern in fabrics using least square support vector machines[J].Fibers and Polymers，2013，14(7):1215-1219.
[13］ KARIMIAN S F，MODARRES M，BRUCK H A. A new method for detecting fatigue crack initiation in aluminum alloy using acoustic emission waveform information entropy[J].Engineering Fracture Mechanics，2020，223:106771.
[14］ WANG F R，CHEN Z，SONG G B.Monitoring of multi-bolt connection looseness using entropy based active sensing and genetic algorithm-based least square support vector machine[J].Mechanical Systems and Signal Processing，2020，136:106507.
[15］ JIANG Q Y，CHANG F L.A novel rolling-element bearing faults classifaication method combines lower-order moment spectra and support vector machine[J].Journal of Mechanical Science and Technology，2019，33(4):1535-1543.
[16］ KIM H E，TAN A C C，MATHEW J，et al. Bearing fault prognosis based on health state probability estimation[J]. Expert Systems with Applications，2012，39(5):5200-5213.
[17］ ZHU K H，SONG X G，XUE D X.A roller bearing fault diagnosis method based on hierarchical entropy and support vector machine with particle swarm optimization algorithm [J]. Measurement，2014，47: 669-675.
[18］ BENKEDJOUH T，MEDJAHER K，ZERHOUNI N，et al. Remaining useful life estimation based on nonlinear feature reduction and support vector regression[J].Engineering Applications of Artificial Intelligence，2013，26(7): 1751-1760.
[19］于震梁，孙志礼，曹汝男，等.基于支持向量机和卡尔曼滤波的机械零件剩余寿命预测模型研究[J].兵工学报，2018，39(5): 991-997
YU Z L，SUN Z L，CAO R N，et al. Research on remaining useful life predictive model of machine parts based on SVM and Kalman filter[J]. Acta Armamentarii，2018，39(5):991-997. (in Chinese)
[20］ ZHANG Y，ZHOU Y G，TANG G，et al. Multivariable least squares support vector machine with time integral operator for the prediction of bearing performance degradation[J].Journal of Mechanical Engineering Science，2019，233(7)：2478-2490.
[21］吕明珠，苏晓明，刘世勋，等.基于VMD-SVM的滚动轴承退化状态识别[J].机械设计与制造，2020（1）:96-100.
L M Z，SU X M，LIU S X，et al.Degradation state recognition of rolling bearing based on VMD-SVM[J]. Machinery Design & Manufacture，2020（1）:96-100. (in Chinese)
[22］陈广，杨震. 基于卷积特征的光纤缺陷检测方法[J]. 中国惯性技术学报，2019,27(1):95-100.
CHEN G，YANG Z.Defect detection method for fiber based on convolutional neural network[J].Journal of Chinese Inertial Technology，2019,27(1):95-100. (in Chinese)
[23］ 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 and E International，2020，113:102272.
[24］张秀英. 基于改进支持向量机的化学镀Ni-P/ZrO₂复合镀层显微硬度预测模型的建立[J].电镀与环保，2019，39(6):45-47.
ZHANG X Y.Establishment of prediction model for microhardness of electroless Ni-P/ZrO₂ composite coating based on improved support vector machine[J].Electroplating & Pollution Control，2019，39(6):45-47. (in Chinese)
[25］ GURGENC T，ALTAY O，ULAS M，et al. Extreme learning machine and support vector regression wear loss predictions for magnesium alloys coated using various spray coating methods[J].Journal of Applied Physics，2020，127(18):185103.
[26］张显程.面向再制造的等离子喷涂层结构完整性及寿命预测基础研究[D].上海:上海交通大学，2007.
ZHANG X C.Basic researches on the structural integrity and life prediction of plasma-sprayed coating-based systems for remanufacturing[D].Shanghai:Shanghai Jiao Tong University，2007.(in Chinese)
[27］马润波，董丽虹，王海斗，等.基于中心复合设计的热喷涂层滚动接触疲劳寿命预测研究[J].兵工学报，2017，38(3): 561-567.
MA R B，DONG L H，WANG H D，et al.Research on contact fatigue life prediction of thermally sprayed coating based on central composite design[J].Acta Armamentarii，2017，38(3):561-567. (in Chinese)
[28］ JIANG R，MURTHY D N P.Modeling failure-data by mixture of 2 Weibull distributions: a graphical approach [J]. IEEE Transactions on Reliability，1995，44(3):477-488.
[29］ KANG J J，XU B S，WANG H D，et al. Competing failure mechanism and life prediction of plasma sprayed composite ceramic coating in rolling-sliding contact condition[J]. Tribology International，2014，73:128-137.
[30］徐滨士，王海斗，朴钟宇，等.再制造的热喷涂合金涂层的结构完整性与服役寿命预测研究[J].金属学报，2011，47(11):1335-1361.
XU B S，WANG H D，PIAO Z Y，et al. Investigation of structural integrity and life time prediction of the thermal sprayed alloy coating for remanufacturing[J].Acta Metallurgica Sinica，2011，47(11): 1335-1361. (in Chinese)
[31］王星.非参数统计[M].北京:清华大学出版社，2009:94-95.
WANG X. Nonparametric statistics [M].Beijing:Tsinghua University Press，2009: 94-95. (in Chinese)
[32］赵军辉，田静秀，李秀萍. 采用黄金分割法的自适应调制无线网络跨层设计[J].应用科学学报，2014，32(6):566-570.
ZHAO J H，TIAN J X，LI X P.Cross-layer design with adaptive modulation and coding based on golden selection in wireless networking[J].Journal of Applied Sciences，2014，32(6):566-570.(in Chinese)
[33］ SHANNON C E.A mathematical theory of communication[J].Bell System Technical Journal，1948，27(3):379-423.
[34］韩中合，朱霄珣. 基于信息熵的支持向量回归机训练样本长度选择[J].中国电机工程学报，2010，30(20):112-116.
HAN Z H，ZHU X X. Selection of training sample length in support vector regression based on information entropy[J]. Proceedings of the CSEE，2010，30(20):112-116. (in Chinese)
[35］高惠璇.统计计算[M].北京：北京大学出版社，2003:15-19.
GAO H X.Statistical calculations[M].Beijing：Peking University Press，2003:15-19. (in Chinese)

[1]	QIU Jiarong, ZENG Pengfei, SHAO Weiping, ZHAO Lijun, HAO Yongping. PSO-LSSVM-Based Ammunition Assembly Quality Prediction Method [J]. Acta Armamentarii, 2022, 43(9): 2379-2387.
[2]	YANG Jianxin， LAN Xiaoping， FENG Yadong， YANG Yiming， GUO Zhiming. An Ammunition Quality Evaluation Method Based on Least Squares Support Vector Machine [J]. Acta Armamentarii, 2022, 43(5): 1012-1022.
[3]	DUAN Hao， CHEN Hui， ZHAI Zhaoyang， HAN Yu， MA Fanhua， CUI Yahui. Performance Prediction of Hydrogen-enriched Compressed Natural Gas Engine Based on Support Vector Machine [J]. Acta Armamentarii, 2022, 43(5): 1002-1011.
[4]	LI Liangyu， SU Tiexiong， MA Fukang， WU Xiaojun， XU Chunlong. Fault Diagnosis Method of High-pressure Common Rail System Based on EEMD-SVM [J]. Acta Armamentarii, 2022, 43(5): 992-1001.
[5]	XU Xiaodong， TANG Shengjin， XIE Jian， YU Chuanqiang， WANG Fengfei， HAN Yangyang. Remaining Useful Life Prediction of Equipment under Random Degradation Stress [J]. Acta Armamentarii, 2022, 43(3): 712-719.
[6]	XU Yuxin, GU Chumei, CAO Jianjun, XU Jinyong, WEI Zhihu. Specific Emitter Identification of Twin Radiation Sources Based on Parallel Classifier Ensemble Learning Using Ant ColonyFeature Selection [J]. Acta Armamentarii, 2022, 43(12): 3132-3141.
[7]	MI Junxia, YU Huilong, XI Junqiang. Prediction of Driver's Lane Changing Behavior Based on MLP-SVM [J]. Acta Armamentarii, 2022, 43(12): 3020-3029.
[8]	LEI Zhenshuo, LIU Songtao, WEN Zhenming, GE Yang. A Real-time Discrimination Method for Operating State of Terminal Guidance Radar in Complex Electromagnetic Environment [J]. Acta Armamentarii, 2021, 42(1): 83-90.
[9]	WANG Cheng， WU Yan， YANG Tingfei. Improving the Detection Accuracy of Wake Targets by Improved One-class Support Vector Machine [J]. Acta Armamentarii, 2020, 41(9): 1887-1893.
[10]	L Guojun， CAO Jianjun， ZHENG Qibin， CHANG Chen， WENG Nianfeng， PENG Cong. Detection of Similar Duplicate Records Based on OCSVM and Multi-objective Ant Colony Optimization [J]. Acta Armamentarii, 2020, 41(2): 324-331.
[11]	YU Jun， LIU Ke， GUO Shuai, YU Guangbin， GUO Zhenyu. Remaining Useful Life Prediction of Planet Bearings Based on Conditional Deep Recurrent Generative Adversarial Network and Action Discovery [J]. Acta Armamentarii, 2020, 41(11): 2170-2178.
[12]	DENG Qing, XUE Qing, LUO Jia. Analysis of Tank Driving Simulation Training Results Based on Support Vector Machine [J]. Acta Armamentarii, 2019, 40(9): 1953-1960.
[13]	DAI Jian, LI Ze, HAO Xinhong, LI Ping. Anti-jamming Method for Pulse Doppler Fuze Based on Joint Feature Extraction of Target Signal [J]. Acta Armamentarii, 2019, 40(2): 225-233.
[14]	GENG Xuehao, ZHOU Kedong, HE Lei, FENG Guotong, LI Junsong. Life Prediction of Gun Barrel Based on Shear Fatigue Damage of Coating Interface [J]. Acta Armamentarii, 2019, 40(12): 2416-2424.
[15]	WANG Xin， ZHAO Ruyan， LU Hongyi， LIU Lei， WU Peng. Service Life Prediction of Solid Motor during Vertical Storage Based on Accelerated Aging and Actual Loadings [J]. Acta Armamentarii, 2019, 40(11): 2212-2219.