摘要
同步带是普通FDM 3D打印设备普遍采用的传动定位部件,同步带失效会直接对打印产品质量造成影响.利用声发射(AE)传感器监测3D打印过程中同步带不同健康状态下的声发射信号,利用集合经验模态分解(EEMD)方法提取其信号特征,并通过隐半马尔可夫模型(HSMM)方法构建针对同步带健康状态的识别模型,进而对同步带正常、磨损和裂纹等三种健康状态进行识别,通过实验表明该方法是可行的.
The synchronous belt is a commonly used driving and positioning part in ordinary FDM 3D printing equipment. The failure of synchronous belts will directly affect the quality of printing products. Acoustic emission （AE） sensors were used to monitor the AE signals in different healthy states of the synchronous band during 3D printing processes. The signal features were extracted by the method of ensemble empirical mode decomposition （EEMD）. The recognition model for the healthy state of the synchronous band was constructed by using the hidden semi-Markov model （HSMM） method, and then the synchronous band was positioned. Three health states such as normal, wear and crack were identified. Experiments show that the method is feasible.
作者
龚厚仙
张浩
周娟
GONG Houxian;ZHANG Hao;ZHOU Juan(Department of Automotive Engineering,Chuzhou Vocational and Technical College,Anhui Chuzhou 239000,China;School of Mechanical Engineering,Zhejiang University,Hangzhou 310027,China;College of Quality and Safety Engineering,China Jiliang University,Hangzhou 310018,China)
出处
《中国计量大学学报》
2018年第3期231-237,258,共8页
Journal of China University of Metrology
基金
国家自然科学基金项目(No.51675481)
安徽省教育厅人才项目(No.gxfx2017224)
关键词
同步带
模式识别
声发射
集合经验模态分解
隐半马尔可夫模型
synchronous belt
pattern recognition
acoustic emission
empirical modal decomposition of sets
hidden semi-Markov model
