声发射
机械加工
波形
材料科学
声学
蓝宝石
脆性
特征提取
钻石
金刚石车削
光学
计算机科学
复合材料
物理
电压
人工智能
激光器
冶金
量子力学
作者
Guo Bi,Tao Xu,Hui-Xue Wang,Jian-Yun Kang,Yunfeng Peng
摘要
This paper is dedicated to feature extraction of acoustic emission (AE) signals from machining hard brittle materials. A diamond intender is used to scratch BK7 and sapphire. Typical characteristics of AE signals from the two materials of are all concentrated in [100-200]KHz frequency span, and band-filtered signals represent obvious local burst-type waveforms, which is closely related to the crack and fragmentation phenomena that occur when brittle material is removed. Locations and oscillation form of burst-type AE are useful information for process monitoring and quality prediction of machined surface. In order to acquire the information, the theory of shift-invariant sparse coding(SISC) is introduced to analysis AE RMS signals. Experimental results of the two typical hard brittle materials show that oscillation form and locations of burst-type AE can be sparsely expressed by a self-learned atom and the corresponding coefficients. From the aspects of machining process monitoring, taking burst-type AE event as a monitor parameter is more accurate and objective in the reflection of locations and scales of cracks on the machined surface induced by machining.
科研通智能强力驱动
Strongly Powered by AbleSci AI