基于声发射的气固两相流流型识别  

Flow regime identification of gas-solid two-phase flow based on acoustic emission

作　　者：王志春[1] 袁小健[1] 李海广[1] 李忠虎[1] 张楼成 

机构地区：[1]内蒙古科技大学信息工程学院,内蒙古包头014010

出　　处：《化学工程》2017年第5期51-55,共5页Chemical Engineering(China)

基　　金：内蒙古自治区自然科学基金资助项目(2014MS0609);国家自然科学基金资助项目(61463041;61362023;61463042)

摘　　要：气固流化床中流型的识别是两相流相关参数检测的重要内容。利用声发射检测技术对气固流化床进行数据采样,结合数理统计、小波算法以及信息熵等方法提取气固流化床中不同流型的特征参数。由实验结果可知,此方法提取出的特征参数真实反映了典型气固流型下的动力学特征,在流化床中,鼓泡床、湍动床和快速流化床在时域、频域有着显著的区别。将小波能量、数理统计的结果以及小波包分解后的信息熵导入支持向量机(SVM)中,进行气固流型识别,正确率85%。因此,声发射检测技术与支持向量机相结合的方法可用于气固两相流流型的识别,具有一定的可行性。Flow regime identification of gas-solid fluidized bed is an important part of two-phase flow parameters detection. Using acoustic emission （AE） testing technology to take sample in fluidized bed and combining with mathematical statistics, wavelet algorithms and information entropy, characteristic parameter of different flow regime in fluidized bed was extracted. The result shows that the characteristic parameters can reflect the dynamic characteristics of typical gas-solid flow regime. In fluidized bed, there are some obviously differences between the bubbling bed, turbulent bed and fast fluidized bed in the time domain and frequency domain signals. Importing the wavelet energy, the results of mathematical statistics and the information entropy generated by wavelet packet decomposition into the support vector machine （SVM） , the flow regime of gas-solid fluidized is identified. The correct rate is 85%. So the combination of AE and SVM can be used to identify flow regime of gas-solid fluidized bed, and the method has certain feasibility.

关 键 词：流化床 声发射 小波算法 信息熵 支持向量机 流型 

分 类 号：O359[理学—流体力学]