欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对固液两相流特征参数和流型之间的非线性关系，提出了一种基于小波包分解和人工神经网络的流型识别方法．该方法首先用FLUENT软件建立物理模型和动力学模型并设置一个监测点，对采集到的速度波动信号进行6层小波包分解，得到最优小波树及其信息熵，然后将信息熵构成的特征向量输入BP神经网络进行训练和识别．最终的测试结果表明：该方法能有效克服传统识别方法存在的主观性，具有较好的识别效果．为固液两相流的流型识别提供了一种有效的选择．
英文摘要：
A Pattern Recognition method based on wavelet packet and artificial neural is proposed for sol- id-liquid two-phase flow characteristic parameters and the non-linear relationship between flow pattern. This method firstly establishs the physical and dynamic model, then sets a monitoring point. To get the optimum wavelet tree and its information entropy, six floors of wavelet packet is used to decompose the collected ve- locity fluctuation signal. Transport the proper vector which is component by information entropy into Back Propagation neural network to train and identify. The recognition results show that this method can effec- tively overcome the subjectivity of traditional identification methods. It has good recognition effect, thus provide an effective choice for solid-liquid two-phase flow pattern recognition.
同期刊论文项目
同项目期刊论文
Structured surface softness abrasive flow precision finish machining and its abrasive flow dynamic n
Intelligent computer-aided instruction modeling and a method to optimize study strategies for parall
期刊信息
位置：