| Popis: |
Publisher Summary Two-component flow is very common in many industry areas such as power plants, steel factories, and chemical manufactures. Because of its complex flowing states and property, it is very difficult to measure two-component flow using traditional detecting method and the measurement accuracy is usually much lower. This is unfavorable to industrial practice. This chapter describes a new method based on fuzzy neural network which is used to recognize the two-component flow pattern. It discusses the structure of the fuzzy neural network, including the selection of the fuzzy logical rule and the training sets. An accelerated learning algorithm is used to train the neural network to shorten its learning time. After computer simulation has been done, it is found that this new method can recognize four typical flow patterns existing in the gas/liquid two-component flow: stratified flow, annular flow, slug flow, and bubble flow. Results useful for the future work are also presented in the chapter. |
