基于MO-PLP-ELM及电容层析成像的两相流流型辨识

提出一种基于多目标优化并行感知器的极限学习机(MO-PLP-ELM)及电容层析成像(ECT)技术的两相流流型辨识算法。首先,为保证样本具有代表性,采用随机思想生成7类流型的训练及测试样本集;其次,对样本模型的电容数据归一化处理;最后,采用MO-PLP-ELM算法进行流型辨识,并与常用的BP神经网络、支持向量机、极限学习机及并行感知器改进极限学习机算法进行比较,结果表明,提出的MO-PLP-ELM算法其辨识率明显高于其它算法,平均辨识率达96.1%。

Identification of Two-phase Flow Based on MO-PLP-ELM and Electrical Capacitance Tomography

Identification of two-phase flow based on multi-objective optimized parallel layer perceptrons extreme learning machine( MO-PLP-ELM) and electrical capacitance tomography( ECT) is proposed. Firstly,the random training method is used to generate the training and testing sets for the studied seven two-phase flow regimes,which assures the representativeness of the samples. Secondly,the capacitance data of the sample are normalized. Finally,the MO-PLP-ELM algorithm is used for flow regime identification,and the results are compared with those of BP neural network,support vector machine,extreme learning machine algorithms and extreme learning machine with parallel layer perceptrons. The results show that the average recognition rate can reach 96. 1% using MO-PLP-ELM,which is obviously higher than other algorithms.