基于ECT技术的管道流型识别与运用研究
|
摘要
流型是反映两相流流动状态的重要参数,流型识别的准确程度在很大程度上会影响两相流流动参数的测量.电容层析成像(ECT)技术作为一种非侵入测量技术,在两相流的测量中有广泛的运用.将ECT系统与支持向量机(SVM)算法相结合,并运用遗传算法对SVM的关键参数进行优化,提高识别准确率.利用ECT系统采集到的电容值进行特征值的选取,对管道中常见的气液两相流的流型进行识别.结果表明,这种遗传优化的SVM与ECT技术结合的方法对所提供的流型具有较高的辨识度.在此基础上运用这一技术对疏浚管道的堵塞情况进行了仿真与识别,结果表明,该方法可以很好的完成管道不同堵塞类别的辨识.
Flow pattern is an important parameter reflecting the flow state of the two-phase flow. The accuracy of flow pattern recognition greatly affects the measurement of flow parameters of two-phase flow. The ECT system is combined with the support vector machine( SVM) algorithm, and the genetic algorithm is used to optimize the key parameters of SVM to improve the recognition accuracy. Eigenvalues are selected by using the capacitance values collected by ECT system to identify the flow patterns of common gas-liquid two-phase flows in pipelines. The results show that the method of combining genetic optimization SVM and ECT technology has a high degree of identification for the flow pattern provided. On this basis, this technology is used to simulate and identify the blockage of dredged pipelines. The results show that this method can well identify different blockage types of pipelines.
Flow pattern is an important parameter reflecting the flow state of the two-phase flow. The accuracy of flow pattern recognition greatly affects the measurement of flow parameters of two-phase flow. The ECT system is combined with the support vector machine( SVM) algorithm, and the genetic algorithm is used to optimize the key parameters of SVM to improve the recognition accuracy. Eigenvalues are selected by using the capacitance values collected by ECT system to identify the flow patterns of common gas-liquid two-phase flows in pipelines. The results show that the method of combining genetic optimization SVM and ECT technology has a high degree of identification for the flow pattern provided. On this basis, this technology is used to simulate and identify the blockage of dredged pipelines. The results show that this method can well identify different blockage types of pipelines.
引文
[1] 张立峰,王化祥.基于SVM及电容层析成像的两相流流型识别[J].仪器仪表学报,2009,30(4):812-816.
[2] 华磊.电阻层析成像系统和相关技术在两相流测量中的应用[D].天津:天津大学,2005.
[3] ZHANG J L, MAO M X, YE J M, et al. Investigation of wetting and drying process in a gas-solid fluidized bed by electrical capacitance tomography and pressure measurement[J]. Powder Technology, 2016(10):1148-1158.
[4] 陈德运.两相流电容层析成像技术的研究[D].哈尔滨:哈尔滨理工大学,2006.
[5] 宋蕾,陈德运,姚玉梅,等.Elman神经网络在ECT系统流型辨识中的应用[J].哈尔滨理工大学学报,2014,19(5):103-108.
[6] CHAUHAN V K, DAHIYA K, SHARMA A. Problem formulations and solvers in linear SVM: a review[J]. Artificial Intelligence Review, 2018(6):1-7.
[7] WANG Z, SHAO Y H, WU T R. A GA-based model selection for smooth twin parametric-margin support vector machine[J]. Pattern Recognition, 2013,46(8):2267-2277.
[8] 肖化,陈小兰,严杰,等.两相流电容层析成象技术研究[J].计量学报,1999,20(4):292-296.
[2] 华磊.电阻层析成像系统和相关技术在两相流测量中的应用[D].天津:天津大学,2005.
[3] ZHANG J L, MAO M X, YE J M, et al. Investigation of wetting and drying process in a gas-solid fluidized bed by electrical capacitance tomography and pressure measurement[J]. Powder Technology, 2016(10):1148-1158.
[4] 陈德运.两相流电容层析成像技术的研究[D].哈尔滨:哈尔滨理工大学,2006.
[5] 宋蕾,陈德运,姚玉梅,等.Elman神经网络在ECT系统流型辨识中的应用[J].哈尔滨理工大学学报,2014,19(5):103-108.
[6] CHAUHAN V K, DAHIYA K, SHARMA A. Problem formulations and solvers in linear SVM: a review[J]. Artificial Intelligence Review, 2018(6):1-7.
[7] WANG Z, SHAO Y H, WU T R. A GA-based model selection for smooth twin parametric-margin support vector machine[J]. Pattern Recognition, 2013,46(8):2267-2277.
[8] 肖化,陈小兰,严杰,等.两相流电容层析成象技术研究[J].计量学报,1999,20(4):292-296.