Abstract:

Based on the good texture expression abilities of the gray level co-occurrence matrix，a flow regime identification method based on gray level co-occurrence matrix and support vector machine was proposed.Gas-liquid two-phase flow images were captured by digital high speed video systems in a horizontal pipe.The image gray level co-occurrence matrix texture feature was extracted by using image processing techniques.Then，the image gray level co-occurrence matrix texture feature eigenvectors of flow regime were established.The support vector machine was trained by using those eigenvectors as flow regime samples and flow regime intelligent identification was realized.The test results showed that the support vector machine could quickly and accurately identify seven typical flow regimes of gas-water two-phase flow in the horizontal pipe.The whole identification accuracy was 100%，and an estimation of the process time was 1.7 s for flow online identification by using the new and effective method.

Key words:

流型识别, 图像处理, 灰度共生矩阵, 支持向量机

摘要：

根据灰度共生矩阵具有较好的纹理表达能力的特性，提出了一种基于图像灰度共生矩阵和支持向量机相结合的气液两相流流型识别的新方法。该方法利用高速摄影系统获取水平管道内气液两相流的流动图像，经过图像处理后，提取图像灰度共生矩阵的纹理特征，进而建立流型图像的灰度共生矩阵纹理特征向量，并以此特征向量作为流型样本对支持向量机进行训练，实现了对流动图像的流型智能化识别。实验结果表明，支持向量机能够快速准确地识别水平管道内的7种典型流型，整体识别率达到100%，每幅流型图像的判别时间约为1.7 s，为流型在线识别提供一种新方法。

关键词:

流型识别, 图像处理, 灰度共生矩阵, 支持向量机