The Identification Method Of Oil-Air-Water Three-Phase Flow Regime Based On Digital Image Processing

Multi-phase flow is widely present in the heat transfer equipment in the spheres of chemistry,petroleum,power engineering and a variety of industrial processing. Considering the advantages of reduction of the lengths of pipes and the equipment investment and fully making use of the oil and gas resources, the subject about pipes where there is transport of a mixture of oil, air and water gradually becomes the hot issues. Particularly in the recent years, the discovery of the oil field in the sea and deserts and the Polar Regions, make the oil development extend to the remote places with poor conditions. This mode of transportation has obviously greater advantages. As a result, it is of great Academic value and of practical significance.High-speed photography method is applied to the flow regime identification. It achieves a visual, non-contact measurement, and does not interfere with the normal operation of the production equipment. Moreover, in the high speed oil-air-water three-phase flow, we can collect clearer flow regime images by adjusting the swapping frequency. Therefore, it has a wide scope of use. Based on a large amount of experimental data, digital image processing, wavelet analysis, chaotic characteristics , neural network, support vector machine and complexity-measuring theory are used in flow regime identification. Intelligent flow regime identification method is discussed systematically from the aspects of theory and experiment.Firstly, the oil-air-water three-phase flow regime images are captured by high-speed digital video systems in the vertical upward pipe. Secondly, after flow regime images noises are removed by using image processing technology and wavelet threshold denoising,the signal frame flow regime eigenvectors are obtained by extracting statistical characteristics of the gray histogram, in flow regime images outline features invariant characteristics and the chaotic characteristics of the image grayscale signals. Thirdly, the oil-air-water three-phase flow regime identification model by utilizing particle swarm optimizer BP (Back Propagation) neutral network and ameliorating SVM(support vector machine) are trained by using those eigenvectors as flow regime samples. So, the flow regime intelligent identification is realized. The test results show that the combination of the chaotic characteristics of image grayscale signals and support vector machine is the best one among these models, but the rate difference of identifying is not distinct. Then we take the measurement of flow field of oil-air-water three-phase based on PTV. Finally, the relation is discussed between complexity measures extracted from gray image time series and flow regime transition in oil-air-water three-phase flow. By analyzing the rules of five complexity measures with the changes of oil-air-water three-phase flow parameters, we could get the inversion characteristics of three-phase flow dynamics which provided an efficient, supplementary diagnostic tool to reveal the flow regime transition mechanism of oil-air-water three-phase flow and to quantitatively identify flow regime. All these provide a new way to identify the oil-air-water three-phase flow regime in light of theory and technology.