In order to achieve the purpose of efficient, safe and reliable operation, it has become the development trend and direction to build an intelligent oilfield transportation pipeline network with big data analysis, com...
详细信息
In order to achieve the purpose of efficient, safe and reliable operation, it has become the development trend and direction to build an intelligent oilfield transportation pipeline network with big data analysis, comprehensive situation awareness and automatic control and management capabilities in the future. In this paper, Supervi-sory Control and Data Acquisition (SCADA) system was used to collect the production and operation data of an oilfield in Western China. The thermal and hydraulic models have been corrected based on these collected data. Then, the influence factors of thermal characteristics of several categories of pipelines were analyzed, and the critical temperature gradient of various categories of pipelines was obtained by interpolating fitting method. Furthermore, the optimal operation conditions of the transportation pipelines were obtained, and the universal relationship of pipeline operationparameters was established as well. The results indicated that the corrected models can predict the temperature drop and pressure drop of multiphase mixture transportation pipeline well, liquid flow rate, water cut and initial temperature do have obvious influences on pipeline operationparameters, and the universal relationship of pipeline operationparameters can effectively guide the production practice of oilfield. However, the operation parameters optimization universal relationship cannot meet the requirements of personalized control of all pipelines. Therefore, this paper proposed an intelligent control strategy for multiphase mixture transportation pipeline in oilfield. This case study is of great significance to guide the optimization of op-eration parameters and ensure high efficiency and safe operation of multiphase mixture transportation pipelines in oilfield.
Heavy oil gathering and transportation system is increasingly attention and the realization of intelligent control has become the oilfield development direction and trend in the future. In this paper, boundary tempera...
详细信息
Heavy oil gathering and transportation system is increasingly attention and the realization of intelligent control has become the oilfield development direction and trend in the future. In this paper, boundary temperature is defined as safe inlet temperature and optimal oil transportation temperature. The intelligent supervisory control and data acquisition system was used to collect the production data of an oilfield in Western China in real-time. The heavy oil transportation pipeline was divided into 9 types through big data analysis. The safe inlet tempera-ture under different conditions was determined by flow loop experiments. Then the total heat transfer coefficient was corrected by the least square method, and the optimal oil transportation temperature was calculated by the mathematical model. The results indicated that the relationship of the temperature drop along the pipeline could be more accurately predicted by the modified total heat transfer coefficient. Heavy oil field gathering and trans-portation system had low-temperature transportation potential in summer and winter. Liquid production, water cut, and the ambient temperature had a significant effect on the temperature gradient and safe inlet temperature. The heavy oil with high liquid production and high water cut had the greatest potential for low-temperature transportation. An oilfield intelligent control and management scheme is proposed to effectively guide heavy oil production. This study is of great significance to guide the optimization of operationparameters of heavy oil field gathering and transportation system, realize energy saving and consumption reduction, and ensure the efficient and stable operation of the pipeline.
For improving the combustion and emission performance of engines operating at high altitude regions, a two OED optimization method was proposed. The influence of each factor on the target was analyzed and discussed th...
详细信息
Because casing repair is expensive and the repair technology is not mature enough. Therefore, it is necessary to identify the casing damage risk well in advance and formulate effective casing damage prevention measure...
详细信息
ISBN:
(纸本)9781728125015
Because casing repair is expensive and the repair technology is not mature enough. Therefore, it is necessary to identify the casing damage risk well in advance and formulate effective casing damage prevention measures. In this paper, XGBoost and LightGBM machine learning algorithms are used to establish the casing damage prediction model for oil production wells. Taking the factors of dynamic production pressure difference and other factors leading to the casing damage of the production layer as input parameters and casing damage as the output parameter, a data set of 653 samples is established. The data set is split into a training set (80%) and hold-out set (20%).In the hold-out set, the casings of 111 production layers were not damaged. The hold-out set contains data corresponding to 131 production layers. Among them, 17 production layer casings were damaged, and the model predicted 13. The other 114 without casing damage are predicted correctly. The overall prediction accuracy is 96.9%. The main controlling factor of casing damage is production pressure difference. The casing damage prediction model is used to analyze the parameter sensitivity, optimize operationparameters such as production pressure difference,and reduce the casing damage probability of the oil production well.
Because casing repair is expensive and the repair technology is not mature enough. Therefore, it is necessary to identify the casing damage risk well in advance and formulate effective casing damage prevention measure...
详细信息
ISBN:
(纸本)9781728125022
Because casing repair is expensive and the repair technology is not mature enough. Therefore, it is necessary to identify the casing damage risk well in advance and formulate effective casing damage prevention measures. In this paper, XGBoost and LightGBM machine learning algorithms are used to establish the casing damage prediction model for oil production wells. Taking the factors of dynamic production pressure difference and other factors leading to the casing damage of the production layer as input parameters and casing damage as the output parameter, a data set of 653 samples is established. The data set is split into a training set (80%) and hold-out set (20%).In the hold-out set, the casings of 111 production layers were not damaged. The hold-out set contains data corresponding to 131 production layers. Among them, 17 production layer casings were damaged, and the model predicted 13. The other 114 without casing damage are predicted correctly. The overall prediction accuracy is 96.9%. The main controlling factor of casing damage is production pressure difference. The casing damage prediction model is used to analyze the parameter sensitivity, optimize operationparameters such as production pressure difference, and reduce the casing damage probability of the oil production well.
暂无评论