Completing the principal engineering components of a pumped storage power station spans between 50 and 60 months,from the inception of construction to the commencement of power generation by the first unit.The filling...Completing the principal engineering components of a pumped storage power station spans between 50 and 60 months,from the inception of construction to the commencement of power generation by the first unit.The filling of the penstock with water represents a critical phase preceding the production of electricity by the first unit.During this interval,the construction of the diversion shaft presents multiple challenges,including intricate construction procedures,considerable construction difficulty,elevated safety risks,and quality control issues.To address this issue,this study uses CFD software to analyze the flow field,pressure gradient,and head loss of shaft curved section with different curvature radius,and examines several key technologies by drawing on the practice of diversion shaft construction at the Meizhou pumped storage power station.These technologies include optimizing the curvature radius of the curved section of diversion shaft,reverse-well excavation for the shaft,and sliding-up for the lining concrete.It is found that as the curvature radius of shaft curved section reduces from 4 to 2 times the shaft diameter,the hydraulic characteristic index does not change much,and the increase of head loss accounts for about 0.18%of the total head loss of the water conveyance system.The result show that optimizing the curvature radius from 4 times to 2 times the shaft diameter is feasible and reasonable,and several improved technical measures have been proposed,such as stabilizing drill rods,mechanical scraper systems,and control technology of the relationship between concrete setting time and formwork sliding.Their implementation effectively mitigates difficulties and safety risks during shaft construction,expedites the project schedule,enhances engineering quality,and creates a 41-month timeline for the principal engineering schedule for the first power unit generation in China.展开更多
Using artificial intelligence(AI) and machine learning(ML) techniques, we developed and validated the smart proxy models for history matching of reservoir simulation, sensitivity analysis, and uncertainty assessment b...Using artificial intelligence(AI) and machine learning(ML) techniques, we developed and validated the smart proxy models for history matching of reservoir simulation, sensitivity analysis, and uncertainty assessment by artificial neural network(ANN). The smart proxy models were applied on two cases, the first case study investigated the application of a proxy model for calibrating a reservoir simulation model based on historical data and predicting well production while the second case study investigated the application of an ANN-based proxy model for fast-track modeling of CO2 enhanced oil recovery, aiming at the prediction of the reservoir pressure and phase saturation distribution at injection stage and post-injection stage. The prediction effects for both cases are promising. While a single run of basic numerical simulation model takes hours to days, the smart proxy model runs in a matter of seconds, saving 98.9% of calculating time. The results of these case studies demonstrate the advantage of the proposed workflow for addressing the high run-time, computational time and computational cost of numerical simulation models. In addition, these proxy models predict the outputs of reservoir simulation models with high accuracy.展开更多
文摘Completing the principal engineering components of a pumped storage power station spans between 50 and 60 months,from the inception of construction to the commencement of power generation by the first unit.The filling of the penstock with water represents a critical phase preceding the production of electricity by the first unit.During this interval,the construction of the diversion shaft presents multiple challenges,including intricate construction procedures,considerable construction difficulty,elevated safety risks,and quality control issues.To address this issue,this study uses CFD software to analyze the flow field,pressure gradient,and head loss of shaft curved section with different curvature radius,and examines several key technologies by drawing on the practice of diversion shaft construction at the Meizhou pumped storage power station.These technologies include optimizing the curvature radius of the curved section of diversion shaft,reverse-well excavation for the shaft,and sliding-up for the lining concrete.It is found that as the curvature radius of shaft curved section reduces from 4 to 2 times the shaft diameter,the hydraulic characteristic index does not change much,and the increase of head loss accounts for about 0.18%of the total head loss of the water conveyance system.The result show that optimizing the curvature radius from 4 times to 2 times the shaft diameter is feasible and reasonable,and several improved technical measures have been proposed,such as stabilizing drill rods,mechanical scraper systems,and control technology of the relationship between concrete setting time and formwork sliding.Their implementation effectively mitigates difficulties and safety risks during shaft construction,expedites the project schedule,enhances engineering quality,and creates a 41-month timeline for the principal engineering schedule for the first power unit generation in China.
文摘Using artificial intelligence(AI) and machine learning(ML) techniques, we developed and validated the smart proxy models for history matching of reservoir simulation, sensitivity analysis, and uncertainty assessment by artificial neural network(ANN). The smart proxy models were applied on two cases, the first case study investigated the application of a proxy model for calibrating a reservoir simulation model based on historical data and predicting well production while the second case study investigated the application of an ANN-based proxy model for fast-track modeling of CO2 enhanced oil recovery, aiming at the prediction of the reservoir pressure and phase saturation distribution at injection stage and post-injection stage. The prediction effects for both cases are promising. While a single run of basic numerical simulation model takes hours to days, the smart proxy model runs in a matter of seconds, saving 98.9% of calculating time. The results of these case studies demonstrate the advantage of the proposed workflow for addressing the high run-time, computational time and computational cost of numerical simulation models. In addition, these proxy models predict the outputs of reservoir simulation models with high accuracy.
