This work proposes an optimization method for gas storage operation parameters under multi-factor coupled constraints to improve the peak-shaving capacity of gas storage reservoirs while ensuring operational safety.Pr...This work proposes an optimization method for gas storage operation parameters under multi-factor coupled constraints to improve the peak-shaving capacity of gas storage reservoirs while ensuring operational safety.Previous research primarily focused on integrating reservoir,wellbore,and surface facility constraints,often resulting in broad constraint ranges and slow model convergence.To solve this problem,the present study introduces additional constraints on maximum withdrawal rates by combining binomial deliverability equations with material balance equations for closed gas reservoirs,while considering extreme peak-shaving demands.This approach effectively narrows the constraint range.Subsequently,a collaborative optimization model with maximum gas production as the objective function is established,and the model employs a joint solution strategy combining genetic algorithms and numerical simulation techniques.Finally,this methodology was applied to optimize operational parameters for Gas Storage T.The results demonstrate:(1)The convergence of the model was achieved after 6 iterations,which significantly improved the convergence speed of the model;(2)The maximum working gas volume reached 11.605×10^(8) m^(3),which increased by 13.78%compared with the traditional optimization method;(3)This method greatly improves the operation safety and the ultimate peak load balancing capability.The research provides important technical support for the intelligent decision of injection and production parameters of gas storage and improving peak load balancing ability.展开更多
An algorithm named InterOpt for optimizing operational parameters is proposed based on interpretable machine learning,and is demonstrated via optimization of shale gas development.InterOpt consists of three parts:a ne...An algorithm named InterOpt for optimizing operational parameters is proposed based on interpretable machine learning,and is demonstrated via optimization of shale gas development.InterOpt consists of three parts:a neural network is used to construct an emulator of the actual drilling and hydraulic fracturing process in the vector space(i.e.,virtual environment);:the Sharpley value method in inter-pretable machine learning is applied to analyzing the impact of geological and operational parameters in each well(i.e.,single well feature impact analysis):and ensemble randomized maximum likelihood(EnRML)is conducted to optimize the operational parameters to comprehensively improve the efficiency of shale gas development and reduce the average cost.In the experiment,InterOpt provides different drilling and fracturing plans for each well according to its specific geological conditions,and finally achieves an average cost reduction of 9.7%for a case study with 104 wells.展开更多
Currently,friction characteristics obtained from empirical parameters or soil direct shear tests are widely applied in the resistance calculation and operational parameter optimization of soil tillage components.Howev...Currently,friction characteristics obtained from empirical parameters or soil direct shear tests are widely applied in the resistance calculation and operational parameter optimization of soil tillage components.However,the operation of soiltouching components is a dynamic process,and there are few reports on the dynamic friction characteristics of soil-contacting components in agricultural tillage based on factors such as different moisture content,pressure,and relative velocity.Herein,a test device to measure the friction characteristics of compressible bulk materials was developed:the interface friction between the soil and 65Mn plate and the internal friction characteristics of soil were tested using this device,and the dynamic changes of interface friction coefficient and internal friction coefficient with moisture content,pressure,and relative velocity were obtained.Based on the dynamic friction parameters of soil,the ditching resistance model of a typical ploughshare opener was established,the ditching resistance value was predicted,and field experiments were performed under different operating speeds(0.5 m/s,0.7 m/s,and 0.9 m/s)and ditching depths(60 mm,100 mm,and 140 mm).The results indicated that the calculated values of the ditching resistance model based on the dynamic friction parameters of soil reduced the error by 15%compared with the calculated values based on the friction characteristics of the soil direct shear test,which verified the accuracy of the ditching resistance model and the validity of the parameters obtained from the test device for the friction characteristics of compressible bulk materials.In addition,the minimum ditching resistance can be obtained when the ditching speed is 0.7 m/s at the same ditching depths,which is consistent with the dynamic friction characteristics of soil.It can be found that the dynamic friction characteristics of bulk materials have basic theoretical support for the optimization of operational component structures and operational parameters.展开更多
基金supported by the Science and Technology Research Program of Chongqing Municipal Education Commission(KJQN202401501,KJZD-M202401501).
文摘This work proposes an optimization method for gas storage operation parameters under multi-factor coupled constraints to improve the peak-shaving capacity of gas storage reservoirs while ensuring operational safety.Previous research primarily focused on integrating reservoir,wellbore,and surface facility constraints,often resulting in broad constraint ranges and slow model convergence.To solve this problem,the present study introduces additional constraints on maximum withdrawal rates by combining binomial deliverability equations with material balance equations for closed gas reservoirs,while considering extreme peak-shaving demands.This approach effectively narrows the constraint range.Subsequently,a collaborative optimization model with maximum gas production as the objective function is established,and the model employs a joint solution strategy combining genetic algorithms and numerical simulation techniques.Finally,this methodology was applied to optimize operational parameters for Gas Storage T.The results demonstrate:(1)The convergence of the model was achieved after 6 iterations,which significantly improved the convergence speed of the model;(2)The maximum working gas volume reached 11.605×10^(8) m^(3),which increased by 13.78%compared with the traditional optimization method;(3)This method greatly improves the operation safety and the ultimate peak load balancing capability.The research provides important technical support for the intelligent decision of injection and production parameters of gas storage and improving peak load balancing ability.
文摘An algorithm named InterOpt for optimizing operational parameters is proposed based on interpretable machine learning,and is demonstrated via optimization of shale gas development.InterOpt consists of three parts:a neural network is used to construct an emulator of the actual drilling and hydraulic fracturing process in the vector space(i.e.,virtual environment);:the Sharpley value method in inter-pretable machine learning is applied to analyzing the impact of geological and operational parameters in each well(i.e.,single well feature impact analysis):and ensemble randomized maximum likelihood(EnRML)is conducted to optimize the operational parameters to comprehensively improve the efficiency of shale gas development and reduce the average cost.In the experiment,InterOpt provides different drilling and fracturing plans for each well according to its specific geological conditions,and finally achieves an average cost reduction of 9.7%for a case study with 104 wells.
基金financially supported by China Agriculture Research System(Grant No.CARS-02)Chongqing Science and Technology Bureau Agricultural High Tech Special Project(Grant No.CSTC2019ngzx0017).
文摘Currently,friction characteristics obtained from empirical parameters or soil direct shear tests are widely applied in the resistance calculation and operational parameter optimization of soil tillage components.However,the operation of soiltouching components is a dynamic process,and there are few reports on the dynamic friction characteristics of soil-contacting components in agricultural tillage based on factors such as different moisture content,pressure,and relative velocity.Herein,a test device to measure the friction characteristics of compressible bulk materials was developed:the interface friction between the soil and 65Mn plate and the internal friction characteristics of soil were tested using this device,and the dynamic changes of interface friction coefficient and internal friction coefficient with moisture content,pressure,and relative velocity were obtained.Based on the dynamic friction parameters of soil,the ditching resistance model of a typical ploughshare opener was established,the ditching resistance value was predicted,and field experiments were performed under different operating speeds(0.5 m/s,0.7 m/s,and 0.9 m/s)and ditching depths(60 mm,100 mm,and 140 mm).The results indicated that the calculated values of the ditching resistance model based on the dynamic friction parameters of soil reduced the error by 15%compared with the calculated values based on the friction characteristics of the soil direct shear test,which verified the accuracy of the ditching resistance model and the validity of the parameters obtained from the test device for the friction characteristics of compressible bulk materials.In addition,the minimum ditching resistance can be obtained when the ditching speed is 0.7 m/s at the same ditching depths,which is consistent with the dynamic friction characteristics of soil.It can be found that the dynamic friction characteristics of bulk materials have basic theoretical support for the optimization of operational component structures and operational parameters.
