In the traditional well log depth matching tasks,manual adjustments are required,which means significantly labor-intensive for multiple wells,leading to low work efficiency.This paper introduces a multi-agent deep rei...In the traditional well log depth matching tasks,manual adjustments are required,which means significantly labor-intensive for multiple wells,leading to low work efficiency.This paper introduces a multi-agent deep reinforcement learning(MARL)method to automate the depth matching of multi-well logs.This method defines multiple top-down dual sliding windows based on the convolutional neural network(CNN)to extract and capture similar feature sequences on well logs,and it establishes an interaction mechanism between agents and the environment to control the depth matching process.Specifically,the agent selects an action to translate or scale the feature sequence based on the double deep Q-network(DDQN).Through the feedback of the reward signal,it evaluates the effectiveness of each action,aiming to obtain the optimal strategy and improve the accuracy of the matching task.Our experiments show that MARL can automatically perform depth matches for well-logs in multiple wells,and reduce manual intervention.In the application to the oil field,a comparative analysis of dynamic time warping(DTW),deep Q-learning network(DQN),and DDQN methods revealed that the DDQN algorithm,with its dual-network evaluation mechanism,significantly improves performance by identifying and aligning more details in the well log feature sequences,thus achieving higher depth matching accuracy.展开更多
A series of dynamic model tests that were performed on a geogrid-reinforced square footing are presented.The dynamic(sinusoidal)loading was applied using a mechanical testing and simulation(MTS)electro-hydraulic servo...A series of dynamic model tests that were performed on a geogrid-reinforced square footing are presented.The dynamic(sinusoidal)loading was applied using a mechanical testing and simulation(MTS)electro-hydraulic servo loading system.In all the tests,the amplitude of loading was±160 kPa;the frequency of loading was 2 Hz.To better ascertain the effect of reinforcement,an unreinforced square footing was first tested.This was followed by a series of tests,each with a single layer of reinforcement.The reinforcement was placed at depths of 0.3B,0.6B and 0.9B,where B is the width of footing.The optimal depth of reinforcement was found to be 0.6B.The effect of adopting this value versus the other two depths was quantified.The single layer of geogrid had an effective reinforcement depth of 1.7B below the footing base.The increase of the depth between the topmost geogrid layer and the bottom of the footing(within the range of 0.9B)did not change the failure mode of the foundation.展开更多
Metal framework composites have higher mechanical properties in examination to metals over an extensive variety of working conditions. This makes them an alluring alternative in swapping metals for different building ...Metal framework composites have higher mechanical properties in examination to metals over an extensive variety of working conditions. This makes them an alluring alternative in swapping metals for different building applications. The present review is a study on the influence of composite titanium on the cutting parameters, mechanical behavior, reinforcements, structure and nanostructure. This review will provide an understanding into selecting the optimum machining parameters for machining titanium composites. It’s also an attempt to give brief explanation by suitably machining the titanium composite which can be made reasonable.展开更多
基金Supported by the China National Petroleum Corporation Limited-China University of Petroleum(Beijing)Strategic Cooperation Science and Technology Project(ZLZX2020-03).
文摘In the traditional well log depth matching tasks,manual adjustments are required,which means significantly labor-intensive for multiple wells,leading to low work efficiency.This paper introduces a multi-agent deep reinforcement learning(MARL)method to automate the depth matching of multi-well logs.This method defines multiple top-down dual sliding windows based on the convolutional neural network(CNN)to extract and capture similar feature sequences on well logs,and it establishes an interaction mechanism between agents and the environment to control the depth matching process.Specifically,the agent selects an action to translate or scale the feature sequence based on the double deep Q-network(DDQN).Through the feedback of the reward signal,it evaluates the effectiveness of each action,aiming to obtain the optimal strategy and improve the accuracy of the matching task.Our experiments show that MARL can automatically perform depth matches for well-logs in multiple wells,and reduce manual intervention.In the application to the oil field,a comparative analysis of dynamic time warping(DTW),deep Q-learning network(DQN),and DDQN methods revealed that the DDQN algorithm,with its dual-network evaluation mechanism,significantly improves performance by identifying and aligning more details in the well log feature sequences,thus achieving higher depth matching accuracy.
基金Projects(41962017,51469005)supported by the National Natural Science Foundation of ChinaProject(2017GXNSFAA198170)supported by the Natural Science Foundation in Guangxi Province,China+1 种基金Project supported by the Guangxi University of Science and Technology Innovation Team Support Plan,ChinaProject supported by the High Level Innovation Team and Outstanding Scholars Program of Guangxi Institutions of Higher Learning,China。
文摘A series of dynamic model tests that were performed on a geogrid-reinforced square footing are presented.The dynamic(sinusoidal)loading was applied using a mechanical testing and simulation(MTS)electro-hydraulic servo loading system.In all the tests,the amplitude of loading was±160 kPa;the frequency of loading was 2 Hz.To better ascertain the effect of reinforcement,an unreinforced square footing was first tested.This was followed by a series of tests,each with a single layer of reinforcement.The reinforcement was placed at depths of 0.3B,0.6B and 0.9B,where B is the width of footing.The optimal depth of reinforcement was found to be 0.6B.The effect of adopting this value versus the other two depths was quantified.The single layer of geogrid had an effective reinforcement depth of 1.7B below the footing base.The increase of the depth between the topmost geogrid layer and the bottom of the footing(within the range of 0.9B)did not change the failure mode of the foundation.
文摘Metal framework composites have higher mechanical properties in examination to metals over an extensive variety of working conditions. This makes them an alluring alternative in swapping metals for different building applications. The present review is a study on the influence of composite titanium on the cutting parameters, mechanical behavior, reinforcements, structure and nanostructure. This review will provide an understanding into selecting the optimum machining parameters for machining titanium composites. It’s also an attempt to give brief explanation by suitably machining the titanium composite which can be made reasonable.
