The gasoline inline blending process has widely used real-time optimization techniques to achieve optimization objectives,such as minimizing the cost of production.However,the effectiveness of real-time optimization i...The gasoline inline blending process has widely used real-time optimization techniques to achieve optimization objectives,such as minimizing the cost of production.However,the effectiveness of real-time optimization in gasoline blending relies on accurate blending models and is challenged by stochastic disturbances.Thus,we propose a real-time optimization algorithm based on the soft actor-critic(SAC)deep reinforcement learning strategy to optimize gasoline blending without relying on a single blending model and to be robust against disturbances.Our approach constructs the environment using nonlinear blending models and feedstocks with disturbances.The algorithm incorporates the Lagrange multiplier and path constraints in reward design to manage sparse product constraints.Carefully abstracted states facilitate algorithm convergence,and the normalized action vector in each optimization period allows the agent to generalize to some extent across different target production scenarios.Through these well-designed components,the algorithm based on the SAC outperforms real-time optimization methods based on either nonlinear or linear programming.It even demonstrates comparable performance with the time-horizon based real-time optimization method,which requires knowledge of uncertainty models,confirming its capability to handle uncertainty without accurate models.Our simulation illustrates a promising approach to free real-time optimization of the gasoline blending process from uncertainty models that are difficult to acquire in practice.展开更多
The nozzle inner-flow characteristic of the“spray G”injector was studied by the computational fluid dynamics(CFD)simulation,and the sensitivity of cycle fuel mass to the conicity and entrance radius of the nozzle ho...The nozzle inner-flow characteristic of the“spray G”injector was studied by the computational fluid dynamics(CFD)simulation,and the sensitivity of cycle fuel mass to the conicity and entrance radius of the nozzle hole were analyzed.Results show that the inner conicity of nozzle hole inhibits the development of cavitation phenomena,and increases the injection rate.While the outer conicity of nozzle hole promotes the diffusion of cavita-tion,leading to reductions of the liquid volume fraction of the nozzle outlet and the local flow resistance of the nozzle hole.The sensitivity of cycle fuel mass to inner-cone nozzle hole is stronger than that of the outer-cone noz-zle,especially at the smaller hole conicity.The increase of injection pressure enhances the sensitivity of the injection characteristics to the nozzle hole structure,in which inner-cone nozzle has higher sensitivity coefficient than the outer-cone nozzle hole.However,the increase of injection pressure aggravates the offset of liquid jet to the nozzle axis of the outer-cone nozzle hole.With the increase of the inner conicity of nozzle,the sensitivity of the injection characteristics to the entrance radius of the hole decreases.With the increase of the outer conicity of nozzle hole,the sensitivity of the injection characteristics to the entrance radius of the hole increases.展开更多
Background:Stool-based molecular markers have shown potential as a strategy for colorectal cancer(CRC)screening.This study aimed to evaluate the feasibility of using microRNA-92a expression as a biomarker for CRC in s...Background:Stool-based molecular markers have shown potential as a strategy for colorectal cancer(CRC)screening.This study aimed to evaluate the feasibility of using microRNA-92a expression as a biomarker for CRC in stool samples.Methods:The level of microRNA-92a was measured in stool samples from 210 CRC patients,29 patients with advanced adenomas,15 patients with other cancers,and 101 healthy controls,using real-time quantitative polymerase chain reaction.Receiver operating characteristic curves were used to evaluate sensitivity and specificity.Results:MicroRNA-92a expression was positive in 70.1%of CRC patients,44.8%of advanced adenomas patients,and 36.6%of healthy controls,using a cut-off value of 31.5.The corresponding sensitivity and specificity for discriminating CRC from advanced adenomas were 66.9%and 63.4%,respectively.Moreover,stool-based microRNA-92a expression was better at detecting CRC cancers in the distal colon(sensitivity 82.1%)than the proximal colon(sensitivity 67.9%).There were no significant differences in clinical stage of CRC when comparing AUCs of each parameter(P>0.05).Conclusion:These findings suggest that microRNA-92a expression in stool samples could serve as a promising non-invasive biomarker for CRC detection.展开更多
基金supported by National Key Research & Development Program-Intergovernmental International Science and Technology Innovation Cooperation Project (2021YFE0112800)National Natural Science Foundation of China (Key Program: 62136003)+2 种基金National Natural Science Foundation of China (62073142)Fundamental Research Funds for the Central Universities (222202417006)Shanghai Al Lab
文摘The gasoline inline blending process has widely used real-time optimization techniques to achieve optimization objectives,such as minimizing the cost of production.However,the effectiveness of real-time optimization in gasoline blending relies on accurate blending models and is challenged by stochastic disturbances.Thus,we propose a real-time optimization algorithm based on the soft actor-critic(SAC)deep reinforcement learning strategy to optimize gasoline blending without relying on a single blending model and to be robust against disturbances.Our approach constructs the environment using nonlinear blending models and feedstocks with disturbances.The algorithm incorporates the Lagrange multiplier and path constraints in reward design to manage sparse product constraints.Carefully abstracted states facilitate algorithm convergence,and the normalized action vector in each optimization period allows the agent to generalize to some extent across different target production scenarios.Through these well-designed components,the algorithm based on the SAC outperforms real-time optimization methods based on either nonlinear or linear programming.It even demonstrates comparable performance with the time-horizon based real-time optimization method,which requires knowledge of uncertainty models,confirming its capability to handle uncertainty without accurate models.Our simulation illustrates a promising approach to free real-time optimization of the gasoline blending process from uncertainty models that are difficult to acquire in practice.
文摘The nozzle inner-flow characteristic of the“spray G”injector was studied by the computational fluid dynamics(CFD)simulation,and the sensitivity of cycle fuel mass to the conicity and entrance radius of the nozzle hole were analyzed.Results show that the inner conicity of nozzle hole inhibits the development of cavitation phenomena,and increases the injection rate.While the outer conicity of nozzle hole promotes the diffusion of cavita-tion,leading to reductions of the liquid volume fraction of the nozzle outlet and the local flow resistance of the nozzle hole.The sensitivity of cycle fuel mass to inner-cone nozzle hole is stronger than that of the outer-cone noz-zle,especially at the smaller hole conicity.The increase of injection pressure enhances the sensitivity of the injection characteristics to the nozzle hole structure,in which inner-cone nozzle has higher sensitivity coefficient than the outer-cone nozzle hole.However,the increase of injection pressure aggravates the offset of liquid jet to the nozzle axis of the outer-cone nozzle hole.With the increase of the inner conicity of nozzle,the sensitivity of the injection characteristics to the entrance radius of the hole decreases.With the increase of the outer conicity of nozzle hole,the sensitivity of the injection characteristics to the entrance radius of the hole increases.
基金This study was supported by the National Natural Science Foundation of China(Grant No.82202907 to Rong-Bin Liu).
文摘Background:Stool-based molecular markers have shown potential as a strategy for colorectal cancer(CRC)screening.This study aimed to evaluate the feasibility of using microRNA-92a expression as a biomarker for CRC in stool samples.Methods:The level of microRNA-92a was measured in stool samples from 210 CRC patients,29 patients with advanced adenomas,15 patients with other cancers,and 101 healthy controls,using real-time quantitative polymerase chain reaction.Receiver operating characteristic curves were used to evaluate sensitivity and specificity.Results:MicroRNA-92a expression was positive in 70.1%of CRC patients,44.8%of advanced adenomas patients,and 36.6%of healthy controls,using a cut-off value of 31.5.The corresponding sensitivity and specificity for discriminating CRC from advanced adenomas were 66.9%and 63.4%,respectively.Moreover,stool-based microRNA-92a expression was better at detecting CRC cancers in the distal colon(sensitivity 82.1%)than the proximal colon(sensitivity 67.9%).There were no significant differences in clinical stage of CRC when comparing AUCs of each parameter(P>0.05).Conclusion:These findings suggest that microRNA-92a expression in stool samples could serve as a promising non-invasive biomarker for CRC detection.