Infant formula is usually produced in an agglomerated powder form. These agglomerates are subjected to many transient forces following their manufacture. These can be difficult to quantify experimentally because of th...Infant formula is usually produced in an agglomerated powder form. These agglomerates are subjected to many transient forces following their manufacture. These can be difficult to quantify experimentally because of their small magnitudes and short durations, Numerical models have the potential to address this gap in the experimental data. The objective of the research described here was to calibrate a discrete element model for these agglomerates using experimental data obtained for quasi-static loading, and to use this model to study the mechanics of the particle response in detail. The Taguchi method was previously proposed as a viable calibration approach for discrete element models. In this work, the method was assessed for calibration of the model parameters （e.g., bond stiffnesses and strengths） considering three responses： the force at failure, strain at failure and agglomerate stiffness. The Weibull moduli for the simulation results and the experimental data were almost identical following calibration and the 37% characteristic stresses were similar. An analysis of the energy terms in the model provided useful insight into the model response. The bond energy and the normal force exerted on the platens were strongly correlated, and bond breakage events coincided with the highest energy dissipation rates.展开更多
Shuttle tankers scheduling is an important task in offshore oil and gas transportation process,which involves operating time window fulfillment,optimal transportation planning,and proper inventory management.However,c...Shuttle tankers scheduling is an important task in offshore oil and gas transportation process,which involves operating time window fulfillment,optimal transportation planning,and proper inventory management.However,conventional approaches like Mixed lnteger Linear Programming(MlLP)or meta heuristic algorithms often fail in long running time.In this paper,a Graph Pointer Network(GPN)based Hierarchical Curriculum Reinforcement Learning(HCRl)method is proposed to solve Shuttle Tankers Scheduling Problem(STSP)The model is trained to divide STSP into voyage and operation stages and generate routing and inventory management decisions sequentially.An asynchronous training strategy is developed to address the coupling between stages.Comparison experiments demonstrate that the proposed HCRL method achieves 12%shortel tour lengths on average compared to heuristic algorithms.Additional experiments validate its generalizability to unseen instances and scalability to larger instances.展开更多
基金financial support from the Irish Research Council for Science,Engineering and Technology(IRCSET)
文摘Infant formula is usually produced in an agglomerated powder form. These agglomerates are subjected to many transient forces following their manufacture. These can be difficult to quantify experimentally because of their small magnitudes and short durations, Numerical models have the potential to address this gap in the experimental data. The objective of the research described here was to calibrate a discrete element model for these agglomerates using experimental data obtained for quasi-static loading, and to use this model to study the mechanics of the particle response in detail. The Taguchi method was previously proposed as a viable calibration approach for discrete element models. In this work, the method was assessed for calibration of the model parameters （e.g., bond stiffnesses and strengths） considering three responses： the force at failure, strain at failure and agglomerate stiffness. The Weibull moduli for the simulation results and the experimental data were almost identical following calibration and the 37% characteristic stresses were similar. An analysis of the energy terms in the model provided useful insight into the model response. The bond energy and the normal force exerted on the platens were strongly correlated, and bond breakage events coincided with the highest energy dissipation rates.
基金supported by the National Natural Science Foundation of China(Nos.22178383 and 21706282)Beijing Natural Science Foundation(No.2232021)Research Foundation of China University of Petroleum(Beijing)(No.2462020BJRC004).
文摘Shuttle tankers scheduling is an important task in offshore oil and gas transportation process,which involves operating time window fulfillment,optimal transportation planning,and proper inventory management.However,conventional approaches like Mixed lnteger Linear Programming(MlLP)or meta heuristic algorithms often fail in long running time.In this paper,a Graph Pointer Network(GPN)based Hierarchical Curriculum Reinforcement Learning(HCRl)method is proposed to solve Shuttle Tankers Scheduling Problem(STSP)The model is trained to divide STSP into voyage and operation stages and generate routing and inventory management decisions sequentially.An asynchronous training strategy is developed to address the coupling between stages.Comparison experiments demonstrate that the proposed HCRL method achieves 12%shortel tour lengths on average compared to heuristic algorithms.Additional experiments validate its generalizability to unseen instances and scalability to larger instances.
