Search

A polyethylene oxide (PEO)-coated polyimide (PI) membrane was prepared by electrospinning method followed by a dip-coating and drying process for high-performance lithium-ion batteries (LIB). Semicrystal PEO was covered on the surface of the fibers and partially enmeshed in PI matrix, which formed unique porous structures. The pores with an average size of 4.1 µm and a porosity of 90% served as ion transport channels. Compared with the cell with Celgard 2400 membrane, the half-cell using PEO-coated PI membrane as a separator exhibits excellent electrochemical performance both at room temperature and at low temperature. The electrolyte uptaking rate of PEO-coated PI membrane was 170% and the ionic conductivity was 3.83 × 10 –3  S cm –1 . PEO-coated PI membrane possessed 5.3 V electrochemical window. The electrode–electrolyte interfacial resistance was 62.4 Ω. The capacity retention ratios with PEO-coated PI membrane were 86.4% at 5 C and 73.5% at 10 C at 25 °C and 75% at 5 C at 0 °C. Furthermore, the cell using the separator demonstrates excellent capacity retention over cycling. These advanced characteristics would boost the application of the PEO-coated PI membrane for high-power lithium ion battery. [ABSTRACT FROM AUTHOR]

• An end-to-end framework to solve JSSPs by using graph neural networks and dueling double deep Q network. • This single policy model is suitable for solving instances that have similar size and is trained only by observing reward signals and following feasible rules. • The trained model behaves like a constructive heuristic algorithm that incrementally constructs a solution, and each action is determined by the output of a Graph Neural Network (GNN) which captures the current state of the partial solution. A key problem in traffic management is to schedule the movements of vehicles to reduce unnecessary costs; this issue has arisen in applications such as train schedule management, air-traffic control, and urban traffic management. This problem can be modeled as a job shop scheduling problem (JSSP), which is an important combinatorial optimization problem that is widely applied in real-world scenarios. However, designing good approximation algorithms for JSSPs often requires significant specialized knowledge and trial-and-error. In this paper, we present an end-to-end framework for solving JSSPs by using graph neural networks (GNNs) and deep Q-Learning. This single-policy model is suitable for solving instances that have similar sizes and is trained only by observing reward signals and following feasible rules. The trained model behaves like a constructive heuristic algorithm that incrementally constructs a solution, and each action is determined by the output of a GNN, which captures the current state of the partial solution. We test the proposed approach on JSSP instances with multiple sizes and demonstrate its competitive performance in all cases (after training). Our proposed framework also has the potential to be applied to other JSS subproblems. [ABSTRACT FROM AUTHOR]