Increasing the energy density of conventional lithium-ion batteries (LIBs) is important for satisfying the demands of electric vehicles and advanced electronics.Silicon is considered as one of the most-promising anodes to replace the traditional graphite anode for the realization of high-energy LIBs due to its extremely high theoretical capacity, although its severe volume changes during lithiation/delithiation have led to a big challenge for practical application. In contrast, the co-utilization of Si and graphite has been well recognized as one of the preferred strategies for commercialization in the near future. In this review, we focus on different carbonaceous additives, such as carbon nanotubes, reduced graphene oxide, and pyrolyzed carbon derived from precursors such as pitch, sugars, heteroatom polymers, and so forth, which play an important role in constructing micrometersized hierarchical structures of silicon/graphite/carbon (Si/G/C) composites and tailoring the morphology and surface with good structural stability, good adhesion, high electrical conductivity, high tap density, and good interface chemistry to achieve high capacity and long cycling stability simultaneously. We first discuss the importance and challenge of the co-utilization of Si and graphite. Then, we carefully review and compare the improved effects of various types of carbonaceous materials and their associated structures on the electrochemical performance of Si/G/C composites. We also review the diverse synthesis techniques and treatment methods, which are also significant factors for optimizing Si/G/C composites. Finally, we provide a pertinent evaluation of these forms of carbon according to their suitability for commercialization. We also make far-ranging suggestions with regard to the selection of proper carbonaceous materials and the design of Si/G/C composites for further development. K E Y W O R D Scarbonaceous additives, graphite, high energy, lithium-ion batteries, silicon ---

No abstract

No abstract

No abstract

Although proton exchange membrane fuel cells have received attention, the high costs associated with Pt-based catalysts in membrane electrode assemblies (MEAs) remain a huge obstacle for large-scale applications. To solve this urgent problem, the utilization efficiency of Pt in MEAs must be increased. Facing numerous interacting parameters in an attempt to keep experimental costs as low as possible, we innovatively introduce machine learning (ML) to achieve this goal. Nine different ML algorithms are trained on the experimental dataset from our laboratory to precisely predict the performance and Pt utilization (maximum R 2 = 0.973/0.968). To determine the best synthesis conditions, black-box interpretation methods are applied to provide reliable insights from both qualitative and quantitative perspectives. The optimized choices of ionomer/catalyst ratio, water content, organic solvent, catalyst loading, stirring method, solid content, and ultrasonic spraying flow rate are properly made with few experimental attempts under ML results' guidance. Promising Pt utilization of 0.147 gPt kW −1 and a power density of 1.02 W cm −2 are achieved at 0.6 V in a single cell (H 2 /air) at an ultralow total loading of 0.15 mg Pt cm −2 . Therefore, this work contributes to the economy of hydrogen energy by paving the way for MEA optimization with complex parameters by ML.