Abstract: A method of performing automatic tuning on a deep learning model includes: utilizing an instruction-based learned cost model to estimate a first type of operational performance metrics based on a tuned configuration of layer fusion and tensor tiling; utilizing statistical data gathered during a compilation process of the deep learning model to determine a second type of operational performance metrics based on the tuned configuration of layer fusion and tensor tiling; performing an auto-tuning process to obtain a plurality of optimal configurations based on the first type of operational performance metrics and the second type of operational performance metrics; and configure the deep learning model according to one of the plurality of optimal configurations.

Abstract: A membrane electrode assembly structure of a fuel cell and a method of making the same are disclosed. The materials to be used include NiO, 8YSZ and 3YSZ that mixed into a slurry, formed into anodes by tape casting, sintered to form an anode substrate, and followed by forming a thin film of electrolyte layer on the surface of the anode substrate, forming a cathode layer on the outer surface of the electrolyte layer to obtain the membrane electrode assembly, which utilizes the 3YSZ having a tetragonal crystal phase to improve the toughness and mechanical strength of the material of NiO-8YSZ through calcination, thus the thickness of the anode substrate can be reduced, and the fuel gas diffusion path and resistance can be appropriately reduced to enhance the conductivity of the anode substrate.

Abstract: A membrane electrode assembly structure of a fuel cell and a method of making the same are disclosed. The materials to be used include NiO, 8YSZ and 3YSZ that mixed into a slurry, formed into anodes by tape casting, sintered to form an anode substrate, and followed by forming a thin film of electrolyte layer on the surface of the anode substrate, forming a cathode layer on the outer surface of the electrolyte layer to obtain the membrane electrode assembly, which utilizes the 3YSZ having a tetragonal crystal phase to improve the toughness and mechanical strength of the material of NiO-8YSZ through calcination, thus the thickness of the anode substrate can be reduced, and the fuel gas diffusion path and resistance can be appropriately reduced to enhance the conductivity of the anode substrate.

Abstract: A fabrication process for production of planar type solid oxide fuel cell with high electrical conductivity and low fuel gas impedance is disclosed. It is a tape casting to produce an anode substrate furnished with a pore array structure on one or plurality of layers of the anode green tape on the utmost outside of the anode. It is to implement the process of solid oxide fuel cell membrane electrode assembly (SOFC-MEA) with precision abrasion to remove nickel depleted layer on the anode surface to complete the production of a unit cell. The fabrication of anode with pore array structure provides a good conduction effect for fuel gas and the solid oxide fuel cell with this treatment has features of high electrical conductivity and low fuel gas impedance to improve the performance of SOFC unit cell.

Abstract: A fabrication process for production of planar type solid oxide fuel cell with high electrical conductivity and low fuel gas impedance is disclosed. It is a tape casting to produce an anode substrate furnished with a pore array structure on one or plurality of layers of the anode green tape on the utmost outside of the anode. It is to implement the process of solid oxide fuel cell membrane electrode assembly (SOFC-MEA) with precision abrasion to remove nickel depleted layer on the anode surface to complete the production of a unit cell. The fabrication of anode with pore array structure provides a good conduction effect for fuel gas and the solid oxide fuel cell with this treatment has features of high electrical conductivity and low fuel gas impedance to improve the performance of SOFC unit cell.