Southeast University

Siyu Wang

Huiyan Zhang

Dengyin Zhang

Rui Xiao

Chao Zhou

Weidan Yan

Bo Peng

Fan Gao

Jiajun Yu

YIhan Wang

Bingbing Luo

Kai Wu

Xiaoye Ruan

Shuying Xu

The provided is a novel heat-induction decoking device and method tailored for the thermal conversion of solid fuels. The efficient heat-induction decoking device for the thermal conversion of the solid fuels includes: a decoking tank body, which is configured to condense a macromolecular tar in a pyrolysis gas and discharge the condensed tar from a bottom to a tar tank for storage; an electromagnetic induction heating system, which is disposed on an outer wall surface of the decoking tank body to heat the outer wall surface of the decoking tank body; an ultrasonic vibration decoking system, which is disposed on the decoking tank body to enable the decoking tank body to generate vibration by ultrasonic wave so as to enhance tar fluidity. This innovative design not only reduces energy consumption and equipment wear but also extends system operational lifespan, thereby offering substantial improvements in economic and environmental sustainability.

Efficient heat-induction decoking device and method for thermal conversion of solid fuels

The present application discloses a method for recovering a face image based on semantic features, which includes obtaining a to-be-recovered face image; inputting the to-be-recovered face image into a recovery model trained to obtain a recovered face image; the recovery model includes: an encoder, configured for generating low-quality face semantic features based on the to-be-recovered face image; a reference image generator, configured for generating a plurality of high-quality face reference images by inputting random noise based on the low-quality face semantic features; a feature transfer, configured for constructing a face component feature dictionary based on the plurality of high-quality face reference images, and transferring high-quality component features in the face component feature dictionary to the low-quality face semantic features to obtain high-quality face semantic features; and a decoder, configured for generating the recovered face image based on the high-quality face semantic features.

Method for recovering face image based on semantic features

A pyrolysis vapor outlet anti-coking device of adsorbing medium self-recycling regeneration includes a particle flow adsorbing system and a medium burning regeneration recycling system in mutual communication. The particle flow adsorbing system is configured to enable an easy-to-coke component to be adsorbed on an outer surface of an adsorbing medium to form a coking layer, and convey the a coking adsorbing medium into the medium burning regeneration recycling system. The medium burning regeneration recycling system is configured to quickly burn the coking layer on the outer surface of the adsorbing medium to realize regeneration of the adsorbing medium and convey the regenerated adsorbing medium into the particle flow adsorbing system for recycling use.

Pyrolysis vapor outlet anti-coking device and method of adsorbing medium self-recycling regeneration

Growing community of inventors

Nanjing, China

Siyu Wang