Abstract: A model training method includes obtaining first and second modal data sets including pieces of data, wherein the pieces of data include sub-modal data pieces, and wherein pieces of the first modal data correspond to pieces of the second modal data; obtaining masked data sets by masking a piece of the first and second sub-modal data, respectively; performing feature prediction on the first masked data set and the second modal data set and the second masked data set and the first modal data set, based on ta feature extraction model, to obtain first and second global features and first and second global recovery features; and generating a trained feature extraction model by optimizing the feature extraction model based on the first global recovery features, the first global features, the second global recovery features, and the second global features.

Abstract: Method for inverse optical proximity correction of super-resolution lithography based on level set algorithm is provided, including: obtaining first mask data according to a target pattern, and constructing a level set function; performing forward simulation, so as to obtain an electric field distribution on a photoresist and a first structural vector electric field distribution on a mask; obtaining a photoresist pattern according to the electric field distribution on the photoresist, and calculating an imaging error between the photoresist pattern and the target pattern; performing accompanying simulation, so as to obtain a second structural vector electric field distribution; obtaining a level set gradient by means of performing calculation according to the first structural vector electric field distribution, the second structural vector electric field distribution and the imaging error; and evolving the level set function, performing update to obtain second mask data, and performing iterative calculation u

Abstract: A level set algorithm based reverse optical proximity effect correction method for super-resolution lithography.

Abstract: The present disclosure provides a secondary imaging optical lithography method and apparatus.

Abstract: The embodiments of the present disclosure propose a negative refraction imaging lithographic method and equipment. The lithographic method includes: coating photoresist on a device substrate; fabricating a negative refraction imaging structure, wherein the negative refraction imaging structure exhibits optical negative refraction in response to beam emitted by exposure source; pressing a mask to be close to the negative refraction imaging structure; disposing the mask and the negative refraction imaging structure above the device substrate at a projection distance; and light emitted by the exposure source passes through the mask, the negative refraction imaging structure, the projection gap and is sequentially projected onto the photoresist for exposure.

Abstract: The present disclosure provides a secondary imaging optical lithography method and apparatus.

Abstract: The present invention provides a failure logic modeling method for a high-speed railway train operation control on-board system, including the following steps: determining the functional relationship between the structure and the parts of the train control on-board system; analyzing the failures of the parts based on known failures of the train control on-board system in combination with brainstorming; establishing an FMEA table to generalize the failures of the parts; editing and simulating the failures by using a modeling tool. By adopting the present invention, the failure modes analyzed are more systematic, and the failure logic modeling can be carried out from a global perspective more easily, the whole process can be better targeted meanwhile, the security analysis complexity of the train control system will be effectively reduced and the development period of the train control system will be shortened.

Abstract: The present invention provides a failure logic modeling method for a high-speed railway train operation control on-board system, including the following steps: determining the functional relationship between the structure and the parts of the train control on-board system; analyzing the failures of the parts based on known failures of the train control on-board system in combination with brainstorming; establishing an FMEA table to generalize the failures of the parts; editing and simulating the failures by using a modeling tool. By adopting the present invention, the failure modes analyzed are more systematic, and the failure logic modeling can be carried out from a global perspective more easily, the whole process can be better targeted meanwhile, the security analysis complexity of the train control system will be effectively reduced and the development period of the train control system will be shortened.