4 results about "Theoretical research" patented technology

The application discloses a large mold cavity degradation and forging quality deviation prediction method under extreme working conditions, and specifically comprises the following steps: step 1, constructing a stress and forging forming coupling analysis model of the large mold under extreme service working condition; step 2, obtaining the change rule of each field quantity in a single cycle service of the large mold under extreme working condition; step 3, establishing a multi-cycle automatic expansion finite element analysis model; step 4, analyzing the service cumulative deformation, wear, damage and cavity shape degradation rule of the mold in multiple cycles; step 5, obtaining the influence rule of the mold degradation on the forging size deviation and calibrating the model. The application can effectively guide the design optimization and service maintenance of the large mold, prolong the service life of the large mold, improve the production precision and stability of the forgings, and is suitable for the service performance prediction of the large mold in the fields of aviation, aerospace and high-end equipment manufacturing, and has important engineering application value and theoretical research significance.

The application discloses a kind of extreme working condition under large mould profile size precision initiative compensation predecision-making method, the extreme working condition is: temperature range is 700 ℃-1200 ℃, forming load is 500MN-800MN;Specifically includes the following steps: step 1, constructs the large mould factor trace mechanism of forging geometric size target deviation;Step 2, degradation prediction input stage;Step 3, compensation amount calculation generation stage;Step 4, construct neural network proxy model.The application realizes the prospective prediction of mould cavity degradation and forging size deviation before forging production and profile compensation predecision-making, can effectively guide the design optimization, service maintenance and profile compensation planning of large mould, significantly improve forging production precision and stability, reduce mould failure and forging scrap risk, applicable to aerospace, high-end equipment manufacturing and other fields under extreme service working condition Large mould application, with important engineering application value and theoretical research significance.

The application discloses a kind of construction methods of multi-section combined mining horizontal pillar critical thickness optimization calculation model, belong to mining process technical field.The method is analyzed by the mechanical state where horizontal pillar is located, based on Mindlin medium thick plate theory, under the boundary condition of four edges fixed support, under the action of multi-stress field of upper uniform load, self gravity, two-way horizontal stress, the bottom surface is in the state of open space, the mechanical model of horizontal pillar;Finite fourier integral transformation method is used to solve and analyze the mechanical model of horizontal pillar, the internal force distribution law of horizontal pillar is obtained, based on maximum tensile stress criterion, the critical thickness optimization model of horizontal pillar is constructed, the mechanical action of horizontal pillar is clarified, the critical thickness optimization model of horizontal pillar constructed has important theoretical research significance and higher popularization and application value for accurately determining the critical thickness of horizontal pillar in mine, ensure the safety of multi-section combined mining.

The present application belongs to the technical field of machine answering, and particularly relates to a question understanding method for machine answering. The present application firstly realizes feature extraction and unified semantic expression of single-mode / multi-mode data through a feature embedding module, an encoder and a contrast learning module, then defines direct statement relations and implied relations, extracts direct statement relations directly shown in the question in the question understanding process to realize fusion understanding of data, and reasons out implied relations required for answering the question, thereby laying a foundation for automatic solution of the question. The present application establishes a basic theory of machine answering, breaks through key technologies of machine answering, is very crucial for expanding a problem solving range and improving problem solving quality, has important theoretical research significance, academic research value and broad application prospect, and meets application services of machine answering.