METHOD FOR EVALUATING SUBSTRATE SURFACE CLEANLINESS ORIENTED TO ADDITIVE FORGING

    公开(公告)号:US20240003824A1

    公开(公告)日:2024-01-04

    申请号:US18247461

    申请日:2022-01-20

    CPC classification number: G01N21/94 G01N2021/945

    Abstract: A method for evaluating a surface cleanliness oriented toward additive forging of a metal substrate employs weight coefficients corresponding to oil contaminants, particles and chips. Contamination scores of different contaminants are determined separately by different methods, and a surface cleanliness thereof is characterized in a quantitative manner by calculating the sum of the product of the weight coefficient and the contamination score of each contaminant. Further, an accurate and systematic method for evaluating a surface cleanliness employs weight coefficient of each contaminant determined based on a degree of adverse influence of the contaminant on the interface bonding of a substrate. Different detection methods are used for different contaminants. The contamination score of each contaminant is determined by the sum of the product of the weight coefficient and the contamination score of the corresponding contaminant, the comparison relationship is thus established, a cleanliness level is finally determined.

    Intelligent control method for dynamic neural network-based variable cycle engine

    公开(公告)号:US11823057B2

    公开(公告)日:2023-11-21

    申请号:US16981682

    申请日:2020-02-28

    CPC classification number: G06N3/084 G06N3/048

    Abstract: An intelligent control method for a dynamic neural network-based variable cycle engine is provided. By adding a grey relation analysis method-based structure adjustment algorithm to the neural network training algorithm, the neural network structure is adjusted, a dynamic neural network controller is constructed, and thus the intelligent control of the variable cycle engine is realized. A dynamic neural network is trained through the grey relation analysis method-based network structure adjustment algorithm designed by the present invention, and an intelligent controller of the dynamic neural network-based variable cycle engine is constructed. Thus, the problem of coupling between nonlinear multiple variables caused by the increase of control variables of the variable cycle engine and the problem that the traditional control method relies too much on model accuracy are effectively solved.

Patent Agency Ranking