4 results about "Orthogonal method" patented technology

The present invention discloses a wireless charging system parameter optimization method based on Taguchi algorithm, which belongs to the field of wireless charging technology. The method comprises: selecting appropriate optimization parameters and optimization targets, ensuring no cross-coupling between the optimization parameters and determining the value range of each variable, screening out the value points of each variable, and converting them into multiple levels; constructing an orthogonal table by Latin square and matrix transformation, and if there is no completely suitable orthogonal table, selecting a deletion method, a quasi-level method, a combination method, or a parallel method to transform the orthogonal table; processing the experimental results of the orthogonal table, and determining the direction and significance of the influence of each parameter on the experimental results; carrying out further simulation according to the determined value range, continuing to apply the orthogonal method, and also carrying out an exhaustive method when there are fewer data points, to finally obtain a parameter combination that meets the requirements. The present invention has the advantages of low computational complexity, easy to jump out of the local minimum, and no reliance on precise mathematical models.

This application relates to the field of data processing technology, and discloses an orthogonal fusion model of emotion, fatigue, and subjective will, as well as a method for assessing mental state. For the problem of emotion recognition, this application proposes a spatiotemporal entropy feature extraction method, which has good adaptability to small sample EEG data; for the problem of low recognition rate in fatigue state recognition, it proposes a power spectrum normalization feature extraction method for brain functional connectivity, which shows higher accuracy in fatigue state recognition; for the problem of feature fusion of emotion, fatigue, and work will, it proposes a mental state assessment model based on the Taguchi orthogonal method that fuses subjective and objective indicators. Experimental results show that the spatiotemporal entropy feature emotion recognition, the power spectrum recognition fatigue state recognition of brain functional connectivity, and the orthogonal fusion mental state assessment model of subjective and objective indicators proposed in this invention can complete the task of recognizing emotional state, fatigue state, and mental state.

This invention relates to an improved method for optimal scheduling of an integrated power-electricity interconnected energy system, belonging to the field of electrical technology. The method includes the following steps: S1) analyzing the structure of the integrated power-electricity interconnected energy system; S2) building a mathematical model for optimal scheduling of the integrated power-electricity interconnected energy system; S3) solving and comparing the optimal scheduling methods of the integrated power-electricity interconnected energy system; and S4) performing simulation analysis of the optimal scheduling of the integrated power-electricity interconnected energy system. Based on decoupling analysis, this invention addresses the problems of existing distributed power flow calculation methods for integrated power-electricity interconnected energy systems by proposing an improvement based on the Schmitt orthogonal method. The improved method and the original optimal scheduling method are simulated separately, and the results are analyzed. The improved method reduces the condition number to 1 through preprocessing, reducing the number of iterations and shortening the calculation time, thereby improving computational efficiency.

This paper discloses a training method for a neural network to invert the equivalent dielectric constant of a honeycomb. Using an orthogonal method, a sample model with honeycomb wall thickness and relative dielectric constant as variables is designed. The honeycomb structure is homogenized using a homogenization method based on H-S theory to obtain the equivalent dielectric constant. The corresponding electromagnetic scattering data is calculated using a developed hexagonal method to generate a honeycomb sample dataset. The neural network is trained using the Pytorch deep learning framework. This neural network can accurately invert the equivalent dielectric constant based on the electromagnetic scattering data of the target model. Training the neural network requires only a limited number of numerical samples and allows for rapid and accurate prediction of unknown parameters, providing excellent problem-solving flexibility and generalization capabilities.