Direct digital frequency synthesizer based on rbf neural network with stage-by-stage optimization

By using a phased optimized RBF neural network, the problems of DDS output signal accuracy and hardware resource consumption were solved, achieving an efficient frequency synthesis scheme and improving the performance and adaptability of DDS.

CN117200707BActive Publication Date: 2026-07-28NANJING UNIV OF POSTS & TELECOMM
0 Cites 0 Cited by

Patent Information

Application Number
CN202311302029.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-10-09
Publication Date
2026-07-28
Estimated Expiration
2043-10-09

AI Technical Summary

Technical Problem

While improving the accuracy of the output signal, existing DDS technology increases hardware resource consumption. The BP neural network algorithm suffers from slow convergence speed, weak nonlinear fitting ability, and easy trapping in local extrema.

Method used

A phased optimization RBF neural network is adopted, including coarse and fine adjustment stages. The K-means++ algorithm is used to select the center value of the hidden layer nodes, and the L-BFGS-B algorithm is combined to adjust the center value, thereby optimizing the training process of the RBF neural network. The network is constructed using a DDS structure consisting of a phase accumulator, an RBF neural network module, a digital-to-analog converter, and a low-pass filter.

Benefits of technology

It improves the accuracy of the DDS output signal and the flexibility of frequency adjustment, reduces the consumption of hardware resources, and enhances the performance and scalability of DDS.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a direct digital frequency synthesizer based on RBF neural network of phased optimization, which comprises a phase accumulator responsible for generating a phase signal, an RBF neural network module responsible for converting the phase signal into a digital amplitude signal, a digital-analog converter responsible for converting the digital amplitude signal into a low-frequency sawtooth signal and a low-pass filter responsible for converting the sawtooth signal into a smooth analog signal. The RBF neural network module comprises a hidden layer and an output layer, each node in the hidden layer has a corresponding radial basis function, so as to map a corresponding characteristic value for each input phase information, multiply the corresponding characteristic value of each node with the corresponding weight in the output layer, and then sum up to obtain an amplitude value corresponding to the phase information. Compared with the prior art, the application introduces the RBF neural network, so that the direct digital frequency synthesizer has stronger scalability and adaptability when processing complex and nonlinear frequency synthesis tasks.
Need to check novelty before this filing date? Find Prior Art