A nonlinear time-varying system solving method based on a neural network
A time-varying system and neural network technology, applied in the field of neural dynamics, can solve the problem of high time cost and achieve the effect of improving the calculation speed
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2019-05-21
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the field of neural dynamics, in particular to a method for solving nonlinear time-varying systems based on neural networks. Background technique
[0002] Nonlinear problems have an important impact on scientific research and engineering application practice. Many practical problems can be described as f(x)=0 and thus solved. But since state variables always evolve over time, computational methods need to be fast enough so that the computed solution can track the theoretical solution. In the past few decades, many researchers have devoted themselves to obtaining efficient, exact or approximate solutions for nonlinear time-varying systems, but because some nonlinear time-varying systems do not have exact analytical solutions, they can only be dealt with by numerical methods. Nonlinear time-varying systems. However, numerical methods are not efficient enough because they are performed in serial processing on digital computers....
Examples
Embodiment
[0044] A neural network-based nonlinear time-varying system solution method, the specific steps include:
[0045] (1) Formulate the actual engineering problem and establish the standard model of the nonlinear time-varying system to be solved;
[0046] (2) Design the error function based on the established standard model of the nonlinear time-varying system;
[0047] (3) Deriving the error function, introducing a monotonically increasing odd activation function according to the standard model of the nonlinear time-varying system and the derivative of the error function;
[0048] (4) Design time-varying parameters, according to error function, time-varying parameters and activation function, set up variable parameter recursive neural network model;
[0049] (5) Solve the variable parameter recurrent neural network, and the state solution obtained is the solution of the actual engineering problem.
[0050] In this embodiment, a specific nonlinear time-varying system equation is...