基于多维泰勒网的多入多出非线性时滞系统辨识

Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2022-04-07 Cooperative journals: 《计算机应用研究》

李晨龙 严洪森

Abstract： For the accuracy and real-time performance of multiple input multiple output (MIMO) nonlinear time-delay system, we propose the identification scheme based on multi-dimensional Taylor Network (MTN) . We use MTN as an identification model. MTN identification model’s learning algorithm adopts the WE-CG algorithm, which combines the weight-elimination (WE) algorithm with the conjugate gradient (CG) algorithm. WE algorithm can simplify the structure of MTN model so as to reduce computational complexity and improve the real-time performance. Finally, there are two experimental examples containing a numerical example and a project one to verify the effectiveness of the proposed identification scheme. And we use the traditional MTN identification scheme to compare. Both the accuracy and the computational complexity analysis illustrate the accuracy and the real-time performance of the proposed scheme. Results from our experiments and comparison show that the proposed scheme can identify the MIMO nonlinear time-delay system accurately, and the proposed identification scheme has a simpler structure and lower computational complexity than the traditional MTN identification scheme.

 Hits 1766  Downloads 372  Comment 0