改进PSO-NN算法在微带线S参数模型中的应用
pplication of Improved PSO-NN Algorithm in the Model for S-Parameter of Microstrip Line
为了克服商用软件研究微带线S参数时计算代价大，耗时长的缺陷，本文提出了粒子群-神经网络算法。首先，为了检验粒子群-神经网络算法的性能，利用三种算法性能校验函数分别对粒子群-神经网络算法、粒子群算法和BP神经网络算法进行测试，并将三者的结果进行比较，比较结果表明粒子群-神经网络算法的精度最高，稳定性最好。最后，将粒子群-神经网络算法应用于微带线S参数建模研究中，用CST软件得到的微带线S参数作为训练数据和验证数据，并与粒子群和BP神经网络算法的结果进行比较，发现粒子群-神经网络算法在误差和稳定性上都有明显优势，表明该算法用于微带线S参数建模中是可行有效的。
o overcome the computational cost, time consuming defects of calculation of S-parameters of the microstrip line with the commercial software, Particle Swarm Optimization-Neural Network (PSO-NN) algorithm is proposed. Firstly, this paper applies PSO-NN algorithm, together with Particle Swarm Optimization (PSO) and BP neural network algorithm, to three Algorithms Performance Check Functions to examine the performance of the PSO-NN algorithm. Compared with the other two algorithms, PSO-NN algorithm is proved to have the highest precision and the best stability. Finally, PSO-NN algorithm is applied to the general model for S-parameter of microstrip line, using the S-parameters data of the microstrip line from CST software as training data and validation data, and again compared with PSO and BP neural network algorithm. The result of the comparison shows that PSO-NN has obvious advantages in reducing the error and improving the stability of the model. This experiment indicates that the PSO-NN algorithm is feasible and effective in the general model for S-parameter of microstrip line.
黄吉畴、王光波、高雪莲、宋宁宁
电子电路
微带线S参数测试函数ST软件粒子群-神经网络算法(PSO-NN)
S-parameter of microstrip lineCheck FunctionsCST softwareParticle Swarm -Neural Network (PSO-NN)
黄吉畴,王光波,高雪莲,宋宁宁.改进PSO-NN算法在微带线S参数模型中的应用[EB/OL].(2013-07-12)[2025-08-05].http://www.paper.edu.cn/releasepaper/content/201307-196.点此复制
评论