计算机仿真
計算機倣真
계산궤방진
COMPUTER SIMULATION
2014年
5期
342-345
,共4页
生物地理学优化算法%系统辨识%海默斯坦模型
生物地理學優化算法%繫統辨識%海默斯坦模型
생물지이학우화산법%계통변식%해묵사탄모형
Biogeography-based optimization%System identification%Hammerstein model
为了研究非线性控制的辨识优化问题，提出辨识非线性模型的新方法。针对传统辨识方法对非线性模型中非线性部分辨识精度低、效果差等缺点，将生物地理学算法引入到非线性辨识中，并结合Hammerstein模型，提出了一种基于生物地理学算法的Hammerstein模型识别方法。为了进一步增强生物地理学算法的辨识精度，采用了带有加权因子的迁移和基于柯西变异的改进生物地理学算法对非线性系统进行辨识。通过数值仿真，并与传统的最小二乘法和基本生物地理学算法进行比较，结果表明利用改进算法能够提高辨识精度，验证了改进算法的有效性和可行性。
為瞭研究非線性控製的辨識優化問題，提齣辨識非線性模型的新方法。針對傳統辨識方法對非線性模型中非線性部分辨識精度低、效果差等缺點，將生物地理學算法引入到非線性辨識中，併結閤Hammerstein模型，提齣瞭一種基于生物地理學算法的Hammerstein模型識彆方法。為瞭進一步增彊生物地理學算法的辨識精度，採用瞭帶有加權因子的遷移和基于柯西變異的改進生物地理學算法對非線性繫統進行辨識。通過數值倣真，併與傳統的最小二乘法和基本生物地理學算法進行比較，結果錶明利用改進算法能夠提高辨識精度，驗證瞭改進算法的有效性和可行性。
위료연구비선성공제적변식우화문제，제출변식비선성모형적신방법。침대전통변식방법대비선성모형중비선성부분변식정도저、효과차등결점，장생물지이학산법인입도비선성변식중，병결합Hammerstein모형，제출료일충기우생물지이학산법적Hammerstein모형식별방법。위료진일보증강생물지이학산법적변식정도，채용료대유가권인자적천이화기우가서변이적개진생물지이학산법대비선성계통진행변식。통과수치방진，병여전통적최소이승법화기본생물지이학산법진행비교，결과표명이용개진산법능구제고변식정도，험증료개진산법적유효성화가행성。
A new parameter identification method for nonlinear model was proposed. In order to overcome the dis-advantage that the recognition accuracy for the nonlinear part of nonlinear model is poor in traditional identification methods, the Biogeography-Based Optimization ( BBO) was introduced to nonlinear system identification and com-bined Hammerstein model, and the Hammerstein model identification method based on BBO algorithm was proposed. In order to enhance the identification performance of the BBO algorithm, the BBO was improved based on partial mi-gration with weight factor and the Cauchy mutation was used to identify nonlinear system. According to a numerical simulation and comparing with the traditional least square method and the basic BBO algorithm, the results show that the algorithm can improved the identification accuracy and obtain a good recognition results, which verifies the effec-tiveness and feasibility of the algorithm.
