非线性系统载荷识别的最小二乘支持向量机法  

Least Squares Support Vector Machine Method for Load Identification of Nonlinear Systems

作　　者：周盼 辛江慧 丁继才 ZHOU Pan;XIN Jianghui;DING Jicai(School of Automotive and Rail Transit,Nanjing Institute of Technology,Nanjing 211167,China;Military Representative Office of Naval Equipment Department in Huludao,Huludao 125004,Liaoning,China)

机构地区：[1]南京工程学院汽车与轨道交通学院,南京211167 [2]海军装备部驻葫芦岛地区军事代表室,辽宁葫芦岛125004

出　　处：《噪声与振动控制》2021年第5期9-13,37,共6页Noise and Vibration Control

基　　金：国家自然科学基金资助项目(51805241);南京工程学院高层次引进人才科研启动基金资助项目(YKJ201731)。

摘　　要：为解除载荷识别问题对原系统先验知识的依赖,提出采用最小二乘支持向量机(Least squares support vector machine,LS-SVM)对非线性系统进行逆模型辨识,随后在该逆模型基础上利用工作状态的响应数据识别时域载荷。通过对某一非线性系统的稳态和非稳态激励的仿真计算,验证该方法的有效性。仿真结果表明LS-SVM能够辨识出可靠的非线性系统的逆模型,进而反演出较精确的时域载荷。该方法不需要了解系统的数学模型及参数,只需少量训练样本即可,因此该方法能够较好地应用于工程实践中。In order to eliminate the dependence of load identification on a priori knowledge of current mechanical system,least squares support vector machine(LS-SVM)is applied to identify the inverse model of nonlinear systems.Then,based on the inverse model,the operational responses were adopted to determine the real time excitation force.A nonlinear system was applied to conduct the simulation and calculate the steady and unsteady input force to verify the validity of the proposed method.Simulation results reveal that the LS-SVM is able to identify reliable inverse model of nonlinear systems and then reconstruct accurate real time excitation force.The presented approach only needs a small quantity of training samples rather than complete knowledge of the mathematical model and parameters of the nonlinear system.So,this approach can well be extended to engineering application.

关 键 词：振动与波 最小二乘支持向量机 逆模型辨识 非线性系统 载荷识别 

分 类 号：TU312[建筑科学—结构工程] O327[理学—一般力学与力学基础]