提出了一种采样数据中存在高频有色噪声的连续模型辨识方法,并将其应用到磁致伸缩作动器的连续模型辨识中。该方法通过引入积分运算,将连续时间系统的微分方程转换为积分方程,从而使噪声的影响可以忽略,直接利用传统的最小二乘法估计出连续时间模型。仿真实例验证了该方法的有效性和可行性,辨识的磁致伸缩作动器具有较高的可信度。Abstract A continuous-time model identification method from sample data with high-frequency colored noise is presented. The method is applied to the continuous-time model identification of magnetostrictive actuator. By introducing an integral operation, the differential equations of continuous-time system can be transformed into integral equations so that the effect of the noise can be eliminated and that a continuous-time model can be estimated directly by using conventional LS methods. Simulation example demonstrates the effectiveness and the feasibility of the presented method. The identified continuous-time model of the magnetostrictive actuator has high reliability.