This paper investigates the sliding

本文研究了基于复合学习的MEMS陀螺仪滑模控制，该方法不仅着重于系统跟踪和稳定性分析，而且还密切关注期望的不确定不确定性的准确性。给出了串行-并行估计模型，并构造了包括跟踪误差和建模误差在内的滤波器误差，以设计神经网络（NN）的权重更新定律。仿真结果表明，该方法具有较好的跟踪性能和较高的精度。

This paper investigates the sliding mode control with composite learning for MEMS Gyroscopes, which not only focuses on the system tracking and stability analysis, but also pays close attention to the accuracy of desired identified uncertain dynamics. The serial–parallel estimation model is given and a filter error included tracking error and modeling error is constructed to design the weights updating law of neural networks (NNs). Simulation results demonstrate that the proposed approach achieves better tracking performance with higher accuracy.

This paper investigates the sliding mode control with composite learning for MEMS Gyroscopes, which not only focuses on the system tracking and stability analysis, but also pays close attention to the accuracy of desired identified uncertain dynamics. The serial–parallel estimation model is given and a filter error included tracking error and modeling error is constructed to design the weights updating law of neural networks (NNs). Simulation results demonstrate that the proposed approach achieves better tracking performance with higher accuracy.<br>