Abstract In electro-hydraulic system (EHS), there exist typical lumped uncertainties due to the uncertain hydraulic parameters and unknown external load, which usually decline the output dynamic performance. To address this problem, this paper proposes a neural adaptive control for single-rod EHS to improve the dynamic tracking performance of the cylinder position under these lumped uncertainties. A Radial-Basis-Function (RBF) neural network is constructed to train the unknown model dynamics caused by lumped uncertainties and obtain the self-learning models. Moreover, an adaptive estimation law is used to self-tune the trained-node weights and the self-learning models are online optimized to enhance the robustness of the neural adaptive controller. The effectiveness of the proposed controller has been verified by comparative simulation and experimental results with the other typical control methods.

中文翻译：

---

具有集总不确定度的单杆电液系统的神经自适应控制

摘要 在电液系统(EHS)中，由于液压参数的不确定性和外部负载的未知性，存在典型的集总不确定性，通常会降低输出动态性能。为了解决这个问题，本文提出了一种单杆 EHS 的神经自适应控制，以提高这些集中不确定性下气缸位置的动态跟踪性能。构建径向基函数（RBF）神经网络以训练由集总不确定性引起的未知模型动力学并获得自学习模型。此外，自适应估计律用于自调整训练节点权重，并在线优化自学习模型以增强神经自适应控制器的鲁棒性。