In this work, we use a neural network as a substitute for the traditional analytic functions employed as an inversion set in feedback linearization control algorithms applied to hydraulic actuators. Although very effective and with strong stability guarantees, feedback linearization control depends on parameters that are difficult to determine, requiring large amounts of experimental effort to be identified accurately. On the other hands, neural networks require little effort regarding parameter identification, but pose significant hindrances to the development of solid stability analyses and/or to the processing capabilities of the control hardware. Here, we combine these techniques to control the positioning of a hydraulic actuator, without requiring extensive identification procedures nor losing stability guarantees for the closed-loop system, at reasonable computing demands. The effectiveness of the proposed method is verified both theoretically and by means of experimental results.

在这项工作中，我们使用神经网络代替了传统的解析函数，该函数在应用于液压执行器的反馈线性化控制算法中用作反演集。尽管非常有效且具有很强的稳定性保证，但是反馈线性化控制取决于难以确定的参数，需要大量的实验工作才能准确识别。另一方面，神经网络在参数识别方面所需的精力很少，但对固体稳定性分析和/或控制硬件的处理能力构成了重大障碍。在这里，我们结合了这些技术来控制液压执行器的位置，而无需进行大量的识别程序，也不会失去对闭环系统的稳定性保证，在合理的计算需求下。理论上和实验结果都验证了该方法的有效性。