Faculty of Aerospace Engineering, K.N. Toosi University of Technology, No. 42 Chamran Alley, North Shahin Street, Hemmat Highway west, Tehran 1475883579, Iran.
ISA Trans. 2012 Jan;51(1):208-19. doi: 10.1016/j.isatra.2011.09.006. Epub 2011 Oct 19.
This paper presents a new intelligent approach for adaptive control of a nonlinear dynamic system. A modified version of the brain emotional learning based intelligent controller (BELBIC), a bio-inspired algorithm based upon a computational model of emotional learning which occurs in the amygdala, is utilized for position controlling a real laboratorial rotary electro-hydraulic servo (EHS) system. EHS systems are known to be nonlinear and non-smooth due to many factors such as leakage, friction, hysteresis, null shift, saturation, dead zone, and especially fluid flow expression through the servo valve. The large value of these factors can easily influence the control performance in the presence of a poor design. In this paper, a mathematical model of the EHS system is derived, and then the parameters of the model are identified using the recursive least squares method. In the next step, a BELBIC is designed based on this dynamic model and utilized to control the real laboratorial EHS system. To prove the effectiveness of the modified BELBIC's online learning ability in reducing the overall tracking error, results have been compared to those obtained from an optimal PID controller, an auto-tuned fuzzy PI controller (ATFPIC), and a neural network predictive controller (NNPC) under similar circumstances. The results demonstrate not only excellent improvement in control action, but also less energy consumption.
本文提出了一种新的智能方法，用于非线性动态系统的自适应控制。一种基于脑情绪学习的智能控制器（BELBIC）的改进版本，该算法基于情绪学习的计算模型，发生在杏仁核中，用于控制真实实验室旋转电液伺服（EHS）系统的位置。由于许多因素，如泄漏、摩擦、滞后、零位偏移、饱和、死区，特别是通过伺服阀的流体流动表达式，EHS 系统通常是非线性和非光滑的。这些因素的值很大，在设计不佳的情况下，很容易影响控制性能。本文推导出 EHS 系统的数学模型，然后使用递推最小二乘法对模型参数进行辨识。下一步，基于这个动态模型设计了一个 BELBIC，并利用它来控制真实实验室的 EHS 系统。为了证明改进后的 BELBIC 的在线学习能力在降低总体跟踪误差方面的有效性，在相似的情况下，将结果与最优 PID 控制器、自整定模糊 PI 控制器（ATFPIC）和神经网络预测控制器（NNPC）的结果进行了比较。结果不仅证明了控制作用的显著改善，而且还证明了能耗的降低。
