Particle swarm optimization-based neural network control for an electro-hydraulic servo system

Abstract

This paper focuses on an electro-hydraulic servo system, which is derived from a shaking table. It proposes a control scheme based on a back propagation (BP) neural network, whose weights are trained by the particle swarm optimization (PSO) according to the fitness, which is determined by the input and the feedback signals. Each particle of PSO includes weights and thresholds of BP. The movement of each particle is adjusted by its local best-known position and the global best-known position in the searching space. With the update, a satisfactory solution can be achieved. In order to show the performance of the proposed control scheme, the designed network is also trained and tested by BP only. The comparisons between the PSO-BP and BP networks demonstrate that the PSO-BP one has better performance than that of BP, both in convergence speed and in convergence accuracy.

Adaptive neural finite-time trajectory tracking control of hydraulic excavators

“…Theorem 3.1. Consider system (8) under Assumption 2, with the HOSM observer (9), the ESN (13), the ANFC controller (19) and the adaptive laws (20) and (22), and then, both the TSM manifold (17) and the trajectory tracking error will converge to a small neighborhood around zero in finite time.…”

“…1. Determine the parameters for the observer (equation (9)), the ESN (13), and the TSM manifold (17) offline; 2. Determine the control parameters for the ANFC controller (19) and the adaptive parameters for equations (20) and (22) online; 3.…”

“…Based on adaptive inverse control theory, adaptive neural inverse control methods have been developed and applied to hydraulic systems. [15][16][17] The input and output signals of the plant were used to learn an inverse model with an online-updated neural network, which meant no explicit knowledge of the plant dynamics was required. To improve control performance, neural-network-based proportional-integral-derivative (PID) control approaches were also developed for hydraulic systems.…”

“…To improve control performance, neural-network-based proportional-integral-derivative (PID) control approaches were also developed for hydraulic systems. 2,18,19 However, for these methods, 2,[15][16][17][18][19] system stability and tracking error convergence cannot be proved in theory. Furthermore, an adaptive robust neural controller was developed for an underwater hydraulic manipulator, which guaranteed asymptotical tracking performance.…”

An Electro-Hydraulic Servo with Intelligent Control Strategy

“…In the previous works, there are many type of control techniques have been reported, which can be utilized to control the tracking capability of a nonlinear electrohydraulic actuator system. Each of the control techniques required a proper tuning technique and some of the advanced tuning techniques have been reported recently such as Particle Swarm Optimization (PSO) [13][14][15][16][17][18], Genetic Algorithm (GA) [19][20][21], and Differential Evolution (DE) [22,23].…”