Neuro-fuzzy-based anti-swing control of automatic tower crane

Abstract

Controlling the position of the final load and the anti-swing control of the loads during the operation of the tower crane are challenging tasks. These are the most important control issues for safe operation, which are difficult to achieve easily with conventional control systems. Hence, the need to integrate the concepts of soft-computing into the tower crane control system. The aim of this research work is to design an adaptive-network-based fuzzy inference system (ANFIS) controller to move the payload to the final position with the lowest possible swing angle. To evaluate the ability of the proposed controller to meet the control requirements, its performance was compared to three other controllers: a conventional proportional derivative (PD) controller, a fuzzy-tuned PD controller and a fuzzy controller. MATLAB-based computer simulations of the crane and controllers were carried out to verify and compare the performance of the proposed controllers. The obtained results show the effectiveness of the ANFIS-based controller in adjusting the load position while keeping the load fluctuations small at the final position. The load oscillation angle is about ±2.28° with the ANFIS controller while it is about ±10° when using the PD controller. In addition, only one ANFIS controller is used for both load position and swing angle control.