Combined neural network-based adaptive input shaping and feedback control for effective automation of tower cranes under payload hoisting

Abstract

This paper proposes a hybrid control that combines an adaptive neural network (NN)-based input shaping control (ISC) with an intelligent fuzzy logic control (FLC) for control of a tower crane. The design has an advantage as the adaptive shaper can handle the payload sway control under parameter uncertainly while the FLC provides accurate trolley and jib positioning. The most challenging operation of the crane, involving simultaneous trolley displacement, jib rotation, and payload hoisting, is investigated using a laboratory tower crane with nominal cylindrical and distributed rectangular payloads. The performance of the NN is compared with gain-scheduling lookup tables (LT) while the FLC is compared with PID. Experimental results show that the proposed NNZVD+FLC provides the highest performance with satisfactory position tracking and maintains the residual sway within ±3°. The work demonstrates that the adaptive ISC can be successfully combined with intelligent feedback controllers for effective automation of crane systems.