Arab J Sci Eng (2018) 43:2725–2733 https://doi.org/10.1007/s13369-017-2747-0 RESEARCH ARTICLE - ELECTRICAL ENGINEERING Decoupled Adaptive Neuro-Interval Type-2 Fuzzy Sliding Mode Control Applied in a 3DCrane System Belkheir Benhellal 1 · Mustapha Hamerlain 2 · Yacine Rahmani 1 Received: 5 December 2016 / Accepted: 16 July 2017 / Published online: 27 July 2017 © King Fahd University of Petroleum & Minerals 2017 Abstract Moving an object attached to a cable along a pre- determined path is a very complex task when the angles of oscillation impose severe constraints. However, to min- imize the swing angle, adaptive control laws are necessary, especially in case where the systems dynamics are prone to uncertainties. In this paper, we propose a decoupled adaptive neuro-interval type-2 fuzzy controller based on the slid- ing mode theory for the control of 3DCrane system. The considered 3DCrane system involves a plan movement in conjunction with a lifting movement. It has three control inputs only (trolley and hoisting forces) with five controlled variables (the trolley position in the XOY plane, the length of the lifting cable, and the two angles of swing). Overall, con- trol subsystems are regarded as being decoupled interactions and that are taken as disturbances acting in the control of each individual subsystem. In the proposed approach, a con- ventional controller (PD) and the neuro-interval type-2 fuzzy controller are used in parallel; the PD controller ensures the asymptotic stability in compact space, the adaptation param- eters of neuro-interval type-2 fuzzy inference system rules are obtained by derivation, and Lyapunov method is used to demonstrate the stability of the online learning algorithm. To validate the proposed approach, the laboratory equipment 3DCrane system is used as an experimental platform. The presented results are obtained for a trajectory tracking with a minimum of oscillations. B Belkheir Benhellal ge.bbenhellal@gmail.com 1 Department of Electronics and Telecommunications, Electrical Engineering Laboratory (LAGE), University of Kasdi Merbah, Ouargla, Algeria 2 Centre for Development of Advanced Technologies, Alger, Algeria Keywords Adaptive neuro-interval type-2 fuzzy control · Sliding mode learning algorithm · 3DCrane system 1 Introduction In many industrial environments, the crane system is one of the most widely used systems for rapid and accurate trans- fer of heavy loads over long distances. However, the rate of change engenders the acceleration of the load carried by the crane, causing undesirable oscillation. This oscillation of the load considerably reduces safety and increases the risk of falling and collision. Therefore, a development of robust control lows for crane systems is required. However, control- ling the 3DCrane systems is not a simple task, as they have less control variable as degrees of freedom. In the literature, there are several approaches to the con- trol of crane systems. The majority of them insist on the minimization of oscillation during a trajectory tracking. In some works the authors applied sliding mode techniques on the crane systems. Zhang et al. [1] have developed a con- trol law based on the second-order sliding mode for quick and accurate transfer with elimination of oscillations dur- ing movement of the load. Authors in [2] applied the sliding mode technique for a point-to-point movement control of a hoisting crane payload. A sliding mode control scheme founded on the super-twisting algorithm (STA) is presented in [3]. The use of sliding mode control approach for the control of crane systems is the subject of several articles. However, other types of control could apply to these systems. Fuzzy control techniques have been validated on crane systems in some works. Authors in [4] have proposed an anti- swing fuzzy logic control scheme for a three-dimensional overhead crane. Chang et al. [5] have presented a novel 123