Zaharuddin Mohamed

Cranes with distributed-mass payload (DMP) have complex sway dynamics, and they are largely affected by changes in the DMP parameters. Although an input shaping technique has been utilised for sway control, it has low robustness to parameter uncertainties and mainly applied to cranes carrying a point mass payload. This paper proposes a robust shaper for efficient swing control of an underactuated overhead crane with a DMP under parameter uncertainties by using an output-based reference command shaping approach. The method has an advantage as it avoids the requirement for accurate measurements and estimations of the systems sway frequencies and damping ratios, which are difficult for DMP. In addition, the approach eliminates the need for controller re-design in cases of parameter changes. The effectiveness of the shaper is investigated using simulations and experiments under several scenarios involving varying cable lengths, changes up to 25% in the DMP masses and lengths, and different input profiles. The superiority and robustness of the shaper is confirmed with the highest hook and payload sway reductions in comparison to another multimode robust shapers. Under a robustness test with a different set of DMP parameters, and with experiments, the proposed shaper reduces the total sway by 46% and 24% as compared to the robust Zero Vibration Derivative (ZVD) and Equal Shaping-Time and Magnitude (ETM) shapers respectively. Interestingly, these are achieved by using only a single design and with a similar speed of trolley position response.

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.

Identification of dynamical systems from frequency response data (FRD) has extensively been studied and effective techniques have been developed. Given different FRD sets obtained from different systems and a fixed state space model structure, is it possible to find a constant parameter vector containing $(\mathbf {A},\mathbf {B},\mathbf {C},\mathbf {D})$ quadruple's numerical content and a FRD-associated mask vector set that approximates the spectral information available in each FRD set? This article proposes a genetic algorithm based optimization approach to determine the real parameter vector $(\mathbf {A},\mathbf {B},\mathbf {C},\mathbf {D})$ and the binary mask vector through a sequential optimization scheme. We study state space models for matching FRD from multiple systems. Results show that the proposed optimization approach solves the problem and compresses multiple dynamical models into a single masked one.

This paper introduces the notion of switched neural networks for learning multiple functions under different switching configurations. The neural network structure has adjustable parameters and for each function the state of the parameter vector is determined by a mask vector, 1/0 for active/inactive or +1/-1 for plain/inverted. The optimization problem is to schedule the switching strategy (mask vector) required for each function together with the best parameter vector (weights/biases) minimizing the loss function. This requires a procedure that optimizes a vector containing real and binary values simultaneously to discover commonalities among various functions. Our studies show that a small sized neural network structure with an appropriate switching regime is able to learn multiple functions successfully. During the tests focusing on classification, we considered 2-variable binary functions and all 16 combinations have been chosen as the functions. The regression tests consider four functions of two variables. Our studies showed that simple NN structures are capable of storing multiple information via appropriate switching.

Levenberg-Marquardt (LM) algorithm is a powerful approach to optimize the parameters of a neural network (NN). Given a training dataset, the algorithm synthesizes the best path toward the optimum. This paper demonstrates the use of LM optimization algorithm when there are more than one dataset and on/off type switching of NN parameters is allowed. For each dataset a pre-selected set of parameters are allowed for modification and the proposed scheme reformulates the Jacobian under the switching mechanism. The results show that a NN can store information available in different datasets by a simple modification to the original LM algorithm, which is the novelty introduced in this study. The results are verified on a regression problem.