Towards the Autonomy: Control Systems for the Ship in Confined and Open Waters

Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach

This work has two objectives. Firstly, it describes a novel physics-informed hybrid neural network (PIHNN) model based on the long short-term memory (LSTM) neural network. The presented model structure combines the first-principle process description and data-driven neural sub-models using a specialized data fusion block that relies on fuzzy logic. The second objective of this work is to detail a computationally efficient model predictive control (MPC) algorithm that employs the PIHNN model. The validity of the presented modeling and MPC approaches is demonstrated for a simulated polymerization reactor. It is shown that the PIHNN structure gives very good modeling results, while the MPC controller results in excellent control quality.

Control of Dynamic Positioning System with Disturbance Observer for Autonomous Marine Surface Vessels

The main goal of the research is to design an efficient controller for a dynamic positioning system for autonomous surface ships using the backstepping technique for the case of full-state feedback in the presence of unknown external disturbances. The obtained control commands are distributed to each actuator of the overactuated vessel via unconstrained control allocation. The numerical hydrodynamic model of CyberShip I and the model of environmental disturbances are applied to simulate the operation of the ship control system using the time domain analysis. Simulation studies are presented to illustrate the effectiveness of the proposed controller and its robustness to external disturbances.

Computationally Efficient Nonlinear Model Predictive Control Using the L1 Cost-Function

Model Predictive Control (MPC) algorithms typically use the classical L2 cost function, which minimises squared differences of predicted control errors. Such an approach has good numerical properties, but the L1 norm that measures absolute values of the control errors gives better control quality. If a nonlinear model is used for prediction, the L1 norm leads to a difficult, nonlinear, possibly non-differentiable cost function. A computationally efficient alternative is discussed in this work. The solution used consists of two concepts: (a) a neural approximator is used in place of the non-differentiable absolute value function; (b) an advanced trajectory linearisation is performed on-line. As a result, an easy-to-solve quadratic optimisation task is obtained in place of the nonlinear one. Advantages of the presented solution are discussed for a simulated neutralisation benchmark. It is shown that the obtained trajectories are very similar, practically the same, as those possible in the reference scheme with nonlinear optimisation. Furthermore, the L1 norm even gives better performance than the classical L2 one in terms of the classical control performance indicator that measures squared control errors.