The all-electric ship (AES) with DC-grid configuration has demonstrated advantages compared to the traditional AC system and has become the state-of-the-art for ships with electric propulsion in the low to medium power range during the past decade. However, the integration with different power sources, such as fuel cells, batteries and diesel gen-sets, increases the system complexity and requires an advanced power management system (PMS) to handle vessel operation and to achieve optimal power control. This paper presents an optimized power management strategy to reduce the total cost of ownership of such vessels, considering not only the fuel cost and emission penalty, but also the power device degradation and equipment replacement cost. In this study, Model Predictive Control (MPC) and Reinforcement Learning (RL)-based PMS control methods are approached respectively. In order to demonstrate the performance of MPC and RL techniques, a typical tugboat load profile is simulated. The testing results are also compared with a traditional rule-based power management control.

With the increasing demand of product supply, manufacturers are in urgent need of online tool condition monitoring (TCM) without compromising with the maintenance cost in terms of time as well as man-power requirement. However, the existing machine learning models for TCM are mostly offline and not suitable for the non-stationary environment of the machining settings. Moreover, the access of the ground truth always imposes a shutdown of the machining process and the existing models are severely affected by such delay in receiving labelled samples. In order to tackle these issues, we propose SERMON as a novel learning model based on a pair of self-evolving mutually-operative recurrent neural networks. The proposed SERMON is well-equipped with features for automated and real-time monitoring of machine fault status even in the finite/infinite label delay scenario. The experimental evaluation of SERMON using real-world dataset on 3D-printing process demonstrates its effectiveness in online fault detection under non-stationary as well as delayed label context of the machining process. Additional comparative study on large-scale benchmark streaming datasets further exhibits the scalability power of SERMON.

Existing methodologies for tool condition monitoring (TCM) still rely on batch approaches which cannot cope with a fast sampling rate of a metal cutting process. Furthermore, they require a retraining process to be completed from scratch when dealing with a new set of machining parameters. This paper presents an online TCM approach based on Parsimonious Ensemble+ (pENsemble+). The unique feature of pENsemble+ lies in its highly flexible principle where both the ensemble structure and base-classifier structure can automatically grow and shrink on the fly based on the characteristics of data streams. Moreover, the online feature selection scenario is integrated to actively sample relevant input attributes. This paper presents advancement of a newly developed ensemble learning algorithm, pENsemble, where the online active learning scenario is incorporated to reduce the operator's labeling effort. The ensemble merging scenario is proposed which allows reduction of ensemble complexity while retaining its diversity. Experimental studies utilizing two real-world manufacturing data streams: 1) metal turning and 2) 3-D-printing processes and comparisons with well-known algorithms were carried out. Furthermore, the efficacy of pENsemble+ was examined using benchmark concept drift data streams. It has been found that pENsemble+ incurs low structural complexity and results in a significant reduction of the operator's labeling effort.

Being motivated by ceiling inspection applications via unmanned aerial vehicles (UAVs) which require close proximity flight to surfaces, a systematic control approach enabling safe and accurate close proximity flight is proposed in this work. There are two main challenges for close proximity flights: (i) the trust characteristics varies drastically for the different distance from the ceiling which results in a complex nonlinear dynamics; (ii) the system needs to consider physical and environmental constraints to safely fly in close proximity. To address these challenges, a novel framework consisting of a constrained optimization-based force estimation and an optimization-based nonlinear controller is proposed. Experimental results illustrate that the performance of the proposed control approach can stabilize UAV down to 1 cm distance to the ceiling. Furthermore, we report that the UAV consumes up to 12.5% less power when it is operated 1 cm distance to ceiling, which is promising potential for more battery-efficient inspection flights.

This paper presents an unmanned aerial vehicle (UAV) push recovery operation using model predictive control (MPC) and moving horizon estimation (MHE) in a symmetric manner. This utilization is motivated by the active use of UAVs, particularly for the contact based inspection of the surrounding's ceilings. To enable a physical interaction operation by an optimization-based algorithm, a primal-dual quadratic programming (QP) solver is structured for the MPC and MHE. The designed system consists of (a) an interaction model to be implemented both on the control and the estimation; (b) an integral action in the predictive controller; (c) a disturbance estimation by MHE to update the MPC. Consequently, the nominal MPC, the integral action in MPC, and the disturbance observer based MPC are compared for a UAV push recovery operation. The numerical investigations demonstrate the applicability of the proposed approach.

Cable-conduit mechanism (CCM) is widely used in robotic hands, rescue robots, rehabilitation robots, and surgical robots because it offers efficient transmission of forces/torques from the external actuator to the end effector with lightweight and high flexibility. However, the accurate position control is challenging in such mechanism due to friction and backlash-like hysteresis between the cable and the conduit. In this paper, a new control approach is proposed to enhance the trajectory tracking performances of the CCM. Unlike current approaches for the CCM in the literature, the proposed scheme considers the position transmission of the CCM as an approximation of backlash-like hysteresis nonlinearities without requiring the exact values of model parameters and their bounds. Online approximation-based robust control laws, which have the capabilities of estimating unknown system parameters, are also established. In addition, the deigned controller can adapt to any changes of the cable-conduit configuration and it is stable. The results of the proposed control techniques have been experimentally validated on a flexible robotic system using a flexible endoscope. Experimental validations show substantial improvements on the performances of position tracking for the use of CCM regardless of the arbitrary changes of the cable-conduit configurations.

Natural Orifice Transluminal Endoscopic Surgery (NOTES) is a method that allows for performing complex operations via natural orifices without skin incisions. Its main tool is a flexible endoscope. Cable-Conduit Mechanisms (CCMs) are often used in NOTES because of its simplicity, safety in design, and easy transmission. Backlash hysteresis nonlinearities between the cable and the conduit pose difficulties in the motion control of the NOTES system. It is challenging to achieve the precise position of robotic arms when the slave manipulator inside the humans body. This paper presents new approaches to model and control for pairs of CCMs. It is known that the change of cable-conduit configuration will affect the backlash hysteresis nonlinearities. To deal with such change, a new nonlinear and adaptive control scheme will be introduced. The backlash hysteresis parameters are online estimated under the assumption of availability of output feedback and unknown bound of nonlinear parameters. To validate the proposed approach, a prototype of single-DOF-Master-Slave system, which consists of a master console, a telesurgical workstation, and a slave manipulator, is also presented. The proposed compensation scheme is experimentally validated using the designed system. The results show that the proposed control scheme efficiently improves the tracking performances of the system regardless of the change of endoscope configuration.

Minimally Invasive Surgery (MIS) has established a revolution in surgical communities, with its many advantages over open surgery. The need of more simplicity and high maneuverability makes the tendon sheath a very suitable mechanism in flexible endoscopic systems. Due to the restriction on size constraints and sterilization problems, traditional sensors cannot be mounted on the tool tips of a slave manipulator. Moreover, in the presence of nonlinear friction and hysteresis between the tendon and the sheath, it is extremely difficult to control the precise motion and sense the force during the operation. This paper proposes a new dynamic friction model to estimate the force at the end effector for the tendon sheath mechanism. The proposed friction model can adapt with any initial pretension of the tendon and any configuration of the sheath. The nonlinearities in both sliding and presliding regimes can be captured by using an internal state variable and functions dependent velocity and acceleration. A specific setup has been designed in order to measure the friction force between the tendon and the sheath. Finally, the validity of the identified model is confirmed by a good agreement of its prediction and experimental data.