Large-scale solar-powered unmanned aerial vehicles possess the capacity to perform long-term missions at different altitudes from near-ground to near-space, and the huge spatial span brings strict disciplines for its ...
详细信息
Large-scale solar-powered unmanned aerial vehicles possess the capacity to perform long-term missions at different altitudes from near-ground to near-space, and the huge spatial span brings strict disciplines for its attitude control such as aerodynamic nonlinearity and environmental disturbances. The design efficiency and control performance are limited by the gain scheduling of linear methods in a way, which are widely used on such aircraft at present. So far, deep reinforcement learning has been demonstrated to be a promising approach for training attitude controllers for small unmanned aircraft. In this work, a low-level attitude control method based on deep reinforcement learning is proposed for solar-powered unmanned aerial vehicles, which is able to interact with high-fidelity nonlinear systems to discover optimal control laws and can receive and track the target attitude input with an arbitrary high-level control module. Considering the risks of field flight experiments, a hardware-in-loop simulation platform is established that connects the on-board avionics stack with the neural network controller trained in a digital environment. Through flight missions under different altitudes and parameter perturbation, the results show that the controller without re-training has comparable performance with the traditional PID controller, even despite physical delays and mechanical backlash.
This study presents the design and development of a soft-core prototype of an overcurrent relay (OCR). The prototype is implemented on the field programmable gate array and its functionality has been verified using ha...
详细信息
This study presents the design and development of a soft-core prototype of an overcurrent relay (OCR). The prototype is implemented on the field programmable gate array and its functionality has been verified using hardware-in-loop testing on the real-time digital simulator. Computational efficiency and memory requirement of the OCR is improved by using integer arithmetic Verilog design platform. Extreme inverse and very inverse characteristics of the OCR based on standard inverse-time characteristics as per IEEE standard C37.112-1996 is used and tested in the proposed design. Digital design of the proposed algorithm, emulation results, complete hardware setup and experimental test results are presented in this study. The performance of the OCR is evaluated for a large range of characteristic parameters (pick-up current and time-dial setting) and various operating conditions which validate the operation of the relay in real time with the power network. The designed relay has the ability to differentiate between fault and inrush current to avoid any mal-operation during energisation of transformers.
In this study, a novel islanding detection technique (IDT) based on the islanding discrimination factor using the periodic maxima of superimposed voltage components is proposed. The voltage profile of the target distr...
详细信息
In this study, a novel islanding detection technique (IDT) based on the islanding discrimination factor using the periodic maxima of superimposed voltage components is proposed. The voltage profile of the target distributed generator is monitored continuously and its sequence components are extracted using half-angle theorem. A modular approach is used to implement the IDT algorithm, which is targeted on the reconfigurable hardware, i.e. field-programmable gate array. hardware description language Verilog has been used to optimise the hardware resources and minimise the computational complexity. hardware-in-loop verification of the proposed IDT has been done for islanding and non-islanding events with a microgrid (MG) test system developed on real-time digital simulator. Various cases for both islanding and non-islanding events, namely different faults are realised on the developed MG system. The results suggest that the proposed scheme successfully differentiates islanding events from a non-islanding event, and also detects the islanding event accurately under perfect power balance condition within half a cycle.
暂无评论