The limited space health intelligence sensing program is developed, the main function is to coordinate the startup and work of each hardware module, and obtain and transmit the monitoring data of operators. By using f...
详细信息
The existing unsupervised random walk keyphrase extraction model mainly relies on the global structural information of the word graph. It ignores the external structure and topic information of the document. To addres...
详细信息
For the sake of the fixed magnitude of candidate control sets, the conventional model predictive current control (MPCC) for asymmetric six-phase permanent magnet motors suffers from huge harmonic currents. This articl...
详细信息
Private and automatic recognition in many applications, such as forensic, access control, and surveillance systems, has become necessary in recent years. Biometrics, which treats individuals' identification based ...
详细信息
System identification (SysID) is the art and science of dealing with dynamic data modelling problems from systems science perspectives. It has been an active field and is still very active today, due to its wide range...
详细信息
There has been a growing concern regarding the security of industrial network protocols in Supervisory control and Data Acquisition (SCADA) systems. These protocols are vulnerable to a plethora of security threats, in...
详细信息
On the one hand, a class of model-free integral sliding modes requires damping injection to stabilize the closed-loop system to a certain bound, [1]. This technique has been extended to a variety of robots, including ...
On the one hand, a class of model-free integral sliding modes requires damping injection to stabilize the closed-loop system to a certain bound, [1]. This technique has been extended to a variety of robots, including quadrotors. However, the damping matrix K value is difficult to calculate precisely. Henceforth, it is customary to overestimate it in practice, which is ritical for airborne robots, such as a lightweight quadrotor, which leads to a higher rate of dissipation with higher energy expenditure, which is highly inefficient. On the other hand, novel Reinforcement Learning (RL) schemes have also been developed for autotuning feedback gains, mainly using Actor-Critic (AC)-RL architectures. In this paper, we synergistically blend both schemes to learn the necessary K that enables the enforcement of integral sliding modes to control of the attitude of the quadrotors. Local robust exponential tracking is achieved without any pre-training of neural networks neither of adaptive parameters nor any knowledge of dynamics. A representative comparative simulation study is presented that shows the effectiveness of our scheme versus the fixed-gain case. The results show how critical it is K to complete the flight mission without wasting energy, then less battery consumption, an essential by-product of our formulation. As a future work, an experimental testbed is under development to test it in soft real-time, including its extension to position tracking.
作者:
Zhao, ChangganOxbridge College
Kunming University of Science and Technology School of Electrical and Information Engineering Kunming650106 China
This paper analyzes the non-linear factors in the electronic throttle, and derives the FPGA digital control FPGA system of the electronic throttle. A simulation model of the system was established in Matlab/Simulink a...
详细信息
This research work for optimal automatic generation control (AGC) of two area and four area power systems with diverse energy sources tuned with area control error (ACE) and brief summary of gray wolf optimization tec...
详细信息
In order to realize the intelligent mining mode of the shearer, this paper designs a remote 5G wireless control device to implement remote wireless control of the shearer. The device consists of two main components: u...
详细信息
暂无评论