In order to improve the endurance of unmanned aerial vehicles (UAVs), a power supply controller with automatic switching between solar energy and battery was designed. The controller is mainly composed of an AT89C51 s...
详细信息
This paper mainly focuses on the research of the bus voltage balance in DC *** to the relationship of power balance of the system,three voltage regulation modes in the microgrid are defined,such as the mode for renewi...
详细信息
This paper mainly focuses on the research of the bus voltage balance in DC *** to the relationship of power balance of the system,three voltage regulation modes in the microgrid are defined,such as the mode for renewing resources,the mode for energy storage unit charging,and the mode for energy storage unit *** on three oprerating modes proposed,the microgrid is modeled as a linear switching *** the design method of the switching system controller is given and the stability of the switching system is ***,simulation results verify the effectiveness of the switching strategy.
Currently, the prevailing approach in pedestrian detection involves leveraging deep learning techniques. However, effectively detecting pedestrian objects at small scales continues to pose a significant challenge in t...
Currently, the prevailing approach in pedestrian detection involves leveraging deep learning techniques. However, effectively detecting pedestrian objects at small scales continues to pose a significant challenge in this field of research. Moreover, many algorithms prioritize accuracy improvement, making it difficult to deploy them in real-world scenarios. This paper proposes an edge device-friendly object detection method. We introduce a target extraction module with a minimal number of non-linear units to preserve fine-grained information in the network. Additionally, we design a trapezoidal FPN structure based on the structural re-parameterization technique, and optimize it specifically for edge devices. Furthermore, we construct a hardware platform to validate the feasibility of our algorithm in real-world applications. In the experimental section, we demonstrate that our proposed method outperforms comparative algorithms on the Caltech pedestrian dataset, while maintaining high speed on edge devices.
In order to improve the utilization efficiency of solar energy, based on the in-depth study of the characteristics of solar energy, a control scheme based on daily motion trajectory was designed. In this scheme, singl...
详细信息
ISBN:
(纸本)9781728190181;9781728190198
In order to improve the utilization efficiency of solar energy, based on the in-depth study of the characteristics of solar energy, a control scheme based on daily motion trajectory was designed. In this scheme, single chip microcomputer is used as the controller to realize the output of SPWM waveform, and the compound PID with multiplexing selection is used to control the Angle of solar panel, so as to achieve the effect of fast and sensitive tracking of solar illumination. Through the angle sensor, on-line monitoring of the angle data of the solar panel, according to the intelligentcontrol optimization algorithm, combined with single-chip microcomputer control technology, a more optimized control scheme is proposed. The experimental data show that the design effect is good and the expected control goal is achieved.
The computer vision techniques have been widely used in the robotic manipulation for perception and positioning. However, duo to the inaccuracy of camera calibration and measurement, there is a greatly need for more a...
详细信息
Graph neural networks (GNNs) are extensions of deep neural networks to graph-structured data. It has already attracted widespread attention for various tasks such as node classification and link prediction. Existing r...
详细信息
In order to accurately evaluate the working state of RV reducer, a fault identification method based on the fault identification model established by Self-Organizing Feature Map (SOM) Neural Network is proposed. First...
In order to accurately evaluate the working state of RV reducer, a fault identification method based on the fault identification model established by Self-Organizing Feature Map (SOM) Neural Network is proposed. Firstly, the data measured by the RV reducer test platform are analyzed by wavelet to obtain the wavelet coefficient. Then, combined with the efficiency data of RV reducer, the mean square frequency, center of gravity frequency and frequency variance of the two groups of data are calculated after Fourier transform and power spectrum analysis. After optimization, several eigenvalues are obtained. The eigenvalues are input into the competitive neural network and SOM neural network to establish the fault identification model. Finally, the results of the fault identification model established by the competitive neural network and SOM neural network are compared. The prediction results show that the fault identification model established by SOM neural network can effectively determine the working state of RV reducer.
暂无评论