会议名称：
AAAI'25/IAAI'25/EAAI'25: Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence
会议地点：
Philadelphia, PA
会议主办单位：
[Chen, Xiaolei;Yan, Junchi] Shanghai Jiao Tong Univ, Sch Artificial Intelligence, Shanghai, Peoples R China.^[Chen, Xiaolei;Yan, Junchi] Shanghai Jiao Tong Univ, Dept CSE, Shanghai, Peoples R China.^[Chen, Xiaolei;Yan, Junchi] Shanghai Jiao Tong Univ, MoE Lab AI, Shanghai, Peoples R China.^[Chen, Xiaolei;Liao, Wenlong;He, Tao;Peng, Pai] COWAROBOT Co Ltd, Wuhu, Peoples R China.^[He, Tao] Univ South China, Sch Elect Engn, Hengyang, Peoples R China.
摘要：
Motion planning is a critical module in autonomous driving, with the primary challenge of uncertainty caused by interactions with other participants. As most previous methods treat prediction and planning as separate tasks, it is difficult to model these interactions. Furthermore, since the route path navigates ego vehicles to a predefined destination, it provides relatively stable intentions for ego vehicles and helps constrain uncertainty. On this basis, we construct Int2Planner, an Intention-based Integrated motion Planner achieves multi-modal planning and prediction. Instead of static intention points, Int2Planner utilizes route intention points for ego vehicles and generates corresponding planning trajectories for each intention point to facilitate multi-modal planning. The experiments on the private dataset and the public nuPlan benchmark show the effectiveness of route intention points, and Int2Planner achieves state-of-the-art performance. We also deploy it in real-world vehicles and have conducted autonomous driving for hundreds of kilometers in urban areas. It further verifies that Int2Planner can continuously interact with the traffic environment. Code and Datasets - https://github.com/cxlz/Int2Planner
会议名称：
39th AAAI Conference on Artificial Intelligence
会议时间：
FEB 25-MAR 04, 2025
会议地点：
Philadelphia, PA
会议主办单位：
[Li, Tengpeng;Wang, Hanli] Tongji Univ, Coll Elect & Informat Engn, Shanghai, Peoples R China.^[Li, Tengpeng;Wang, Hanli] Tongji Univ, Sch Comp Sci & Technol, Shanghai, Peoples R China.^[Li, Xianfei;Liao, Wenlong;He, Tao;Peng, Pai] COWAROBOT, Shenzhen, Peoples R China.^[He, Tao] Univ South China, Sch Elect Engn, Hengyang, Hunan, Peoples R China.
会议论文集名称：
AAAI Conference on Artificial Intelligence
摘要：
Autonomous driving is a challenging task that requires perceiving and understanding the surrounding environment for safe trajectory planning. While existing vision-based end-to-end models have achieved promising results, these methods are still facing the challenges of vision understanding, decision reasoning and scene generalization. To solve these issues, a generative planning with 3D-vision language pre-training model named GPVL is proposed for end-to-end autonomous driving. The proposed paradigm has two significant aspects. On one hand, a 3D-vision language pre-training module is designed to bridge the gap between visual perception and linguistic understanding in the bird's eye view. On the other hand, a cross-modal language model is introduced to generate holistic driving decisions and fine-grained trajectories with perception and navigation information in an auto-regressive manner. Experiments on the challenging nuScenes dataset demonstrate that the proposed scheme achieves excellent performances compared with state-of-the-art methods. Besides, the proposed GPVL presents strong generalization ability and real-time potential when handling high-level commands in various scenarios. It is believed that the effective, robust and efficient performance of GPVL is crucial for the practical application of future autonomous driving systems.
摘要：
It is challenging to construct nano-scaled meta-structures enabling efficient and versatile electro-optic modulations, especially those related to circular dichroism ( CD), which is useful in detection of chiral molecules and optical manipulation. In this study, we have modeled chiral metasurfaces based on single-crystal LiNbO3 using finite element method. The numerical calculation and characterization indicate that a quasi-BIC(q-BIC) resonance with a high Q-factor optical signal of 9.3 x 10(4) and a peak CD signal of 0.89 at 972.76 nm could be obtained by breaking the structural symmetry of the chiral metasurface. The pockels effect of LiNbO3 is enhanced via q-BIC resonance, resulting in a highly efficient electro-optic modulation of the CD signal. The modulation efficiency was found to be 1 nm/1.25x10(5) V/m at 972.76 nm. Furthermore, we have investigated in detail the polarization-dependent electro-optic properties of the LiNbO3 metasurface. The polarization states of the output far-field radiation can be actively tuned by electro-optic modulation efficiently. The modulation ranges of polarized rotary angle were found to be 55 degrees and 48 degrees for right-handed and left-handed polarization, respectively. The ellipticity can be tuned in a range of 62 degrees and 3.3 degrees for right-handed and left-handed polarization, respectively. Benefiting from the high Q-factor, this metasurface shows a high sensitivity to environmental refractive index of 590nm/RIU and a high figure of merit of 5.9x10(4). These results show that the studied metasurface is promising as an electro-optic modulator and for applications in sensing of chiral responses.
摘要：
In this paper, a flexible non-enzymatic sweat glucose sensor loaded with copper-nickel composite nanomaterials on carbon electrode integrated with wireless monitoring system were developed. The non-enzymatic glucose sensor was fabricated efficiently and simply by electrodepositing copper-nickel bimetallic composite on a carbon-based screen-printing electrode (Cu-Ni/CSPE). Besides, a wireless monitoring system for glucose detection was designed and composed with a signal processing circuit using ADUCM355 chip. The results of electrocatalytic experiments showed that the sensitivity of the Cu-Ni/C-SPE sensor was 5507.4 μA/(mM∙cm<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>), the linear detection range was 25 μM∼2.275 mM, the detection limit was 0.149 μM, and the response time was < 1s.
摘要：
The electrocatalytic nitrogen reduction reaction (eNRR) under ambient conditions is deemed a promising alternative for NH3 synthesis. In this paper, an FeP–Fe3O4 nanocomposite electrocatalyst was prepared by phosphating annealing using Fe2O3 as a precursor, and the resulting FeP–Fe3O4 exhibited excellent N2-to-NH3-producing activity over a wide potential window. The highest faradaic efficiency of FeP–Fe3O4 is 11.02% at −0.1 V vs. reversible hydrogen electrode (RHE), and the maximum NH3 yield reaches 12.73 μg h−1 mgcat−1, comparable to or exceeding the reported values in this field. Furthermore, the FeP–Fe3O4 nanocomposite electrocatalyst presents high electrochemical stability, selectivity, and durability.
作者机构：
[Wen, Juan; Xiao, Qiankang; Qu, Xing; Lin, Siyu] Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.;[Liu, Jie] Univ South China, Sch Comp Software, Hengyang 421001, Peoples R China.
通讯机构：
[Wen, J ] U;Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.
关键词：
Active distribution network;Fault location;Dynamic quantum genetic algorithm;Evaluation objective function
摘要：
The fault location of an active distribution network is a vital analysis to prevent major outages in the power system. Considering the influence of renewable distributed generations on fault characteristics, this paper proposes a novel location method based on a dynamic quantum genetic algorithm to solve for fault locations in active distribution networks. In the method, the fault current code is measured based on feeder terminal units. A universal switching function is presented to convert the feeder switch status into an uploaded fault current code. The fault location model is defined as an optimization problem that presents the evaluation objective function with an anti-false-positive factor. The dynamic quantum genetic algorithm is developed to locate the fault feeder according to the uploaded fault current code of the feeder terminal unit. The algorithm adopts dynamic rotating gate strategy and adaptive quantum crossover strategy to satisfy the requirements of quickness and accuracy for fault location. Moreover, the method avoids easily falling into a local optimum by integrating the discrete quantum mutation. The proposed fault location technique is tested and compared to other existing techniques on a 33-bus active distribution network. The simulation results show that the proposed fault location method can locate fault feeders accurately with fast computational times under conditions of single or multiple faults and with an information distortion of the feeder terminal unit.
会议论文集名称：
2024 25th International Conference on Electronic Packaging Technology (ICEPT)
关键词：
AlGaN/GaN MIS-HEMTs;neutron irradiation;frequency-dependent conductance method;interface states
摘要：
We investigate the degradation effects of neutron irradiation on AIGaN/GaN metal-insulator-semiconductor high electron mobility transistors (MIS-HEMTs) in this work. The performance of the devices is characterized through relevant electrical current-voltage (I-V) test and capacitance- voltage (C-V) test. The result indicates that the electrical parameter of the device degrades after neutron irradiation, such as positive shift of threshold voltage, reduction in output drain current, and the increase of the on-resistance. Additionally, combining with the frequency-dependent conductance method, it displays that shallow energy level- interface states at the AIGaN/GaN heterojunction increase, along with slightly shifting to deeper energy level after neutron irradiation. Neutron irradiation introduces more interface states and increase the scattering which degrading the carrier concentration and mobility, causing related degradation on electrical performances. This study provides useful reference value for the application of GaN-based devices in the aerospace.
摘要：
With the development of microelectronics and communication technology, wireless sensor networks(WSNs) technology has been widely concerned. In order to deal with the complex sensing environment and improve the sustainable services, it is urgent to study the high energy efficiency strategy of heterogeneous wireless sensor networks(HWSNs). In this paper, a hybrid clustering scheduling strategy based on genetic algorithm(HCSS-GA) is proposed, which consolidated a variety of factors such as residual energy, communication distance, node density and heterogeneous factors to optimize cluster-head election, and then form a energy-efficient cluster structure. Static clustering is performed after the network has acquired energy-balanced clusters whereas dynamic clustering is performed to re-form the energy-efficient cluster structure when the network topology changes. Through the organic combination of dynamic clustering and static clustering, it not only avoids a lot of communication energy consumption caused by frequent network re-clustering, but also adjusts the network structure adaptively without losing flexibility. Simulation results show that HCSS-GA is more energy-efficient and provides more sustainable network lifetime, which is superior to other advanced algorithms.
摘要：
An asynchronous switched linear parameter-varying (LPV) fault-tolerant control method is proposed for quad-tilt rotor UAVs to address actuator faults and persistent external disturbances. The nonlinear longitudinal dynamics of quad-tilt rotor UAVs with both abrupt and time-varying actuator faults are converted to a switched LPV system. A group of LPV controllers are designed, and each of them is adaptable to a specific subspace of parameters. Closed-loop stability and ℒ<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</inf> disturbance attenuation performance of the underlying switched LPV system are analyzed using multiple parameter-dependent Lyapunov functions and the persistent dwell-time technique, where delays in the detection of actuator failure are taken into account. Numerical results demonstrate the effectiveness of the proposed switched LPV fault-tolerant control scheme.
会议论文集名称：
EITCE '23: Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer Engineering
关键词：
Pixel circuit;Threshold voltage;Mobility;OLED degradation;Thin film transistors
摘要：
A voltage-programmed pixel circuit is presented for active-matrix organic light-emitting diode (AMOLED) displays. The circuit contains seven amorphous indium gallium zinc oxide (a-IGZO) thin film transistors (TFTs) and one capacitor. In the compensation stage, the circuit extracts the threshold voltages of the driving TFT and OLED, and obtains a mobility dependent discharge voltage. The circuit requires only one capacitor to compensate for variations of the electrical characteristics of the driving TFT, i.e. variations of threshold voltage and mobility, and the degradation of the OLED. The circuit simulation results show that the relative current error rates are below 5.70% for threshold voltage variations of +/- 0.5V, below 5.66% for mobility variations of +/- 30%.
会议论文集名称：
EITCE '23: Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer Engineering
关键词：
Pixel circuit;LTPS TFTs;Threshold voltage variation;Mobility variation;Voltage drop;OLED degradation
摘要：
A voltage-programmed pixel circuit is presented for active-matrix organic light-emitting diode (AMOLED) displays. The circuit is made up by six p-type low temperature poly-silicon (LTPS) thin-film transistors (TFTs) and two capacitors (6T2C). In the extraction stage, the circuit extracts the driving TFT's threshold voltage and the power supply voltage. In the data input stage, the circuit generates a charging voltage, which is associated with the driving TFT's mobility and OLED's threshold voltage. Consequently, the pixel circuit not only compensates for the TFT's electrical characteristics variations, i.e., the threshold voltage and mobility variations, but also compensates for the voltage drop and the OLED degradation. The circuit simulation results show that the OLED current error rates (CERs) are lower than 7.13% when the threshold voltage varies +/- 0.5V, lower than 4.89% when the mobility varies +/- 30%, and lower than 8.92% when the voltage drop varies -0.5V.
作者机构：
[Liu, Fuchun; Liu, Zeyong; Chen, Xujian; Liu, FC] South China Univ Technol, Sch Automat Sci & Engn, Guangzhou, Peoples R China.;[Huang, Zewen] Univ South China, Sch Elect Engn, Hengyang, Peoples R China.
会议名称：
2023 35th Chinese Control and Decision Conference (CCDC)
会议时间：
20 May 2023
会议地点：
Yichang, China
会议主办单位：
[Liu, Fuchun;Chen, Xujian;Liu, Zeyong] South China Univ Technol, Sch Automat Sci & Engn, Guangzhou, Peoples R China.^[Huang, Zewen] Univ South China, Sch Elect Engn, Hengyang, Peoples R China.
会议论文集名称：
2023 35th Chinese Control and Decision Conference (CCDC)
关键词：
LiDAR point cloud;Multi-scale contextual feature;Semantic segmentation
摘要：
Semantic segmentation of point clouds scanned by LiDAR is one of the means for robots to perceive the environment autonomously. Aiming at the sparse and unstructured characteristics of LiDAR point clouds, we use the spherical projection formula to project LiDAR point clouds to a dense range image. A 2D convolutional neural network based on the encoder-decoder structure is used to perform semantic segmentation on the range image. After segmentation on the range image, we re-project the semantic result of the range image to the LiDAR point clouds using a kNN method. To extract the context features of the range image, we design a multi-scale contextual feature extraction module based on the feature pyramid network, so the encoder-decoder network can better obtain the semantic features of the range image. The experimental results show that the mIoU of the proposed model is 55.2% and 45.0% in SemanticKITTI and SemanticPOSS, which is 3.0% and 16.1% higher than that of the RangeNet++ network, respectively.
会议名称：
2022 9th International Forum on Electrical Engineering and Automation (IFEEA)
会议时间：
04 November 2022
会议地点：
Zhuhai, China
会议主办单位：
[Wang, Shoutao;Chen, Wenguang;Liu, Zhijian;Wei, Caiyi;Peng, Yuanyuan] Univ South China, Sch Elect Engn, Hengyang, Peoples R China.
会议论文集名称：
2022 9th International Forum on Electrical Engineering and Automation (IFEEA)
关键词：
Printed circuit board;Bidirectional pulse power supply;Forward and reverse pulse duty cycle ratio;Current density;Frequency
摘要：
Printed circuit boards are the most important basic electronic components in the electronics industry, and copper plating technology is widely used in the field of printed circuit board manufacturing. Pulse plating is more efficient and environmentally friendly than DC plating, and the plating layer of pulse plating is more uniform and detailed. The effect of bi-directional pulse power supply parameters on the copper plating effect of printed circuit board surface was investigated by using a self-developed bidirectional pulse power supply. The experimental results show that the frequency, forward and reverse pulse duty cycle and current density of the bidirectional pulse power supply have certain effects on the copper plating effect.
期刊：
2022 8th International Conference on Hydraulic and Civil Engineering: Deep Space Intelligent Development and Utilization Forum (ICHCE),2022年:651-655
通讯作者：
Xie, FQ
作者机构：
[Xie, Fuqiang; Guo, Lei; Yang, Bin] Univ South China, Sch Elect Engn, Hengyang, Peoples R China.
通讯机构：
[Xie, FQ ] U;Univ South China, Sch Elect Engn, Hengyang, Peoples R China.
会议名称：
2022 8th International Conference on Hydraulic and Civil Engineering: Deep Space Intelligent Development and Utilization Forum (ICHCE)
会议时间：
25 November 2022
会议地点：
Xi’an, China
会议主办单位：
[Guo, Lei;Xie, Fuqiang;Yang, Bin] Univ South China, Sch Elect Engn, Hengyang, Peoples R China.
会议论文集名称：
2022 8th International Conference on Hydraulic and Civil Engineering: Deep Space Intelligent Development and Utilization Forum (ICHCE)
关键词：
component;Deep learning;Lane detection;non-local attention;frame-similarity loss
摘要：
Lane detection plays an important role in autonomous driving. For video instance lane detection, both global spatial and temporal information is significantly important. However, the global spatial features and the temporal features are not been well exploited in recent studies. In this work, we address the video instance lane detection task by capturing global context based on non-local attention network. Specifically, we designed a twin non-local attention network to extract long-range dependencies along the spatial and temporal dimensions, respectively. Meanwhile, the global spatial and temporal features can be adaptively fused by gating mechanisms for better results. In addition, the frame-similarity loss is proposed to further exploit the information of adjacent frames. The experimental results on the video instance lane detection (VIL-100) dataset verify that our method achieves better results compared with other comparison methods. Ablation experiments further demonstrate the effectiveness of each sub-module.
作者：
Liu, Fuchun;Deng, Haixing;Huang, Zewen;Zeng, Ming
作者机构：
[Liu, Fuchun; Deng, Haixing; Zeng, Ming] South China Univ Technol, Sch Automat Sci & Engn, Guangzhou 510640, Peoples R China.;[Liu, Fuchun] Minist Educ, Key Lab Autonomous Syst & Networked Control, Guangzhou 510640, Peoples R China.;[Liu, Fuchun] Unmanned Aerial Vehicle Syst Engn Technol Res Ctr, Guangzhou 510640, Peoples R China.;[Huang, Zewen] Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.
会议名称：
2022 7th International Conference on Automation, Control and Robotics Engineering (CACRE)
会议时间：
July 2022
会议地点：
Xi'an, China
会议主办单位：
[Liu, Fuchun;Deng, Haixing;Zeng, Ming] South China Univ Technol, Sch Automat Sci & Engn, Guangzhou 510640, Peoples R China.^[Liu, Fuchun] Minist Educ, Key Lab Autonomous Syst & Networked Control, Guangzhou 510640, Peoples R China.^[Liu, Fuchun] Unmanned Aerial Vehicle Syst Engn Technol Res Ctr, Guangzhou 510640, Peoples R China.^[Huang, Zewen] Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.
会议论文集名称：
2022 7th International Conference on Automation, Control and Robotics Engineering (CACRE)
关键词：
RF ablation;LC resonant circuit;RF sampling;power closed-loop control
摘要：
As an emerging device used in surgery, Radiofrequency (RF) ablation is widely used in minimally invasive surgeries. In the process of surgery, the system needs to output constant power to ensure the quality of surgery when the tissue location or ambient temperature and humidity change. The hardware of the RF ablation system was designed in this paper, and the power closed-loop control was realized. The system uses a microcontroller STM32F303VCT6 and the dual ADC alternate sampling method to require the RF output signal. The RF output power is obtained by frequency-domain analysis of the sampled signal using the Discrete Fourier Transform (DFT) algorithm, and the power is controlled using a PID controller so that the actual output power quickly tracks the user-set power. The experimental results of power control show that the controller can adjust the power of the RF ablation system to the set value within 500 ms, without overshoot in the control process and within +/- 1 W of power fluctuation after stabilization. Meanwhile, the controller can realize power tracking of the ablation system when the load changes.
期刊：
Proceedings of SPIE - The International Society for Optical Engineering,2022年12705:108 ISSN：0277-786X
通讯作者：
Zhang, XZ;Ouyang, LJ
作者机构：
[Zhang, XZ; Zhang, Xiaozhi; Zhou, Liu] Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.;[Zhu, Minjie; Ouyang, Lijun; Ouyang, Yan; Xiong, Dongping; Ouyang, LJ] Univ South China, Sch Comp Software, Hengyang 421001, Peoples R China.
通讯机构：
[Zhang, XZ ; Ouyang, LJ ] U;Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.;Univ South China, Sch Comp Software, Hengyang 421001, Peoples R China.
会议名称：
14th International Conference on Graphics and Image Processing (ICGIP)
会议时间：
OCT 21-23, 2022
会议地点：
ELECTR NETWORK
会议主办单位：
[Zhou, Liu;Zhang, Xiaozhi] Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.^[Zhu, Minjie;Xiong, Dongping;Ouyang, Lijun;Ouyang, Yan] Univ South China, Sch Comp Software, Hengyang 421001, Peoples R China.
会议论文集名称：
Proceedings of SPIE
关键词：
Magnetic resonance imaging (MRI);fast MRI;deep learning;Non-Local;remote dependencies
摘要：
As an advanced medical imaging technology, magnetic resonance imaging (MRI) has great advantages and application potentials in medical clinical diagnosis. However, since the long scanning time and the artifacts caused by patient movements, the imaging results are always not satisfactory. Therefore, accelerating MRI and improving the imaging quality are the key problems. In this work, we propose a novel deep network that combines the U-net architecture with non-local attention blocks for MRI reconstruction. We employ the U-net to construct the basic network. The non-local attention is exploited to capture the remote dependencies in MRI images which calculates the weighted average of the remaining multiple location features as the value of the response location. The U-net has limitations in capturing long-term dependencies, however, the non-local attention can solve this problem well. Furthermore, we develop the residual module to better retain the detail information. The proposed model is compared with some recent leading MRI reconstruction methods, including the state-of-the-art deep learning-based methods. Compared with these methods, the proposed residual non-local attention network provides superior MRI reconstruction results and retains better perceptual image details.
摘要：
To solve the problem that the traditional simultaneous localization and mapping (SLAM) algorithm will reduce the pose estimation accuracy and system robustness in dynamic environments, this paper proposes a visual-inertial SLAM system suitable for dynamic environments. This paper designs a plane segmentation network called scSE-PlaneNet, which is an encoder-decoder structure combined with an attention mechanism. scSE-PlaneNet is used to provide static plane features for subsequent SLAM systems. Then, the error calculated according to the principle of plane homography is used to accelerate the pose optimization. We conduct experiments on multiple sequences of the ADVIO dataset, and the results show that our proposed method can obtain higher accuracy in camera pose estimation compared to the current state-of-the-art VINS-MONO system.
摘要：
Nowadays, falling is a growing threat to the elderly. This paper combines millimeter wave radar technology, machine learning algorithm, wireless communication technique and cloud platform to realize a fall detection system. In this project, the millimeter wave radar is used to sample the human posture point cloud data, and we create a data set that consist of point of clouds of two different human poses. Random forest and BP neural network are used to train the fall detection model. The system will send the human posture point data to the trained model and realize the fall detection. Besides, the system will use 4G communication technology to transform the data to the web cloud platform. This web page serves as an warning function, which can report the acceleration, speed and other information. According to our experiments, the millimeter wave radar system that we built in this paper can effectively detect human point cloud, and can send human point cloud data packets to the recognition model to detect human falls. In machine learning part, both Random forest and BP neural network models show very strong robustness after repeated adjusting parameters. Random forest has the advantages of light weight and interpretability, which can reach 93% recognition accuracy. The recognition accuracy of BP neural network is even up to 95%, which is higher than other detection models in previous works. Besides, BP neural network model also has higher recall rate in the categories of human falls, which fully meets the requirements of this project.
作者机构：
[Li, Longjin; Jia, Lei] Univ South China, Dept Elect Engn, Hengyang, Peoples R China.
会议名称：
2022 25th International Conference on Electrical Machines and Systems (ICEMS)
会议时间：
29 November 2022
会议地点：
Chiang Mai, Thailand
会议主办单位：
Rajamangala Univ Technol Lanna
会议论文集名称：
2022 25th International Conference on Electrical Machines and Systems (ICEMS)
关键词：
Brushless doubly-fed generator;Pole-changing;Finite element
摘要：
In this paper, a nested-loop rotor brushless doubly-fed generator (BDFG) with improved stator single winding pole-changing design scheme is presented. The BDFG is simulated at 400 rpm and 600 rpm through finite element (FE) method. It is found that the improved stator single winding pole-changing design scheme is effective in reducing the machine harmonic contents and improving the PW generated voltage, CW current waveforms quality.
