|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | TDD-net: a tiny defect detection network for printed circuit boards显示文摘Tiny defect detection (TDD) which aims to perform the quality control of printed circuit boards (PCBs) is a basic and essential task in the production of most electronic products. Though significant progress has been made in PCB defect detection, traditional methods are still difficult to cope with the complex and diverse PCBs. To deal with these problems, this article proposes a tiny defect detection network (TDD-Net) to improve performance for PCB defect detection. In this method, the inherent multi-scale and pyramidal hierarchies of deep convolutional networks are exploited to construct feature pyramids. Compared with existing approaches, the TDD-Net has three novel changes. First, reasonable anchors are designed by using k-means clustering. Second, TDD-Net strengthens the relationship of feature maps from different levels and benefits from low-level structural information, which is suitable for tiny defect detection. Finally, considering the small and imbalance dataset, online hard example mining is adopted in the whole training phase in order to improve the quality of region-of-interest (ROI) proposals and make more effective use of data information. Quantitative results on the PCB defect dataset show that the proposed method has better portability and can achieve 98.90% mAP, which outperforms the state-of-arts. The code will be publicly available. | Runwei Ding Linhui Dai Guangpeng Li Hong Liu | 2019 | CAAI Transactions on Intelligence Technology2019，4，2： | 27 |
| 2 | ACP-based social computing and parallel intelligence: Societies 5.0 and beyond显示文摘 | XiaoWang Lingxi Li Yong Yuan Peijun Ye Fei-Yue Wang | 2016 | CAAI Transactions on Intelligence Technology2016，1，4： | 21 |
| 3 | Multi-robot path planning based on a deep reinforcement learning DQN algorithm显示文摘The unmanned warehouse dispatching system of the‘goods to people’model uses a structure mainly based on a handling robot,which saves considerable manpower and improves the efficiency of the warehouse picking operation.However,the optimal performance of the scheduling system algorithm has high requirements.This study uses a deep Q-network(DQN)algorithm in a deep reinforcement learning algorithm,which combines the Q-learning algorithm,an empirical playback mechanism,and the volume-based technology of productive neural networks to generate target Q-values to solve the problem of multi-robot path planning.The aim of the Q-learning algorithm in deep reinforcement learning is to address two shortcomings of the robot path-planning problem:slow convergence and excessive randomness.Preceding the start of the algorithmic process,prior knowledge and prior rules are used to improve the DQN algorithm.Simulation results show that the improved DQN algorithm converges faster than the classic deep reinforcement learning algorithm and can more quickly learn the solutions to path-planning problems.This improves the efficiency of multi-robot path planning. | Yang Yang Li Juntao Peng Lingling | 2020 | CAAI Transactions on Intelligence Technology2020，5，3： | 15 |
| 4 | A study on key technologies of unmanned driving显示文摘 | Xinyu Zhang Hongbo Gao Mu Guo Guopeng Li Yuchao Liu Deyi Li | 2016 | CAAI Transactions on Intelligence Technology2016，1，1： | 14 |
| 5 | A survey on rough set theory and its applications显示文摘 | Qinghua Zhang Qin Xie Guoyin Wang | 2016 | CAAI Transactions on Intelligence Technology2016，1，4： | 13 |
| 6 | Robust Position Anti-Interference Control for PMSM Servo System With Uncertain Disturbance显示文摘Aiming to suppress the influence of uncertain disturbances in the drive control of permanent magnet synchronous machines(PMSM),such as the parameter uncertainties and load disturbance,a robust anti-interference control for the angular position tracking control of a PMSM servo system has been proposed in this paper.During the position tracking,uncertain system disturbances being regarded as a lumped unknown term will be online observed by a nonlinear disturbance observer(NDOB),of which the influence will consequently be counteracted by a robust backstepping compensator(RBC).The asymptotical stability of proposed control scheme is analyzed and designed according to the Lyapunov stability criterion,and its convergence against the system uncertain disturbance is verified on a prototype PMSM servo platform and shows good performance in rotor angular position tracking and anti-interference. | Longfei Li Jie Xiao Yun Zhao Kan Liu Xiaoyan Peng Haozhe Luan Kaiqing Li | 2020 | CES Transactions on Electrical Machines and Systems2020，4，2： | 13 |
| 7 | Accurate Torque Modeling With PSO-Based Recursive Robust LSSVR for a Segmented-Rotor Switched Reluctance Motor显示文摘In order to improve the reliability in torque calculation of SRM,an accurate nonlinear torque model regresses by recursive robust least squares support vector regression(RR-LSSVR)is proposed in this paper.The model is in terms of a segmented-rotor switched reluctance motor(SSRM).The characteristics of the SSRM is introduced to show its nonlinear characteristics both in magnetic and torque.Then,its mathematic model is established,and an accurate inductance measurement method and a torque calculation method are presented.After this,the principle of the RR-LSSVR and why it can adjust weights according to errors are described.The model used the RR-LSSVR algorithm shows an outstanding capability in accuracy and quickness compared with other algorithms.Finally,to further validate the accuracy of the proposed model in practical application,simulation and experiment are designed based on a 16/10 SSRM. | Jiangling Wu Xiaodong Sun Jianguo Zhu | 2020 | CES Transactions on Electrical Machines and Systems2020，4，2： | 11 |
| 8 | Social network search based on semantic analysis and learning显示文摘 | Feifei Kou Junping Du Yijiang He Lingfei Ye | 2016 | CAAI Transactions on Intelligence Technology2016，1，4： | 11 |
| 9 | On-Line Fault Diagnosis and Fault-Tolerant Operation of Modular Multilevel Converters –A Comprehensive Review显示文摘Modular multilevel converters(MMCs)have been one of the most broadly used multilevel converter topologies in industrial applications,particularly in medium-voltage motor drives and high-voltage dc power conversion systems.However,due to the utilization of large amount of semiconductor devices,the reliability of MMCs becomes one of the severe challenges constraining their further development and applications.In this paper,common electrical faults of the MMC have been summarized and analyzed,including open-circuit switching faults,short-circuit switching faults,dc-bus short-circuit faults,and single line-to-ground faults on the ac side.A thorough and comprehensive review of the existing online fault diagnostic methods has been conducted.In addition,fault-tolerant operation strategies for such various fault scenarios in MMCs have been presented.All the fault diagnosis and fault-tolerant operation strategies are comparatively evaluated,which aims to provide a state-of-the-art reference on the MMC reliability for future research and industrial applications. | JiangBiao He Qichen Yang Zheng Wang | 2020 | CES Transactions on Electrical Machines and Systems2020，4，4： | 9 |
| 10 | Analysis and Design of Four-Plate Capacitive Wireless Power Transfer System for Undersea Applications显示文摘This paper presents a four-plate undersea capacitive wireless power transfer(CPT)system for underwater applications such as autonomous underwater vehicles(AUVs).Generally,a CPT system transfers the power based on electric fields.The complex resonant compensation networks are used to make the CPT system work in the resonant condition.The resonant voltage is always very high.It will be a big challenge to the human safety.In this paper,a virtual electrons periodic reciprocating flow theory is proposed for the CPT system.In one switching cycle,the electrons firstly flow in the forward direction through the forward path and then flow in the inverse direction through the inverse path.The CPT system has been deeply studied with the vacuum dielectric or the air dielectric.However,for the CPT system,there are few papers to show the underwater application.In this paper,an undersea four-plate CPT system is designed and studied in the underwater condition.The two coupling capacitors and other elements of the CPT system could build a closed-loop path.A small value inductor is adapted as a resonant compensation network for the four-plate CPT system.The DC voltage is inverted to the AC voltage in the primary side with the single-phase full-bridge inverter.The resonant voltage is rectified to the DC voltage in the secondary side with the single-phase full-bridge diode rectifier.A 100 W power level CPT system is constructed to verify the theory analysis and the calculation.The theory analysis is verified by the simulated and experimental results.The stable output voltage and load power are achieved in this paper. | Lei Yang Yuanqi Zhang Xiaojie Li Jiale Jian Zhe Wang Jingjing Huang Li Ma Xiangqian Tong | 2021 | CES Transactions on Electrical Machines and Systems2021，5，3： | 9 |
| 11 | A New Switching Sequences of SVPWM for Six-Phase Induction Motor with Features of Reduced Switching Losses显示文摘In this paper,new SVPWM switching sequences for six-phase asymmetrical induction motor drives are derived with the aim to reduce inverter’s switching losses.Total three switching sequences are introduced in this paper.These sequences are derived such that the phases get continuously clamped when a current of the phases is around its peak magnitude and hence reduced switching losses are recorded.The comparative performances of these modulation techniques are studied with two existing switching sequences.Simulation,analytical and experimental results are presented.Based on these results,it is found that new switching sequences reduce switching losses effectively in dual three phase inverters. | Shaikh Mohammed Suhel Rakesh Maurya | 2021 | CES Transactions on Electrical Machines and Systems2021，5，2： | 8 |
| 12 | Model Predictive Current Control with Adaptive-adjusting Timescales for PMSMs显示文摘A model predictive current control(MPCC)with adaptive-adjusting method of timescales for permanent magnet synchronous motors(PMSMs)is proposed in this paper to improve the dynamic response and prediction accuracy in transient-state,while lessening the computational burden and improving the control performance in steady-state.The timescale characteristics of different parts of MPCC,such as signal sampling,prediction calculation,control output,model error correction,are analyzed,and the algorithm architecture of MPCC with multi-timescale is proposed.The difference between reference and actual speed,and the change rate of actual speed are utilized to discriminate the transient state of speed change and load change,respectively.Adaptive-adjusting method of control period and prediction stepsize are illustrated in detail after operation condition discrimination.Experimental results of a PMSM are presented to validate the effectiveness of proposed MPCC.In addition,comparative evaluation of single-step MPCC with fixed timescale and proposed MPCC is conducted,which demonstrates the superiority of proposed control strategy. | Feng Niu Xi Chen Shaopo Huang Xiaoyan Huang Lijian Wu Kui Li Youtong Fang | 2021 | CES Transactions on Electrical Machines and Systems2021，5，2： | 8 |
| 13 | A Technology for Online Parameter Identification of Permanent Magnet Synchronous Motor显示文摘Accuracy of the motor parameters is important in realizing high performance control of permanent magnet synchronous motor(PMSM).However,the inductance and resistance of motor winding vary with the change of temperature,rotor position and current frequency.In this paper,a technology based on circuit model is introduced for realizing online identification of the parameter of PMSM.In the proposed method,a set of nonlinear equations containing the parameters to be identified is established.Considering that it is very difficult to obtain the analytical solution of a nonlinear system of equations,Newton iterative method is used for solving the equations.Both the simulation and testing results confirm the effectiveness of the method presented. | XiaoJun MA Chao BI | 2020 | CES Transactions on Electrical Machines and Systems2020，4，3： | 8 |
| 14 | A Grid Interface Current Control Strategy for DC Microgrids显示文摘In this paper,a grid interface current control strategy is presented for a DC microgrid,which aims to reduce the disturbance from PV generation and the load variation to the main grid without a grid interface converter.The grid interface current is directly controlled by a battery DC-DC converter within the DC microgrid.Based on a comprehensive analysis of the battery DC-DC converter and interface current control,the control system has been mathematically modelled.This enabled two transfer functions to be derived that reflect the dynamic response of the inductor current to the duty cycle variation(inner loop),and the dynamic response of the grid interface current to the inductor current variation(outer loop).Experimental study has been done to assess the effectiveness of the proposed control strategy.The experimental results indicate that the proposed control strategy has a good performance to control the grid interface current without an interface converter,regardless the variations of both PV and the load conditions. | Muhannad Alshareef Zhengyu Lin Fulong Li Fei Wang | 2021 | CES Transactions on Electrical Machines and Systems2021，5，3： | 8 |
| 15 | PSO Based Controlled Six-phase Grid Connected Induction Generator for Wind Energy Generation显示文摘This paper deals a detailed performance investigation of asymmetrical six-phase grid connected induction generator(GCIG)in two proposed configurations in variable speed operation.During the system development,regulation of DC-link voltage has been proposed using particle swarm optimization(PSO)based PI controller,ensuring the power flow to utility grid through back to back converters.The closed loop operation of asymmetrical six-phase GCIG using indirect field oriented control in different configurations has been carried out in Matlab/Simulink environment.Analytical results have been verified using real time test results on virtual platform of Typhoon HIL supported with some experimental validation. | Arif Iqbal Girish Kumar Singh | 2021 | CES Transactions on Electrical Machines and Systems2021，5，1： | 7 |
| 16 | Arm Voltage Balancing Control of Modular Multilevel Resonant Converter显示文摘Modular multilevel resonant converter is an promising candidate for high voltage applications since it has advantageous features,such as high efficiency,high voltage capability and easy fault-tolerant operation.However,the inequality of arm inductance in practice will lead to imbalance between the upper and lower arm voltages,which will induce large ripples in the circulating current and a dc bias on the voltage generated by modular circuits.To compensate for the voltage imbalance,effects of arm duty cycle changes on arm voltages are discussed.An arm voltage balancing control method is proposed:adjust arm duty cycle according to arm voltage deviation in every switching cycle.Simulation and experimental results are presented to validate the theoretical analysis and the proposed control method. | Jianjia Zhang Shuai Shao Yucen Li Junming Zhang Kuang Sheng | 2020 | CES Transactions on Electrical Machines and Systems2020，4，4： | 7 |
| 17 | Multi-layer Quasi Three-dimensional Equivalent Model of Axial-Flux Permanent Magnet Synchronous Machine显示文摘Axial-flux permanent magnet synchronous machine(AFPMSM)enjoys the merits of high torque density and high efficiency,which make it one good candidate in the direct-drive application.The AFPMSM is usually analyzed based on the three-dimensional finite element method(3D FEM)due to its three-dimensional magnetic field distribution.However,the 3D FEM suffers large amount of calculation,time-consuming and is not suitable for the optimization of AFPMSM.Addressing this issue,a multi-layer quasi three-dimensional equivalent model of the AFPMSM is investigated in this paper,which could take the end leakage into consideration.Firstly,the multi-layer quasi three-dimensional equivalent model of the AFPMSM with single stator and single rotor is derived in details,including the equivalent processes and conversions of structure dimensions,motion conditions and electromagnetic parameters.Then,to consider the influence of end leakage on the performance,a correction factor is introduced in the multi-layer quasi three-dimensional equivalent model.Finally,the proposed multi-layer quasi three-dimensional equivalent model is verified by the 3D FEM based on an AFPMSM under different structure parameters.It demonstrates that the errors of flux linkage and average torque obtained by the multi-layer quasi three-dimensional equivalent model and 3D FEM are only around 2%although the structure parameters of the AFPMSM are varied.Besides,the computation time of one case based on the multi-layer quasi three-dimensional equivalent model is only 6 min,which is much less than that of the 3D FEM,1.8 h,under the same conditions.Thus,the proposed multi-layer quasi three-dimensional equivalent model could be used to optimize the AFPMSM and much time could be saved by this method compared with the 3D FEM. | Mingjie He Weiye Li Jun Peng Jiangtao Yang | 2021 | CES Transactions on Electrical Machines and Systems2021，5，1： | 7 |
| 18 | A Novel Hybrid Seven-Level Converter for Permanent Magnet Synchronous Motor Driving System Based on Model Predictive Control显示文摘A novel hybrid three-phase seven-level converter is proposed in the paper.Each phase consists of a four-level bridge and a two-level H bridge,which contains ten switching devices and a floating capacitor.The circuit structure is introduced and working principle of the converter containing 14 commutation paths is analyzed,which is easy to control the floating capacitor voltage.In order to drive permanent magnet synchronous motor(PMSM)with the proposed converter,model predictive control(MPC)strategy is adopted.The control objectives such as controlling the currents of PMSM and capacitor voltages balancing are included in a cost function with two weight factors,which can control the currents of PMSM and balance the capacitor voltages simultaneously.To validate the proposed control scheme,simulations in two cases are carried out by using Matlab/Simulink software.Finally,the feasibility and efficiency in two cases are verified with the experimental test bench based on RT_LAB. | Yuansheng Hu Cungang Hu Pinjia Zhang Yunlei Zhang | 2019 | CES Transactions on Electrical Machines and Systems2019，3，4： | 6 |
| 19 | Design and Optimization of Segmented PM Consequent Pole Hybrid Excited Flux Switching Machine for EV/HEV Application显示文摘Hybrid Excited Flux Switching Machines(HEFSMs)unique feature of high torque density(T_(den))of Permanent Magnet(PM)machines and flux regulation capability of wound field excitation machines.Due to aforesaid unique features,stator active HEFSMs are preferred for EV/HEV applications.In this paper a new Segmented PM Consequent Pole HE-FSM(SPMCPHEFSM)with flux bridge is proposed for EV/HEV.The developed SPMCPHEFSM exhibits improved flux modulation and flux regulation capability at reduced PM usage(suppressed PM volume by 46.52%and PM cost by 46.48%)and eliminating stator leakage flux.First,SPMCPHEFSM is geometric optimized(GO)for investigating influence of leading design with key performance indicators such as flux linkage(Ф_(pp)),average torque(T_(avg)),cogging torque(T_(cog)),T_(den),average power(P_(avg))and power density(P_(den))and then proceeded optimized model to structure modification for optimal stator design and position of field excitation coils(FEC).Comprehensive performance analysis reveals that the developed SPMCPHEFSM show improvedФ_(pp)maximum up to 9.11%,improved T_(avg)maximum up to 23.63%,truncate T_(cog)up to 18.9%whereas T_(den)and P_(den)are boost up to 23.55%and 89.72%respectively. | Wasiq Ullah Faisal Khan Muhammad Umair | 2020 | CES Transactions on Electrical Machines and Systems2020，4，3： | 6 |
| 20 | Modeling and Hardware-in-the-Loop System Realization of Electric Machine Drives-A Review显示文摘This paper presents a state-of-the-art review in modeling approach of hardware in the loop simulation(HILS)realization of electric machine drives using commercial real time machines.HILS implementation using digital signal processors(DSPs)and field programmable gate array(FPGA)for electric machine drives has been investigated but those methods have drawbacks such as complexity in development and verification.Among various HILS implementation approaches,more efficient development and verification for electric machine drives can be achieved through use of commercial real time machines.As well as implementation of the HILS,accurate modeling of a control target system plays an important role.Therefore,modeling trend in electric machine drives for HILS implementation is needed to be reviewed.This paper provides a background of HILS and commercially available real time machines and characteristics of each real time machine are introduced.Also,recent trends and progress of permanent magnet synchronous machines(PMSMs)modeling are presented for providing more accurate HILS implementation approaches in this paper. | Jae Suk Lee Gilsu Choi | 2021 | CES Transactions on Electrical Machines and Systems2021，5，3： | 6 |
您所在的机构暂未开通此部分的功能，请联系管理员