检索结果-内蒙古大学图书馆

Composite-mask GAN based on refined optical flow and disparity map for SLAM visual odometry

Optoelectronics Letters 2025年

作者： JI Yuehui JIANG Jingwei LIU Junjie SONG Yu GAO Qiang School of Electrical Engineering and Automation， Tianjin University of Technology Tianjin Key Laboratory of Control Theory and Application for Complex Systems

Although deep learning methods have been widely applied in slam visual odometry over the past decade with impressive improvements， the accuracy remains limited in complex dynamic environments. In this paper， a composite mask-based generative adversarial network is introduced to predict camera motion and binocular depth maps. Specifically， a perceptual generator is constructed to obtain the corresponding parallax map and optical flow from between two neighboring frames. Then， an iterative pose improvement strategy is proposed to improve the accuracy of pose estimation. Finally， a composite mask is embedded in the discriminator to sense structural deformation in the synthesized virtual image， thereby increasing the overall structural constraints of the network model， improving the accuracy of camera pose estimation， and reducing drift issues in the Visual Odometer. Detailed quantitative and qualitative evaluations on the KITTI dataset show that the proposed framework outperforms existing conventional， supervised learning and unsupervised depth VO methods， providing better results in both pose estimation and depth estimation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Switching Power Supply Design Suitable for Motor control 29

Switching Power Supply Design Suitable for Motor Control

引用

第29届中国控制与决策会议

作者： Zhi-Chao Zhao Li guo-hong Tianjin University of Technology Tianjin Complex System Control Theory and Application Key Laboratory

ISBN: (纸本)9781509046584

Motor control systems require multi-channel stable output low voltage DC power *** to the needs of motor control system,a switching power supply can meet the requirements of motor control is *** topology of switching power supply and the uses of PWM control chips are *** positive and negative bias generation circuit of IGBT is *** circuit components' choices and design method of a high frequency transformer of the flyback switching power supply are ***,the basic performances of switching power supply were tested;the results show that it can meet the requirements of motor control systems.

关键词： switching power supply motor drive pulse width control chip high frequency transformer

来源：评论

学校读者我要写书评

暂无评论

Power consumption prediction modeling of cement manufacturing based on the improved multiple non-linear regression algorithm

Power consumption prediction modeling of cement manufacturin...

引用

2014 International Conference on Manufacturing Technology and Electronics applications, ICMTEA 2014

作者： Zhao, Hui Zhang, Ning Wang, Hong Jun Tianjin Agricultural University Tianjin university of technology Tianjin complex system control theory and application of key laboratory Tianjin China Tianjin university of technology Tianjin complex system control theory and application of key laboratory Tianjin China

ISBN: (纸本)9783038353287

The principal component analysis (PCA) is applied in this paper, since the existing power consumption prediction models of cement manufacturing influenced by many factors are quite complex and have low accuracy. In this way, four new key factors affecting the power consumption of cement manufacturing are obtained instead of the eleven original ones, with the complexity of the computing model simplified. Built upon this is the power consumption prediction model of cement manufacturing based on an improved multiple non-linear regression algorithm. Then the efficiency of the model, obviously improved the forecasting precision, is verified in Pingyi Zhonglian Cement Plant. In other words, a theoretical basis for cement plants power consumption forecasting management is provided in this paper. © (2014) Trans Tech Publications, Switzerland.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Research of waste heat power generation main steam valve control

Research of waste heat power generation main steam valve con...

引用

2014 International Conference on Manufacturing Technology and Electronics applications, ICMTEA 2014

作者： Zhao, Hui Wang, Ya Fei Wang, Hong Jun Tianjin Agricultural University and Tianjin university of technology Tianjin complex system control theory and application of key laboratory Tianjin China Tianjin university of technology Tianjin complex system control theory and application of key laboratory Tianjin China

ISBN: (纸本)9783038353287

In order to improve the stability of steam turbine under large disturbance, the controller of cement waste heat power generation valve was designed by using exponential terminal sliding mode variable structure control method. In this paper, taking a single machine infinite bus power system as an example, established mathematical model of waste heat generator valve system, and designed the valve controller of synchronous generator based on the exponential terminal sliding mode variable structure control theory. Then, valve control simulation model was set up and simulation experiment was performed by MATLAB. Finally, verify the effectiveness of the scheme by comparison analysis. Simulation results show that the controller can effectively improve the transient stability of power system and the dynamic quality. © (2014) Trans Tech Publications, Switzerland.

关键词： Waste heat

来源：评论

学校读者我要写书评

暂无评论

Image Segmentation Method of Crop Diseases Based on Improved Segnet Neural Network 17

Image Segmentation Method of Crop Diseases Based on Improved...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Yue, Youjun Li, Xuesong Zhao, Hui Wang, Hongjun Tianjin University of Technology Tianjin Key Laboratory of Complex System Control Theory and Application Tianjin300384 China

ISBN: (纸本)9781728164151

In crop disease image segmentation, traditional convolutional neural networks have the problem of low image accuracy. For this reason, this paper proposes a segmentation method that combines conditional random fields with segnet networks. First, input the training set in the data set into the segnet network for training, and obtain the initial segmentation result and the network with updated parameters;secondly, the image segmented by the segnet network is sent to the conditional random field in the form of pixels and classification vectors corresponding to the pixels At the same time, construct an energy function to represent the relative relationship between pixels, and then keep training;in order to get the conditional random field in the training set, you need to adjust and optimize the image segmented by the segnet network to get it;then in the verification set, the segnet network and the weight parameters of the conditional random field model are further adjusted and optimized to obtain the final conditional random field and segnet network;finally, the final conditional random field and segnet network are applied to the crop disease image segmentation. The test results show that compared with the Otsu threshold and Grabcut segmentation methods, the segmentation accuracy P, recall rate R, and comprehensive evaluation index F of this method are all the maximum, and the average processing time of a single image is 0.86 s;compared with pspnet and deeplab methods, Under the premise that the segmentation accuracy P, the recall rate R, and the comprehensive evaluation index F are basically unchanged, the average processing time of a single image is significantly reduced. The results show that the best comprehensive effect can be achieved by segmenting crop disease images in complex environments using the method in this paper. © 2020 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Fault Type identification in Transmission Lines based on VMD-FE and IGWO-KELM 17

Fault Type identification in Transmission Lines based on VMD...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Yue, Youjun Li, Lixin Wang, Hongjun Zhao, Hui Tianjin University of Technology Tianjin Key Laboratory of Complex System Control Theory and Application Tianjin300384 China

ISBN: (纸本)9781728164151

In view of the damage of transmission line short-circuit faults and low fault identification rate, A novel fault identification method based on variational mode decomposition-fuzzy entropy and improved grey wolf algorithm - kernel extreme learning machine is proposed. First, the VMD is used to decompose the three-phase current after the fault to obtain a series of three-phase stable modal components;secondly, the fuzzy entropy value of each group of components is calculated separately as the fault characteristics of the transmission line;Finally, The fault characteristics of the transmission line are input to the kernel extreme learning machine for training to obtain the diagnosis model. The experimental results show that the method is not affected by the distance of the fault, the initial phase angle of the fault and the transition resistance, and can accurately identify the fault type. © 2020 IEEE.

关键词： Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

application of Hybrid Energy Storage Device in High Power Direct-current Power Supply 17

Application of Hybrid Energy Storage Device in High Power Di...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Liu, Yue Wang, Chunjie Chen, Peng Yin, Jinliang School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin Complex System Control Theory and Application Key Laboratory Tianjin China

ISBN: (纸本)9781728164151

The drop-away current of 1500V low-voltage direct-current circuit breaker used in metro DC traction power supply system needs to be checked regularly. The instantaneous power is very high when the detection device is working, and the field power supply is often difficult to meet the requirements. Therefore, an energy storage unit is needed to supply power to the detector. In this paper, a design scheme of high-power DC power supply with supercapacitor and battery as energy storage is proposed, and the energy management and discharge control strategies are studied in theory and simulation, which verify the effectiveness and feasibility of the scheme. © 2020 IEEE.

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

Research on the control system of six joint industrial robot based on CPAC 17

Research on the control system of six joint industrial robot...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Dong, Chao Xie, Bang Shao, Xin Complex System Control Theory and Application Key Laboratory 391 Binshui Xidao Xiqing District Tianjin300384 China

ISBN: (纸本)9781728164151

The defects of the existing commercial robot control system are analyzed and the feasibility of the open control system is studied. The robot control system was designed based on the CPAC development platform with the six-joint robot as the research object. Firstly, a kinematic model of the robot was established by the d-h linkage coordinate system method, and its motion control was described in detail from two aspects of forward and inverse kinematics. Secondly, the inverse kinematics of the robot was solved by using the RPY description method and PIPER criterion, and the correctness of the robot kinematics model was verified. Third, the robot control system software design. Finally, the function modules of the control system are verified through experiments. The experiments show that the robot runs with a small error of pose and posture, which can meet the requirements of the control system and meet the expected design objectives. © 2020 IEEE.

关键词： control systems

来源：评论

学校读者我要写书评

暂无评论

The junction temperature measurement of insulated gate bipolar transistor based on multi-layer feed -forward neural network is presented 17

The junction temperature measurement of insulated gate bipol...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Dong, Chao Mao, Peiye Complex System Control Theory and Application Key Laboratory 391 Binshui Xidao Xiqing District Tianjin300384 China

ISBN: (纸本)9781728164151

For large power flow type insulated gate bipolar transistor (IGBT) saturation voltage drop and non-linear relation between the collector current and junction temperature of junction temperature prediction problem, set up a big electric saturated pressure drop down IGBT test system, access to settle moderate collector current and saturation nonlinear relation between the pressure drop curve, analyses the relation curve change rule the corresponding physical mechanism. The error back propagation (BP) neural network model was established by using Matlab software to predict the junction temperature. The comparison with the prediction results of the polynomial mathematical model shows that the relative error and prediction error of the neural network model are smaller than that of the polynomial mathematical model, and the prediction accuracy of the junction temperature is higher. It shows the feasibility of neural network for junction temperature prediction, so BP neural network model can be given priority when selecting junction temperature prediction model. © 2020 IEEE.

关键词： Junction temperature

来源：评论

学校读者我要写书评

暂无评论

application of Difficult Sample Mining based on Cosine Loss in Face Recognition 17

Application of Difficult Sample Mining based on Cosine Loss ...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Dong, Enzeng Qiao, Yifan Zhang, Zufeng Complex System Control Theory and Application Key Laboratory 391 Binshui Xidao Xiqing District Tianjin300384 China

ISBN: (纸本)9781728164151

Due to the development of deep convolutional neural networks, face recognition has made great progress, and its main goal is how to improve feature recognition capabilities. In this regard, several loss functions based on angular boundaries have been proposed to increase the feature margin between different classes. Although very good results have been achieved in this direction, there are still some problems. These loss functions only expand the feature margin from the perspective of real classification in training, and do not provide distinguishability for misclassified samples. In order to solve this problem, this paper improves on the original cosine loss function, and implements feature learning in the direction of difficult samples based on misclassified feature vectors. © 2020 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：