检索结果-南通市图书馆

第36届中国控制会议

作者： ZHENG Xiuli SUN Rong CHEN Mingjie ZHAO Jie fu huixuan Academy of Automatication Harbin Engineering University Harbin Engineering University

ISBN: (纸本)9781538629185

In order to decrease both the weight and the size of submarine,the variable vector propeller（i.e.,VVP） has been applied on *** this paper we will study the horizontal motion control for submarine with variable vector ***,we will build the reasonable simplification of the horizontal motion equations about submarine with variable vector propeller according to the need of control ***,we will build the rules of pitch matching for the variable vector propeller,so we can get the pitch state of WP,and we will give the thrust of WP in this pitch ***,considering the characteristic of nonlinearity,time-variation,coupling,stochastic disturb of wave and ocean current,and dubious parameters in horizontal motion control system of submarine with variable vector propeller,the backstepping sliding mode controller based on model reference adaptive is designed for *** adaptive rules are introduced in the backstepping sliding mode control during the design of *** applying the backstepping sliding mode controller based on adaptive rules for horizontal motion of submarine with WP,we can overcome the influence caused by some factors such as uncertainty and complexity of control system,and hold the performance of *** formulation consults proved that backstepping sliding mode controller based on model reference adaptive can have better adaptive ability for uncertainty and complexity than the fuzzy sliding controller.

关键词： Variable Vector Propeller Pitch Angle Horizontal Motion Control Backstepping Sliding Mode Controller and Model Reference Adaptive

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Autonomous positioning of omnidirectional mobile robot based on visual inertial navigation

Autonomous positioning of omnidirectional mobile robot based...

引用

第三十九届中国控制会议

作者： Peng Li Binghan Leng huixuan fu College of Automation Harbin Engineering University

With the development of artificial intelligence,robot intelligence has gradually become a hot research *** positioning of robot is an important part of realizing its *** technology can effectively solve this *** monocular camera is cheap and easy to install,but the monocular vision SLAM has the problem of scale uncertainty,which reduces its *** on the ORB-SLAM2 algorithm,this paper uses the monocular camera as the sensor,uses the integrated IMU inside the omni-directional mobile unmanned car to provide scale information,and carries out information fusion in a tightly coupled ***,the experiment on the autonomous positioning of the actual omni-directional mobile unmanned car platform verifies the feasibility and practicability of the ORB-SLAM2 algorithm with monocular camera as sensor combined with inertial element（IMU） in the autonomous positioning of mobile robot.

关键词： ORB-SLAM2 IMU Mobile robot Autonomous positioning

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Combination of Particle Swarm Optimization with LSSVM for Pipeline Defect Reconstruction

Combination of Particle Swarm Optimization with LSSVM for Pi...

引用

2015年中国智能自动化学术会议

作者： huixuan fu Yuchao Wang Sheng Liu Harbin Engineering University

The nuclear function parameter and penalty parameter are pivotal factors which decide performance of Least Squares Support Vector Machines(LSSVM).Usually, most users select parameters for an LSSVM by rule of thumb, so they frequently fail to generate the optimal approaching effect for the function. In order to get optimal parameters automatically, a new approach based on particle swarm optimization and LSSVM was proposed, which automatically adjusts the parameters for LSSVM, ensuring the accuracy of parameter selection. This method was applied to pipeline 2D defect reconstruction;simulation results showed the method can overcome the difficulty of magnetic flux leakage signals, described defect geometrical characteristics, improving the reconstruction accuracy and practical value.

关键词： Pipeline Magnetic flux leakage 2D defect reconstruction PSO Least squares support vector machines

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Adaptive fuzzy Control Based on Variable Universe for Ship Course

Adaptive Fuzzy Control Based on Variable Universe for Ship C...

引用

2015年中国智能自动化学术会议

作者： Yuchao Wang huixuan fu Sheng Liu College of Automation Harbin Engineering University

Aiming at the conventional fuzzy controller for ship course accuracy is not high and there is contradiction between the number of control rules and ***,a variable universe fuzzy controller algorithm for ship course was *** analyzing the contraction–expansion factors,one of them was found able to satisfy the general contraction–expansion factor *** simulation results show that variable universe fuzzy controller for ship course has high performance,and the proposed control strategy has superior property in effectiveness and robustness than conventional controller.

关键词： Ship Course-keeping Variable universe fuzzy control

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

基于改进PV-RCNN的3D目标检测算法实验研究

引用

实验技术与管理 2022年第2期39卷 23-28页

作者：傅荟璇刘凌风王宇超哈尔滨工程大学智能科学与工程学院黑龙江哈尔滨150001

3D目标检测结合了深度信息,能够提供目标的位置、方向和大小等空间场景信息,在自动驾驶和机器人领域发展迅速。针对PV-RCNN在3D目标检测时不能够充分适应不同的物体尺度、不同的点云密度、部分变形和杂波等问题,对3D目标检测的任务进行... 详细信息

3D目标检测结合了深度信息,能够提供目标的位置、方向和大小等空间场景信息,在自动驾驶和机器人领域发展迅速。针对PV-RCNN在3D目标检测时不能够充分适应不同的物体尺度、不同的点云密度、部分变形和杂波等问题,对3D目标检测的任务进行实验研究。通过加入自适应可变形卷积、上下文融合模块和Gumbel Subset Sampling模块来训练层级特征,使得编码关键点自适应地朝着最具有判别和代表性的特征对齐,提高提案框回归精度。实验结果表明,改进后的PV-RCNN 3D目标检测精度得到了提升,尤其是在远距离物体识别和检测方面。

关键词： 3D检测 PV-RCNN 自适应可变形卷积上下文融合模块

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Ship detection based on Improved YOLO Algorithm

Ship detection based on Improved YOLO Algorithm

引用

第40届中国控制会议

作者： huixuan fu Rui Zhang Xiangyun Ning Yuchao Wang College of Intelligent Systems Science and Engineering Harbin Engineering University

With the continuous development of marine economy,marine ship detection has a very wide application prospect To solve the problems of low ship detection accuracy and easy missing detection of small targets in complex marine environment,an improved YOLOv3 target detection algorithm is ***,before data training,the methods of image blending and small target enhancement are adopted to overcome the influence of complex environment background on target detection and the imbalance of small target data,and improve the network’s ability to extract image features and detect small targets during the training ***,the convolution in the original network is replaced by Octave convolution,which reduces the amount of calculation during network training and improves the detection speed of the network through image frequency *** the same time,GIOU loss function is introduced to alleviate the problems that the gradient is zero when the detection frames do not overlap,and IOU cannot distinguish the alignment of prediction frames and annotation data in different ways,thus improving the accuracy of detecting the target *** experimental results show that the mAP of the improved YOLOv3 algorithm on the self-made ship data set can reach 84.07%,and the improved algorithm is improved by 3.52% compared with the original algorithm,and the detection speed can reach 31.8 frames/s,which effectively improves the accuracy and speed of detecting ships at sea.

关键词： YOLOv3 Small target enhancement Octave convolution GIOU

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Crack Segmentation Based on Improved YOLACT++ Algorithm

Crack Segmentation Based on Improved YOLACT++ Algorithm

引用

2021中国智能自动化大会(CIAC2021)

作者： huixuan fu Dan Meng Wenjie Wu Yuchao Wang Harbin Engineering University Marine Design and Research Institute of China

Cracks are the biggest safety hazard of bridges, and automatic detection of bridge cracks will be of great significance. In view of the low accuracy of existing detection algorithms in crack detection, an improved YOLACT++instance segmentation algorithm is proposed. On the feature extraction network,the RRe LU activation function is used instead of the ReLU activation function to solve the problem that neurons will not be activated when the input is *** model training, in view of the over-fitting problem caused by the difficulty of learning features of the original model on fewer cracked training samples, the method of data argumentation is used to expand the number of data sets, and the idea of transfer learning is introduced to solve the problem of slow convergence caused by the small number of training samples. The experimental results on the self-made crack image dataset show that the improved YOLACT++ algorithm improves 8.89% when the confidence is 70.

关键词： Crack detection Target detection YOLACT++ Instance segmentation

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Maritime Ship Targets Recognition with Deep Learning

Maritime Ship Targets Recognition with Deep Learning

引用

第37届中国控制会议

作者： huixuan fu Yuan Li Yuchao Wang Peng Li College of Automation Harbin Engineering University

In order to improve the accuracy of intelligent recognition of the marine ships besides the realization of the algorithm,a deep learning technique is introduced applying Faster RCNN algorithm to the recognition of marine *** marine target recognition system structure based on Faster RCNN is *** effectiveness of Faster RCNN algorithm is verified on the VOC2007 dataset,and the marine vessel target recognition experiment is carried *** the basis,the target database of ships in different marine environments is established and marked,and the new dataset is used to train Faster RCNN network model,the new trained Faster RCNN network model is compared with the old one by taking the marine ship target recognition *** experimental results show that the Faster RCNN model trained on the new created dataset has good recognition ability and robustness for the targets of marine ships while it can be more accurate giving the target area with the low missed detection rate.

关键词： Ship Target Recognition Deep Learning Faster RCNN RPN

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Formation Control of Unmanned Vessels with Saturation Constraint Based on Backstepping

Formation Control of Unmanned Vessels with Saturation Constr...

引用

第40届中国控制会议

作者： Yuchao Wang Shichuan Wang huixuan fu Zhongkai Li College of Intelligent Systems Science and Engineering Harbin Engineering University Maintenance Branch State Grid Jibei Electric Power Co.Ltd.

In this paper,a formation control method based on backstepping and control force saturation constraint is proposed to solve the formation control problem of surface unmanned vessel with actuator input *** to the control strategy of the virtual leader vessel,it can prevent the trouble of the leader vessel and improve the performance of the *** formation controller is designed by using the virtual leader strategy combined with the backstepping and the generalized saturation function to avoid the insufficient force of the *** stability of the closed-loop system is analyzed by Lyapunov method,and it is proved that the whole system is uniformly final bounded,and the tracking error can be arbitrarily small by choosing reasonable design *** simulation results show that the formation controller designed in this paper has strong anti-saturation ability and can effectively complete formation control.

关键词： Formation control saturation constraint backstepping virtual leader unmanned vessel

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Research on Prediction Method of Ship Rolling Motion Based on Deep Learning

Research on Prediction Method of Ship Rolling Motion Based o...

引用

第三十九届中国控制会议

作者： Yuchao Wang Mingyue Zhang huixuan fu Qiusu Wang College of Automation Harbin Engineering University

In order to improve the accuracy of the ship ’s rolling motion prediction when sailing at sea, a combined prediction algorithm of ship rolling motion based on Complete Ensemble Empirical Mode Decomposition（CEEMD）-Long Short Term Memory Network（LSTM） is proposed. The traditional prediction method ignores the relationship between the data. LSTM has the memory of data, it does not need a lot of data processing or complex modeling process,. The CEEMD algorithm decomposes the original sequence of ship rolling into several modal functions with different characteristics, which makes the non-stationary time series stable and periodic. The LSTM prediction model is established for each component, and the prediction results of each component are superimposed to obtain short-term rolling prediction value. In order to verify the effectiveness of the algorithm proposed in this paper, the real ship data is used for verification. The first 85% of the data is used as the training set, and the last 15% is used for testing. Finally, the effectiveness of the proposed model is verified by experimental results.

关键词： deep learning CEEMD LSTM ship rolling

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：