检索结果-内蒙古大学图书馆

AIMS Electronics and Electrical engineering 2025年第1期9卷 99-117页

作者： Dong, Ruyi Yang, Kai Wang, Tong College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China

Deep reinforcement learning algorithms are widely used in the field of robot control. Sparse reward signals lead to blind exploration, affecting the efficiency of the manipulator during path planning for multi-axis systems at any given end-effector start and target position. To address the problem of tracking randomly located targets in three-dimensional space, this paper proposes a PPO (proximal policy optimization) algorithm with a fused reward mechanism, which enhances the tracking and guidance capabilities of the manipulator in multiple dimensions and reduces the blind randomness of the manipulator during the detection and sampling process. The fusion reward mechanism consists of four dimensions: trajectory correction reward, core area acceleration guidance reward, ladder adaptability reward, and abnormal termination penalty. Finally, a 7-degree-of-freedom Kuka manipulator is built on the PyBullet platform for simulation experiments. Experimental results show that, compared with the sparse reward mechanism, the PPO algorithm with the fused reward mechanism has a higher average success rate as high as 94.88% in task tracking, which can effectively improve the tracking efficiency and accuracy of the spatial manipulator. © 2025 the Author(s)

关键词： deep reinforcement learning fusion reward mechanism intelligent control manipulator proximal policy optimization tracking

来源：评论

学校读者我要写书评

暂无评论

Grouping Decision Algorithm for Dynamic Terminals in Random Access Networks

引用

Journal of Communications and information Networks 2024年第2期9卷 176-183页

作者： Hongliang Sun Tongfei Chen Chuangye Zhao Mengxin Chen College of Information and Control Engineering Jilin Institute of Chemical TechnologyJilin 132022China

This paper proposes a grouping decision algorithm for random access networks with the carrier sense multiple access (CSMA) mechanism, which can balance the traffic load and solve the hidden terminal issue. Considering the arrival characteristics of terminals and quality of service (QoS) requirements, the traffic load is evaluated based on the effective bandwidth theory. Additionally, a probability matrix of hidden terminals is constructed to take into account the dynamic nature of hidden terminal relations. In the grouping process, an income function is established with a view to the benefits of decreasing the probability of hidden terminal collisions and load balancing. Then, we introduce the grey wolf optimization (GWO) algorithm to implement the grouping decision. Simulation results demonstrate that the grouping algorithm can effectively alleviate the performance degradation and facilitate the management of network resources.

关键词： random access network hidden terminal collision probability effective bandwidth traffic load grey wolf optimization

来源：评论

学校读者我要写书评

暂无评论

SSA-CONV-LSTM-BASED TIME-SPACE DEMAND FORECASTING METHOD FOR ONLINE CAR RESERVATION

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and Computer Science 2024年第1期86卷 139-154页

作者： Xing, Xue Zhai, Yaqi College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China

In order to address the disparity between residents' travel demand and online car rental supply under certain space-time conditions and to improve the travel efficiency of passengers, a method for predicting online car rental demand is proposed herein. Accordingly, the popular point of interest (POI) coordinates was selected as the node to divide the geographical map according to the Tyson polygon, the origin-destination (OD) demand data from the drip track data of the local area of the second ring road in Chengdu was extracted, and the OD data was matched with the demand of the divided area to obtain the OD flow matrix. The extracted OD flow matrix was then used to study the law of online car demand under the condition of space-time change, and it was concluded that the change of online car demand exhibits a clear temporal and spatial correlation. Subsequently, the sparrow optimization algorithm-based research on the online car demand prediction method based on the convolution-long and short memory neural network (SSA-Conv-LSTM) was conducted. The results indicate that the SSA-Conv-LSTM network demand forecasting model for car rental was 0.8 higher than the Conv-LSTM model and had greater accuracy and reliability than alternative models. In addition, the SSA-Conv-LSTM prediction model further improves the accuracy of the model for the demand prediction of online car reservations and provides data support to the relevant departments to formulate a reasonable and feasible regional scheduling plan for online car reservations. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Traffic Light Recognition Based on Improved YOLOv5l

引用

Journal of Shanghai Jiaotong University (Science) 2024年 1-15页

作者： Dong, Ruyi Shi, Cong College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin Jilin132022 China

Accurate recognition of traffic lights is essential for ensuring the safety of passengers and pedestrians, especially in the context of self-driving car technology. However, traffic lights present challenges due to their small size and limited recognition accuracy. This paper proposes an enhanced version of the YOLOv5l algorithm specifically designed for traffic light recognition. First, the K-means++ clustering algorithm is employed to generate the prior frame. Second, the SiLU activation function in the basic convolution module is replaced with the adaptive Meta-ACONC activation function, significantly improving the model’s detection accuracy. Third, the coordinate attention mechanism is integrated into the trunk feature extraction network to incorporate coordinate information into the channel, thereby enhancing the network’s sensitivity to small target positions and mitigating the ambiguity caused by increased network depth. Finally, the network’s detection scale is improved by removing the original 20 × 20 large target detection head, leading to an improved accuracy and speed for detecting small targets. The proposed approach is evaluated on self-created traffic light datasets, and compared with the original YOLOv5l model;the improved YOLOv5l model achieves a 7.1% increase in mAP@0.5, reaching 83.3%, effectively meeting the requirements for traffic light detection and recognition. © Shanghai Jiao Tong University 2024.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Research on Defect Detection of Wind Turbine Blades Based on Morphology and Improved Otsu Algorithm Using Infrared Images

引用

Computers, Materials & Continua 2024年第10期81卷 933-949页

作者： Shuang Kang Yinchao He Wenwen Li Sen Liu School of Mechanical and Control Engineering Baicheng Normal UniversityBaicheng137000China School of Information and Control Engineering Jilin Institute of Chemical TechnologyJilin132022China

To address the issues of low accuracy and high false positive rate in traditional Otsu algorithm for defect detection on infrared images of wind turbine blades(WTB),this paper proposes a technique that combines morphological image enhancement with an improved Otsu ***,mathematical morphology’s differential multi-scale white and black top-hat operations are applied to enhance the *** algorithm employs entropy as the objective function to guide the iteration process of image enhancement,selecting appropriate structural element scales to execute differential multi-scale white and black top-hat transformations,effectively enhancing the detail features of defect regions and improving the contrast between defects and ***,grayscale inversion is performed on the enhanced infrared defect image to better adapt to the improved Otsu ***,by introducing a parameter K to adjust the calculation of inter-class variance in the Otsu method,the weight of the target pixels is *** with the adaptive iterative threshold algorithm,the threshold selection process is further *** results show that compared to traditional Otsu algorithms and other improvements,the proposed method has significant advantages in terms of defect detection accuracy and reducing false positive *** average defect detection rate approaches 1,and the average Hausdorff distance decreases to 0.825,indicating strong robustness and accuracy of the method.

关键词： Morphological enhancement improved Otsu algorithm infrared image grayscale inversion adaptive iterative thresholding

来源：评论

学校读者我要写书评

暂无评论

An Improved UNet Lightweight Network for Semantic Segmentation of Weed Images in Corn Fields

引用

Computers, Materials & Continua 2024年第6期79卷 4413-4431页

作者： Yu Zuo Wenwen Li School of Information and Control Engineering Jilin Institute of Chemical TechnologyJilin132022China School of Mechanical and Control Engineering Baicheng Normal UniversityBaicheng137000China

In cornfields,factors such as the similarity between corn seedlings and weeds and the blurring of plant edge details pose challenges to corn and weed *** addition,remote areas such as farmland are usually constrained by limited computational resources and limited collected ***,it becomes necessary to lighten the model to better adapt to complex cornfield scene,and make full use of the limited data *** this paper,we propose an improved image segmentation algorithm based on ***,the inverted residual structure is introduced into the contraction path to reduce the number of parameters in the training process and improve the feature extraction ability;secondly,the pyramid pooling module is introduced to enhance the network’s ability of acquiring contextual information as well as the ability of dealing with the small target loss problem;and lastly,Finally,to further enhance the segmentation capability of the model,the squeeze and excitation mechanism is introduced in the expansion *** used images of corn seedlings collected in the field and publicly available corn weed datasets to evaluate the improved *** improved model has a total parameter of 3.79 M and miou can achieve 87.9%.The fps on a single 3050 ti video card is about *** experimental results show that the network proposed in this paper can quickly segment corn weeds in a cornfield scenario with good segmentation accuracy.

关键词： Semantic segmentation deep learning UNet pyramid pooling module

来源：评论

学校读者我要写书评

暂无评论

Highly constrained cooperative guidance for flexible landing on asteroids

引用

Chinese Journal of Aeronautics 2025年第4期38卷 349-360页

作者： Chang LYU Zixuan LIANG Shengying ZHU School of Aerospace Engineering Beijing Institute of TechnologyBeijing 100081China Key Laboratory of Autonomous Navigation and Control for Deep Space Exploration(Beijing Institute of Technology) Ministry of Industry and Information TechnologyBeijing 100081China

Flexible lander,composed of multiple nodes connected by flexible material,can reducethe bouncing and overturning during the asteroid *** satisfy the complex constraints inthe node cooperation of the flexible landing,an intelligent cooperative guidance method is *** method consists of a double-layer cooperative guidance structure,a guidance parameterdetermination approach,and an action priority *** double-layer contains a basic guid-ance used to satisfy the terminal state constraints,and a compensatory guidance used to satisfythe lander's attitude *** the compensatory guidance,the parameters are determinedby multi-agent system,which are trained according to the performance index of flexible landing *** action priority strategy is used to reduce the detrimental effect of parameter inconsis-tency on the node *** simulation of flexible landing shows that the cooperativeguidance method is effective in improving the landing accuracy while satisfying the ***,the method is robust to the disturbance in the navigation and control.

关键词： Asteroid Flexible lander Multi-constraint Cooperative guidance Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

From earthquake resistance structure to earthquake resilience city–urban seismic resilience assessment

引用

Earthquake engineering and engineering Vibration 2025年第1期24卷 1-13页

作者： Xie Lili Zhao Yonggang Wen Weiping Zhai Changhai Key lab of Structures Dynamic Behaviour and Control of the Ministry of Education Harbin Institute of TechnologyHarbin 150090China Key lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology Harbin Institute of TechnologyHarbin 150090China Institute of Engineering Mechanics China Earthquake AdministrationHarbin 150080China

Earthquakes pose significant perils to the built environment in urban *** avert the calamitous aftermath of earthquakes,it is imperative to construct seismic resilient *** to the intricacy of the concept of urban seismic resilience(USR),its assessment is a large-scale system engineering *** assessment of USR should be based on the notion of urban seismic capacity(USC)assessment,which includes casualties,economic loss,and recovery time as *** loss is also included in the assessment of USR in addition to these *** assessment indicator system comprising five dimensions(building and lifeline infrastructure,environment,society,economy,and institution)and 20 indicators has been devised to quantify *** analytical hierarchy process(AHP)is utilized to compute the weights of the criteria,dimensions,and indicators in the urban seismic resilience assessment(USRA)indicator *** the necessary data for a city are obtainable,the seismic resilience of that city can be assessed using this *** illustrate the proposed methodology,a moderate-sized city in China was selected as a case *** assessment results indicate a high level of USR,suggesting that the city possesses strong capabilities to withstand and recover from potential future earthquakes.

关键词： urban seismic capacity urban seismic resilience assessment analytic hierarchy process functionality loss

来源：评论

学校读者我要写书评

暂无评论

Research on Performance Optimization of Spark Distributed Computing Platform

引用

Computers, Materials & Continua 2024年第5期79卷 2833-2850页

作者： Qinlu He Fan Zhang Genqing Bian Weiqi Zhang Zhen Li School of Information and Control Engineering Xi’an University of Architecture and TechnologyXi’an710054China Shaanxi Institute of Metrology Science Xi’an710043China

Spark,a distributed computing platform,has rapidly developed in the field of big *** in-memory computing feature reduces disk read overhead and shortens data processing time,making it have broad application prospects in large-scale computing applications such as machine learning and image ***,the performance of the Spark platform still needs to be *** a large number of tasks are processed simultaneously,Spark’s cache replacementmechanismcannot identify high-value data partitions,resulting inmemory resources not being fully utilized and affecting the performance of the Spark *** address the problem that Spark’s default cache replacement algorithm cannot accurately evaluate high-value data partitions,firstly the weight influence factors of data partitions are modeled and ***,based on this weighted model,a cache replacement algorithm based on dynamic weighted data value is proposed,which takes into account hit rate and data *** integration and usage strategies are implemented based on LRU(LeastRecentlyUsed).Theweight update algorithm updates the weight value when the data partition information changes,accurately measuring the importance of the partition in the current job;the cache removal algorithm clears partitions without useful values in the cache to releasememory resources;the weight replacement algorithm combines partition weights and partition information to replace RDD partitions when memory remaining space is ***,by setting up a Spark cluster environment,the algorithm proposed in this paper is experimentally *** have shown that this algorithmcan effectively improve cache hit rate,enhance the performance of the platform,and reduce job execution time by 7.61%compared to existing improved algorithms.

关键词： Spark memory optimization memory replacement strategy

来源：评论

学校读者我要写书评

暂无评论

Machine learning based damage state identification:A novel perspective on fragility analysis for nuclear power plants considering structural uncertainties

引用

Earthquake engineering and engineering Vibration 2025年第1期24卷 201-222页

作者： Zheng Zhi Wang Yong Pan Xiaolan Ji Duofa College of Civil Engineering Taiyuan University of TechnologyTaiyuan 030024China Key Lab of Structures Dynamic Behavior and Control(Harbin Institute of Technology) Ministry of EducationHarbin 150090China Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology Harbin Institute of TechnologyHarbin 150090China

Seismic fragility analysis(SFA)is known as an effective probabilistic-based approach used to evaluate seismic *** are various sources of uncertainties associated with this approach.A nuclear power plant(NPP)system is an extremely important infrastructure and contains many structural uncertainties due to construction issues or structural deterioration during *** of structural uncertainties effects is a costly and time-consuming endeavor.A novel approach to SFA for the NPP considering structural uncertainties based on the damage state is proposed and *** results suggest that considering the structural uncertainties is essential in assessing the fragility of the NPP structure,and the impact of structural uncertainties tends to increase with the state of ***,machine learning(ML)is found to be superior in high-precision damage state identification of the NPP for reducing the time of nonlinear time-history analysis(NLTHA)and could be applied in the damage state-based ***,the impact of various sources of uncertainties is investigated through sensitivity *** Sobol and Shapley additive explanations(SHAP)method can be complementary to each other and able to solve the problem of quantifying seismic and structural uncertainties simultaneously and the interaction effect of each parameter.

关键词： seismic fragility analysis damage state structural uncertainties machine learning sensitivity analysis

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：