检索结果-内蒙古大学图书馆

2024 International Conference on automation in manufacturing, Transportation and Logistics, ICaMaL 2024

作者： Song, Yi-Tian Sun, Yan-Ning Zhu, Jia-Yang Liu, Li-Lan Gao, Zeng-Gui Zhang, Jia-Hao School of Mechatronic Engineering and Automation Shanghai University Shanghai China Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai China

ISBN: (纸本)9798350378658

Numerous process items and procedures in the assembly process of a diesel engine have a direct and significant impact on its performance, and accurate and effective assembly process control is a key technical bottleneck in improving the quality consistency of batch-produced diesel engines. Accurate prediction of assembly quality can provide support for online control of assembly quality. However, due to the significant class imbalance between qualified and unqualified products of diesel engine assembly quality, the traditional imbalance learning makes it difficult to capture the small changes between classes. Therefore, an improved random balance sampling method is proposed, combined with the LightGBM classifier to create a quality prediction model. Firstly, class balancing of the training dataset is achieved by generating random weights for each class and fusing oversampling and undersampling. Then, a LightGBM-based quality prediction model is built. Finally, the effectiveness of this approach is validated using real industrial diesel engine assembly data. The comparison results demonstrate that the proposed method outperforms traditional resampling techniques. This study provides an accurate quality prediction model, laying the groundwork for the assembly quality control model of diesel engines. © 2024 IEEE.

关键词： Diesel engines

来源：评论

学校读者我要写书评

暂无评论

Cervical lesion segmentation via transformer-based network 5

Cervical lesion segmentation via transformer-based network

引用

5th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2024

作者： Shen, Nanyan Lu, Wei Gao, Huayu Li, Jing Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai China Shanghai University School of Mechatronic Engineering and Automation Shanghai China

ISBN: (纸本)9798350373820

Colposcopic diagnosis and directed biopsy is the foundation of cervical cancer screening. Automatic segmentation of cervical lesion in colposcopic images can provide great assistance and convenience. However, the existing methods based on CNNs only differentiate the abnormality from healthy tissue, which is hard to further subdivide the lesion. In this paper, a Transformer-based network called TransNet is proposed which can extract the cervical lesion and recognize the corresponding category of each lesion. Unlike the other CNN-based methods, a more powerful vision transformer is adopted as the encoder. Extensive experiments on a large clinical colposcopic image dataset show that TransNet outperforms the existing state-of-art methods and achieves great improvement. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on 3D Model Retrieval Technology Based on Audio Recognition 1

引用

13th International Workshop of Advanced manufacturing and automation, IWAMA 2023

作者： Zhou, Chuanhong Wu, Junyang Chen, Kunpeng School of Automation and Mechanical Engineering Shanghai University Shanghai200072 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai200072 China

ISBN: (数字)9789819706655

ISBN: (纸本)9789819706648

At present, the number of 3D models in machinery industry is increasing, and the commonly used keyword retrieval methods need a lot of manual labeling work, and many complex 3D models are difficult to describe accurately in words. This paper proposes a 3D model retrieval algorithm based on audio recognition, which can quickly and effectively find 3D models in massive models. This paper takes the 3D model of STL file format as the research object, and its main work is as follows: Firstly, a new rotation normalization algorithm for 3D models is proposed. Then a point density control scheme of STL file based on unit volume is proposed. After that, an audio fingerprint extraction algorithm for 3D model is proposed. Finally,the original speed matching method and the neighborhood matching method are proposed to calculate the similarity between models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Structural Topology Optimization Based on SIMP-BESO Coupling Algorithm 1

引用

13th International Workshop of Advanced manufacturing and automation, IWAMA 2023

作者： Zhou, Chuanhong Sun, Yi Tan, Youquan School of Automation and Mechanical Engineering Shanghai University Shanghai200072 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai200072 China

ISBN: (数字)9789819706655

ISBN: (纸本)9789819706648

Structure topology optimization technology plays an increasingly important role in mechanical engineering, as it allows high quality structures to be obtained while meeting the demands for lightweight structures. Using topology optimization makes it possible to distribute the material in a given area appropriately to minimize the weight of the structure while meeting the performance requirements. And it reduces the structural design cycle and gives engineers more structural options. This paper takes the SIMP algorithm as the object of study and proposes a SIMP-BESO coupling algorithm for solving the grayscale problem in the algorithm. This algorithm is based on the concept of the termination factor for SIMP, linking the optimization process to the number of iterations. Dynamic movement factor makes the iterative process "fast then slow" to achieve the phenomenon of removing the grayscale elements in structure, and structures with smaller flexibility and larger stiffness can be obtained. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Shape optimization

来源：评论

学校读者我要写书评

暂无评论

ECA-TabTransformer for the Growth Periods Classification and Disease Detection of Barley Grass through Multispectral imaging 5

ECA-TabTransformer for the Growth Periods Classification and...

引用

5th International Conference on Artificial Intelligence and Electromechanical automation, AIEA 2024

作者： Jing, Zhifeng Cai, Hongxia Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai China

ISBN: (纸本)9798350366174

The industrialized production of barley grass requires precise control of each growth period and effective detection of the disease state. Compared with visual detection, multispectral detection could achieve precise classification of barley grass growth periods and diseases early detection benefits from physiological information of plants. This study aims to achieve the barley grass growth periods classification and disease detection through multispectral imaging taken by low-cost instrument. We proposed ECA-TabTransformer model which introduced Efficient Channel Attention block to enhance original TabTransformer and achieved a higher accuracy of 97.99% compared to algorithms such as CNN+DT, and the performance of multispectral detection also exceeded visual detection. Multispectral detection has better performance than visual detection for barley grass growth periods classification and disease detection. Proposed method has superiority performance, but there is no linear relationship between the performance and the dimensional changes of input. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Research on Online Palletizing Algorithm Based on Buffer 1

引用

13th International Workshop of Advanced manufacturing and automation, IWAMA 2023

作者： Zhou, Chuanhong Xu, Qinfeng Xu, Yang School of Automation and Mechanical Engineering Shanghai University Shanghai200072 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai200072 China

ISBN: (数字)9789819706655

ISBN: (纸本)9789819706648

Online hybrid palletizing scene can not predict the size of the subsequent goods, easy to make the surface of the stacking type uneven, resulting in the subsequent goods can not be stacked and the stability of the stacking type is reduced, forming a collapse phenomenon. Aiming at the online scene problem in mixed cargo palletizing, this paper proposes an online palletizing algorithm based on buffer by setting buffer, combining the overall search strategy of greedy algorithm and the specific strategy of block construction heuristic algorithm. The effectiveness of the algorithm is verified by the examples of airport baggage stacking. The experimental results show that the algorithm can solve the online palletizing problem. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Pick-up strategies for and electrical characterization of ZnO nanowires with a SEM-based nanomanipulator

引用

Nanotechnology and Precision Engineering 2023年第1期6卷 26-31页

作者： Mei Liu Lingdi Kong Weilin Su Aristide Djoulde Kai Cheng Jinbo Chen Jinjun Rao Zhiming Wang Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and AutomationShanghai UniversityShanghai 200444China Guangdong Key Laboratory of Fuel Cell Technology School of Chemistry and Chemical EngineeringSouth China University of TechnologyGuangzhou 510640China

Because of their unique mechanical and electrical properties,zinc oxide(ZnO)nanowires are used widely in microscopic and nanoscopic devices and structures,but characterizing them remains *** this paper,two pick-up strategies are proposed for characterizing the electrical properties of ZnO nanowires using SEM equipped with a *** pick up nanowires efficiently,direct sampling is compared with electrification fusing,and experiments show that direct sampling is more stable while electrification fusing is more *** nanowires have cut-off properties,and good Schottky contact with the tungsten probes was *** piezoelectric experiments,the maximum piezoelectric voltage generated by an individual ZnO nanowire was 0.07 V,and its impedance decreased with increasing input signal frequency until it became *** work offers a technical reference for the pick-up and construction of nanomaterials and nanogeneration technology.

关键词： ZnO nanowires nanomanipulator picking up strategy piezoelectric properties electrical characterization

来源：评论

学校读者我要写书评

暂无评论

Analysis on steering characteristics of crawler pipeline robot

引用

High Technology Letters 2023年第1期29卷 60-67页

作者：耿林康 RAO Jinjun LEI Jingtao School of Mechatronic Engineering and Automation Shanghai UniversityShanghai 200444P.R.China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai 200444P.R.China

In order to improve the elbow passing performance and different diameter adaptability of pipeline robot,a supported crawler pipeline robot is designed,which adopts screw nut mechanism and hinge four-bar mechanism to adapt to the complex environment such as variable diameter pipeline and *** steering characteristics passing through the elbow are studied,the kinematic of pipeline robot bending steering is established,the geometric constraint(GC)and steering constraint(SC)in the elbow are analyzed,and the steering experiment is *** results show that the robot can pass through the elbow by the SC *** SC model can reduce the motor current and energy consumption when the robot passes through the elbow.

关键词： crawler pipeline robot steering characteristics geometric constraint(GC) steering constraint(SC)

来源：评论

学校读者我要写书评

暂无评论

Intuitive Human-Robot-Environment Interaction With EMG Signals:A Review

引用

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1075-1091页

作者： Dezhen Xiong Daohui Zhang Yaqi Chu Yiwen Zhao Xingang Zhao State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016 Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169 University of Chinese Academy of Sciences Beijing 100049China

A long history has passed since electromyography(EMG)signals have been explored in human-centered robots for intuitive ***,it still has a gap between scientific research and real-life *** studies mainly focused on EMG decoding algorithms,leaving a dynamic relationship between the human,robot,and uncertain environment in real-life scenarios seldomly *** fill this gap,this paper presents a comprehensive review of EMG-based techniques in human-robot-environment interaction(HREI)*** general processing framework is summarized,and three interaction paradigms,including direct control,sensory feedback,and partial autonomous control,are ***-based intention decoding is treated as a module of the proposed *** key issues involving precision,stability,user attention,compliance,and environmental awareness in this field are *** important directions,including EMG decomposition,robust algorithms,HREI dataset,proprioception feedback,reinforcement learning,and embodied intelligence,are proposed to pave the way for future *** the best of what we know,this is the first time that a review of EMG-based methods in the HREI system is *** provides a novel and broader perspective to improve the practicability of current myoelectric interaction systems,in which factors in human-robot interaction,robot-environment interaction,and state perception by human sensations are considered,which has never been done by previous studies.

关键词： robot summarized Robot

来源：评论

学校读者我要写书评

暂无评论

A deep learning model-based framework for abnormal state monitoring of blast furnace heat loads 14

A deep learning model-based framework for abnormal state mon...

引用

14th International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, QR2MSE 2024

作者： Xu, Hong-Wei Sun, Yan-Ning Liu, Li-Lan Department of Mechanical and Automation Engineering Shanghai University Shanghai200444 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai200444 China

ISBN: (纸本)9781837242672

Heat load is a pivotal metric for ensuring the safety of blast furnace equipment in the iron and steel smelting industry, crucial for monitoring the heat exchange process of blast furnace cooling walls and evaluating the erosion of furnace bodies. The variability of blast furnace heat load, influenced by factors such as feed and oxygen supply, often results in abnormal internal furnace temperatures and drastic heat load fluctuations, hindering effective preventive maintenance. This study introduces a deep-learning-based framework for monitoring the abnormal state of blast furnace heat load. Initially, a two-stage data preprocessing method for monitoring ironmaking parameters is proposed: the first stage eliminates missing and abnormal values from the monitoring parameters, while the second stage employs a feature selection model to identify key influencing parameters. Subsequently, a real-time prediction model of blast furnace heat load is designed, integrating one-dimensional convolutional neural networks (1DCNN) with bidirectional long short-term memory (BiLSTM) networks. This model uses a two-layer 1DCNN for automatic feature extraction from time series data, complemented by a single-layer BiLSTM network to accurately predict anomalous trends in heat load. This deep learning framework has demonstrated superior performance in prediction accuracy and abnormal trend identification compared to alternative models. © The Institution of Engineering & Technology 2024.

关键词： Iron and steel industry

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：