检索结果-内蒙古大学图书馆

Dynamic model construction and parameter identification for the intelligent mining electric shovel considering different disturbances

引用

Structural and Multidisciplinary optimization 2025年第5期68卷 1-22页

作者： Hu, Zhengguo Lin, Shibin Gong, Zhuangzhuang He, Xiwang Pang, Yong Song, Xueguan School of Mechanical Engineering Dalian University of Technology Dalian116024 China State Key Laboratory of High-Performance Precision Manufacturing Dalian116024 China

The harsh working environment of the front-end mechanism of mining electric shovels poses significant challenges for intelligent excavation. The intelligent mining electric shovel relies on the dynamic model of the front-end mechanism during excavation trajectory planning and tracking control, but accurately constructing the dynamic model of large electric shovels is difficult. Therefore, a dynamic model parameter identification framework for intelligent mine shovel is proposed in this paper. Firstly, the dynamic model of the front-end working mechanism of the intelligent mine electric shovel (IMES) is constructed based on the Lagrange method, and it is simplified and linearized. Then, an optimal excavation excitation trajectory optimization method based on high order polynomials is proposed to generate excitation trajectory. In order to improve the identification accuracy, a hybrid filtering method combining mean filtering and wavelet filtering is proposed in this paper, which is used to process the experimental data of optimal excitation trajectory and ensure that the data meet the identification requirements. Finally, two identification methods of dynamic model parameters are proposed, which are based on adaptive ridge regression and optimization algorithm. Through these two methods, the dynamic parameters of IMES are identified respectively under different uncertain disturbance conditions. Through numerical simulation and experimental verification, the feasibility of the framework for dynamic parameter identification of IMES is proved. The proposed framework provides theoretical support for subsequent trajectory planning and adaptive tracking control of IMES. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Shovels

来源：评论

学校读者我要写书评

暂无评论

Novel Algorithm for modelling complex Physical systems with Bond-Graph and Python Integration

Novel Algorithm for Modelling Complex Physical Systems with ...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Ali, Amir R. Tarek, Mariam Obaya, Omar M. Mechatronics Engineering Department New Cairo11835 Egypt German University in Cairo ARAtronics Laboratory Mechatronics Engineering Department New Cairo11835 Egypt Digital Media Engineering Department New Cairo11835 Egypt

ISBN: (纸本)9798350351408

This work explores the synergistic integration between Python and Bond Graph modeling for a wide range of engineering systems, encompassing mechanical, hydraulic, electrical, thermal, and chemical domains. Employing 20-sim for Bond Graph modeling and simulation, and Python for parameter optimization, our objective is to empower engineers in the design, analysis, and diagnostic processes of complex engineering systems through the prism of modeling and simulation. The convergence of Bond Graph and Python represents a burgeoning field that amalgamates the robust Bond Graph modeling and simulation techniques with the versatility and user-friendliness inherent to the Python programming language. Bond Graphs provide a visual framework to depict intricate dynamic systems and elucidate their energy flows, while Python offers an extensive ecosystem of libraries and tools for numerical computation, data analysis, and visualization. This work not only surveys diverse approaches and tools for harmonizing Bond Graph modeling with Python programming but also delineates the profound advantages of this integration. These advantages encompass augmented simulation capabilities, enriched model analysis, and the facilitation of experimentation. Moreover, this study delves into the intricate challenges of bridging the gap between Bond Graph formalisms and the computational environment of Python. Drawing inspiration from notable applications, including the modeling of mechanical, electrical, and biological systems, as well as control system design and optimization, this work underscores the remarkable potential of Bond Graph and Python integration. Additionally, it provides an insightful review of the existing software and libraries that facilitate this integration, thereby equipping researchers and engineers to implement Bond Graph-based models and simulations within Python environments. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

S-wave velocity inversion and prediction using a deep hybrid neural network

引用

Science China Earth Sciences 2022年第4期65卷 724-741页

作者： Jun WANG Junxing CAO Shuang ZHAO Qiaomu QI State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation Chengdu University of TechnologyChengdu 610059China Key Laboratory of Earth Exploration and Information Techniques(Chengdu University of Technology) Ministry of EducationChengdu 610059China Research Institute of Exploration and Development Southwest Petroleum CompanySINOPECChengdu 610041China

The S-wave velocity is a critical petrophysical parameter in reservoir description,prestack seismic inversion,and geomechanical ***,obtaining the S-wave velocity from field measurements is *** no measured Swave data are available,petrophysical modelling provides the most accurate S-wave velocity ***,because of the complexity of underground geological structures and diversity of rock minerals,the prediction results of petrophysical modelling are easily affected by factors such as the cognition and experience of the ***,the development of novel robust and simple S-wave velocity inversion and prediction methods independent of the modeller is *** by ensemble learning and based on the geologic sedimentation law of reservoirs and their characteristics in logging response,an Swave velocity inversion and prediction method based on deep hybrid neural network was developed by combining the classical convolution neural network(CNN)with the long short-term memory(LSTM)*** the conventional logging data such as acoustic and density as the input in the proposed method,the CNN was used to establish the nonlinear mapping relationship between the input data and S-wave velocity,and the LSTM network was used to integrate the vertical variation trend of the ***,intelligent data-driven inversion and prediction of the S-wave velocity were *** experimental results revealed that the proposed method exhibited a strong generalisation ability and could obtain prediction results comparable to those of petrophysical modelling with a single-well data set for ***,a novel methodology for robust and convenient S-wave velocity prediction was *** proposed method has considerable academic and application implications.

关键词： Deep learning Convolutional neural network Long short-term memory network hybrid neural network Sedimentary constraint S-wave velocity prediction Petrophysical inversion

来源：评论

学校读者我要写书评

暂无评论

Research on Fault Location in DC Distribution Network Based on hybrid Whale Algorithm 7

Research on Fault Location in DC Distribution Network Based ...

引用

7th International Conference on Power and Energy Applications, ICPEA 2024

作者： Xu, Yan Sun, Jiayi Tang, Qizun Yao, Ziqi North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources Baoding China

ISBN: (数字)9798350356113

ISBN: (纸本)9798350356113

Aiming at the current DC distribution network fault model complexity, lower fault location accuracy, slower convergence speed and greater influence by the transition resistance and other problems, this paper adopts the hybrid whale algorithm to improve and solve the problem. First of all, this paper establishes the mathematical models of inter-pole faults and single-pole grounding faults on the basis of the six-terminal ring DC distribution network model, introduces the local search mechanism of bat algorithm on the basis of whale optimization algorithm, forms the hybrid whale algorithm, formulates the fault localization principle based on the hybrid whale algorithm, and introduces the data culling and data completion methods based on the local outlier factor method and moving average method. Through experimental simulation, the fault localization method is verified to have the advantages of high localization accuracy and small influence by transition resistance, and the localization error under data distortion is reduced through data processing. Finally, the hybrid whale algorithm is compared with other intelligent algorithms to verify that the hybrid whale algorithm has the advantages of high accuracy and fast convergence speed. © 2024 IEEE.

关键词： DC distribution systems

来源：评论

学校读者我要写书评

暂无评论

Surrogate-Assisted hybrid Metaheuristic for Mixed-Variable 3-D Deployment optimization of Directional Sensor Networks 5

Surrogate-Assisted Hybrid Metaheuristic for Mixed-Variable 3...

引用

5th International Conference on Data-Driven optimization of complex systems, DOCS 2023

作者： Zhang, Yuntian Chen, Chen Wu, Tongyu Miao, Changhao Ding, Shuxin School of Automation Beijing Institute of Technology Beijing100081 China National Key Lab of Autonomous Intelligent Unmanned Systems Beijing100081 China Signal and Communication Research Institute China Academy of Railway Sciences Corporation Limited Beijing100081 China Natl. Engineering Research Center of System Technology for High-Speed Railway and Urban Rail Transit Traffic Management Laboratory for High-Speed Railway Beijing100081 China

ISBN: (纸本)9798350393521

A major concern in designing sensor networks is the deployment problem. However, establishing an efficient algorithm for the real-world deployment problem is challenging due to three issues, which are 1) the realistic mixed-integer nonlinear programming problem (MINLP) with mixed-variable;2) the combinatorial subset selection problem;and 3) the expensive computational cost for fitness evaluation in the 3-D coverage problem. Therefore, this paper addresses these challenges and proposes a surrogate-assisted hybrid metaheuristic for mixed-variable 3-D deployment optimization of directional sensor networks (DSNs). First, an MINLP with flexible coordinate transformation technique and an efficient mixed-variable encoding scheme are introduced to model and represent the problem. We propose hybrid metaheuristic which applies two reproduction methods respectively for discrete and continuous variables. Second, we design sparse population-based incremental learning (s-PBIL) to handle inherent subset selection problem. s-PBIL could accurately learn the required information, and automatically learn a sparse distribution. Third, a mixed-variable surrogate with unifying space under Bayesian model management is incorporated to reduce the expensive computational cost. Experiment results on real-world deployment scenarios scaling from small-size to large-size show the effectiveness of the proposed algorithm. © 2023 IEEE.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Autonomous drilling and deburring processing planning method of multi-robot systems

Autonomous drilling and deburring processing planning method...

引用

2025 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots, SIMPAR 2025

作者： Zhang, Tianyi Wang, Yongqing Li, Te Liang, Bochao Shi, Shaohan Liu, Haibo Dalian University of Technology State Key Laboratory of High-Performance Precision Manufacturing Dalian116024 China Dalian University of Technology Dalian 116024 State Key Laboratory of High-Performance Precision Manufacturing Intelligent Manufacturing Longcheng Laboratory Changzhou213164 China

ISBN: (纸本)9798331516857

Large workpieces are characterized by enormous size and complex structures. Traditional single-machine manufacturing methodologies encounter challenges such as inefficiency, inconsistent quality, and spatial constraints. Conversely, multi-robot systems exhibit high processing flexibility, providing a suitable foundation for producing large workpieces. However, as the number of tasks and robots increases, programming methods that rely on human instruction will become increasingly complex and inefficient. Consequently, this paper proposes a multi-process trajectory planning procedure for multi-robot systems. This paper realizes multi-robot and multi-task allocation, path planning, and collision avoidance based on the distributed optimization strategy of predicting subsequent constraints. The gray wolf algorithm, augmented with local search strategies, is utilized for task allocation and path planning. The processing trajectory is further optimized by rotating the starting point and task process direction. Ultimately, a delay-waiting-based time scheduling algorithm is employed to ensure the safety and reliability of the trajectory. This paper validates the planning efficacy of the entire process through simulations. The results validate the effectiveness of the proposed procedure in planning processing trajectories for large workpieces, ensuring optimal processing efficiency while maintaining the safety and reliability of the trajectory. © 2025 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Multi-Tasking optimization for High-Efficiency Time Series Data Clustering

引用

Tsinghua Science and Technology 2024年第2期29卷 343-355页

作者： Rui Wang Wenhua Li Kaili Shen Tao Zhang Xiangke Liao Xiangjiang Laboratory Changsha 410205China College of Systems Engineering National University of Defense TechnologyChangsha 410073China Ant Group Co. Ltd.Hangzhou 310000China College of Computer Science and Technology NUDTChangsha 410073China

Time series clustering is a challenging problem due to the large-volume,high-dimensional,and warping characteristics of time series *** clustering methods often use a single criterion or distance measure,which may not capture all the features of the *** paper proposes a novel method for time series clustering based on evolutionary multi-tasking optimization,termed i-MFEA,which uses an improved multifactorial evolutionary algorithm to optimize multiple clustering tasks simultaneously,each with a different validity index or distance ***,i-MFEA can produce diverse and robust clustering solutions that satisfy various preferences of *** on two artificial datasets show that i-MFEA outperforms single-objective evolutionary algorithms and traditional clustering methods in terms of convergence speed and clustering *** paper also discusses how i-MFEA can address two long-standing issues in time series clustering:the choice of appropriate similarity measure and the number of clusters.

关键词： time series clustering evolutionary multi-tasking multifactorial optimization clustering validity index distance measure

来源：评论

学校读者我要写书评

暂无评论

Human EEG Beta Band Power is Related to Tibialis Anterior Muscle Activation Reductions during Walking with an Ankle Exoskeleton

Human EEG Beta Band Power is Related to Tibialis Anterior Mu...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Song, Seongmi Haynes, Courtney A. Naeem, Jasim Bradford, J. Cortney Texas A&M University Department of Kinesiology College StationTX United States U.S. ARMY DEVCOM ArmyResearch Laboratory Aberdeen Proving Ground Humans in Complex Systems Division MD United States U.S. ARMY DEVCOM ArmyResearch Laboratory DCS CORP Aberdeen Proving Ground Humans in Complex Systems Division MD United States

ISBN: (纸本)9798350337020

To achieve efficient and effortless movement with exoskeletons, it is essential to optimize human-exoskeleton fluency. Current methods for measuring fluency include energetic cost, muscle activation, and spatiotemporal gait parameters, but cortical brain dynamics have not been well studied Understanding individual cortical responses could improve the application of personalized exoskeleton assistance through human-in-the-loop (HIL) optimization approaches. Our research aimed to enhance the understanding of individual responses and identify a potential objective function based on electrocortical activity. We found that electrocortical responses show more individual variability than muscle activations, emphasizing the need for personalized cortical optimization to maximize exoskeleton assistance. We also found a significant negative relationship between changes in TA muscle activation and EEG beta power in the motor area. These findings suggest that EEG beta power changes could be a possible objective function for HIL applications. © 2023 IEEE.

关键词： Brain Cost function Electroencephalography Electromyography Exoskeleton

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning to Identify and Optimize Sensitive Parameters in Urban Flood Model Considering Subsurface Characteristics

引用

International Journal of Disaster Risk Science 2024年第1期15卷 116-133页

作者： Hengxu Jin Yu Zhao Pengcheng Lu Shuliang Zhang Yiwen Chen Shanghua Zheng Zhizhou Zhu Key Laboratory of VGE of Ministry of Education Nanjing Normal UniversityNanjing 210023China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing 210023China

This study presents a novel method for optimizing parameters in urban flood models,aiming to address the tedious and complex issues associated with parameter ***,a coupled one-dimensional pipe network runoff model and a two-dimensional surface runoff model were integrated to construct an interpretable urban flood ***,a principle for dividing urban hydrological response units was introduced,incorporating surface attribute *** K-means algorithm was used to explore the clustering patterns of the uncertain parameters in the model,and an artificial neural network(ANN)was employed to identify the sensitive ***,a genetic algorithm(GA) was used to calibrate the parameter thresholds of the sub-catchment units in different urban land-use zones within the flood *** results demonstrate that the parameter optimization method based on K-means-ANN-GA achieved an average Nash-Sutcliffe efficiency coefficient(NSE) of *** to the ANN-GA and K-means-deep neural networks(DNN) methods,the proposed method better characterizes the runoff generation and flow *** study demonstrates the significant potential of combining machine learning techniques with physical knowledge in parameter optimization research for flood models.

关键词： Artifcial neural network Coupled urban fooding model Genetic algorithm K-means algorithm Subcatchment delineation Uncertain parameters

来源：评论

学校读者我要写书评

暂无评论

Modeling of Oil Reservoir Exploitation Based on Deep Learning Agents

Modeling of Oil Reservoir Exploitation Based on Deep Learnin...

引用

2025 SPE Conference at Oman Petroleum and Energy Show, OPES 2025

作者： Liu, Aodi Li, Jing Bi, Jianfei Zhao, Beichen Zeng, Tao Zeng, Nannuo Deng, Chuanzhong Lin, Botao College of Artificial Intelligence China University of Petroleum Beijing China MOE Key Laboratory of Petroleum Engineering China University of Petroleum Beijing China Al Research Center Research Institute of Petroleum Exploration and Development PetroChina Beijing China CNOOC China Co. Ltd. Hainan branch Hainan Haikou China

ISBN: (纸本)9781959025740

Geological models often involve a large number of grid cells, leading to a significant computational burden in numerical simulations. Moreover, each variation in input parameters necessitates a separate simulation run, making real-time applications and large-scale parameter optimization increasingly challenging. Traditional numerical methods, while accurate, become computationally prohibitive for high-dimensional and nonlinear systems, limiting their feasibility in data-intensive scenarios. Thus, there is a critical need for more efficient and scalable alternatives. To address these challenges, we propose a novel agent model based on the Transformer architecture. The self-attention mechanism in Transformers enables efficient capture of complex, nonlinear relationships between inputs and outputs, even with limited training data. By incorporating physics-based constraints, the model mitigates dependence on large-scale datasets while ensuring physically consistent solutions, enhancing both accuracy and generalizability. Unlike purely data-driven models, this hybrid approach leverages domain knowledge to improve stability and robustness. Our proposed method maintains the accuracy of traditional numerical simulations while significantly enhancing computational efficiency. By accelerating inference and reducing the need for repeated full-scale simulations, it facilitates rapid predictions and real-time decision-making in geological modeling. Additionally, its scalability allows for efficient sensitivity analysis and uncertainty quantification, further broadening its applicability. This framework represents a paradigm shift, offering a cost-effective and high-performance solution for complex, high-dimensional physical systems, with potential applications in reservoir simulations, fluid dynamics, and geophysical modeling. Copyright 2025, Society of Petroleum Engineers.

关键词： Potential flow

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：