检索结果-内蒙古大学图书馆

8th International Conference on System Reliability and Safety, ICSRS 2024

作者： Zhao, Zhiqian Wang, Yuefeng Jiao, Yinghou School of Mechatronics Engineering Harbin Institute of Technology Harbin China Beijing Jingdiao Technology Group Beijing China

ISBN: (纸本)9798350354508

The success of traditional fault diagnosis methods depends on obtaining a large number of training samples in the form of full faults, which may not be available in practical applications. Recent studies have shown the feasibility of constructing virtual representations reacting to fault situations by building physical models when fault samples are insufficient. In this paper, a virtual data-driven domain-based adaptive fault diagnosis method based on adaptive regularisation consistency, ARC, is proposed to ensure the consistency between the virtual and real domains. Firstly, the bearing dynamic model is constructed to obtain the simulation data, and the simulation data and the real data are input into the trained original model and the target model at the same time. The data distributions of the simulated and real samples are adaptively brought closer by adding weights to the maximum mean discrepancy (MMD);Kullback-Leibler Divergence (KLD) is used to make the feature representations extracted from the target model similar to each other and between the original model and the feature representations extracted from the target model, and regularization is used to fine-tune the feature extraction of the model. An entropy-based adaptive pseudo-labelling selection method is proposed to filter low-quality samples and prevent negative transfer. The diagnostic results of the case study show that the proposed method is able to utilize the diagnostic knowledge from the simulation data to achieve fault diagnosis of mechanical equipment and outperforms the commonly used unsupervised cross-domain fault diagnosis methods. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Adaptive chaotic class topper optimization to solve Non-convex CHPED problems in power systems 13

Adaptive chaotic class topper optimization to solve Non-conv...

引用

13th IEEE Power and Energy Society: Innovative Smart Grid Technologies - Asia, ISGT Asia 2024

作者： Gupta, Pradeep Kumar Tuttelberg, Kaur Kilter, Jako Tallinn University of Technology Dept. of Electrical Power Engineering and Mechatronics Tallinn Estonia

ISBN: (纸本)9798350373929

This paper proposed a population-based meta-heuristic algorithm, an adaptive chaotic class topper optimization (AC-CTO) algorithm for solving combined heat and power economic dispatch (CHPED) problems. The proposed algorithm is an improved version of classical class topper optimization, where the desirable practical solutions are obtained based on the learning process, improving the students' knowledge. Here, the complexity of combined heat and power is increased due to their mutual interdependence and is non-linear in nature. The main goal is to achieve the minimum fuel cost while satisfying demand, considering the practical system constraints such as valve-point effects, prohibited operating zones, and transmission loss. To evaluate the performance, the proposed algorithm is tested for two case studies, one without system losses - 4 unit system and the other with system losses - 7 unit system. The results of the study indicate that AC-CTO algorithms outperform popular optimization methods to solve the CHPED problems and obtain the lowest fuel cost. © 2024 IEEE.

关键词： Adaptive Chaotic Class Topper Optimization (AC-CTO) Class Topper Optimization Combined Heat and Power Economic Dispatch (CHPED) Economic Load Dispatch

来源：评论

学校读者我要写书评

暂无评论

Exploring the Metallurgical and Mechanical Characteristics of Magnesium/Silicon Carbide Surface Composites Manufactured via Friction Stir Processing

引用

Journal of The Institution of Engineers (India): Series D 2024年第3期105卷 1793-1800页

作者： Selvan, T.A. Velusamy, K. Senthilkumar, K.M. Arivalagan, P. Mechatronics Engineering Department Sri Krishna College of Engineering and Technology Tamil Nadu Coimbatore India Mechanical Engineering Department Annai Mathammal Sheela Engineering College Tamil Nadu Namakkal India Mechanical Engineering Department Kumaraguru College of Technology Tamil Nadu Coimbatore India Mechanical Engineering Department Sri Krishna College of Technology Tamil Nadu Coimbatore India

The proposed research endeavors to enhance the longevity of magnesium alloy materials by employing friction stir processing (FSP) to incorporate metallic particles. The experimental phase encompassed the manipulation of silicon carbide (SiC) particles at varying weights of 0% (neat FSP), 4%, and 8% in conjunction with a magnesium alloy matrix (AZ-91) using the FSP method. Subsequent evaluation focused on both metallurgical and mechanical aspects of the prepared samples. The results obtained highlighted the uniform dispersion of SiC particles within the matrix stir zone, exhibiting an absence of intermetallic reactions as indicated by scanning electron microscopic analysis. Notably, the samples containing 8 wt% SiC exhibited higher levels of hardness, impact and tensile strength, with fracture occurring at the thermo-mechanically affected zone, while also displaying improved ductility. In quantitively 26.13% increase in hardness, 47.88% higher impact strength, and 33.33% greater tensile strength was obtained. This can be attributed to the amalgamation of dispersion strengthening, which significantly influenced the overall strength of the fabricated surface composites. The enhanced strength is due to the pinning effect generated by SiC particles, combined with the utilization of the FSP process. The resulting surface composites, following these processing techniques, hold promising potential for integration into future applications, particularly within the automotive and marine sectors. © The Institution of Engineers (India) 2023.

关键词： Magnesium alloys

来源：评论

学校读者我要写书评

暂无评论

Effect of Welding Current and Electrode Polarity on Weld Bead Geometry and Shape Relationships in Gravity-Assisted Mechanized Contact Shielded Metal Arc Welding 21st

Effect of Welding Current and Electrode Polarity on Weld Bea...

引用

21st ISME International conference on Advances in Mechanical engineering, ISME 2023

作者： Kumar, Manoj Shrimali, Ritesh Singh, Ayush Kumar Pandey, Sunil Department of Mechanical - Mechatronics Engineering The LNM Institute of Information Technology Jaipur302031 India

ISBN: (纸本)9789819736539

The paper reports how welding current and electrode polarity affect on weld bead geometry and shape relationships in a gravity-assisted SMAW process. An air-hardening MFH 350 electrode was used. Various weld bead geometry parameters, i.e., bead height, bead penetration, bead width, and shape relationships, i.e., weld reinforcement form factor, weld penetration shape factor, percent dilution, and linear heat input, have been recorded and computed. A gravity-assisted mechanized setup, fabricated in the welding research laboratory was used for continuous mechanized contact welding. The mechanization fully eliminated the effect of the welder’s skill on the melting rate and the BG and SR. The melting rate and hence the welding speed of the bead on plate deposition were varied by varying the welding current. The welding current was varied from 120 to 180 amperes. The whole experiment was conducted with DCEN and DCEP. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Research laboratories

来源：评论

学校读者我要写书评

暂无评论

Multi-Agents Trajectory Prediction for Autonomous Vehicles with Multi-Modal Predictions 15

Multi-Agents Trajectory Prediction for Autonomous Vehicles w...

引用

15th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2024

作者： Neamah, Husam A. Alghazawi, Mohammad Korondi, Peter Electrical Engineering and Mechatronics Department University of Debrecen Debrecen Hungary College of Engineering National University Science and Technology Dhi Qar Iraq Electrical Engineering and Mechatronics Department Faculty of Engineering University of Debrecen Debrecen Hungary

ISBN: (纸本)9798350378245

This paper presents an advanced deep learning framework designed to improve motion prediction in autonomous driving, enhancing safety through better environmental understanding. The Crat-Pred model is enhanced, demonstrating superior performance over existing benchmarks in both qualitative and quantitative analyses, with improved training times and computational efficiencies. The proposed approach addresses a critical research gap by predicting the motion of both vehicles and pedestrians. By utilizing convolutional neural networks and replacing Long-Short-Term Memory (LSTM) networks with Temporal Convolutional Networks (TCN), significant improvements in computational speed and efficiency are achieved. The primary objective is to develop a unified prediction model for all road agents, advancing autonomous navigation. Experiments using the Argoverse 2 dataset validate the model's performance in real-world conditions, showcasing its superiority in forward motion prediction and computational efficiency. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Scheduling Optimization of Flexible Workshop Dynamics Based on Big Data 28

Scheduling Optimization of Flexible Workshop Dynamics Based ...

引用

28th International Conference on Automation and Computing, ICAC 2023

作者： Ji, Siyang Yan, Jihong School of Mechatronics Engineering Harbin Institute of Technology Heilongjiang China

ISBN: (纸本)9798350335859

Modern machining has the characteristics of 'small batch, multiple machining types, and complex processes'. The production process generates a large amount and variety of data, and the production strategy is complex and variable. The generation of scheduling strategies needs to consider the actual production status of the workshop and the disturbances in the current status to ensure that the scheduling results meet the actual order requirements. This paper proposes a dynamic scheduling optimization strategy based on workshop big data. We design a big data-based scheduling optimization computing framework, which integrates big data resources such as workshop machine tool processing status, workpiece processing information, and order information to obtain relevant data affecting processing in real-time, and quickly respond to changes in workshop factors to ensure consistency between scheduling constraints and actual situations. In addition, we have improved the traditional genetic algorithm and the method of calculating the fitness value, solving the problem of deviation from the original scheduling plan caused by the disturbance of urgent order insertion, rework and repair, machine tool maintenance, and scheduling time. This improves the real-time and dynamic decision-making of machining scheduling. The proposed scheduling optimization strategy has been applied to a certain aviation engine machining workshop, reducing the overall machining time and improving machining efficiency compared to the original scheduling strategy of the workshop. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Deterministic and probabilistic comparison of the discrepancy between the numerical simulation and experimental test considering passive and active vibration isolation 31

Deterministic and probabilistic comparison of the discrepanc...

引用

31st International Conference on Noise and Vibration engineering, ISMA 2024 and 10th International Conference on Uncertainty in Structural Dynamics, USD 2024

作者： Mohan Kumar, M.K. Platz, R. Deggendorf Institute of Technology Faculty of Mechanical Engineering and Mechatronics Bavaria Weissenburg91781 Germany

ISBN: (纸本)9789082893175

Identification and quantification of model form discrepancy and uncertainty in structural dynamic systems improve the accuracy and credibility of model predictions. The purpose and novelty of this investigation is to compare the deterministic discrepancies of three different linear mathematical models describing the same realized experimental test rig for passive and active vibration isolation: an analytical one-mass oscillator model as the simplest model form, an analytical two-mass oscillator model, and a finite element model. The finite element model and the two-mass model incorporate the inertia, damping, and stiffness of an additional frame structure required to realize the test rig, unlike the one-mass model. Acceleration responses of the calibrated models are validated against experimental results to demonstrate the models' capability to predict dynamic responses. This deterministic investigation lays the groundwork for a simple probabilistic Bayesian inference metric, aiming to quantify model form uncertainty by estimating probabilistic discrepancy. © 2024 Proceedings of ISMA 2024 - International Conference on Noise and Vibration engineering and USD 2024 - International Conference on Uncertainty in Structural Dynamics. All rights reserved.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Reduced Order Model Based Output Feedback Control for Hydraulic Quadruped Robot Single Leg 9

Reduced Order Model Based Output Feedback Control for Hydrau...

引用

9th International Conference on Fluid Power and mechatronics, FPM 2023

作者： Zhang, Zhenyang Yang, Qingjun Wang, Xuan Xu, Hongguang School of Mechatronics Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350304947

ISBN: (纸本)9798350304947

An output feedback control method is introduced to the displacement tracking control of the hydraulic drive system of a hydraulic quadruped robot in this paper, only the motion displacement is required for the control implementation, achieving high performance tracking control of hydraulic quadruped robot foot trajectory. By using singular perturbation theory to simplify system model, the unknown dynamics are lumped as one term, solving the problem of mechanical/hydraulic double dynamics coupling system with mismatched uncertain disturbances. Then the extended state observer(ESO) is designed to estimate the velocity and unknown dynamics of the hydraulic drive system. The control law is designed based on reduced order model and extended state observer, and the stability of the system is proved theoretically. Extensive comparative co-simulations and experiment based on a hydraulic quadruped robot single leg are conducted. From the comparison of co-simulation results, it can be seen that the control effect of the proposed method is significantly improved, and the experimental results verify the effectiveness of the proposed control method. © 2023 IEEE.

关键词： System stability

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic Based Obstacle Avoidance Algorithm for Unmanned Systems 8

Fuzzy Logic Based Obstacle Avoidance Algorithm for Unmanned ...

引用

8th IEEE International Conference on engineering Technologies and Applied Sciences, ICETAS 2023

作者： Palaniappan, Rajkumar Nataraj, Sathees Kumar Ismail, Zeyad Noaman, Noaman M College of Engineering University of Technology Bahrain Department of Mechatronics Engineering Salmabad Bahrain

ISBN: (纸本)9798350327090

Researchers that create autonomous systems are very interested in obstacle avoidance. An autonomous system's ability to avoid obstacles more intelligently is a key component. Only artificial intelligence approaches can accomplish this. In this research, a smart obstacle avoidance system based on fuzzy inference system is proposed. The distance from the obstacle and the angle at which the autonomous system is facing the obstacle are the inputs to the fuzzy inference system. The suggested system's outputs include steering and speed adjustments for the autonomous vehicle to better avoid collision with obstacles. With the help of the correlation coefficient and root mean squared error, the developed fuzzy system was assessed. A correlation coefficient was obtained for the suggested system. For steering and speed adjustment, the proposed system received correlation coefficients of 0.983 and 0.974, respectively. Comparable results were found for steering and speed adjustment, with root mean squared errors of 0.0865 and 0.08633, respectively. The results of the performance review were quite successful, and the system that was created was dependable. The similar mechanism will be implemented in hardware in the future, and testing will take place. © 2023 IEEE.

关键词： Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Applications of Hybrid Conditional Planning in Service Robotics

Applications of Hybrid Conditional Planning in Service Robot...

引用

2023 International Conference on Robotics and Automation in Industry, ICRAI 2023

作者： Nouman, Ahmed Saleem, Muhammad Khurram Örebro Sweden University of Engineering & Technology Mechatronics Engineering Department Taxila Pakistan

ISBN: (纸本)9781665464727

Hybrid planning computes task plans in full observability (a sequence of possible actuation actions) via the integration of low-level feasibility checks in classical planning approaches. Conditional planning extends the classical planning framework to account for plans under partial observability. We use a hybrid conditional planning approach to compute plans that include sensing and actuation actions in solving real-world problems by addressing uncertainties due to incomplete information at the planning phase. We generate a hybrid conditional plan of actions using parallel instances of a non-monotonic hybrid HCPLAN that supports defaults, integration of external computations, and non-deterministic actions. We show our hybrid conditional planning framework's HCPLAN applicability through service robotics scenarios with manipulation and navigation tasks. Furthermore, we evaluate the effect of parallel threads on the computation of hybrid conditional framework on different benchmark scenarios for the service robotics domains. © 2023 IEEE.

关键词： Motion planning

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：