检索结果-内蒙古大学图书馆

Optimizing Robotic Manipulation With Decision-RWKV: A Recurrent Sequence Modeling Approach for Lifelong Learning

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN engineering 2025年第3期25卷 031004页

作者： Dong, Yujian Wu, Tianyu Song, Chaoyang Southern Univ Sci & Technol Sch Design 1088 Xueyuan Rd Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Dept Mech & Energy Engn 1088 Xueyuan Rd Shenzhen 518055 Peoples R China

Models based on the transformer architecture have seen widespread application across fields such as natural language processing (NLP), computer vision, and robotics, with large language models (LLMs) like ChatGPT revolutionizing machine understanding of human language and demonstrating impressive memory capacity and reproduction capabilities. Traditional machine learning algorithms struggle with catastrophic forgetting, detrimental to the diverse and generalized abilities required for robotic deployment. This article investigates the receptance weighted key value (RWKV) framework, known for its advanced capabilities in efficient and effective sequence modeling, integration with the decision transformer (DT), and experience replay architectures. It focuses on potential performance enhancements in sequence decision-making and lifelong robotic learning tasks. We introduce the decision-RWKV (DRWKV) model and conduct extensive experiments using the D4RL database within the OpenAI Gym environment and on the D'Claw platform to assess the DRWKV model's performance in single-task tests and lifelong learning scenarios, showing its ability to handle multiple subtasks efficiently. The code for all algorithms, training, and image rendering in this study is available online (open source).

关键词： foundation models recurrent models lifelong learning robot learning artificial intelligence computational foundations for engineering optimization data-driven engineering engineering informatics machine learning for engineering applications multiphysics modeling and simulation

来源：评论

学校读者我要写书评

暂无评论

Mixed Finite Element Formulation in Nonlinear Geometrical Analysis of Space Trusses and Application to Trusses With Member Length Imperfection

引用

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN engineering 2025年第1期25卷 014501页

作者： Dao, Ngoc Tien Thi, Thuy Van Tran Hanoi Architectural Univ Fac Civil Engn Hanoi 084 Vietnam

Space trusses usually have a significant number of elements. As a result, it is inevitable that some elements have imperfections. In this study, the authors proposed a mixed finite element method for nonlinear geometrical analysis of space trusses. The post-buckling behavior of space trusses with length imperfections was predicted using a code list written in the programming software. The numerical results indicate that when the length imperfection approaches zero, the results converge to those obtained in studies on standard trusses. A second approach based on the displacement model is also proposed, in which the Lagrange multiplier method is used to deal with the member length imperfection. The results show that the two approaches proposed by the authors are effective, in which the mix formulation based on the finite element model is superior to that based on the displacement model. These results verify the accuracy of the method. Based on the proposed method, the effects of imperfections in the element layers on the truss were studied. The results show that the imperfections in the top two element layers have the maximum influence on the limit load value, whereas the remaining layers have a negligible influence. The combination of the imperfect lengths of these two layers of elements can produce results in which the limit load value is much larger than in the case of a perfect system. Based on the obtained results, it is possible to provide a solution for improving the overall stability of truss structures by creating reasonable imperfections.

关键词： large displacement analysis space trusses member length imperfection mixed finite element method nonlinear geometrical analysis arc-length method post-buckling behaviour of space trusses Lagrange multiplier method advanced computing infrastructure computational foundations for engineering optimization computational metrology multiscale modeling and simulation physics-Based simulations

来源：评论

学校读者我要写书评

暂无评论

Dynamic Analysis of Aortic Flows: Transient Response of Flow-Compliance and Flow-Resistance When Subjected to Sinusoidal Variations of Input Pressure

引用

ASME Open Journal of engineering 2025年 4卷 041004页

作者： Nisar, Syed Anas Banerjee, Debjyoti

The dynamic response of the ascending aorta to sinusoidal pressure inputs using the hyperelastic Mooney–Rivlin model was explored in this study. Flow capacitance models were deployed to estimate the capacity of the aorta by predicting the change in blood volume as a function of the pressure variation. The results gleaned from this study are crucial for understanding the cardiovascular malfunction. The numerical predictions obtained from the hyperelastic model were validated using results in the literature. The numerical model was formulated using nonlinear stress–strain characteristics of aortic tissues, and this strategy provides sufficient accuracy for predicting the response of the aorta to pressure variations (that mirror natural heart rhythms). The results from this study demonstrate the essential role of the aorta in mitigating the effects of pulsatile blood flow, thereby protecting the vascular system from significant pressure spikes by acting as a damper that leverages flow capacitance effects. By emphasizing the need to integrate realistic, patient-specific bio-mechanical properties into simulation models, the results obtained from this study set the stage for advancing diagnostic, therapeutic, and management strategies in cardiovascular therapy. These models can be refined extensively using actual patient data and can provide a platform for future exploration by integrating them into clinical diagnostic systems, which in turn, can improve therapeutic outcomes for cardiovascular patients.

关键词： Fluid dynamics computational foundations for engineering optimization bio-heat and mass transfer fluid mechanics/dynamics fluid mechanics bio-mechanical dynamics design engineering cardiovascular engineering cardiovascular devices dynamics and control cardiovascular diagnostics flexible structures bio-research dynamic systems flows in biological systems complex systems fluidics bio-fluid dynamics flexible-body dynamics fluid friction bio-inspired design computational fluid dynamics (CFD) biomedical simulation fluid instability biomechanics computational engineering fluid control systems Flow (Dynamics) electrochemical capacitors Capacitance digital twins applied mechanics complex flows fluid flow Aorta Cardiovascular system Transients (Dynamics) fluid–structure interaction damping biologically-inspired methods bio-system sensor dynamics of structures design and control of biological systems biological systems applications Pressure compliant mechanisms compliant mechanism synthesis fluid transients design and design optimization dynamical analysis and method bio-engineering simulation biomedical systems

来源：评论

学校读者我要写书评

暂无评论

A Two-Layer Heterogeneous Ant Colony System With Applications in Part-Picking Planning

引用

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN engineering 2023年第2期23卷 021014页

作者： Xie, Liangang Li, Xianda Wei, Xiangzhi Shanghai Jiao Tong Univ Inst Intelligent Mfg & Informat Engn Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Sch Mech Engn Shanghai 200240 Peoples R China Donghua Univ Coll Mech Engn Shanghai 201620 Peoples R China

The tape carrier packaging machine with multiple sucking discs is designed for modern, high-speed packaging production line, which is an important part of the electronic manufacturing process. The efficiency of the part-picking can directly affect the efficiency of the packaging production line. The problem involves at least three coupled sub-problems: the number of picking rounds, the matching relationship between the parts and sucking discs, and the picking order. Because the actual industrial production requires real-time or soft real-time scheduling, the challenge is how to efficiently solve this multi-dimensional combinatorial optimization problem within a fairly limited time. The existing advanced algorithms such as the genetic algorithm and the simulated annealing algorithm usually require complex and time-consuming encoding and decoding while solving this problem. In contrast, the ant colony algorithm has advantages in the convergence rate and parallel computing, especially for searching high dimensional paths in dynamic environments. In order to further improve the comprehensive performance of the ant colony algorithm in solving multi-dimensional coupled optimization problems in extremely limited time, we propose a novel two-layer heterogeneous ant colony system based on three strategies: (1) a bottom-up two-layer solution framework to decouple the original tightly coupled problem into a loosely coupled problem composed of two sub-problems;(2) a candidate cluster augmentation strategy based on the Delaunay triangulation to improve the diversity and quality of the clusters;(3) a co-evolution between a pair of heterogeneous colonies by mixing the high-quality pheromone properly as well as a co-evolution based on the prior knowledge. Finally, through a large set of comparisons, the average picking efficiency of Two-layer Heterogeneous Ant Colony System improved by the three proposed strategies is 13-16% higher than that of other popular heuristic algorithms.

关键词： ant colony optimization co-evolution mechanism part-picking computational foundations for engineering optimization

来源：评论

学校读者我要写书评

暂无评论

Supply Chain as a Complex System: Environmental Impact Evaluation and Perception

引用

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN engineering 2022年第6期22卷 064502页

作者： Cappelletti, Federica Menghi, Roberto Rossi, Marta Germani, Michele Univ Politecn Marche Dept Ind Engn & Math Sci DIISM Via Brecce Bianche 12 I-60131 Ancona IT Italy

Customers are aware of the complexity of supply chains and link this to a high environmental burden. However, if not coupled with quantitative results, this may be overestimated. The present paper proposes a general method used in the specific case of deep environmental evaluation of a swimming goggles distribution. The results are compared to the consumers' perceptions, collected and analyzed from questionnaires, and the remaining product lifecycle stages, assessed through the life cycle assessment (LCA). The design and prototyping phases take place in Italy, the goods are manufactured in Asia, and further commercialized worldwide. The environmental analysis enabled the identification of the most impacting lifecycle phases. Results highlight that for small products, with a simple use phase like the goggles, the distribution phase retains a small percentage of the overall environmental impact;thus, it is reasonable to simplify the modeling of the supply chain by selecting a limited number of significant scenarios. This work proves how important is to quantify and rationalize the environmental impacts of a complex system. The end of life and transport phases are perceived as high impacting, but the life cycle assessment analysis reveals that the materials and manufacturing phases retain the highest impacts and are the first that should be improved. Consequently, proper dissemination, cooperation, and communication strategies should be carried out by the goggles brand toward suppliers and stakeholders;the company is now studying how to replace virgin materials with recycled content to lower the environmental impact without hampering the product's performance.

关键词： computational foundations for engineering optimization data-driven engineering knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

sMF-BO-2CoGP: A Sequential Multi-Fidelity Constrained Bayesian optimization Framework for Design Applications

引用

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN engineering 2020年第3期20卷 031007页

作者： Tran, Anh Wildey, Tim McCann, Scott Sandia Natl Labs Optimizat & Uncertainty Quantificat Albuquerque NM 87123 USA Xilinx Inc San Jose CA 95124 USA

Bayesian optimization (BO) is an efiective surrogate-based method that has been widely used to optimize simulation-based applications. While the traditional Bayesian optimization approach only applies to single-fidelity models, many realistic applications provide multiple levels of fidelity with various computational complexity and predictive capability. In this work, we propose a multi-fidelity Bayesian optimization method for design applications with both known and unknown constraints. The proposed framework, called sMF-BO-2CoGP, is built on a multi-level CoKriging method to predict the objective function. An external binary classifier, which we approximate using a separate CoKriging model, is used to distinguish between feasible and infeasible regions. The sMF-BO-2CoGP method is demonstrated using a series of analytical examples, and a fiip-chip application for design optimization to minimize the deformation due to warping under thermal loading conditions.

关键词： computational foundations for engineering optimization inverse methods for engineering applications inverse methods for engineering applications multi-disciplinary optimization

来源：评论

学校读者我要写书评

暂无评论

Epsilon-Greedy Thompson Sampling to Bayesian optimization

引用

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN engineering 2024年第12期24卷 121006页

作者： Do, Bach Adebiyi, Taiwo Zhang, Ruda Univ Houston Uncertainty Quantificat Lab Civil & Environm Engn Houston TX 77204 USA

Bayesian optimization (BO) has become a powerful tool for solving simulation-based engi-neering optimization problems thanks to its ability to integrate physical and mathematicalunderstandings, consider uncertainty, and address the exploitation-exploration *** sampling (TS) is a preferred solution for BO to handle the exploitation-explora-tion tradeoff. While it prioritizes exploration by generating and minimizing random samplepaths from probabilistic models-a fundamental ingredient of BO-TS weakly managesexploitation by gathering information about the true objective function after it obtainsnew observations. In this work, we improve the exploitation of TS by incorporating the epsilon-greedy policy, a well-established selection strategy in reinforcement learning. Wefirstdelineate two extremes of TS, namely the generic TS and the sample-average TS. Theformer promotes exploration, while the latter favors exploitation. We then adopt the epsilon-greedy policy to randomly switch between these two extremes. Small and large valuesof epsilon govern exploitation and exploration, respectively. By minimizing two benchmark func-tions and solving an inverse problem of a steel cantilever beam, we empirically show that epsilon-greedy TS equipped with an appropriate epsilon is more robust than its two extremes, matchingor outperforming the better of the generic TS and the sample-average TS.

关键词： Thompson sampling Bayesian optimization epsilon-greedy policy exploitation-exploration dilemma cyclic constitutive law computational foundations for engineering optimization inverse methods for engineering applications machine learning for engineering applications

来源：评论

学校读者我要写书评

暂无评论

A Tacholess Order Tracking Method Based on the STFTSC Algorithm for Rotor Unbalance Fault Diagnosis Under Variable-Speed Conditions

引用

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN engineering 2024年第2期24卷 021009页

作者： Wu, Binyun Hou, Liang Wang, Shaojie Lian, Xiaozhen Xiamen Univ Pen Tung Sah Inst Micro Nano Sci & Technol Xiamen 361102 Peoples R China Xiamen Univ Shenzhen Res Inst Shenzhen 518057 Peoples R China

Due to the fact that rotors usually operate in a non-stationary mode with changing speeds, the conventional rotor unbalance detection method based on the stationary signal will produce a major "spectrum ambiguity issue" and affect the accuracy of rotor unbalance detection. To this end, a tacholess order tracking method based on the STFTSC algorithm is suggested in this study, where the STFTSC algorithm is developed by combining the short-time Fourier transform and the seam carving algorithm. First, the STFTSC algorithm is utilized to accurately extract the instantaneous frequency (IF) of the rotor and calculate the instantaneous phase under variable-speed conditions. Subsequently, the original signal is resampled in the angular domain to transform the non-stationary time domain signal into a stable angle domain signal, eliminating the effect of the speed variations. Finally, the angular domain signal is transformed into the order domain signal, which uses the discrete Fourier transform and the discrete spectrum correction method to identify the amplitude and phase corresponding to the fundamental frequency component of the signal. The simulation results show that the IF extracted by the STFTSC algorithm has higher extraction accuracy compared with the traditional STFT spectral peak detection method and effectively eliminates the effect of speed fluctuations. A rotor dynamic-balancing experiment shows that the unbalance correction effect based on the STFTSC algorithm is remarkable, with the average unbalance amount decrease rate on the left and right sides being 90.02% and 92.56%, respectively, after a single correction.

关键词： variable-speed conditions rotor balancing fault diagnosis STFTSC algorithm tacholess order tracking big data and analytics computational foundations for engineering optimization computational metrology computer-aided engineering

来源：评论

学校读者我要写书评

暂无评论

Research on Path Planning for Reducing Vibration Fatigue of Precision Equipment Transportation

引用

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN engineering 2022年第1期22卷 011009页

作者： Huang, Ying Xie, Quanmin Wang, Xingjun Taizhou Univ Coll Aeronaut Engn Coll Intelligent Mfg Taizhou 318000 Peoples R China Sorbonne Univ Pierre & Marie Curie Univ CNRS Jean le Rond dAlembert InstUMR 7190Paris 6 Case 162 F-75252 Paris 05 France Jianghan Univ Hubei Key Lab Blasting Engn Wuhan 430056 Peoples R China Lanzhou Univ Coll Civil Engn & Mech Key Lab Mech Disaster & Environm Western China Lanzhou 730000 Peoples R China

This paper analyzes the safety and reliability problems of large precision instruments and equipment in highway transportation, aiming at reducing the vibration fatigue damage of equipment to the greatest extent from the perspective of road planning. Based on the dynamic response model of the equipment, the relationship between the ground spectrum response and the cumulative fatigue damage of the equipment is analyzed. Based on the method of probability and statistics, an equipment fatigue prediction model is established. Based on the study of the relationship between the roughness of pavement grade and the reliability of equipment, the low-risk path planning is proposed. This paper adapts the Dijkstra shortest path algorithm. Not only the basic information such as the length of the highway is considered but also the road factors related to the reliability of the equipment and the environmental factors affecting the driving safety are considered. Try to avoid the adverse environment which has a great impact on the reliability of the equipment, reduce the vibration fatigue of the equipment in the process of transportation, and improve the quality of transportation. Using geographic information system secondary development, database, global positioning system positioning, and other technologies, this paper provides users with the shortest path and low-risk path planning for reference, which has a certain practical significance for highway transportation of high reliability products such as vulnerable products, precision instruments, and special equipment.

关键词： precision equipment transportation road excitation vibration fatigue prediction path planning computational foundations for engineering optimization computer-aided engineering engineering informatics model-based systems engineering

来源：评论

学校读者我要写书评

暂无评论

Information Exchange Patterns in Digital engineering: An Observational Study Using Web-Based Virtual Design Studio

引用

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN engineering 2021年第4期21卷 041012页

作者： Thekinen, Joseph Grogan, Paul T. Stevens Inst Technol Collect Design Lab Sch Syst & Enterprises Hoboken NJ 07030 USA

This paper performs an observational human subjects study to investigate how design teams use an information system to exchange, store, and synthesize information in an engineering design task. Framed through the lens of decision-based design, a surrogate design task models an aircraft design problem with 12 design parameters across four roles and six system-level functional requirements. A virtual design studio provides a browser-based interface for four participants in a 30-min design session. Data collected across 10 design sessions provide process factors about communication patterns and outcome factors about the resulting design. Correlation analysis shows a positive relationship between design iteration and outcome performance but a negative relationship between chat messages and outcome performance. Discussion explains how advances in information exchange, storage, and synthesis can support future design activities.

关键词： computational foundations for engineering optimization engineering informatics human computer interfaces interactions model-based systems engineering decentralized multidisciplinary engineering design process modeling

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：