检索结果-内蒙古大学图书馆

AIAA SciTech Forum

作者： Ball, Nicholas Daultry Panesi, Marco MacArt, Jonathan F. Sirignano, Justin Univ Oxford Math Inst Oxford England Univ Illinois Aerosp Engn Champaign IL USA Univ Notre Dame Aerosp & Mech Engn Fremantle WA 6959 Australia

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

Numerical simulation of the Boltzmann equation, most commonly by the DSMC method, can provide highly accurate descriptions of supersonic, rarefied flows. However, it is computationally expensive in the transitional flow regime, with Knudsen numbers 0.01 less than or similar to Kn less than or similar to 0.1, motivating the use of simpler, but less accurate models such as the BGK equation. We develop and implement optimization methods for calibrating machine learning-based BGK models to high-fidelity DSMC data. We derive and validate an adjoint equation for optimization over the BGK equation with a general form of the collision frequency. We train a neural network model for the collision frequency using automatic differentiation to implement the adjoint equations, and apply this model to the formation of a 1D shock.

关键词： Compressible Flow Neural Networks Reduced Order Modelling Direct Simulation Monte Carlo Direct Numerical Simulation optimization algorithm Conservation of Mass Boltzmann Equation Machine Learning Mach Numbers

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Energy-Conscious Scheduling Under Time-of-Use Electricity Price

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 11490-11504页

作者： Wang, Caixia Fang, Wenxuan Dai, Xin He, Renchu Du, Wei Tang, Yang East China Univ Sci & Technol State Key Lab Ind Control Technol Minist Educ Shanghai 200237 Peoples R China East China Univ Sci & Technol Key Lab Smart Mfg Energy Chem Proc Minist Educ Shanghai 200237 Peoples R China Huzhou Inst Ind Control Technol Huzhou 313099 Peoples R China Westlake Univ Trustworthy & Gen Artificial Intelligence Lab Hangzhou 310030 Zhejiang Peoples R China China Univ Petr Coll Artificial Intelligence Sch Dept Automat Beijing 102249 Peoples R China

In the context of carbon peaking and carbon neutrality, green production scheduling that considers energy has attracted increasing attention. Reinforcement learning (RL) has emerged as a topic for developing efficient algorithms for solving complex combinatorial optimization problems, such as real-world shop scheduling problems. In this paper, we investigate the energy-conscious scheduling problem (ECSP) under time-of-use (TOU) electricity price with the goal of minimizing both the waiting time and extra electricity cost. A mathematical model is formulated, and an efficient deep RL (DRL)-based optimization method is proposed to solve the problem effectively. We design a novel ECSP network (ECSPNet) tailored to handle various ECSP scales based on the characteristics of the problem. Moreover, the Tchebycheff decomposition method is used to solve the multi-objective optimization problems, complemented by the application of the policy gradient method from reinforcement learning to train the ECSPNet without size limitations. Experiments verify that the proposed ECSPNet outperforms state-of-the-art methods and is computationally efficient, even on instances of larger scales unseen in training. Real-world case studies reveal that the proposed method can reduce annual total electricity cost by approximately 30% while effectively maximizing production efficiency.

关键词： Electricity Costs Production Job shop scheduling Automation Energy consumption Training Conferences Power demand Decision making Deep reinforcement learning energy-conscious scheduling problem time of use electricity price optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A hybrid machine learning model for NOx emission concentration prediction from sludge incineration

引用

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION 2025年 196卷

作者： Luo, Song Wang, Lihua Ji, Hongxian Zhong, Qifeng Cui, Haibin Wang, Fei Zhejiang Univ State Key Lab Clean Energy Utilizat Hangzhou 310027 Peoples R China Shanghai Chengtou Water Grp Co Ltd Shanghai 201709 Peoples R China

Accurate prediction of NOx emission concentration is crucial for optimizing combustion processes and enhancing flue gas treatment in incineration systems. However, the traditional prediction models that employ data-driven methods face significant challenges due to insufficient input feature information, as well as low computational efficiency and robustness. These limitations hinder the accurate real-time prediction of NOx emission concentration. To address this issue, this paper proposes an advanced hybrid model for predicting NOx emission concentration. Initially, static and dynamic flame features are extracted from flame images and integrated with Distributed Control System (DCS) parameters to serve as the model's input features, while the NOx emission concentration constitutes the model's output feature. Subsequently, the lag time between NOx emissions and the input features is determined using mutual information (MI), followed by data reorganization to develop various predictive models for NOx emission concentration. Finally, the extremely randomized trees (ERT) model, demonstrating superior performance, is further optimized using Bayesian optimization with tree-structured Parzen estimators (BO-TPE). Experimental results indicate that the ERT model optimized with BO-TPE outperforms state-of-the-art models, making it suitable for online optimization of industrial pollutant control and potentially contributing to cleaner production.

关键词： NO x emission concentration prediction Sludge incineration Flame image Extremely randomized trees optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Design Framework for optimization of Curvilinearly Stiffened Variable Stiffness Composite Laminates with Manufacturing Constraints

Design Framework for Optimization of Curvilinearly Stiffened...

引用

AIAA SciTech Forum

作者： Agarwal, Mayank Kapania, Rakesh K. Minaya, Chris Venkataraman, Satchi Hammerand, Daniel C. Virginia Polytech Inst & State Univ Kevin T Crofton Dept Aerosp & Ocean Engn Blacksburg VA 24061 USA San Diego State Univ Dept Aerosp Engn San Diego CA 92182 USA M4 Engn Inc Long Beach CA 90807 USA

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

Stiffened Variable Angle Tow (VAT) Laminates with optimized curvilinear fiber paths and curvilinear stiffeners are known to significantly improve structural performance over traditional laminates by increasing the buckling loads as a result of tailored stiffness and redistribution of the in-plane loads. optimization of such laminates is highly non-convex and non-linear with a large design space. optimization space can be made convex with the use of lamination parameters;however, that necessitates a second-level optimization for fiber path recovery. Further, the presence of manufacturing defects can highly impact the final performance of the design. Therefore, the current study focuses on designing a robust framework for the optimization of curvilinearly stiffened VAT composite laminates with fiber angles of each layer directly as design variables along with curvilinear stiffener layout and sizing parameters as well as manufacturability constraints. A novel approach is proposed to consider the fiber angles at the nodes of a coarse design mesh as design variables for steering the tow path and interpolate them to a finer analysis mesh using Lagrange shape functions. UGENS subroutine in Abaqus is employed to obtain the sectional forces and moments at each integration point for static and buckling analysis of the laminate. Tie constraints are used to enforce the displacement and rotation compatibility at the stiffener plate interface. Tow path recovery is done to obtain the realizable layout from the design fiber angles using a median based seeding strategy and parallel shifting techniques. The relationship between divergence of the 2D vector field obtained from the tow streamlines and the gap/overlap propagation is used to implement manufacturability constraints in the top-level optimization. Simulia's Isight package is used for integrating different analysis and data I/O components into a single optimization framework. Built-in particle swarm optimization (PSO) in Isig

关键词： Composite Laminates Stiffness Particle Swarm optimization Abaqus Finite Element Modeling Composite Structures Streamlines Buckling Analysis optimization algorithm MATLAB

来源：评论

学校读者我要写书评

暂无评论

Multi-condition Robust optimization Design of High Subsonic Cascades Considering the Uncertain Changes of Inlet Flow Condition

Multi-condition Robust Optimization Design of High Subsonic ...

引用

Asia-Pacific International Symposium on Aerospace Technology (APISAT)

作者： Wuan, Zhao Jiang, Chen Yi, Liu Hang, Xiang Beihang Univ Sch Energy & Power Engn Beijing 100191 Peoples R China

ISBN: (纸本)9789819740123;9789819740109;9789819740093

To achieve the design of high-performance and highly robust subsonic compressor cascades across various Reynolds numbers, this study investigates the impact of inlet flow fluctuations on cascade performance at different Reynolds numbers, followed by a rigorous data-driven optimization algorithm for robust optimization. The impact of fluctuation in inlet Mach number and incidence angle on the aerodynamic performance of the cascade is investigated using the two-dimensional normal distribution variable generation method within a non-intrusive polynomial chaos framework. The total pressure loss of the cascade increases with the decrease in Reynolds number, and the influence of inlet flow condition fluctuation becomes more pronounced. The sensitivity of the static pressure ratio to inlet flow fluctuation remains essentially unchanged with variations in Reynolds number. After robust optimization, compared with the prototype, the mean value of total pressure loss is reduced by 10.40% and the standard variance by 28.82%. The region with high entropy fluctuation decreases obviously.

关键词： Robust optimization Quantization of Uncertainty Non-intrusive Polynomial Chaos optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Design and optimization of reactive distillation: a review

引用

Frontiers of Chemical Science and Engineering 2022年第6期16卷 799-818页

作者： Chang Shu Xingang Li Hong Li Xin Gao School of Chemical Engineering and Technology National Engineering Research Center of Distillation TechnologyCollaborative Innovation Center of Chemical Science and Engineering(Tianjin)Tianjin UniversityTianjin 300072China

Reactive distillation process,a representative process intensification technology,has been widely applied in the chemical ***,due to the strong interaction between reaction and separation,the extension of reactive distillation technology is restricted by the difficulties in process analysis and *** overcome this problem,the design and optimization of reactive distillation have been widely studied and illustrated for plenty of reactive mixtures over the past three *** design and optimization methods of the reactive distillation process are classified into three categories:graphical,optimization-based,and evolutionary/heuristic *** primary objective of this article is to provide an up-to-date review of the existing design and optimization *** and output information,advantages and limitations of each method are stated,the modification and development for original methodologies are also *** on future research on the design and optimization of reactive distillation method are proposed for further research.

关键词： reactive distillation process intensification design method reactive phase diagram optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Bees algorithm with Integration of Probabilistic Models for Global optimization 3rd

Bees Algorithm with Integration of Probabilistic Models for ...

引用

3rd Symposium on Intelligent Manufacturing and Mechatronics, SympoSIMM 2020

作者： Bahari, Muhammad Syahril Azmi, Nur Athirah Yusof, Zahayu Md Pham, Duc Truong School of Manufacturing Engineering Universiti Malaysia Perlis Arau Perlis Malaysia School of Quantitative Sciences UUM College of Arts and Sciences Universiti Utara Malaysia Sintok Kedah06010 Malaysia School of Mechanical Engineering College of Physical Sciences University of Birmingham Birmingham United Kingdom

ISBN: (纸本)9789811608650

The standard Bees algorithms (SBA) is a population-based search algorithm inspired by the nature that revolves around mimicking the food foraging behavior of honey bees in order to solve optimization problems. This study had implemented the probabilistic method in Estimated Distribution algorithm (EDA) into the SBA to improve the performance of the algorithm in terms of speed and accuracy. The newly proposed algorithm is tested on ten benchmark test functions. Then, the accuracy and speed are compared to SBA. The performance of the algorithm had also been validated on two engineering design optimization problems with specific constraints condition. The results of the benchmark test functions showed that the proposed algorithm provides very competitive results in terms of improved speed and convergence rate. The results of the design engineering optimization problems prove that the proposed algorithm can perform well in solving challenging problems with constrained and unknown search spaces. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Bees algorithm optimization algorithm Probabilistic model

来源：评论

学校读者我要写书评

暂无评论

MATCNN: Infrared and Visible Image Fusion Method Based on Multiscale CNN With Attention Transformer

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Liu, Jingjing Zhang, Li Zeng, Xiaoyang Liu, Wanquan Zhang, Jianhua Shanghai Univ Sch Microelect Shanghai Key Lab Chips & Syst Intelligent Connecte Shanghai 200444 Peoples R China Fudan Univ State Key Lab Integrated Chips & Syst Shanghai 201203 Peoples R China Fudan Univ State Key Lab Integrated Chipsand Syst Shanghai 201203 Peoples R China Sun Yat Sen Univ Sch Intelligent Syst Engn Shenzhen 510006 Peoples R China

While attention-based approaches have shown considerable progress in enhancing image fusion and addressing the challenges posed by long-range feature dependencies, their efficacy in capturing local features is compromised by the lack of diverse receptive field extraction techniques. To overcome the shortcomings of existing fusion methods in extracting multiscale local features and preserving global features, this article proposes a novel cross-modal image fusion approach based on a multiscale convolutional neural network with an attention Transformer (MATCNN). MATCNN utilizes the multiscale fusion module (MSFM) to extract local features at different scales and employs the global feature extraction module (GFEM) to extract global features. Combining the two reduces the loss of detail features and improves the ability of global feature representation. Simultaneously, an information mask is used to label pertinent details within the images, aiming to enhance the proportion of preserving significant information in infrared images and background textures in visible images in fused images. Subsequently, a novel optimization algorithm is developed, leveraging the mask to guide feature extraction through the integration of content, structural similarity index (SSIM) measurement, and global feature loss. Quantitative and qualitative evaluations are conducted across various datasets, revealing that MATCNN effectively highlights infrared salient targets, preserves additional details in visible images, and achieves better fusion results for cross-modal images. The code of MATCNN will be available at https://***/zhang3849/***.

关键词： Global feature extraction module (GFEM) image fusion multiscale convolutional neural network with atten-tion transformer (MATCNN) multiscale convolutional neural network with atten-tion transformer (MATCNN) multiscale fusion module (MSFM) optimization algorithm optimization algorithm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Artificial ecosystem-based optimization: a novel nature-inspired meta-heuristic algorithm

引用

NEURAL COMPUTING & APPLICATIONS 2020年第13期32卷 9383-9425页

作者： Zhao, Weiguo Wang, Liying Zhang, Zhenxing Hebei Univ Engn Sch Water Conservancy & Hydropower Handan 056021 Hebei Peoples R China Univ Illinois Prairie Res Inst Illinois State Water Survey Champaign IL 61820 USA

A novel nature-inspired meta-heuristic optimization algorithm, named artificial ecosystem-based optimization (AEO), is presented in this paper. AEO is a population-based optimizer motivated from the flow of energy in an ecosystem on the earth, and this algorithm mimics three unique behaviors of living organisms, including production, consumption, and decomposition. AEO is tested on thirty-one mathematical benchmark functions and eight real-world engineering design problems. The overall comparisons suggest that the optimization performance of AEO outperforms that of other state-of-the-art counterparts. Especially for real-world engineering problems, AEO is more competitive than other reported methods in terms of both convergence rate and computational efforts. The applications of AEO to the field of identification of hydrogeological parameters are also considered in this study to further evaluate its effectiveness in practice, demonstrating its potential in tackling challenging problems with difficulty and unknown search space. The codes are available at.

关键词： Artificial ecosystem-based optimization Global optimization Constrained problems optimization algorithm Engineering design Hydrogeological parameter

来源：评论

学校读者我要写书评

暂无评论

Certified interval model updating using scenario optimization

Certified interval model updating using scenario optimizatio...

引用

AIAA SciTech Forum

作者： Callens, Robin R. P. Moens, David Faes, Matthias G. R. Katholieke Univ Leuven Dept Mech Engn Div LMSD B-2860 St Katelijne Waver Belgium TU Dortmund Univ Chair Reliabil Engn Dept Mech Engn D-44227 Dortmund Germany

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

Interval model updating is typically performed when gathering data is expensive, time-consuming, or complex and only a limited amount of data is available to perform non-deterministic model updating. In these situations, the fitted intervals will only provide an estimate of the exact interval bounds. This is because the limited data available is unlikely to include any samples that fall precisely on the interval boundaries. In these situations, an analyst could use a metric to assess the accuracy of identified model uncertainties against unseen missing data. Furthermore, when this metric is able to estimate the required amount of data for accurate uncertainty quantification, data-gathering efforts are minimized. This paper defines this metric as the reliability of a data-enclosing set as the probability that future unseen data will fall within the set. Recently, Crespo et al. [1] presented a scenario optimization approach to determine a lower bound for this reliability without having to characterize the underlying distribution of the data generation mechanism. To calculate the reliability, the scenario optimization approach needs the number of hyper-parameters to fit the data enclosing set, the number of samples, and the dimension of the data enclosing set. Once these are obtained, and a confidence level is determined, the approach calculates the lower bound of the reliability. Additionally, analysts can calculate the number of samples required to fit the data enclosing set with predefined lower bound reliability before the measurement campaign. The goals of this paper are to develop the certified interval model updating based on scenario optimization and to apply this to a dynamical modal analysis of a structural finite element model. A four-level building numerical model is used to illustrate the accuracy and the practical application of the developed methodologies.

关键词： Uncertainty Quantification Modal Analysis Structural Finite Elements Convex optimization optimization algorithm Surface 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：