检索结果-内蒙古大学图书馆

Physical-based surrogate model and its application in 3D-1D fusion optimization of a marine two-stroke engine

APPLIED THERMAL ENGINEERING 2025年 271卷

作者： Han, Xiao Liu, Long Xia, Qian Liu, Dai Tian, Jianyi Harbin Engn Univ Coll Power & Energy Engn Harbin 150001 Peoples R China China Shipbldg Power Engn Inst Co Ltd Shanghai 200129 Peoples R China Ningbo Geely Royal Engine Parts Co Ltd Ningbo 315000 Peoples R China

Marine two-stroke low-speed engines face challenges of complex experimentation and high computational costs, making 1D-3D integrated simulation optimization using surrogate models combined with optimization algorithms a potential solution. However, existing surrogate models suffer from issues such as high data dependency and low interpretability. To address this, this study develops simplified physical-based surrogate models, including a scavenging multi-stage model, a scavenging swirl model, and a swirl mixing controlled combustion (SMCC) surrogate model, calibrated via genetic algorithm (GA). Validation against experimental data shows errors within 5%. These models are coupled to enable full-cycle performance simulation. Subsequent multiobjective optimization using non-dominated sorting genetic algorithm ii (NSGA-ii) reduces maximum pressure (Pmax) and maximum pressure rise rate (dPmax) by 3.23% and 2.06%, respectively, while improving Brake Thermal Efficiency (BTE) by 1.1%. The optimized surrogate model maintains consistency with CFD results, with errors within 5%, but requires significantly less computational time than traditional CFD-based optimization. Therefore, physical-based simplified surrogate models integrated with optimization algorithms provide an effective approach for system-level simulation and multi-objective optimization of marine two-stroke low-speed engines.

关键词： Marine two-stroke low-speed engines 1D-3D fusion optimization Simplified physical-based model non-dominated sorting genetic algorithm ii (NSGA-ii)

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization algorithms for freight allocation in a food grain supply chain

引用

APPLIED SOFT COMPUTING 2025年 171卷

作者： Anoop, K. P. Panicker, Vinay V. Siby, Jerin Aryadutt, C. S. Natl Inst Technol Calicut Dept Mech Engn Supply Chain & Syst Simulat Lab Kozhikode 673601 India

This article addresses multi-objective optimization of a freight allocation problem and presents the case of a food grain organization in India (FOI). The inventory and warehouse parameters that are relevant in the regional level allocation of food grains (using freight trains) are represented using three penalty factors, namely rake penalty factor, capacity utilization penalty factor, and weekly penalty factor. The article formulates a tri-objective optimization model to minimize each of the three penalty factors. Two customized multi-objective optimization algorithms are developed based on Multi-Objective Simulated Annealing (MOSA) and Elitist non-dominated sorting genetic algorithm ii (NSGA ii) to solve the formulated model. The algorithms are tested and validated via computational experiments designed using historical data collected from the FOI. The algorithms help the transportation managers at the FOI to generate improved and balanced transportation plans (with respect to the three objectives) in a quick time. Further, the performance of the algorithms is compared based on seven different performance metrics reported in literature. The MOSA-based algorithm performs equally or better than the NSGA ii-based algorithm with respect to four performance metrics.

关键词： Food grain supply chain Multi-objective optimization Freight allocation Multi-objective simulated annealing non-dominated sorting genetic algorithm ii

来源：评论

学校读者我要写书评

暂无评论

Model-agnostic local explanation: Multi-objective genetic algorithm explainer

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 139卷

作者： Nematzadeh, Hossein Garcia-Nieto, Jose Hurtado, Sandro Aldana-Montes, Jose F. Navas-Delgado, Ismael Univ Malaga ITIS Software Arquitecto Francisco Penalosa 18 Malaga 29071 Spain Univ Malaga Dept Lenguajes & Ciencias Comp Malaga Spain

Late detection of plant diseases leads to irreparable losses for farmers, threatening global food security, economic stability, and environmental sustainability. This research introduces the Multi-Objective genetic algorithm Explainer (MOGAE), a novel model-agnostic local explainer for image data aimed at the early detection of citrus diseases. MOGAE enhances eXplainable Artificial Intelligence (XAI) by leveraging the non-dominated sorting genetic algorithm ii (NSGA-ii) with an adaptive Bit Flip Mutation (BFM) incorporating densify and sparsify operators to adjust superpixel granularity automatically. This innovative approach simplifies the explanation process by eliminating several critical hyperparameters required by traditional methods like Local Interpretable Model-Agnostic Explanations (LIME). To develop the citrus disease classification model, we preprocess the leaf dataset through stratified data splitting, oversampling, and augmentation techniques, then fine-tuning a pre-trained Residual Network 50 layers (ResNet50) model. MOGAE's effectiveness is demonstrated through comparative analyses with the Ensemble-based genetic algorithm Explainer (EGAE) and LIME, showing superior accuracy and interpretability using criteria such as numeric accuracy of explanation and Number of Function Evaluations (NFE). We assess accuracy both intuitively and numerically by measuring the Euclidean distance between expert-provided explanations and those generated by the explainer. The appendix also includes an extensive evaluation of MOGAE on the melanoma dataset, highlighting its versatility and robustness in other domains. The related implementation code for the fine-tuned ResNet50 and MOGAE is available at https://***/KhaosResearch/Plant-disease-explanation.

关键词： Citrus diseases Multi-objective genetic algorithm explainer non-dominated sorting genetic algorithm ii Residual network 50 layers Local Interpretable Model-agnostic Explanations Melanoma detection

来源：评论

学校读者我要写书评

暂无评论

A bi-objective optimisation model for the drone scheduling problem in island delivery

引用

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH 2025年

作者： Yang, Ying Liu, Jiaxin Wang, Shuaian Hong Kong Polytech Univ Dept Logist & Maritime Studies Kowloon Hong Kong 999077 Peoples R China Tsinghua Univ Shenzhen Int Grad Sch Dept Logist & Transportat Shenzhen Peoples R China

Drone-assisted parcel delivery to remote islands is increasingly replacing traditional methods, offering improved efficiency and enhanced service reliability. This paper addresses the drone scheduling problem in island delivery (DSP-ID) by optimising drone delivery routes. In particular, we first introduce a bi-objective mixed-integer linear programming model that concurrently optimises delivery time and energy consumption. To address the model, both a heuristic non-dominated sorting genetic algorithm ii (NSGA-ii) and an exact augmented epsilon-constraint method are developed. The efficacy and robustness of the proposed model and algorithms are evaluated through experiments across various scales. Results indicate that both algorithms yield high-quality solutions for DSP-ID in small-scale scenarios. However, as the problem size expands, the performance of the augmented epsilon-constraint method wanes under time constraints, whereas the NSGA-ii consistently delivers high-quality solutions. Additionally, we provide decision-makers with actionable insights for selecting the most effective drone delivery routes.

关键词： Island delivery drone scheduling problem bi-objective optimisation model energy consumption non-dominated sorting genetic algorithm ii augmented epsilon-constraint

来源：评论

学校读者我要写书评

暂无评论

The heating effect analysis of electromagnetic induction heating system based on the multi objective optimization strategy

引用

JOURNAL OF ENERGY STORAGE 2025年 105卷

作者： Wang, Borui Yan, Mingyin Shenyang Univ Technol Sch Mech Engn Shenyang 110000 Peoples R China

Lithium-ion battery heating in cold weather is necessary to ensure its low-temperature performance and lifetime, so the multi objective optimization heating strategy based on the non-dominated sorting genetic algorithm ii is introduced to improve the heating effect of electromagnetic induction heating system, in which the generated Pareto frontier as the research sample is input in K-medoid algorithm in order to reduce the feasible range of solution sets and then get the optimal induction coil parameters combination, and the temperature rise and terminal voltage output performance of battery are characterized by the electrochemical-thermal coupling model. Firstly, under the optimal parameters combination (N = 180, f = 9 kHZ, IA = 6 A), the battery can be heated from 243.15 K to 293.15 K in 1430 s with the temperature difference of 2.74 K, and the temperature field is mainly generated by the heat conduction from active material to mandrel during the heating process due to skin effect and material property. Secondly, the internal resistance is decreased by more than 3 times after the heating, giving rise to the substantial improvement of energy output ability. Finally, neither noticeable discharging capacity retention loss nor apparent voltage output difference is founded after the 200 repeated heating cycles, as compared with the normal charging-discharging cycle at 293.15 K, so the heating strategy has almost no effect on the battery aging and lifetime deterioration. Therefore, the proposed heating strategy can realize a suitable tradeoff among temperature-rising effect, lifespan and low-temperature operating performance, which has substantial potential to be a feasible method for improving the applicability of electric vehicles in a cold weather.

关键词： Multi objective optimization non-dominated sorting genetic algorithm ii Electromagnetic induction heating system Electrochemical-thermal coupling model Optimal parameters combination

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic approach to multi-objective ergonomic workforce scheduling for Bi-hazard industrial tasks

引用

INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE AND ENGINEERING MANAGEMENT 2025年第1期20卷 32-41页

作者： Rattanamanee, Tarit Nanthavanij, Suebsak King Mongkuts Univ Technol North Bangkok Fac Engn Dept Mat Handling & Logist Engn Bangkok 10800 Thailand Log Plus Min & Serv Co Ltd Suksawad Rd Phra Pradaeng Sumut Prakarn Thailand

This paper considers the daily scheduling of workers who are simultaneously exposed to two ergonomic hazards when performing their assigned tasks. Safe daily rotating work schedules are generated to minimize the maximum exposure amounts of both hazards simultaneously. A non-dominated sorting genetic algorithm ii (NSGA-ii) method is employed to generate near-optimal workforce scheduling solutions. A numerical example shows that for a small multi-objective problem, the NSGA-ii is able to yield the same set of non-dominated Pareto points as those obtained from a multi-objective optimization model with epsilon-constraint method. A computational experiment further demonstrates that the NSGA-ii can yield acceptable non-dominated Pareto points in reasonable computation times irrespective of the problem size.

关键词： Workforce scheduling problem ergonomic hazard reduction multi-objective optimization non-dominated sorting genetic algorithm ii

来源：评论

学校读者我要写书评

暂无评论

Capacity allocation optimization for integrated energy system with P2G and CCS

Capacity allocation optimization for integrated energy syste...

引用

2024 International Conference on Energy Technology and Electrical Power, ETEP 2024

作者： Mu, Hailin Jiang, Chengwei Wang, Hongye School of Energy and Power Engineering Dalian University of Technology Dalian 116024 China

ISBN: (纸本)9781510690400

Integrated energy system (IES) offer multiple effective pathways to promote renewable energy utilization and carbon emission reduction. To further optimize the utilization rate of renewable energy and cut carbon emissions, this paper proposes an IES coupled with power-to-gas (P2G) and carbon capture system (CCS). It optimizes the system's capacity by comprehensively considering the total cost savings rate, primary energy reduction rate, and carbon dioxide emission reduction rate. The problem is solved using the non-dominated sorting genetic algorithm ii (NSGA-ii) and the technique for order of preference by similarity to ideal solution (TOPSIS). The research results indicate that, compared to other conventional models, the proposed method enhances renewable energy utilization, reduces carbon emissions and operational costs, and exhibits superior overall performance. © 2025 SPIE.

关键词： capacity optimization Integrated energy system non-dominated sorting genetic algorithm ii Renewable energy

来源：评论

学校读者我要写书评

暂无评论

Optimization of industrial waste composition for eco-cement production using machine learning with meta-heuristic method

引用

Resources, Conservation and Recycling 2025年 220卷

作者： Luo, Wei Liu, Longming Hu, Jingping Hou, Huijie Hu, Hongyun Yang, Jiakuan Hubei Wuhan430074 China Hubei Key Laboratory of Multi-media Pollution Cooperative Control in Yangtze Basin Hubei Wuhan430074 China Engineering Laboratory of Solid Waste Treatment Disposal and Recycling Hubei Wuhan430074 China State Key Laboratory of Coal Combustion Hubei Wuhan430074 China

Industrial solid waste utilization in ecological cement production reduces carbon emissions and resource consumption. However, waste composition variability challenges product consistency, hindering widespread implementation. This study presents a novel artificial intelligence driven optimization framework that combines triple back-propagation neural network (BPNN), non-dominated sorting genetic algorithm-ii (NSGA-ii) and super-efficiency data envelopment analysis (SE-DEA), to optimize raw material proportions. The triple BPNN architecture, which separately models raw meal grinding, clinker calcination, and clinker homogenization, demonstrates superior prediction accuracy. By integrating SE-DEA within NSGA-ii, the algorithm achieves balanced optimization across multiple performance metrics. Cement produced using this optimization framework demonstrates improved long-term mechanical properties, with 28-day compressive strength ranking in the top 4.11 % and 28-day flexural strength in the top 7.41 % of the historical production data from the same facility. The proposed framework exhibits significant potential for the development and promotion of ecological cement technology while promoting industrial waste utilization at large scale. © 2025 Elsevier B.V.

关键词： Backpropagation neural networks Ecological cement Industrial solid waste non-dominated sorting genetic algorithm ii Super-efficiency data envelopment analysis

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for Wind Speed Forecasting: A Review on Multi-Scale Decomposition and Intelligent Fusion Strategies

Advances in Wind Engineering

引用

Advances in Wind Engineering 2025年

作者： Hui Liu Rui Yang Institute of Artificial Intelligence and Robotics (IAIR) Key Laboratory of Traffic Safety on Track of Ministry of Education School of Traffic and Transportation Engineering Central South University Changsha 410075 Hunan China

Accurate and reliable short-term wind speed forecasting is essential for the effective utilization and scientific dispatch of wind energy. In recent years, with the rapid development of Artificial Intelligence (AI) technology, the capabilities of prediction models have been significantly improved. However, there are still many challenges in dealing with non-stationary signals, coordinating multi-objective conflicts, and enhancing model robustness. This paper reviews the three core links in wind speed forecasting: multi-scale signal decomposition, hybrid modeling framework, and multi-objective optimization algorithm. First, this paper systematically summarizes common signal decomposition methods, including Empirical Mode Decomposition (EMD), Variational Mode Decomposition (VMD), and wavelet transform-based techniques, and analyzes the characteristics of these methods in terms of frequency resolution, adaptability, and model ensemble capabilities. Secondly, from the perspective of structural form and functional complementarity, this paper explores how to combine shallow models, deep neural networks, and ensemble strategies to build an efficient hybrid prediction model. Finally, a variety of Multi-Objective Optimization (MOO) algorithms are evaluated, such as the non-dominated sorting genetic algorithm ii (NSGA-ii), the Multi-Objective Particle Swarm Optimization algorithm (MOPSO), and the Strength Pareto Evolutionary algorithm ii (SPEA-ii). Their potential in model architecture adjustment, fusion strategy design, and balancing prediction accuracy, stability, and computational efficiency is analyzed. This paper comprehensively evaluates related studies according to the "decomposition-prediction-optimization" process. At the same time, it emphasizes the importance of developing a wind speed prediction system that is robust, interpretable, and easy to deploy. This study provides a unified perspective and reference framework for building intelligent and goal-oriented wind

关键词： ADMM Alternating Direction Method of Multipliers AI Artificial Intelligence ANN Artificial Neural Networks AutoML Automated Machine Learning AVMD Adaptive Variational Mode Decomposition BEMD Bivariate or Complex Empirical Mode Decomposition CEEMD Complementary versions such as Complete Ensemble Empirical Mode Decomposition CEEMDAN Complete Ensemble Empirical Mode Decomposition with Adaptive Noise CFD Computational Fluid Dynamics CNN Convolutional Neural Networks CWT Continuous Wavelet Transform DFT Discrete Fourier Transform DRL Deep Reinforcement Learning ECMWF European Centre for Medium-Range Weather Forecasts EEMD Ensemble Empirical Mode Decomposition ELM Extreme Learning Machines EMD Empirical Mode Decomposition ESN Echo State Network FFT Fast Fourier Transform GDE3 Generalized Differential Evolution 3 GNNs Graph Neural Networks GRU Gated Recurrent Unit LES Large Eddy Simulation IMFs Intrinsic Mode Functions LightGBM Light Gradient Boosting Machine LSTM Long Short-Term Memory MAE Mean Absolute Error MEMD Multivariate Empirical Mode Decomposition MODWT Maximal Overlap Discrete Wavelet Transform ε -MOEA Epsilon Multi-Objective Evolutionary algorithm MOEA/D Multi-Objective Evolutionary algorithm based on Decomposition MOO Multi-Objective Optimization MOPSO Multiple Objective Particle Swarm Optimization MRVMD Multi-resolution Variational Mode Decomposition MVMD Multivariate Variational Mode Decomposition NSGA-ii non-dominated sorting genetic algorithm ii NWP Numerical Weather Prediction PAES Pareto Archived Evolution Strategy PINNs Physics-Informed Neural Networks RANS Reynolds-Averaged Navier–Stokes RL Reinforcement Learning RMSE Root Mean Square Error SPEA-ii Strength Pareto Evolutionary algorithm ii SSA Singular Spectrum Analysis SVD Singular Value Decomposition SVM Support Vector Machines SVR Support Vector Regression VMD Variational Mode Decomposition WD, Wav elet Decomposition WRF Weather Research and Forecasting WT Wavelet Transform XGBoost eXtreme Gradient Boosting Artificial Intelligence Wind speed forec

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization of proton exchange membrane fuel cells by RSM and NSGA-ii

引用

ENERGY CONVERSION AND MANAGEMENT 2023年第1期277卷

作者： Chen, Zhijie Zuo, Wei Zhou, Kun Li, Qingqing Huang, Yuhan Jiaqiang, E. Wuhan Univ Sci & Technol State Key Lab Refractories & Met Wuhan 430081 Peoples R China Univ Technol Sydney Ctr Green Technol Sch Civil & Environm Engn Sydney NSW 2007 Australia Hunan Univ Coll Mech & Vehicle Engn Changsha 410082 Peoples R China Wuhan Univ Sci & Technol Natl Prov Joint Engn Res Ctr High Temp Mat & Linin Wuhan 430081 Peoples R China

This study optimized the performance of a proton exchange membrane fuel cell by combining the response surface methodology and non-dominated ranking genetic algorithm. Firstly, the design variables are determined, including operating pressure (p), operating temperature (T), Anode stoichiometry ratio (lambda(a)), thickness of the proton exchange membrane (H-mem) and gas diffusion layer (GDL) porosity (epsilon(GDL)). The objective functions are also identified, including power density (P), system efficiency (eta) and exergy efficiency. Then, the Box-Behnken design is employed to arrange the numerical investigations. Analysis of variance is used to verify the appropriateness and reliability of the constructed regression models. Response surface analysis is used to show the interaction between each pair of design parameters. Finally, the Pareto optimal frontier is obtained by non-dominated ranking genetic algorithm ii and the regression models constructed by response surface methodology. The Pareto optimal solution offers a power density of 0.6327 W center dot cm(-2), a system efficiency of 26.16% and an exergy efficiency of 43.94 %, which is 13.18 %, 7.06 % and 20.29 % better than the initial direct current channel, respectively. The corresponding design variables is p = 2.6498 atm, T = 341.621 K, lambda(a) = 1.1808, H-mem = 0.0577 mm and epsilon(GDL) = 0.4908. This work provides a new multi-objective optimization method for designing more efficient proton exchange membrane fuel cells.

关键词： Proton exchange membrane fuel cell Multi-objective optimization Response surface methodology non-dominated sorting genetic algorithm ii

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：