检索结果-内蒙古大学图书馆

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 Huazhong Univ Sci & Technol HUST Sch Environm Sci & Engn Wuhan 430074 Hubei Peoples R China Hubei Key Lab Multimedia Pollut Cooperat Control Y Wuhan 430074 Hubei Peoples R China Engn Lab Solid Waste Treatment Disposal & Recyclin Wuhan 430074 Hubei Peoples R China State Key Lab Coal Combust Wuhan 430074 Hubei Peoples R 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.

关键词： Ecological cement Industrial solid waste Backpropagation neural networks 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

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

Physical properties optimization of nerve guidance conduits utilizing genetic algorithm: A CFD analysis

引用

RESULTS IN ENGINEERING 2024年 21卷

作者： Nazarrashidi, Kiarash Rassoli, Aisa Sharbatdar, Mahkame KN Toosi Univ Technol Dept Mech Engn Tehran Iran

Nerve guidance conduits, or NGCs, used as structures in tissue engineering, play an important role in reconstruction and the growth of axons after nerve injuries. To produce an appropriate scaffold for nerve growth and transfer the suitable amount of growth factors, these channels should be designed and built with topological, mechanical, and biological properties and functional mass transfer requirements. This study deals with a computational design approach of a nerve guidance conduit which, after validating the geometry, simulates the blood flow utilizing the Carreau-Yasuda model and optimizes physical properties. The physical properties are hydraulic pressure, porosity, diffusivity and water absorption. The optimization process consists of three distinct steps: initially, a single objective function is implemented using a genetic algorithm (GA) to determine the optimal hydraulic pressure for the nerve guidance conduit, resulting in a final value of 0.039 Pa. Subsequently, the GA is employed again to optimize porosity, leading to a final value of 0.6473. Finally, a multi-objective function is utilized to consider porosity, diffusivity, and water absorption, simultaneously.

关键词： Nerve guidance conduit Nerve injury CFD Optimization non-Newtonian model genetic algorithm non-dominated sorting genetic algorithm ii

来源：评论

学校读者我要写书评

暂无评论

Multi-mode resource-constrained project scheduling problem along with material ordering under time-of-use electricity tariffs and carbon taxes

引用

ANNALS OF OPERATIONS RESEARCH 2024年 1-45页

作者： Pouramin, Maryam Mirzazadeh, Abolfazl Davari-Ardakani, Hamed Mosadegh, Hadi Alajegerdi, Edris Kharazmi Univ Fac Engn Dept Ind Engn Tehran Iran Amirkabir Univ Technol Dept Ind Engn & Management Syst Tehran Iran Univ Neyshabur Fac Sci Dept Phys Neyshabur Iran

The research highlights the potential of integrating energy management and the Multi-Mode Resource-Constrained Project Scheduling Problem, which includes material ordering. It addresses the pressing concerns of escalating electricity consumption and greenhouse gas emissions by considering renewable energy resources, time-of-use (TOU) electricity tariffs, and carbon taxes. In this regard, a mixed integer linear programming model is developed. To solve the small-sized problem instances, epsilon-constraint method is used. However, since the problem under consideration is NP-hard and exact methods fail to provide solutions for large-sized instances within a reasonable timeframe, two multi-objective meta-heuristic algorithms, non-dominated sorting genetic algorithm ii (NSGA-ii) and Multi-Objective Particle Swarm Optimization (MOPSO), are used as solution methods. Comparing results obtained by NSGA-ii and MOPSO demonstrates the superiority of NSGA-ii in the majority of performance metrics, regardless of the problem size. Through comprehensive sensitivity analysis of key model parameters, including TOU electricity tariffs and carbon tax rates, the research determines the optimal project duration and cost. Sensitivity analyses offer insights for sustainable project planning, highlighting the role of renewables in electricity consumption. Minimizing carbon taxes and proactive resource management underscore environmental responsibility, while TOU tariffs enhance sustainable energy practices. Overall, strategically integrating renewables in certain scenarios optimizes project execution, aligning with sustainability objectives for efficient and successful outcomes.

关键词： Multi-mode resource constrained project scheduling problem Material ordering Electricity cost Carbon dioxide emission non-dominated sorting genetic algorithm ii Multi-objective particle swarm optimization algorithm

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

Crushing stress and vibration fatigue-life optimization of a battery-pack system

引用

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION 2023年第3期66卷 1-16页

作者： Zhang, Xiaoxi Xiong, Yue Pan, Yongjun Du, Haifeng Liu, Binghe Chongqing Univ Coll Mech & Vehicle Engn Chongqing 400044 Peoples R China China Automot Engn Res Inst Chongqing 401122 Peoples R China

The mechanical failure of battery-pack systems (BPSs) under crush and vibration conditions is a crucial research topic in automotive engineering. Most studies evaluate the mechanical properties of BPSs under a single operating condition. In this study, a dual-objective optimization method based on non-dominated sorting genetic algorithm ii (NSGA-ii) is proposed to evaluate the crushing stress of BPS modules and the vibration fatigue life of the BPS. This method can obtain better combinations of the thicknesses of the BPS components, which helps engineers achieve robust and efficient designs. First, a nonlinear finite element (FE) model of a BPS is developed and experimentally verified. The crush and vibration simulations are performed, and the FE analysis data are obtained. Second, two third-order response surface models are created to characterize the relationship between the input (thicknesses of the BPS components) and the output (crushing stress of the BPS modules and vibration fatigue life of the BPS). Finally, a linear weighting model and an NSGA-ii model are used to conduct dual-objective optimization. The solution of the linear weighting method and the non-dominated Pareto solution set of the thicknesses of the BPS components are obtained and compared. Furthermore, a reasonable interval in the Pareto frontier is defined and considered the best solution to the dual-objective optimization problem. Therefore, the reliability of the BPS is improved to ensure the safety of electric vehicles in crushing and vibration environments. This method offers an effective solution to the problem of evaluating the mechanical responses of BPSs under various operating conditions. It can be used to generate a robust design for safe and durable BPSs.

关键词： Battery-pack system Crushing stress Vibration fatigue life Third-order response surface model 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

Multi-objective Approach for iiR Filter Design and Bit-Width Optimization

引用

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2023年第8期42卷 4836-4867页

作者： Zelmat, Mohammed Lamini, El-Sedik Tagzout, Samir Belbachir, Hacene Belouchrani, Adel USTHB Fac Math RECITS Lab Algiers Algeria Res Ctr Appl Econ Dev Algiers Algeria EPE Proxylan SPA Algiers Algeria CERIST Res Ctr Sci & Tech Informat Algiers Algeria Ecole Natl Polytech LDCCP lab Algiers Algeria

Digital filter design optimization counts as one of the most challenging problems in circuit development. Furthermore, the bit-width allocation has a crucial impact on the efficiency and accuracy of fixed-point digital filters. The conventional implementation procedure involves studying the bit-width allocation problem after determining the filter coefficients. This sequential procedure leads frequently to an excessive bit-width allocation, hence an extra implementation cost. The main contribution of this paper is to propose a new implementation procedure based on the simultaneous handling of both design issues and the bit-width optimization for the infinite impulse response filter. In this study, the problem is formalized by a multi-objective programming technique using the non-dominated sorting genetic algorithm ii. The joint consideration of the two problems offers a better trade-off between design and bit-width allocation. The output of our approach is compared to the results of existing algorithms. Simulation results show that the multi-objective method significantly reduces the implementation cost while ensuring filter stability and an acceptable mean square error (MSE) compared to the existing algorithms.

关键词： Filter design System identification Bit-width optimization Precision analysis non-dominated sorting genetic algorithm ii IC design

来源：评论

学校读者我要写书评

暂无评论

Multi-objective approach for optimized planning of electric vehicle charging stations and distributed energy resources

引用

ELECTRICAL ENGINEERING 2023年第6期105卷 4105页

作者： Ferraz, Rafael S. F. Ferraz, Renato S. F. Medina, Augusto C. Rueda C. Fardin, Jussara F. F. Univ Fed Espirito Santo Postgrad Program Elect Engn Ave Fernando Ferrari BR-29075910 Vitoria ES Brazil

The increasing inclusion of electric vehicles (EVs) in distribution systems is a global trend due to their several advantages, such as increased autonomy and reduced price. However, this growth requires a high investment in electric vehicle charging stations (EVCSs) infrastructure to satisfy the demand. Thus, in this paper, an adequate planning of the EVCSs allocation and sizing is carried out to ensure better power quality indices, in addition to reducing costs related to EVCSs installation and EV users' recharging. Besides the optimal planning of EVCSs, this paper performs the optimal allocation and sizing of distributed energy resources (DERs) in order to mitigate the problem related to voltage levels and power losses. Additionally, a spatial distribution of EVs was performed for the 24 h, considering residential and commercial nodes of a distribution feeder test, from the closeness centrality of graph theory. The non-dominated sorting genetic algorithm ii (NSGA-ii) was applied to obtain the Pareto curve, which made it possible to minimize the objective functions for the IEEE 34-node test feeder. Even with the integration of EV loads, the optimal allocation and sizing of EVCSs and DERs promoted a reduction in voltage deviation and power losses of 11.576% and 56.683%, respectively, in addition to a low variation in the energy costs of 4.447%.

关键词： Distributed energy resource Electric vehicle charging station non-dominated sorting genetic algorithm ii Power quality indices

来源：评论

学校读者我要写书评

暂无评论

Location-inventory-reliability optimisation problem in a multi-objective multi-period three-level supply chain network with stochastic demand

引用

EUROPEAN JOURNAL OF INDUSTRIAL ENGINEERING 2023年第4期17卷 479-528页

作者： Abdi, Farid Farughi, Hiwa Sadeghi, Heibatolah Arkat, Jamal Univ Kurdistan Pasdaran St Sanandaj *** Iran Univ Kurdistan Fac Ind Engn Pasdaran St Sanandaj *** Iran

One of the efficient methods of improving the reliability of factories is allocating appropriate redundant components that play an important role in responding to customers' demands, timely delivery and cost reduction. In this study, the issue of simultaneous optimisation of facility location-inventory-redundancy allocation has been investigated. In this regard, a multiple-period three-level problem has been taken into account. It has been assumed that demand for each retailer is stochastic and follows the normal distribution. In order to deal with the fluctuations of demand, the risk pooling effect has been applied. For this purpose, an integer nonlinear programming model has been proposed to optimise the cost of the supply chain as well as its reliability. Since facility location-inventory and redundancy allocation are categorised as NP-hard problems, non-dominated sorting genetic algorithm (NSGA-ii) and archived multi-objective simulated annealing (AMOSA) algorithms have been developed for solving the aforementioned problem. Finally, their results have been evaluated by using comparison metrics of multi-objective algorithms. [Submitted: 9 September 2021;Accepted: 9 March 2022]

关键词： supply chain management location-inventory model redundancy allocation stochastic demand risk pooling non-dominated sorting genetic algorithm ii NSGA-ii archive multi-objective simulated annealing Taguchi methods

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimization Approach for Allocation of Electric Vehicles Parking Lots and Smart Charging with Distributed Energy Resource

引用

JOURNAL OF CONTROL AUTOMATION AND ELECTRICAL SYSTEMS 2023年第5期34卷 1070-1079页

作者： Ferraz, Rafael S. F. Ferraz, Renato S. F. Rueda-Medina, Augusto C. Fardin, Jussara F. Univ Fed Espirito Santo Postgrad Program Elect Engn Fernando Ferrari BR-29075910 Vitoria ES Brazil

Electric vehicles (EVs) are a promising solution to resolve the greenhouse emission issue as well as the fossil fuels scarcity problem in the future. However, as the number of EVs significantly increases, the excessive charging demand of EV parking lots (EVPLs) in the charging station may incur an instability problem to the electricity network. In this paper, the optimal allocation and sizing of EVPLs were carried out in order to minimize the costs of the EVPLs installation and EV users' distance traveled and recharge. As a consequence, it encourages the participation of vehicle users in a demand response program related to smart charging and time of use tariffs. It is important to mention that the increasing inclusion of EVs negatively affects the voltage level and power losses of the distribution system. Therefore, this paper also performs the optimal allocation and sizing of distributed energy resources (DERs) in order to mitigate these problems. The non-dominated sorting genetic algorithm ii (NSGA-ii) was applied to obtain the Pareto curve, which made it possible to minimize the objective functions for the IEEE 33-node test feeder and 25-node transportation network. Furthermore, it was considered a spatial distribution of EVs for the 24-h from the closeness centrality of graph theory. The optimal planning of EVPLs and DERs promoted a 35%, 23.14% and 34.11% reduction of the travel distance, voltage deviation and power losses, respectively.

关键词： Charging scheduling Distributed energy resource Electric vehicle parking lot 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：