检索结果-内蒙古大学图书馆

A new fractional Abel polynomials neural network method for nonlinear models of heat transfer

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER 2025年 162卷

作者： Hassani, Hossein Avazzadeh, Zakieh Turan-Dincel, Arzu Katani, Roghayeh Anand Int Coll Engn Dept Math Jaipur 303012 Rajasthan India Anhui Univ Stony Brook Inst Hefei 230601 Anhui Peoples R China Yildiz Tech Univ Dept Math Engn TR-34220 Istanbul Turkiye Univ Yasuj Fac Sci Yasuj Iran Univ South Africa Dept Math Sci Florida South Africa

Nowadays, the study and advancements in neural networks and optimization techniques are the most interesting research topics. This progress has empowered researchers to address more intricate and realistic challenges associated with nonlinear models. This research presents a new approach called the fractional Abel polynomials neural network (FAPNN) for solving nonlinear heat transfer models. The mentioned NN consists of three layers (input layer, hidden layer, output layer). Fractional Abel and arcsinh(t) functions have been used as activation functions in the hidden and output layers, respectively, to construct the FAPNN. To mitigate storage and computational costs, new operational matrices (OMs) are devised. Based on FAPNN and OMs for fractional Abel polynomials, a series solution is achieved for the nonlinear heat transfer models. The Lagrange multipliers method is adopted so that the nonlinear heat transfer models can be transformed into a class of nonlinear algebraic system of equations and we solve these equations using Matlab and Maple software. Ultimately, four sets of numerical examples are provided along with comparisons from the literature such as the variational iteration, homotopy perturbation, differential transformation, and Chebyshev wavelets methods, to confirm the effectiveness of the suggested FAPNN approach. Experimental results demonstrate the effectiveness of our proposed method.

关键词： Fractional Abel polynomials neural network Optimal solutions Nonlinear models of heat transfer optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Tight Constraint Prediction for Efficient Powered Descent Guidance

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2025年第5期48卷 1054-1070页

作者： Briden, Julia Gurga, Trey Johnson, Breanna Cauligi, Abhishek Linares, Richard MIT Dept Aeronaut & Astronaut 125 Massachusetts Ave Cambridge MA 02139 USA NASA Johnson Space Ctr Flight Mech & Trajectory Design Branch EG52101 E NASA Pkwy Houston TX 77058 USA CALTECH Jet Prop Lab Pasadena CA 91109 USA

In this work, we present transformer-based powered descent guidance (T-PDG), a scalable algorithm for reducing the computational complexity of the direct optimization formulation of the spacecraft powered descent guidance problem. T-PDG uses data from prior runs of trajectory optimization algorithms to train a transformer neural network, which accurately predicts the relationship between problem parameters and the globally optimal solution for the powered descent guidance problem. The solution is encoded as the set of tight constraints corresponding to the constrained minimum-cost trajectory and the optimal final landing time. By leveraging the attention mechanism of transformer neural networks, large sequences of time series data can be accurately predicted when given only the spacecraft state and landing site parameters. When applied to the real problem of Mars-powered descent guidance, T-PDG reduces the time for computing the 3-degree-of-freedom fuel-optimal trajectory when compared to lossless convexification, improving solution times by up to an order of magnitude. A safe and optimal solution is guaranteed by including a feasibility check in T-PDG before returning the final trajectory.

关键词： Electric Power Conversion Powered Descent Initiation Convolutional Neural Network Pontryagin's Minimum Principle Planets Computing and Informatics Proportional Integral Derivative Structural Kinematics and Dynamics Numerical Interpolation optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Vortex-Induced Vibration Performance Prediction of Double-Deck Steel Truss Bridge Based on Improved Machine Learning algorithm

引用

JOURNAL OF MARINE SCIENCE AND ENGINEERING 2025年第4期13卷 767-767页

作者： Yang, Yang Hou, Huiwen Yao, Gang Wu, Bo Chongqing Univ Sch Civil Engn Key Lab New Technol Construct Cities Mt Area Chongqing 400045 Peoples R China Chongqing Jiaotong Univ Sch Civil Engn Chongqing 400074 Peoples R China

The span of a double-deck cross-sea bridge that can be used for both highway and railway purposes is usually 1 to 16 km. Compared with small-span bridges and single-layer main girder forms, its lightweight design and low damping characteristics make it more prone to vortex-induced vibration (VIV). To predict the VIV performance of a double-deck steel truss (DDST) girder with additional aerodynamic measures, the VIV response of a DDST bridge was investigated using wind tunnel tests and numerical simulation, a learning sample database was established with numerical simulation results, and a prediction model for the amplitude of the DDST girder and VIV parameters was established based on three machine learning algorithms. The optimization algorithm was selected using root mean square error (RMSE) and the coefficient of determination (R2) as evaluation indices and further improved with a genetic algorithm and particle swarm optimization. The results show that for the amplitude prediction of the main girder, the backpropagation neural network model is the most effective. The most improved algorithm yields an RMSE of 0.150 and an R2 of 0.9898. For the prediction of VIV parameters, the Random Forest model is the most effective. The RMSE values of the improved optimal algorithm are 0.017, 0.026, and 0.295, and the R2 values are 0.9421, 0.8875, and 0.9462. The prediction model is more efficient in terms of computational efficiency compared to the numerical simulation method.

关键词： vortex-induced vibration machine learning optimization algorithm additional aerodynamic measures double-deck steel truss girder prediction model

来源：评论

学校读者我要写书评

暂无评论

Multiphase Iterative algorithm for Mixed-Integer Optimal Control

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2025年第4期48卷 757-770页

作者： Pei, Chaoying You, Sixiong Di, Yu Dai, Ran Purdue Univ W Lafayette IN 47907 USA Missouri Univ Sci & Technol Dept Mech & Aerosp Engn Rolla MO 65409 USA Purdue Univ Sch Aeronaut & Astronaut W Lafayette IN 47907 USA Purdue Univ Dept Stat W Lafayette IN 47907 USA

Mixed-integer optimal control problems (MIOCPs) frequently arise in the domain of optimal control problems (OCPs) when decisions including integer variables are involved. However, existing state-of-the-art approaches for solving MIOCPs are often plagued by drawbacks such as high computational costs, low precision, and compromised optimality. In this study, we propose a novel multiphase scheme coupled with an iterative second-order cone programming (SOCP) algorithm to efficiently and effectively address these challenges in MIOCPs. In the first phase, we relax the discrete decision constraints and account for the terminal state constraints and certain path constraints by introducing them as penalty terms in the objective function. After formulating the problem as a quadratically constrained quadratic programming (QCQP) problem, we propose the iterative SOCP algorithm to solve general QCQPs. In the second phase, we reintroduce the discrete decision constraints to generate the final solution. We substantiate the efficacy of our proposed multiphase scheme and iterative SOCP algorithm through successful application to two practical MIOCPs in planetary exploration missions.

关键词： optimization algorithm Powered Descent Guidance Mixed Integer Optimal Control Quadratically Constrained Quadratic Programming

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective optimization for Curvilinearly Stiffened Porous Sandwich Plates Reinforced with Graphene Nanoplatelets

引用

AIAA JOURNAL 2022年第12期60卷 6825-6841页

作者： Xiao, Yushan Wu, Zhen Zhang, Xinyu Ren, Xiaohui Northwestern Polytech Univ Sch Aeronaut Xian 710072 Peoples R China Xian Aeronaut Univ Sch Mech Engn Xian 710065 Peoples R China

With the development of innovative manufacturing technology, multi-objective optimization algorithms for optimal design of advanced composite structures have gained increasing attention. An effective and high-accurate prediction on the mechanical behavior of structures is the basic core of optimization algorithms. Thus, a novel refined sinusoidal higher-order theory (NRSHT) combined with isogeometric analysis (IGA) is developed as the high-precision solver. A novel curvilinearly stiffened porous sandwich plate reinforced with graphene nanoplatelets (CSP-GPL) is proposed as the research object. Compared with previous higher-order theories, the proposed NRSHT can more accurately forecast the natural frequencies of CSP-GPL through several numerical and experimental tests. Subsequently, the shape and material distribution design of CSP-GPL are studied with multi-objective optimization. The random forest regression (RFR) is utilized as the high-fidelity surrogate model to construct the objective function in the improved Nondominated Sorting Genetic algorithm (NSGA-II), which can significantly accelerate the integration of NRSHT-IGA and NSGA-II. Finally, the Pareto-optimal solutions, optimizing for fundamental frequency and total mass of CSP-GPL, are obtained from the present platform, which can give effective suggestions for the future designer to meet specific requirements.

关键词： Finite Element Analysis optimization algorithm Surrogate Model Composite Structures Genetic algorithm Mechanical Properties Nonlinear Vibrations Dynamic Response Abaqus Computer Aided Engineering

来源：评论

学校读者我要写书评

暂无评论

Deep Belief-MobileNet1D: A novel deep learning approach for anomaly detection in industrial big data

引用

INTERNET OF THINGS 2025年 31卷

作者： Chen, Tzu-Chia Tamkang Univ Dept Artificial Intelligence New Taipei 251301 Taiwan

Early fault or unusual behavior detection can reduce the risk of equipment failure improve performance and increase safety. Anomaly detection in industrial big data involves identifying deviations from normal patterns in large-scale datasets. This method assists in preventing equipment failures optimizing maintenance schedules and raising overall operational efficiency in industrial settings by identifying anomalous behaviors or outliers. Through the utilization of deep learning procedures, this investigation endeavours to apply are fined procedure for anomaly detection in industrial big data. Pre-processing, feature selection and Anomaly detection are three steps of a process that are used. The input data is first fed into MapReduce framework where it is divided and pre-processed. Imputation of missing data and Yeo-Jhonson transformation are then applied to eliminate noise from data. After pre-processed data is generated, it is put through a feature selection phase using Serial Exponential Lotus Effect optimization algorithm (SELOA). The algorithm is created newly by combining Lotus Effect optimization algorithm (LOA) with Exponential Weighted Moving Average (EWMA). Finally, anomaly detection is done using the features that are selected by means of Deep Belief-MobileNet1D, which combines MobileNet1D and Deep Belief Network (DBN). With a recall of 96.2 %, precision of 92.8 %, F1 score of 94.5 % and accuracy of 95.9 %, results show that the proposed strategy surpasses standard approaches. These findings demonstrate Deep Belief-MobileNet1D model's ability to detect anomalies in industrial big data.

关键词： Anomaly detection Deep learning Big data Feature selection optimization algorithm Industrial application

来源：评论

学校读者我要写书评

暂无评论

A hybrid framework for day-ahead electricity spot-price forecasting: A case study in China

引用

APPLIED ENERGY 2024年 373卷

作者： Huang, Siwan Shi, Jianheng Wang, Baoyue An, Na Li, Li Hou, Xuebing Wang, Chunsen Zhang, Xiandong Wang, Kai Li, Huilin Zhang, Sui Zhong, Ming Huaneng Clean Energy Res Inst Bldg AFuture Sci Pk Beijing 102209 Peoples R China China Huaneng Grp Co Ltd 6 Fuxingmennei St Beijing 100031 Peoples R China Huaneng Shandong Power Generat Co Ltd Jinan Shandong Peoples R China Huaneng Jiangxi Power Generat Co Ltd Ganzhou Jiangxi Peoples R China Huaneng Power Int Inc Shanghai Shidongkou Power Plant 1 Shanghai Peoples R China

The electricity price volatility can be aggravated by multiple factors, such as load pattern, line limit, regulations, renewable energy generations, weather conditions and holiday. Due to these complex dynamic characteristics of electricity prices, highly accurate forecasting is quite challenging. Our objective is to provide a hybrid framework to forecast 96-point day-ahead electricity price for the following day. We first conducted a day similarity algorithm (DSA) to construct features from electricity price corresponding to the similar days. A deep neural network (DNN) model was developed from 60 important features, including supply, demand and similar day characteristics, selected by eXtreme Gradient Boosting (XGBoost) algorithm. The hyperparameters were tuned using adaptive TPE (ATPE) method. The framework was validated in the real-world dataset of electricity spot market in Shandong Province in China. The proposed framework had good forecasting performance with the lowest MAE of 0.138, MSE of 0.028, RMSE of 0.166 and U2 of 0.434 in the test set and outperformed the other models significantly. The framework presented a robust methodology for market participants to forecast electricity prices accurately, increase profits and improve decision-making skills.

关键词： Electricity price forecasting Similar day analysis Feature selection optimization algorithm Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of carbon emissions in China's construction industry using an improved grey prediction model

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2024年 938卷 173351页

作者： Liu, Jia-Bao Yuan, Xi-Yu Lee, Chien-Chiang Anhui Jianzhu Univ Sch Math & Phys Hefei 230601 Peoples R China Nanchang Univ Sch Econ & Management Nanchang Peoples R China Lebanese Amer Univ Adnan Kassar Sch Business Beirut Lebanon Nanchang Univ Res Ctr Cent China Econ & Social Dev Nanchang Peoples R China

As a significant source of global energy consumption and greenhouse gas emissions, the construction industry garners widespread attention due to its high carbon emissions. Anticipating its development trends is crucial for energy conservation and emission reduction. In this paper, we utilize the carbon emission data from China 's national and provincial construction sectors from 2012 to 2021, employ the grey prediction model optimized by the particle swarm optimization algorithm, coupled with a metabolic algorithm, to forecast the carbon emissions of the construction industry across China and its provinces. The results demonstrate that: (1) The dynamic grey prediction model combined with the metabolism algorithm has a better prediction effect than the classical model, and the relative error is reduced from 5.103 % to 0.874 %. (2) The carbon emissions of China 's construction industry will continue to rise in the next decade, but the growth rate will decrease, and the proportion of indirect carbon emissions continues to increase. (3) There is a marked regional disparity in carbon emissions, with the eastern region exhibiting higher emission levels yet slower growth. In contrast, the western region has lower emission levels but experiences faster growth. These studies provide valuable insights for both the existing approaches to energy conservation and emission reduction, as well as for future policy improvements.

关键词： Construction industry Grey prediction model optimization algorithm Carbon emission Metabolic algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimum design of planar quasi-Yagi antenna for wearable Internet of Things (IoT) applications

引用

MICROWAVE AND OPTICAL TECHNOLOGY LETTERS 2024年第1期66卷 e33839-e33839页

作者： Dass, Ruby Thirumoorthy, Gopalakrishnan Ananthakrishnan, Gayathri Kannan, Anusha Rajendran, Sureshbabu Narayanan, Manikandan Arputharaj, Kannan Vellore Inst Technol Sch Comp Sci & Engn Vellore Tamil Nadu India Manipal Acad Higher Educ Manipal Inst Technol Dept Informat Technol Manipal India Vellore Inst Technol Sch Informat Technol & Engn Vellore Tamil Nadu India Vellore Inst Technol Sch Comp Sci & Engn Chennai Tamil Nadu India Kamaraj Coll Engn Dept Elect & Commun Engn Virudunagar India

This paper presents the design of a novel dual-band quasi-Yagi antenna for on-body communications. The proposed antenna is designed on 0.05 mm thin microwave laminate and is designed to cover the 2.45 and 3.5 GHz spectrum to meet the needs of on-body Internet of Things networks. Microstrip to slot-line transition is used for the excitation of the feeder element. The conventional feeder of the quai-Yagi is replaced with F-shaped radiators to obtain a dual-band response. In addition, a pair of directors are used to enhance the antenna gain. The proposed quasi-Yagi antenna is optimized using the spider monkey algorithm. The chosen algorithm is used to synthesize the dimensions of the dual-band radiator and is preferred to obtain quick convergence, unlike the traditional optimization algorithms. The optimized planar quasi antenna offers 5% bandwidth in both operating bands with a measured gain of 5.7 and 5.8 dBi, respectively. The optimization time is also considerably reduced in comparison with traditional optimization algorithms. The simulated and optimized antenna is fabricated and tested.

关键词： dual-band antennas IoT antennas optimization algorithm wearable antennas

来源：评论

学校读者我要写书评

暂无评论

Harnessing artificial neural networks for inverse design and analysis of MEMS-based Fabry-Pérot filters

引用

SENSORS AND ACTUATORS A-PHYSICAL 2024年 373卷

作者： Liu, Zhenya Wang, Junchao Wu, Yifan Zhang, Yidan Zhang, Meng Cao, Jing Liu, Jun Hangzhou Dianzi Univ Sch Integrated Circuit Sci & Engn Hangzhou 310018 Peoples R China China Elect Technol Grp Cooperat Informat Sci Acad Beijing 100041 Peoples R China

MEMS-based Fabry-P & eacute;rot (MEMS-FP) filters have become increasingly important in optical applications such as frequency selection spectroscopy and spectral analysis. Prior to the manufacturing of MEMS-FP devices, conducting a thorough theoretical analysis of their properties is crucial. Currently, Finite Element Analysis (FEA) is the primary method for investigating the theoretical performance of MEMS-FP during the design process. However, the complexity of modeling and prolonged simulation times associated with FEA software pose significant challenges, impeding the development timeline for MEMS-FP devices. To address these challenges, we proposed a machine learning -based method to computer -aided design of the MEMS-FP devices. Our approach involves using an Artificial Neural Network (ANN) to predict their physical properties and an inverse design method, utilizing optimization algorithms such as PSO, NSGA-II, and SA, to derive the optimal design scheme for MEMS-FP devices. Our method accelerates the prediction of physical properties of MEMSFP devices and enables the design automation of optimal schemes in just minutes within a limited design space. This approach not only reduces the research time and complexity associated with MEMS-FP devices but also shortens their development cycle. Furthermore, one specific MEMS-FP device is fabricated and tested for proof -of -concept of our proposed method.

关键词： MEMS-FP Machine learning optimization algorithm Design automation

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：