检索结果-内蒙古大学图书馆

Novel hybrid method to predict the ground-displacement field caused by shallow tunnel excavation

Science China(Technological Sciences) 2023年第1期66卷 101-114页

作者： KONG FanChao LU DeChun MA YiDing TIAN Tao YU HaiTao DU XiuLi Institute of Geotechnical and Underground Engineering Bejing University of TechnologyBejing 100124China Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education Tongji UniversityShanghai 200092China

Based on machine-learning(ML) and analytical methods, a hybrid method is developed herein to predict the ground-displacement field(GDF) caused by tunneling. The extreme learning machine(ELM), as a single hidden layer feedforward neural network, is used as an ML model to predict maximum settlement smaxof the ground surface. The particle swarm optimization(PSO) algorithm is applied to optimize the parameters for the ELM method, namely, weight and bias values from the input layer to the hidden layer. The mean square error of the k-fold cross validation sets is considered the fitness function of the PSO algorithm. For 38 data samples from published papers, 30 samples are used as the training set, and 8 samples are used as the test set. For the test samples, the error of five samples ranges between-5 and 5 mm. The error of only one sample is slightly greater than 10 mm. The proposed PSO-ELM method demonstrates good prediction performance of smax. A deformation parameter of the nonuniform displacement mode for the tunnel cross-section is calibrated based on predicted smax. When the determined nonuniform displacement mode is used as the boundary condition of the tunnel cross-section, the GDF of a shallow circular tunnel is analytically predicted based on the complex-variable method prior to tunnel excavation. For a specific engineering case,i.e., the Heathrow Express tunnel, the proposed PSO-ELM-analytical method can well predict the surface-settlement trough curve, horizontal displacements at different depths, and vertical displacements above the tunnel.

关键词： extreme learning machine particle swarm optimization complex-variable method analytical solution of a shallow tunnel prediction method of ground-displacement field

来源：评论

学校读者我要写书评

暂无评论

Enhanced QUBO Formulations for The Flow Shop Scheduling Problem

Enhanced QUBO Formulations for The Flow Shop Scheduling Prob...

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Farhani, Yousra Saiem, Malak Arbaoui, Taha Hnaien, Faicel Algiers Algeria Laboratory of Computer Science and Digital Society University of Technology of Troyes Troyes France INSA Lyon Université Lumière Lyon 2 Université Claude Bernard Lyon 1 Université Jean Monnet Saint-Etienne DISP UR4570 Villeurbanne France

ISBN: (纸本)9798400704956

In recent years, the Flow shop Scheduling Problem (FSP) has gained significant attention, prompting researchers to develop various methods, from conventional to hybrid optimization algorithms. Driven by the rapid growth of quantum computing capabilities, quantum approaches applied to optimization problems have attracted an increasing research effort. This work attempts to solve the permutation flow shop scheduling problem using quantum annealing by formulating the problem as a Quadratic Unconstrained Binary optimization model (QUBO). Two QUBO formulations tailored to address the FSP are used. The first formulation is based on the position-based modelling while the second is based on five approximations of FSP as a Traveling Salesman Problem (TSP). The QUBO formulations are tested, using D-Wave's quantum annealers, on the well-known Taillard FSP benchmark and compared against each other. Results show that the proposed position-based QUBO reaches better solutions than the TSP-based QUBOs. This work is an attempt to highlight the increasing effectiveness of quantum annealers in addressing complex optimization problems and their limitations compared to conventional classical methods. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Destripe Any Scale: Effective Stripe Removal Via Multiscale Decomposition Using the Luojia3-02 Stripe-Noise Dataset

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 13602-13621页

作者： Chen, Ru Wang, Mi Pi, Yingdong Wang, Ru Peng, Tao Yang, Fan Dai, Rongfan Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan430079 China Wuhan University School of Cyber Science and Engineering Wuhan430079 China

Stripe noise is a significant challenge in remotely sensed satellite images, primarily originating from inconsistencies in push-broom scanning systems. This noise manifests as linear, repetitive patterns that degrade image quality and impede the accurate data analysis. Existing destriping methods, including traditional statistical and frequency-based techniques, optimization-based approaches, and deep-learning models, each exhibit limitations in effectively addressing both small-scale and large-scale stripe noise, particularly in complex and heterogeneous imaging scenarios. To overcome these challenges, we present Destripe Any Scale, a novel hybrid destriping framework that integrates multiscale decomposition with deep-learning techniques. We first introduce the Luojia3-02 stripe-noise dataset, constructed from Luojia3-02 (Wuhan-1) satellite imagery, including stripe-noise patterns across multiple spatial scales. Building upon this dataset, we propose a multilevel perceptual stripe-noise-removal network. This network employs an independent-weight learning strategy to separately capture and optimize large-scale and small-scale noise features, facilitating the precise extraction of multiscale noise features. To further enhance performance, we construct a multiscale image pyramid that decouples mixed noise into distinct resolution levels. Within this framework, stripe noise is progressively suppressed across hierarchical levels, while a column-guided correction mechanism ensures consistency across scales and preserves the fidelity of image details. Experimental evaluations using Luojia3-02 data demonstrate that, without relying on external calibration, the proposed network and processing framework effectively eliminate multiscale stripe noise caused by sensor-induced radiometric errors, significantly improving both radiometric quality and visual clarity. Compared with traditional methods, our approach exhibits superior robustness and adaptability in handling complex, l

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Fermentation design and process optimization strategy based on machine learning

引用

生物设计研究（英文） 2025年第1期7卷 25-34页

作者： Zhen-Zhi Wang Du-Wen Zeng Yi-Fan Zhu Ming-Hai Zhou Akihiko Kondo Tomohisa Hasunuma Xin-Qing Zhao State Key Laboratory of Microbial Metabolism and School of Life Sciences & BiotechnologyShanghai Jiao Tong UniversityShanghai200240China Engineering Biology Research Center Kobe University1-1 RokkodaiNadaKobe657-8501Japan

Fermentation optimization is important for industrialization of biological manufacturing,and has been widely applied to diverse sectors including medicine,food,cosmetics and bioenergy,which is related to substantial economic *** development is considered to be the core part of fermentation technology,as it directly influences the product yield and overall success of the fermentation ***,fermentation design and process optimization also play a crucial role in fully exploring the genetic potential of engineered strains for efficient *** to the fact that fermentation process is influenced by complex factors,so far,machine learning has been widely used in this area with its strong capabilities of simulation and *** review provides a brief introduction to the process of fermentation design and process optimization based on machine *** the workflow,experimental design strategy is fundamental to explore and characterize the perfor-mance of fermentation ***,machine learning modelling is employed to simulate the operation of fermentation system and the appropriate fermentation conditions,such as medium composition and process parameters,will be ***,in recent years,some extension ideas of fermentation design based on machine learning have also been proposed,including automated fermentation process control,data mining for exploring strain characteristics,transfer learning,hybrid model building,and soft sensor *** strategies have created more application scenarios for machine learning,enhancing its adaptability in designing and optimizing the complex fermentation system for efficient bioproduction.

关键词： Machine learning Fermentation optimization Automated fermentation process control Efficient bioproduction Process Design

来源：评论

学校读者我要写书评

暂无评论

Technologies and studies of gas exchange in two-stroke aircraft piston engine:A review

引用

Chinese Journal of Aeronautics 2024年第1期37卷 24-50页

作者： Yu ZHOU Xueyu LI Shuiting DING Shuai ZHAO Kun ZHU Longtao SHAO Farong DU Gerui WANG Zheng XU Research Institute of Aero-Engine Beihang UniversityBeijing 100191China Aircraft/Engine Integrated System Safety Beijing Key Laboratory Beijing 100191China School of Transportation Science and Engineering Beihang UniversityBeijing 100191China Civil Aviation University of China Tianjin 300300China Aero Engine Academy of China Beijing 101304China School of Energy and Power Engineering Beihang UniversityBeijing 100191China Beihang Hangzhou Innovation Institute Yuhang Hangzhou 310052China

The in-cylinder gas exchange process is crucial to the power performance of two-stroke aircraft piston engines,which is easily influenced by complex factors such as high-altitude performance variation and in-cylinder flow *** paper reviews the development history and characteristics of gas exchange types,as well as the current state of theory and the validation methods of gas exchange technology,while also discusses the trends of cutting-edge technologies in the *** paper provides a theoretical foundation for the optimization and engineering design of gas exchange systems and,more importantly,points out that the innovation of gas exchange types,the modification of theoretical models,and the technology of variable airflow organization are the key future research directions in this field.

关键词： Aircraft piston engine Aircraft power systems Gas exchange High-altitude performance In-cylinder flow Two-stroke Unmanned Aerial Vehicles(UAVs)

来源：评论

学校读者我要写书评

暂无评论

Enhanced Parameter Extraction of Photovoltaic Models Through the hybridization of Ant Lion Optimizer and Cuckoo Search (ALOCS) 2nd

Enhanced Parameter Extraction of Photovoltaic Models Through...

引用

2nd International Conference on Green Energy Conversion System, ICGECS 2023

作者： Youssef, Rehouma Mohamed, Naoui Aicha, Degla Bilal, Danoune Mohammed Assad, Hamida Mohamed Lassaad, Sbita Abdelmoumen, Gougui LAGE Laboratory University of Ouargla Ouargla30000 Algeria LEVRES Laboratory University of El Oued EL Oued39000 Algeria Research Unit of Energy Processes Environment and Electrical Systems ENIG University of Gabés Gabés6029 Tunisia Centre de Dévelopment des Energies Renouvelables—CDER 62 Route de l’observatoire Bouzareah Algeria Sustainable Development and Computer Science Laboratory SDCS-L Ahmed Draia University Adrar Algeria

ISBN: (纸本)9789819761470

The identification of photovoltaic (PV) model unknown parameters using measured characteristic curves is of great importance for designers involved in modelling, simulation, and control of PV systems. This paper introduces an enhanced heuristic algorithm, namely ALO-CS (Ant Lion Optimizer-Cuckoo Search), which combines the strengths of both ALO and CS optimization algorithms. The primary objective is to accurately extract the parameters of various commercial PV modules. To the best of our knowledge, this novel approach has not been previously explored in the literature, making it a unique contribution. In order to evaluate its effectiveness, a comparative analysis is conducted against several state-of-the-art methods. The experimental and analytical results demonstrate that the proposed hybrid ALO-CS algorithm outperforms improved JAYA and other methods in terms of accuracy and quality, establishing its competitive advantage. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Ant lion optimizer Cuckoo search optimization Extraction Photovoltaic cell PV panel

来源：评论

学校读者我要写书评

暂无评论

Empowering MPPT Efficiency in Partial Shading with Machine Learning Driven Metaheuristic Strategies: Recent Developments

Empowering MPPT Efficiency in Partial Shading with Machine L...

引用

International Conference on Artificial Intelligence in Renewable Energetic systems, IC-AIRES 2024

作者： Belhachat, F. Larbes, C. Bennia, R. Laboratory of Communication and Photovoltaic Conversion Devices National Polytechnic School Algiers Algeria

ISBN: (纸本)9783031803000

The use of MPPT control technology has proven to be the most effective way to improve the performance of photovoltaic systems (PVS), especially in partial shading conditions (PS-C). Therefore, accurately determining the "maximum power point (MPP)" is crucial in PVS design. Thus, many MPPT methods have been proposed in the literature, ranging from simple to complex algorithms. However, choosing the best strategy for PVS implementation can be challenging due to the wide range of choices. Recently, metaheuristic optimization algorithms, machine-learning models, and their hybridization have attracted much attention from researchers due to their multiple advantages in solving optimization challenges. In view of these advantages, this paper focuses on the examination of the recent advancements in hybrid intelligent MPPT techniques operating under PS-C published over the last five years. The paper evaluates and compares all selected and classified categories based on diverse criteria such as computational complexity level, percentage of efficiency, convergence speed, converter, application and configuration type, and validation, discussing the strengths and weaknesses of each approach and suggesting directions for future research. Results from evaluation and comparison highlight the promise of hybrid intelligent solutions in improving MPPT technique performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

optimization Strategy of hybrid Cascade On-Load Tap Changer Positions Based on Ant Colony Algorithm 10

Optimization Strategy of Hybrid Cascade On-Load Tap Changer ...

引用

10th IEEE International Power Electronics and Motion Control Conference, IPEMC 2024 ECCE Asia

作者： Chen, Dezhi Li, Boqiao Ministry of Education Shenyang University of Technology Key Laboratory of Special Motors and High Voltage Electrical Appliances China

ISBN: (纸本)9798350351330

The hybrid cascade DC system is increasingly recognized for its robust transmission capacity and reliability within power systems. This study aims to investigate and enhance the performance of on-load tap-changers in hybrid cascade DC systems to bolster operational efficiency and reliability. To achieve this objective, an optimization algorithm is developed. These algorithms will consider various factors including system voltage stability and the frequency of on-load tap changer operations, ultimately determining the optimal solution through calculations and optimization processes. This paper outlines the design of a hybrid cascade DC system and validates its stability. Additionally, using an iconic switch as a case study, the tap-changer process of the on-load tap-changer is simulated, and the impact of different control methods is deliberated. © 2024 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

A Novel Parameter-Optimized Recurrent Attention Network for Pipeline Leakage Detection

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 1064-1076页

作者： Tong Sun Chuang Wang Hongli Dong Yina Zhou Chuang Guan The authors are with the Sanya Offshore Oil&Gas Research Institute Northeast Petroleum UniversitySanya 572024 Artificial Intelligence Energy Research Institute Northeast Petroleum University Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast Petroleum UniversityDaqing 163318China

Accurate detection of pipeline leakage is essential to maintain the safety of pipeline ***,deep learning(DL)has emerged as a promising tool for pipeline leakage detection(PLD).However,most existing DL methods have difficulty in achieving good performance in identifying leakage types due to the complex time dynamics of pipeline *** the other hand,the initial parameter selection in the detection model is generally random,which may lead to unstable recognition *** this reason,a hybrid DL framework referred to as parameter-optimized recurrent attention network(PRAN)is presented in this paper to improve the accuracy of ***,a parameter-optimized long short-term memory(LSTM)network is introduced to extract effective and robust features,which exploits a particle swarm optimization(PSO)algorithm with cross-entropy fitness function to search for globally optimal *** this framework,the learning representation capability of the model is improved and the convergence rate is ***,an anomaly-attention mechanism(AM)is proposed to discover class discriminative information by weighting the hidden states,which contributes to amplifying the normalabnormal distinguishable discrepancy,further improving the accuracy of *** that,the proposed PRAN not only implements the adaptive optimization of network parameters,but also enlarges the contribution of normal-abnormal discrepancy,thereby overcoming the drawbacks of instability and poor ***,the experimental results demonstrate the effectiveness and superiority of the proposed PRAN for PLD.

关键词： attention mechanism(AM) long shortterm memory(LSTM) parameter-optimized recurrent attention network(PRAN) particle swarm optimization(PSO) pipeline leakage detection(PLD)

来源：评论

学校读者我要写书评

暂无评论

Data-driven Reactive Power optimization of Distribution Networks via Graph Attention Networks

引用

Journal of Modern Power systems and Clean Energy 2024年第3期12卷 874-885页

作者： Wenlong Liao Dechang Yang Qi Liu Yixiong Jia Chenxi Wang Zhe Yang Wind Engineering and Renewable Energy Laboratory Ecole Polytechnique Federale de Lausanne(EPFL)Lausanne 1015Switzerland the College of Information and Electrical Engineering China Agricultural UniversityBeijing 100083China the College of Electrical Engineering and Automation Shandong University of Science and TechnologyQingdao 266590China the Department of Electrical and Electronic Engineering(Energy Digitalization Laboratory) The University of Hong KongHong KongChina the Department of Electrical Engineering The Hong Kong Polytechnic UniversityHong KongChina

Reactive power optimization of distribution networks is traditionally addressed by physical model based methods,which often lead to locally optimal solutions and require heavy online inference time *** improve the quality of the solution and reduce the inference time burden,this paper proposes a new graph attention networks based method to directly map the complex nonlinear relationship between graphs(topology and power loads)and reactive power scheduling schemes of distribution networks,from a data-driven *** graph attention network is tailored specifically to this problem and incorporates several innovative features such as a self-loop in the adjacency matrix,a customized loss function,and the use of max-pooling ***,a rulebased strategy is proposed to adjust infeasible solutions that violate *** results on multiple distribution networks demonstrate that the proposed method outperforms other machine learning based methods in terms of the solution quality and robustness to varying load ***,its online inference time is significantly faster than traditional physical model based methods,particularly for large-scale distribution networks.

关键词： Reactive power optimization graph neural network distribution network machine learning data-driven

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：