检索结果-内蒙古大学图书馆

Parameter prediction optimization of data center's heat dissipation system using machine learning algorithms

APPLIED THERMAL ENGINEERING 2023年第1期232卷

作者： Chen, Xianzhong Tu, Rang Yang, Xu Univ Sci & Technol Beijing Sch Civil & Resources Engn Beijing 100083 Peoples R China Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing 100083 Peoples R China

In this study, an optimization control method based on knowledge and operational data was investigated for a centralized water-cooling heat dissipation system in a data center. First, a numerical model describing the heat transfer and thermodynamic processes of the heat dissipation system was established, and five thermal characteristic parameters were extracted to identify the system. The thermal characteristic parameters, used as inputs to the model, were identified in real time using the mechanism formula from the operational data. Subsequently, the operational data of the heat dissipation system in a real data center were used to validate the numerical model. The model accuracy was within 15 %. The water flow rate of the actual system was optimized, showing that the average PUE of four typical cases under the optimized conditions were 1.12, 1.25, 1.13 and 1.3, respectively, with an improving rate between 4.3 % and 12.4 %. Next, considering the reasonable value ranges of the five thermal characteristic parameters and four direct input parameters, 62,208 groups of working conditions were designed, and the optimized water flow rate and the corresponding COP and PUE for each working condition were obtained using the numerical model. Finally, a prediction model that combined the heat transfer mechanisms was established based on an optimized dataset. machine learning algorithms were applied to establish neural networks between the nine inputs and three optimized operating parameters. Based on the prediction model and thermal characteristic parameter identification module, software was developed to suggest optimized water flow rates and predict the PUE and COP in real time from the operational data.

关键词： Data center Heat dissipation system Numerical model Thermal characteristic parameter machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Fault prediction algorithm for offshore wind energy conversion system based on machine learning

Fault prediction algorithm for offshore wind energy conversi...

引用

International Conference on High Performance Big Data and Intelligent Systems (HPBD and IS)

作者： Yang, Jing Li, Junda Shangdong JiaoTong Univ Weihai Weihai 264209 Shandong Peoples R China Shanxi Agr Univ Jinzhong Jinzhong 030800 Shanxi Peoples R China

ISBN: (纸本)9781665413275

In view of the low accuracy and long time sum di fference of fault prediction methods in offshore wind power con version system, a fault prediction algorithm for offshore wind p ower conversion system is designed based on SVM method in m achine learning. The fault data of offshore wind power conversi on system are preprocessed by principal component analysis, a nd the fault characteristics of offshore wind power conversion s ystem are extracted by leftflush method. Based on the principle of SVM, the fault prediction LSSVM model of offshore wind p ower conversion system is constructed. The test results show th at this method has good fault prediction effect for offshore win d power conversion system, and can effectively improve the acc uracy of fault prediction and shorten the time of fault predictio n.

关键词： machine learning algorithm principal componen t analysis method SVM offshore wind energy conversion system fault prediction

来源：评论

学校读者我要写书评

暂无评论

machine learning-based improved plastic stress distribution method for strength prediction of CFST members

引用

STRUCTURES 2025年 74卷

作者： Zhou, Zheng Yang, Lifu Zhou, Xuhong Shi, Caijun Hunan Univ Coll Civil Engn Changsha 410082 Peoples R China

The plastic stress distribution (PSD) method is used as the primary method in typical design codes for calculating the strength of concrete-filled steel tubular (CFST) members. However, the PSD method can only be applied to members with limited ranges of material strengths and cross-sectional slenderness ratios, and the calculation methods are lacking or relatively complicated for members beyond the limitations. In this work, an improved PSD method is proposed for the strength prediction of CFST members with different cross-sectional slenderness ratios and material strengths, by using the concrete strength factor fi1 to consider the possible compressive strength increase or reduction of the concrete due to the confinement or local buckling from the steel tube and the steel strength factor fi2 to consider the potential compressive strength reduction of the steel tube due to local buckling. The direct inverse analysis using the improved particle swarm optimization algorithm is then conducted to identify the strength factors fi1 and fi2 based on the extensive experimental results. machine learning algorithms are finally explored to train the rules between the strength factors (fi1 and fi2) and the member properties including the diameter or width and depth, wall thickness, and material strength, and the predicted results are in good agreement with the experimental results. These results further specify the accurate plastic stress distribution, and provide a strong justification for possible changes to the design codes to expand the use of the PSD method to all types of CFST members.

关键词： Concrete-filled steel tubes Plastic stress distribution method Direct inverse analysis Particle swarm optimization algorithm machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

machine learning-enhanced combustion modeling for predicting laminar burning velocity of ammonia-hydrogen mixtures using improved reaction mechanisms

引用

ENERGY 2025年 320卷

作者： Rao, Anas Li, Wei Abbasi, Muhammad Salman Shahid, Muhammad Ihsan Farhan, Muhammad Zulfiqar, Sana Chen, Tianhao Ma, Fanhua Li, Xin Tsinghua Univ Sch Vehicle & Mobil Natl Key Lab Intelligent Green Vehicles & Transpor Beijing 100084 Peoples R China Univ Engn & Technol Dept Mech Engn Lahore 54890 Pakistan Xijing Univ Engn Res Ctr Hydrogen Energy Equipment & Safety De Xian 710123 Shaanxi Peoples R China Xijing Univ Sch Mech Engn Xian 710123 Shaanxi Peoples R China Univ Management & Technol C-2 Block Phase 1 Johar Town Lahore 54770 Punjab Pakistan

The ammonia/hydrogen mixture is a promising zero-carbon fuel for internal combustion engines, with optimal efficiency in spark ignition engines at equivalence ratios of 0.6-1 and hydrogen fractions of 0.4-0.6. However, existing reaction mechanisms lose accuracy in this range, limiting combustion modeling. To address this, prediction accuracy is improved using refined reaction kinetics and machine learning algorithms. GRI Mech3.0 is refined by enhancing H/O, N2O, HNO, NH, and NH2 mechanisms, forming Model I for pure ammonia and Model II for lean burn ammonia-hydrogen mixtures. The simulated laminar burning speed of these models is compared with literature and seven other mechanisms. Combustion analysis includes sensitivity analysis of coefficients, nitric oxide emission rates, sub-mechanisms, and reaction sensitivities to assess their impact, with machine learning algorithms to improve accuracy. Model II achieves the highest accuracy under stoichiometric (RMSE = 1.4590 cm/s) and lean burn conditions (RMSE = 1.3701 cm/s). As different mechanisms suit various conditions, machine learning algorithms further enhance prediction accuracy. The support vector machine with particle swarm optimization improves computational accuracy by 2.9745 times over reaction kinetics, demonstrating its effectiveness. This study develops refined reaction mechanisms and machine learning models for practical applications in ammonia-hydrogen fueled SI engines.

关键词： Ammonia/hydrogen fuel Laminar burning speed Reaction kinetics machine learning algorithm PSO-SVM

来源：评论

学校读者我要写书评

暂无评论

Rapid and sensitive detection of pharmaceutical pollutants in aquaculture by aluminum foil substrate based SERS method combined with deep learning algorithm

引用

ANALYTICA CHIMICA ACTA 2025年 1351卷 343920页

作者： Huang, Zixi Lei, Yongqian Liang, Weixin Cai, Yili Guo, Pengran Sun, Jian Guangdong Univ Technol Sch Environm Sci & Engn Guangzhou Key Lab Environm Catalysis & Pollut Cont Guangdong Key Lab Environm Catalysis & Hlth Risk C Guangzhou 510006 Peoples R China Guangdong Acad Sci Inst Anal China Natl Analyt Ctr Guangzhou Guangdong Prov Key Lab Chem Measurement & Emergenc Guangzhou 510070 Peoples R China Guangdong Acad Sci Inst Anal Guangdong Prov Engn Res Ctr Online Monitoring Wate China Natl Analyt Ctr Guangzhou 510070 Peoples R China

Background: Pharmaceutical residual such as antibiotics and disinfectants in aquaculture wastewater have significant potential risks for environment and human health. Surface enhanced Raman spectroscopy (SERS) has been widely used for the detection of pharmaceuticals due to its high sensitivity, low cost, and rapidity. However, it is remain a challenge for high-sensitivity SERS detection and accurate identification of complex pollutants. Results: Hence, in this work, we developed an aluminum foil (AlF) based SERS detection substrate and established a multilayer perceptron (MLP) deep learning model for the rapid identification of antibiotic components in a mixture. The detection method demonstrated exceptional performance, achieving a high SERS enhancement factor of 4.2 x 10(5) and excellent sensitivity for trace amounts of fleroxacin (2.7 x 10(-8) mol/L), levofloxacin (1.95 x 10(-8) mol/L), and pefloxacin (6.9 x 10(-8) mol/L),sulfadiazine, methylene blue, and malachite green at a concentration of 1 x 10(-8) mol/L can all be detected, the concentrations of the six target compounds and their Raman intensities exhibit a good linear relationship. Moreover, the AlF SERS substrate can be prepared rapidly without adding organic reagents, and it exhibited good reproducibility, with RSD<9.6 %. Additionally, the algorithm model can accurately identify the contaminants mixture of sulfadiazine, methylene blue, and malachite green with a recognition accuracy of 97.8 %, an F1-score of 98.2 %, and a 5-fold cross validation score of 97.4 %, the interpretation analysis using Shapley Additive Explanations (SHAP) reveals that MLP model can specifically concentrate on the distribution of characteristic peaks. Significance: The experimental results indicated that the MLP model demonstrated strong performance and good robustness in complex matrices. This research provides a promising detection and identification method for the antibiotics and disinfectants in actual aquaculture wastewate

关键词： Surface-enhance Raman scattering (SERS) Aquaculture wastewater Pharmaceutical pollutants machine learning algorithm Rapid detection

来源：评论

学校读者我要写书评

暂无评论

Integrated finite element analysis and machine learning approach for exploring the flexural behavior of steel-spontaneous combustion coal gangue aggregate concrete composite beams with studs

引用

STRUCTURES 2025年 72卷

作者： Zhang, Tirui Wang, Qinghe Zhang, Xinlong Liu, Yuting Ding, Jinan Shenyang Jianzhu Univ Sch Civil Engn Shenyang 110168 Peoples R China China Northeast Architectural Design & Res Inst Co Shenyang 110000 Peoples R China Shenyang Jianzhu Univ Sch Management Shenyang 110168 Peoples R China

This study investigates how varying the replacement ratio of spontaneous-combustion coal gangue aggregate (SCGA) affects the steel-concrete composite beams' flexural behavior with studs. Using ABAQUS software, pushout models of studs and flexural models of composite beams were developed, with their reliability confirmed through comparisons with previously published experimental findings. A parameter analysis was conducted to quantify the impact of the SCGA replacement ratio on the studs' shear resistance and the composite beams' flexural behavior. Additionally, machine learning techniques were employed to set up models for predicting the studs' shear resistance and assessing both the composite beams' flexural capacity and bending stiffness, with their predictive performance evaluated accordingly. The impact of each parameter on the studs' shear resistance and the composite beams' flexural behavior was also quantified. The findings suggest that the studs' shear resistance and the composite beams' flexural behavior decline as the SCGA replacement ratio increases. Specifically, compared with natural concrete specimens, the shear resistance of studs exhibiting replacement ratios of 50 % and 100 % was found to drop by 4.04 %-5.68 % and 7.90 %-11.18 %, respectively. The composite beams' flexural capacity decreased by 1.05 %-2.62 % and 2.24 %-5.44 %, while the bending stiffness decreased by 3.62 %-4.65 % and 8.27 %-10.00 %, respectively. The XGBoost model, optimized with advanced algorithms, effectively predicts the studs' shear resistance and assesses both the composite beams' flexural capacity and bending stiffness, with prediction errors maintained within 15 % and a minimum comprehensive performance index of 0.20. SHapley Additive exPlanations value analysis identified the stud's diameter and the SCGA concrete's compressive strength as the main influence factors of the studs' shear resistance. In terms of composite beams' flexural capacity, the key factor is the SCGA co

关键词： Spontaneous-combustion coal gangue aggregate concrete Steel-concrete composite beam Shear stud Flexural behavior Finite element analysis machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Advancing smart transportation: A review of computer vision and photogrammetry in learning-based dimensional road pavement defect detection

引用

COMPUTER SCIENCE REVIEW 2025年 56卷

作者： Tafida, Adamu Alaloul, Wesam Salah Zawawi, Noor Amila Bt Wan Musarat, Muhammad Ali Sani, Adamu Abubakar Univ Teknol PETRONAS Dept Civil & Environm Engn Bandar Seri Iskandar 32610 Perak Malaysia Univ Teknol PETRONAS Inst Autonomous Syst Offshore Engn Ctr Bandar Seri Iskandar 32610 Perak Malaysia Abubakar Tafawa Balewa Univ Dept Quant Surveying Bauchi Nigeria Abubakar Tafawa Balewa Univ Dept Bldg Bauchi Nigeria

Road infrastructure networks are crucial in facilitating smart mobility, as indicated by the emergence of innovative transportation concepts that offer improved efficiency and environmental sustainability. This study seeks to review the literature regarding road pavement condition assessment performance improvement tools which utilize various computer vision and photogrammetry tools aided by machine learning algorithms towards mitigating challenges encountered and promoting smart transportation trends. A comprehensive search of available literature was conducted, and relevant studies were analyzed to identify computer vision and photogrammetry tools used, learning-based algorithms deployed and contribution to the improvement of road infrastructure to aid smart transportation. The review considered emerging challenges of the techniques, identified research gaps and explored the potentials of the techniques as it relates to aiding wider acceptance of the implementation of autonomous vehicles and smart transportation The study found gaps in knowledge relating to the computer vision (CV) and photogrammetry tools standardization of evaluation parameters, the applicability of the models for real-time assessment and implications regarding the adoption of autonomous vehicles and smart transportation which were not sufficiently considered in the previous cited literature. Future research areas were highlighted and its implication regarding the promotion of smart transportation.

关键词： Smart transportation Road infrastructure Computer vision and photogrammetry machine learning algorithm Road defect detection

来源：评论

学校读者我要写书评

暂无评论

Numerical thermodynamic-economic study and machine learning-based optimization of an innovative biogas-driven integrated power plant combined with sustainable liquid CO2 and liquid H2 production-storage processes

引用

CASE STUDIES IN THERMAL ENGINEERING 2025年 69卷

作者： Yuan, Ruijia Shi, Fan Abed, Azher M. Shaban, Mohamed Samad, Sarminah Almadhor, Ahmad Abdullaeva, Barno Aoudia, Mouloud Alkhalaf, Salem Babiker, Samah G. Anhui Univ Finance & Econ Sch Management Sci & Engn Bengbu Peoples R China Al Mustaqbal Univ Coll Engn & Technol Air Conditioning & Refrigerat Tech Engn Dept Babylon 51001 Iraq Al Mustaqbal Univ Al Mustaqbal Ctr Energy Res Babylon 51001 Iraq Islamic Univ Madinah Fac Sci Dept Phys Madinah 42351 Saudi Arabia Princess Nourah Bint Abdulrahman Univ Coll Business Adm Dept Management Riyadh 11671 Saudi Arabia Jouf Univ Coll Comp & Informat Sci Dept Comp Engn & Networks Sakaka Saudi Arabia Tashkent State Pedag Univ Dept Math & Informat Technol Vice Rector Sci Affairs Tashkent Uzbekistan Northern Border Univ Dept Ind Engn Coll Engn POB 1321 Ar Ar 91431 Saudi Arabia Qassim Univ Coll Comp Dept Comp Engn Buraydah Saudi Arabia Red Sea Univ Fac Appl Sci Dept Elect Phys Port Sudan Sudan

Innovative heat recovery, CO2 capture, and energy storage methodologies are pivotal for developing sustainable and eco-friendly solutions for the energy sector. Hence, this study proposes implementing an oxyfuel combustion process for a biogas power plant, modified by an innovative heat recovery method and a CO2 capture-liquefaction technique. Furthermore, the design incorporates high-temperature water electrolysis to produce hydrogen, which is then introduced into a hydrogen liquefaction process utilizing a Claude cycle for adequate long-term storage. The research employs thermodynamic, exergoeconomic, and net present value assessments, accompanied by an extensive parametric study and optimization process. Hence, a machine learning algorithm is implemented using artificial neural networks combined with the NSGA-II method for multi-criteria optimization, focusing on exergy efficiency, net present value, and products' sum unit cost as objective functions. The implemented optimization reduces the optimization time to under 30 min, which is significantly more efficient than traditional heuristic techniques, which typically require several hours for similar systems. This optimization framework is highly applicable to both industrial and district energy systems. This approach enhances predictive analytics and streamlines resource management. In industrial environments, it effectively optimizes energy use and production processes by examining various operational factors, which leads to cost reductions and improved efficiency via predictive maintenance and cohesive energy strategies. The optimal outcomes reveal the mentioned objective functions' values at 47.22 %, 58.73 M$, and 33.53 $/GJ, respectively. Under these optimal conditions, liquid carbon dioxide and liquid hydrogen outputs are quantified at 4931 lit/h and 1848 lit/h, respectively. Finally, the proposed system can omit CO2 emissions by 1.36 kg/kWh under optimal conditions, which reflects a 5.60 % better performan

关键词： Environmental challenges Biogas Oxyfuel combustion process Carbon dioxide capture-liquefaction Liquid hydrogen storage machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

SERS-ATB: A comprehensive database server for antibiotic SERS spectral visualization and deep-learning identification

引用

ENVIRONMENTAL POLLUTION 2025年 373卷 126083页

作者： Yuan, Quan Tang, Jia-Wei Chen, Jie Liao, Yi-Wen Zhang, Wen-Wen Wen, Xin-Ru Liu, Xin Chen, Hui-Jin Wang, Liang Xuzhou Med Univ Sch Med Informat & Engn Xuzhou Jiangsu Peoples R China Shengli Oilfield Cent Hosp Dept Lab Med Dongying Shandong Peoples R China Southern Med Univ Guangdong Prov Peoples Hosp Guangdong Acad Med Sci Lab Med Guangzhou Guangdong Peoples R China Xuzhou Med Univ Sch Clin Med 1 Dept Clin Med Xuzhou Jiangsu Peoples R China Univ Queensland Sch Agr & Food Sci Brisbane Qld Australia Edith Cowan Univ Ctr Precis Hlth Sch Med & Hlth Sci Perth WA Australia Univ Western Australia Sch Biomed Sci Div Microbiol & Immunol Crawley WA Australia

The rapid and accurate identification of antibiotics in environmental samples is critical for addressing the growing concern of antibiotic pollution, particularly in water sources. Antibiotic contamination poses a significant risk to ecosystems and human health by contributing to the spread of antibiotic resistance. Surfaceenhanced Raman spectroscopy (SERS), known for its high sensitivity and specificity, is a powerful tool for antibiotic identification. However, its broader application is constrained by the lack of a large-scale antibiotic spectral database crucial for environmental and clinical use. To address this need, we systematically collected 12,800 SERS spectra for 200 environmentally relevant antibiotics and developed an open-access, web-based database at http://***/. We compared six machine learning algorithms with a convolutional neural network (CNN) model, which achieved the highest accuracy at 98.94%, making it the preferred database model. For external validation, CNN demonstrated an accuracy of 82.8%, underscoring its reliability and practicality for real-world applications. The SERS database and CNN prediction model represent a novel resource for environmental monitoring, offering significant advantages in terms of accessibility, speed, and scalability. This study establishes the large-scale, public SERS spectral databases for antibiotics, facilitating the integration of SERS into environmental programs, with the potential to improve antibiotic detection, pollution management, and resistance mitigation.

关键词： Antibiotic Surface-enhanced Raman spectroscopy Raman spectra machine learning algorithm Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Rapid response to pressure variations in water distribution networks through machine learning-enhanced data acquisition

引用

AQUA-WATER INFRASTRUCTURE ECOSYSTEMS AND SOCIETY 2024年第7期73卷 1358-1371页

作者： Kim, Hyunjun Jung, K. J. Lee, S. Jeong, E. H. Pusan Natl Univ Dept Mech Engn 2 Busandaehak Ro63 Beon Gil Busan South Korea Flowork Lab Res & Dev Dept 8 Seojeon Ro Busan South Korea

This study investigates rapid dynamic pressure variations in water distribution networks due to critical incidents such as pipe bursts and valve operations. We developed and implemented a machine learning (ML)-based methodology that surpasses traditional slow cycles of pressure data acquisition, facilitating the efficient capture of transient phenomena. Employing the Orion ML library, which features advanced algorithms including long short-term memory dynamic threshold, autoencoder with regression, and time-series anomaly detection using generative adversarial networks, we engineered a system that dynamically adjusts data acquisition frequencies to enhance the detection and analysis of anomalies indicative of system failures. The system's performance was extensively tested using a pilot-scale water distribution network across diverse operational conditions, yielding significant enhancements in detecting leaks, blockages, and other anomalies. The effectiveness of this approach was further confirmed in real-world settings, demonstrating its operational feasibility and potential for integration into existing water distribution infrastructures. By optimizing data acquisition based on learned data patterns and detected anomalies, our approach introduces a novel solution to the conventionally resource-intensive practice of high-frequency monitoring. This study underscores the critical role of advanced ML techniques in water network management and explores future possibilities for adaptive monitoring systems across various infrastructural applications. HIGHLIGHTS Developed a machine learning (ML)-based system to dynamically monitor pressure in water networks. Utilized advanced Orion ML library algorithms for real-time anomaly detection. Enhanced operational efficiency by optimizing data acquisition rates. Demonstrated effectiveness in pilot and real-world water distribution settings. Integrated Orion ML library with advanced algorithms to improve infrastructure resilience.

关键词： data acquisition machine learning algorithm network anomaly detection operational insight pressure wave detection water distribution network

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：