检索结果-内蒙古大学图书馆

degradation prediction of PEM fuel cell using LSTM based on Gini gamma correlation coefficient and improved sand cat swarm optimization under dynamic operating conditions

引用

APPLIEd ENERGY 2025年 392卷

作者： Huang, Ruike Zhang, Xuexia dong, Sidi Huang, Lei Li, Yuan Southwest Jiaotong Univ Sch Elect Engn Chengdu 611756 Sichuan Peoples R China Southwest Jiaotong Univ Natl Rail Transit Electrificat & Automat Engn Tech Chengdu 611756 Peoples R China

Accurate longevity prediction is crucial for the optimal functioning of Proton Exchange Membrane Fuel Cells (PEMFC). This paper proposes the relative voltage loss rate (RVLR) as a novel aging indicator to overcome the limitations of traditional static indicators like voltage and power, which fall short under dynamic operating conditions. An innovative approach using an LSTM neural network model enhanced by Improved Sand Cat Swarm Optimization (ISCSO) and the Gini Gamma Correlation Coefficient method (GG) is presented for predicting PEMFC degradation across variable conditions. This method first conducts a Gini Gamma correlation analysis, then employs the LSTM network to forge a degradation prediction model for the PEMFC, optimizing the number of neurons in the hidden layer, initial weights, and iteration count through ISCSO. Comparative discussions with eight alternative methods and validations through aging experiments on PEMFC under two different conditions underscore the accuracy of this new approach in various application environments. Specifically, the ISCSO-LSTM model achieves R2 values of 0.9713 and 0.9822, MAE values of 0.0026 and 0.0019, and RMSE values of 0.0050 and 0.0032 across the two different datasets, respectively. These results demonstrate the robustness, accuracy, and reliability of the proposed method for accurate degradation prediction.

关键词： Proton exchange membrane fuel cells Relative voltage loss rate Gini gamma correlation coefficient method Improved sand cat swarm optimization algorithm Long short-term memory degradation prediction

来源：评论

学校读者我要写书评

暂无评论

Groundwater storage anomalies projection by optimized deep learning refines groundwater management in typical arid basins

引用

JOURNAL OF HYdROLOGY 2025年 649卷

作者： deng, Xiaoya Wang, Guangyan Han, Feifei Gong, Yanming Hao, Xingming Zhang, Guangpeng Zhang, Pei Shan, Qianjuan China Inst Water Resources & Hydropower Res Dept Water Resources Beijing 100038 Peoples R China Xinjiang Tarim River Basin Management Bur Korla 841000 Xinjiang Peoples R China Xian Univ Technol Sch Water Resources & Hydropower Xian 710048 Peoples R China Chinese Acad Sci Xinjiang Inst Ecol & Geog Urumqi 830011 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

The GRACE satellite provides tools for accurately characterizing the spatiotemporal variations of regional groundwater storage anomalies (GWSA) under the background of climate change and anthropogenic disturbances. However, its low spatial resolution restricts the refined management of groundwater. Multi-scale geographically weighted regression (MGWR) residuals are innovatively introduced for bias correction, which improves the GRACE-based GWSA downscaling accuracy (average R2 = 0.98). Further application of the Kmeans identifies four spatial distribution patterns of GWSA in the Tarim River mainstream (TRM), which showed a downward trend from 2003 to 2020. However, under effective groundwater management (such as ecological water transfer, ecological gate water diversion, etc.), the decline rate is gradually decreasing. Feature contribution analysis demonstrates that soil moisture storage (SMS), land surface temperature (LST), and normalized difference vegetation index (NdVI) are the primary driving factors of GWSA changes. Using the long short-term memory (LSTM) deep learning model optimized by multi-strategy gray wolf optimizationd* algorithm (MSGWO), the GWSA of four spatial patterns is predicted under two shared socioeconomic pathways (SSPs, including SSP245 and SSP585). The model achieved a maximum R/NSE of 0.95/0.91 on the train dataset and 0.88/0.71 on the test dataset, outperforming similar models. The future groundwater reserves of TRM will show an improving trend, indicating that groundwater management has achieved significant benefits. Notably, high emissions without government intervention (SSP585) have exacerbated the risk of groundwater resource shortages, and refined groundwater management needs to be further strengthened in the future. Overall, the proposed GRACEbased GWSA downscaling framework and MSGWO-LSTM predictive model provide tools for the refined scientific management of groundwater in arid basins.

关键词： GRACE-based groundwater storage anomalies Multi-scale geographically weighted regression Multi-strategy gray wolf optimization algorithm deep learning Arid basins Case study

来源：评论

学校读者我要写书评

暂无评论

dynamic task offloading in edge computing for computer access point selection based on adaptive deep reinforcement learning with meta-heuristic optimization

引用

APPLIEd SOFT COMPUTING 2025年 176卷

作者： Vidya, S. Gopalakrishnan, R. KS Rangasamy Coll Technol Dept Elect & Elect Engn Namakkal 637215 Tamil Nadu India

The computationally intensive tasks are processed by mobile devices which include data processing, virtual reality, and artificial intelligence. The computational resources of the mobile devices are very low so they are suited to perform all tasks with low latency. Mobile Edge Computing (MEC) is a cutting-edge computing model that offloads computation-intensive tasks to MEC servers to increase the capability of computing in Mobile devices (Mds). due to the extensive use of Wireless Local Area Networks (WLAN), each Md can use numerous Wireless Access Points (WAPs) to offload tasks to a server. In this research work, the task offloading problem is determined by considering the delay-sensitive task along with edge load dynamics to reduce the long-term cost. The distributed* algorithm based on Adaptive deep Reinforcement Learning (AdRL) is introduced, where every device is analyzed for offloading decisions without knowing the task model of other devices. The parameters in the model are optimized using the Fitness-based Piranha Foraging Optimizationd* algorithm (F-PFOA) to enhance the performance of the model. Finally, the evaluation is done by using the various metrics to showcase the effectiveness of the proposed model, and it gives the throughput is 93.5, which is enhanced than other existing models. Thus, the simulation outcome with a greater number of mobile devices and corresponding edge nodes showed that the developed optimization minimizes the dropped task's ratio and average task delay respectively. The result of the designed model outperformed better than other available models.

关键词： dynamic Task Offloading Mobile Edge Computing Computer Access Point Selection Fitness-Based Piranha Foraging Optimization algorithm Adaptive deep Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

Advancing healthcare systems: A tri-tier architecture by using data communication, AI data generative and regulation and compliance standards

引用

EXPERT SYSTEMS 2025年第2期42卷

作者： Qureshi, Kashif Naseer Nafea, Hanaa Kim, Pyoungwon Univ Limerick Dept Elect & Comp Engn Limerick Ireland Taibah Univ Coll Comp Sci & Engn Dept Comp Sci Al Madinah Al Munawwarah Saudi Arabia Incheon Natl Univ Coll Educ Incheon South Korea Lero Sci Fdn Ireland Res Ctr Software Limerick Ireland

Traditional healthcare systems have suffered from different data communication, security, data processing, and compliance issues. The traditional systems are also not well equipped to handle the new technologies like Artificial Intelligence (AI) by enabling more accurate diagnostics, personalized treatment plans, and improved patient outcomes. The existing data communication and security protocols and compliance are also not fully implemented to tackle the system's challenges. This article proposes a Tri-Tier architecture by using data communication, AI data generative, and regulation and compliance tiers. The data communication tier is based on advanced sensing and monitoring technologies like cloud and edge-based systems integrated with security detection mechanisms. The edge and cloud layer provides the all functions of the perception layer like smart sensing, visual sensing, and monitoring services, and can control the device's perception and behaviour. The second tier provides the AI data generative functionalities to handle real-time synthetic medical images for predictive analytics to enhance patient care. This tier also automates routine tasks, such as administrative work and data analysis, which can free up healthcare professionals to focus on more complex tasks. The last regulation and compliance tier is responsible for handling the standards and compliance for healthcare systems. Experiments are conducted to test the data communication and security level of the proposed architecture. The results showed the suitability of existing solutions and synchronization with the proposed architecture.

关键词： algorithm artificial intelligence compliance data communication data processing education healthcare security systems

来源：评论

学校读者我要写书评

暂无评论

Two-stage robust co-optimization of energy and reserve scheduling for resilient distribution systems considering line reinforcement

引用

ENERGY 2025年 316卷

作者： Han, Haiteng Yu, Lichengzi Zhou, Yizhou Zang, Haixiang Cao, Yang Chen, Sheng Sun, Guoqiang Wei, Zhinong Hohai Univ Sch Elect & Power Engn Nanjing 211100 Peoples R China

In recent years, the resilience of distribution systems has faced challenges due to the increasing frequency of extreme weather events and the intensifying global effects of climate change. To mitigate the adverse effects of these weather occurrences, we propose a day-ahead energy scheduling and line reinforcement strategy designed to address day-ahead spare capacity scheduling during extreme weather conditions, while also accommodating the unpredictability associated with such events. Initially, we integrate a rapid power regulation model for photovoltaic (PV) power plants to enhance the swift regulation of new energy sources. Subsequently, we develop a two-stage robust planning approach aimed at minimizing both load shedding and dispatch costs amidst extreme weather uncertainties. It enhances the system resilience, lowering load shedding by 7.8 %. Finally, the proposed model is decomposed into master and subproblems and solved iteratively through the application of nested column-and-constraint generation (NC&CG)d* algorithm. Numerical results demonstrate that the proposed approach improves economic efficiency by reducing the total investment by 3.8 % and the day-ahead cost by 3.05 %, as well as enhancing the system resilience by mitigating potential load shedding under extreme conditions.

关键词： Two-stage robust optimization day-ahead dispatch distribution systems Extreme weather events Nested column-and-constraint generation algorithm

来源：评论

学校读者我要写书评

暂无评论

Scalable Methods for Multiple Time Series Comparison in Second Order dynamics

引用

TECHNOMETRICS 2025年第1期67卷 82-96页

作者： Jin, Lei Li, Bo Texas A&M Univ Corpus Christi Dept Math & Stat Corpus Christi TX 78412 USA Univ Illinois Dept Stat Champaign IL USA

Statistical comparison of multiple time series in their underlying frequency patterns has many real applications. However, existing methods are only applicable to a small number of mutually independent time series, and empirical results for dependent time series are only limited to comparing two time series. We propose scalable methods based on a newd* algorithm that enables us to compare the spectral density of a large number of time series. The newd* algorithm helps us efficiently obtain all pairwise feature differences in frequency patterns between M time series, which plays an essential role in our methods. When all M time series are independent of each other, we derive the joint asymptotic distribution of their pairwise feature differences. The asymptotic dependence structure between the feature differences motivates our proposed test for multiple mutually independent time series. We then adapt this test to the case of multiple dependent time series by partially accounting for the underlying dependence structure. Additionally, we introduce a global test to further enhance the approach. To examine the finite sample performance of our proposed methods, we conduct simulation studies. The new approaches demonstrate the ability to compare a large number of time series, whether independent or dependent, while exhibiting competitive power. Finally, we apply our methods to compare multiple mechanical vibrational time series.

关键词： algorithm dynamics Pairwise differences Periodogram Spectral method Vibration data

来源：评论

学校读者我要写书评

暂无评论

Assimilation of linear viscoelastic measurements by joint inference of relaxation spectrum

引用

JOURNAL OF RHEOLOGY 2025年第1期69卷 1-14页

作者： Shanbhag, Sachin Ricarte, Ralm G. Ezzeddine, dana Barzycki, daniel Florida State Univ Dept Sci Comp Tallahassee FL 32306 USA Florida State Univ Florida A&M Univ Coll Engn Dept Chem & Biomed Engn Tallahassee FL 32310 USA

We develop a two-stage computational method to assimilate linear viscoelastic material functions (LMFs), viz., stress relaxation modulus, creep compliance, and the complex modulus, by inferring a consensus discrete relaxation spectrum (dRS) that simultaneously fits all three LMFs. In the first stage, the dRS corresponding to the different LMFs is deduced independently, before they are combined heuristically to generate an initial guess for the consensus dRS. In the second stage, this initial guess is refined using nonlinear least squares regression. The effectiveness of this method for data fusion and validation is demonstrated by analyzing experimental data collected on two different polymer melt systems. We also investigate the performance of the method when the timescales probed by the LMFs do not overlap, or are limited to 4-6 decades, as is typically the case for thermorheologically complex materials. To explore these questions, we generate synthetic datasets by obscuring information from one of the experimental datasets. We find that the computational protocol works quite well. As expected, the quality of the inferred dRS is marginally impaired because information is suppressed.

关键词： Linear viscoelasticity Relaxation spectrum data validation algorithm data fusion

来源：评论

学校读者我要写书评

暂无评论

development of a Software and Hardware Complex for Monitoring Processes in Production Systems

引用

SENSORS 2025年第5期25卷 1527-1527页

作者： Pechenin, Vadim Paringer, Rustam Ruzanov, Nikolay Khaimovich, Aleksandr Samara Natl Res Univ Res Lab Artificial Intelligence Prod Syst Moskovskoye Shosse 34 Samara 443086 Russia Samara Natl Res Univ Dept Tech Cybernet Moskovskoye Shosse 34 Samara 443086 Russia Samara Natl Res Univ Dept Engine Prod Technol Moskovskoye Shosse 34 Samara 443086 Russia

The article presents a detailed exposition of a hardware-software complex that has been developed for the purpose of enhancing the productivity of accounting for the state of the production process. This complex facilitates the automation of the identification of parts in production containers and the utilisation of supplementary markers. The complex comprises a mini computer (system unit in industrial version) with connected cameras (IP or WEB), a communication module with LEd and signal lamps, and developed software. The cascaded* algorithm developed for the detection of labels and objects in containers employs trained convolutional neural networks (YOLO and VGG19), thereby enhancing the recognition accuracy while concurrently reducing the size of the training sample for neural networks. The efficacy of the developed system was assessed through laboratory experimentation, which yielded experimental results demonstrating 93% accuracy in detail detection using the developed* algorithm, in comparison to the 72% accuracy achieved through the utilisation of the traditional approach employing a single neural network.

关键词： camera hardware-software complex container detection neural network algorithm

来源：评论

学校读者我要写书评

暂无评论

A REVIEW OFd* algorithmS FOR dISTRIBUTIONALLY ROBUST OPTIMIZATION USING STATISTICAL dISTANCES

引用

JOURNAL OF INdUSTRIAL ANd MANAGEMENT OPTIMIZATION 2025年第3期21卷 1749-1770页

作者： Wang, Zude Jiang, Suhong Lin, Yue Tao, Yuan Chen, Caihua Nanjing Univ Sch Management & Engn Nanjing Peoples R China Nanjing Univ Finance & Econ Sch Accounting Nanjing Peoples R China Chinese Univ Hong Kong Dept Syst Engn & Engn Management Hong Kong Peoples R China

distributionally robust optimization (dRO) utilizing statistical distances has witnessed significant advancements, driven by its appealing properties and promising applications. However, its computational complexity poses a challenge, especially in large-scale scenarios. To address this challenge, extensive research efforts have been directed towards developingd* algorithms tailored for dRO problems utilizing statistical distances. This paper focuses on exploring solution methodologies for dRO problems mainly incorporating both phi-divergences and Wasserstein metric, providing a comprehensive survey of existingd* algorithmic frameworks.

关键词： distributionally robust optimization statistical distance phi-divergence Wasserstein metric algorithm

来源：评论

学校读者我要写书评

暂无评论

ARC-LIGHT:d* algorithm for Robust Characterization of Lunar Surface Imaging for Ground Hazards and Trajectory

引用

AEROSPACE 2025年第3期12卷 177-177页

作者： Cushen, Alexander Bueno, Ariana Carrico, Samuel Wettstein, Corrydon Adalja, Jaykumar Ishvarbhai Shi, Mengxiang Garcia, Naila Garcia, Yuliana Gamba, Mirko Ruf, Christopher Univ Michigan Climate & Space Sci & Engn Dept Ann Arbor MI 48109 USA Univ Michigan Dept Aerosp Engn Ann Arbor MI 48109 USA Univ Michigan Elect Engn & Comp Sci Dept Ann Arbor MI 48109 USA Univ Michigan Dept Mech Engn Ann Arbor MI 48109 USA

Safe and reliable lunar landings are crucial for future exploration of the Moon. The regolith ejected by a lander's rocket exhaust plume represents a significant obstacle in achieving this goal. It prevents spacecraft from reliably utilizing their navigation sensors to monitor their trajectory and spot emerging surface hazards as they near the surface. As part of NASA's 2024 Human Lander Challenge (HuLC), the team at the University of Michigan developed an innovative concept to help mitigate this issue. We developed and implemented a machine learning (ML)-based sensor fusion system, ARC-LIGHT, that integrates sensor data from the cameras, lidars, or radars that landers already carry but disable during the final landing phase. Using these data streams, ARC-LIGHT will remove erroneous signals and recover a useful detection of the surface features to then be used by the spacecraft to correct its descent profile. It also offers a layer of redundancy for other key sensors, like inertial measurement units. The feasibility of this technology was validated through development of a prototyped* algorithm, which was trained on data from a purpose-built testbed that simulates imaging through a dusty environment. Based on these findings, a development timeline, risk analysis, and budget for ARC-LIGHT to be deployed on a lunar landing was created.

关键词： Plume Surface Interaction (PSI) lunar landing navigation machine learning Artemis dust imaging algorithm surface hazards

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：