期刊文献+
共找到5,575篇文章
< 1 2 250 >
每页显示 20 50 100
Road pavement performance prediction using a time series long short-term memory (LSTM) model
1
作者 Chuanchuan HOU Huan WANG +1 位作者 Wei GUAN Jun CHEN 《Journal of Zhejiang University-Science A(Applied Physics & Engineering)》 2025年第5期424-437,共14页
Intelligent maintenance of roads and highways requires accurate deterioration evaluation and performance prediction of asphalt pavement.To this end,we develop a time series long short-term memory(LSTM)model to predict... Intelligent maintenance of roads and highways requires accurate deterioration evaluation and performance prediction of asphalt pavement.To this end,we develop a time series long short-term memory(LSTM)model to predict key performance indicators(PIs)of pavement,namely the international roughness index(IRI)and rutting depth(RD).Subsequently,we propose a comprehensive performance indicator for the pavement quality index(PQI),which leverages the highway performance assessment standard method,entropy weight method,and fuzzy comprehensive evaluation method.This indicator can evaluate the overall performance condition of the pavement.The data used for the model development and analysis are extracted from tests on two full-scale accelerated test tracks,called MnRoad and RIOHTrack.Six variables are used as predictors,including temperature,precipitation,total traffic volume,asphalt surface layer thickness,pavement age,and maintenance condition.Furthermore,wavelet denoising is performed to analyze the impact of missing or abnormal data on the LSTM model accuracy.In comparison to a traditional autoregressive integrated moving average(ARIMAX)model,the proposed LSTM model performs better in terms of PI prediction and resiliency to noise.Finally,the overall prediction accuracy of our proposed performance indicator PQI is 93.8%. 展开更多
关键词 Asphalt pavement performance model International roughness index(IRI) Rutting depth(RD) Long short-term memory(lstm)model Pavement management system
原文传递
Informer-LSTM融合算法在蓝莓基质温湿度预测中的研究与应用
2
作者 胡玲艳 陈鹏宇 +6 位作者 郭占俊 徐国辉 秦山 付康 盖荣丽 汪祖民 张雨萌 《郑州大学学报(理学版)》 北大核心 2026年第1期78-86,共9页
为了精准预测温室蓝莓基质的温湿度变化趋势,提出一种融合Informer-LSTM算法的温湿度预测方法。以温室蓝莓现场环境数据为研究对象,使用LSTM算法捕捉时间序列数据中的依赖关系并与自注意力机制相结合,使模型在聚焦自注意力特征的同时兼... 为了精准预测温室蓝莓基质的温湿度变化趋势,提出一种融合Informer-LSTM算法的温湿度预测方法。以温室蓝莓现场环境数据为研究对象,使用LSTM算法捕捉时间序列数据中的依赖关系并与自注意力机制相结合,使模型在聚焦自注意力特征的同时兼顾LSTM特征,以增强其长期记忆力。在生成初步预测序列后,再应用LSTM算法修正模型的短期注意力,提高模型的反应速度。实验结果显示,Informer-LSTM预测模型在预测准确率、鲁棒性和响应速度等方面都有显著的优势。当温度湿度等时序输入数据发生明显变化时,模型能快速捕获短期内输入数据的动态模式变化。该模型在智慧温室管理中,对辅助人工决策及实现智能化控制具有较高实际价值。 展开更多
关键词 智慧农业 温室蓝莓 Informer模型 lstm模型 温湿度预测
在线阅读 下载PDF
基于Modelica-LSTM双驱动的数字孪生机床热误差补偿模型构建
3
作者 孙丽 王诗灏 +3 位作者 姜锋 关咏臻 徐家淳 刘荣玺 《制造技术与机床》 北大核心 2025年第10期205-213,共9页
针对数控机床在高速、高负载运行中因热变形导致的热误差问题,提出一种基于Modelica多领域建模与长短期记忆网络(long short-term memory,LSTM)联合驱动的热误差补偿方法。通过Modelica构建机床机械、电气、热力学多物理场耦合的高保真... 针对数控机床在高速、高负载运行中因热变形导致的热误差问题,提出一种基于Modelica多领域建模与长短期记忆网络(long short-term memory,LSTM)联合驱动的热误差补偿方法。通过Modelica构建机床机械、电气、热力学多物理场耦合的高保真数字孪生模型,结合LSTM对机理模型未覆盖的非线性动态误差进行数据驱动补偿。实验以五轴数控加工中心DMG MORI DMU 50为对象,在预热、阶梯加载及扰动工况下采集温度、振动和热误差数据,验证模型性能。结果表明,Modelica-LSTM双驱动模型相较于单一Modelica机理模型,均方根误差降低51.2%,补偿后误差波动幅度减少72%,在高温及动态工况下显著提升预测精度。该方法为高精密机床热误差补偿提供了物理与数据协同驱动的有效解决方案。 展开更多
关键词 数控机床 热误差补偿 modelICA 长短期记忆网络 多领域建模 数字孪生
在线阅读 下载PDF
基于LSTM-Transformer模型的突水条件下矿井涌水量预测
4
作者 李振华 姜雨菲 +1 位作者 杜锋 王文强 《河南理工大学学报(自然科学版)》 北大核心 2026年第1期77-85,共9页
目的矿井涌水量精准预测对预防矿井水害和保障矿井安全生产具有重要意义,为精准预测矿井涌水量,构建适用于华北型煤田受底板L_(1-4)灰岩含水层和奥陶系灰岩含水层水害威胁的矿井涌水量预测模型。方法以河南某典型矿井的水文监测数据为基... 目的矿井涌水量精准预测对预防矿井水害和保障矿井安全生产具有重要意义,为精准预测矿井涌水量,构建适用于华北型煤田受底板L_(1-4)灰岩含水层和奥陶系灰岩含水层水害威胁的矿井涌水量预测模型。方法以河南某典型矿井的水文监测数据为基础,提出LSTMTransformer模型。利用LSTM捕捉矿井涌水量的动态时序特征,通过Transformer的多头注意力机制分析含水层水位变化和矿井涌水量之间的复杂时序关联,构建水位动态变化驱动下的矿井涌水量精准预测框架。结果结果表明,LSTM-Transformer模型预测精度显著优于LSTM,CNN,Transformer和CNN-LSTM模型的,其均方根误差为20.91 m^(3)/h,平均绝对误差为16.08 m^(3)/h,平均绝对百分比误差为1.12%,且和单因素涌水量预测模型相比,水位-涌水量双因素预测模型预测结果更加稳定。结论LSTM-Transformer模型成功克服传统方法在捕捉复杂水文地质系统中水位-涌水量动态关联上的局限,为矿井涌水量动态预测提供可解释性强、鲁棒性好的解决方案,也为类似地质条件下矿井涌水量预测提供了新方法。 展开更多
关键词 涌水量预测 水位动态响应 lstm-Transformer耦合模型 时间序列预测 注意力机制 矿井安全生产
在线阅读 下载PDF
结合注意力机制的ConvLSTM与新安江模型相融合的混合水文模型
5
作者 张珂 刘杰 +2 位作者 王宇昊 申笑萱 齐千嘉 《水资源保护》 北大核心 2026年第1期137-143,151,共8页
为提高新安江模型(XAJ)在中小流域汇流计算中的精度,构建了结合注意力机制的卷积长短期记忆神经网络(ConvLSTM),用于替代XAJ中的汇流模块,从而建立了结合物理机制与机器学习技术的混合水文模型XAJ-ACL,基于呈村流域实测数据,探究了XAJ-... 为提高新安江模型(XAJ)在中小流域汇流计算中的精度,构建了结合注意力机制的卷积长短期记忆神经网络(ConvLSTM),用于替代XAJ中的汇流模块,从而建立了结合物理机制与机器学习技术的混合水文模型XAJ-ACL,基于呈村流域实测数据,探究了XAJ-ACL在中小流域有限样本容量条件下的性能,并分别采用ConvLSTM和传统LSTM替代XAJ汇流模块,构建了混合水文模型XAJ-CL和XAJ-LSTM进行对比分析。结果表明:在呈村流域径流模拟中,XAJ-ACL的模拟精度优于XAJ,测试期XAJ-ACL的纳什效率系数为0.85,相关系数为0.93,均高于XAJ;在3组小容量样本训练中,测试期XAJ-ACL的平均纳什效率系数分别为0.847、0.832和0.808,均高于XAJ-CL和XAJ-LSTM,且模拟结果表现出更好的稳定性;与XAJ相比,XAJ-ACL显著提升了有限资料条件下对中小流域汇流过程非线性规律的模拟能力。 展开更多
关键词 新安江模型 注意力机制 卷积长短期记忆神经网络 混合水文模型 汇流过程 径流模拟 呈村流域
在线阅读 下载PDF
CNN-BiLSTM残差网络的抗体抗原相互作用预测模型
6
作者 周宇 胡俊 周晓根 《小型微型计算机系统》 北大核心 2026年第1期73-79,共7页
抗体与抗原之间的相互作用是免疫系统识别和对抗病原体的核心机制,同时也是抗体药物设计的关键环节.近年来涌现出一些基于深度学习的方法来提升抗体抗原相互作用预测的效率和精度.为进一步提高预测性能,本文提出了一种新型深度学习模型C... 抗体与抗原之间的相互作用是免疫系统识别和对抗病原体的核心机制,同时也是抗体药物设计的关键环节.近年来涌现出一些基于深度学习的方法来提升抗体抗原相互作用预测的效率和精度.为进一步提高预测性能,本文提出了一种新型深度学习模型CBAAI.该模型整合了卷积神经网络(CNN)、双向长短时记忆网络(BiLSTM)以及残差网络的优势.具体而言,CBAAI首先将抗体和抗原序列输入蛋白质语言模型,提取高质量的序列特征嵌入.然后,通过基于CNN和BiLSTM的残差单元对序列特征进行融合,以构建抗体抗原相互作用预测模型.在HIV和SARS-CoV-2两个独立测试集上的实验结果表明,与当前的主流方法相比,CBAAI在多个评估指标上均取得了显著的性能提升. 展开更多
关键词 抗体 抗原 蛋白质语言模型 卷积神经网络 双向长短时记忆网络
在线阅读 下载PDF
Dynamic intelligent prediction approach for landslide displacement based on biological growth models and CNN-LSTM 被引量:2
7
作者 WANG Ziqian FANG Xiangwei +3 位作者 ZHANG Wengang WANG Luqi WANG Kai CHEN Chao 《Journal of Mountain Science》 2025年第1期71-88,共18页
Influenced by complex external factors,the displacement-time curve of reservoir landslides demonstrates both short-term and long-term diversity and dynamic complexity.It is difficult for existing methods,including Reg... Influenced by complex external factors,the displacement-time curve of reservoir landslides demonstrates both short-term and long-term diversity and dynamic complexity.It is difficult for existing methods,including Regression models and Neural network models,to perform multi-characteristic coupled displacement prediction because they fail to consider landslide creep characteristics.This paper integrates the creep characteristics of landslides with non-linear intelligent algorithms and proposes a dynamic intelligent landslide displacement prediction method based on a combination of the Biological Growth model(BG),Convolutional Neural Network(CNN),and Long ShortTerm Memory Network(LSTM).This prediction approach improves three different biological growth models,thereby effectively extracting landslide creep characteristic parameters.Simultaneously,it integrates external factors(rainfall and reservoir water level)to construct an internal and external comprehensive dataset for data augmentation,which is input into the improved CNN-LSTM model.Thereafter,harnessing the robust feature extraction capabilities and spatial translation invariance of CNN,the model autonomously captures short-term local fluctuation characteristics of landslide displacement,and combines LSTM's efficient handling of long-term nonlinear temporal data to improve prediction performance.An evaluation of the Liangshuijing landslide in the Three Gorges Reservoir Area indicates that BG-CNN-LSTM exhibits high prediction accuracy,excellent generalization capabilities when dealing with various types of landslides.The research provides an innovative approach to achieving the whole-process,realtime,high-precision displacement predictions for multicharacteristic coupled landslides. 展开更多
关键词 Reservoir landslides Displacement prediction CNN lstm Biological growth model
原文传递
A Comparative Study of Optimized-LSTM Models Using Tree-Structured Parzen Estimator for Traffic Flow Forecasting in Intelligent Transportation 被引量:1
8
作者 Hamza Murad Khan Anwar Khan +3 位作者 Santos Gracia Villar Luis Alonso DzulLopez Abdulaziz Almaleh Abdullah M.Al-Qahtani 《Computers, Materials & Continua》 2025年第5期3369-3388,共20页
Traffic forecasting with high precision aids Intelligent Transport Systems(ITS)in formulating and optimizing traffic management strategies.The algorithms used for tuning the hyperparameters of the deep learning models... Traffic forecasting with high precision aids Intelligent Transport Systems(ITS)in formulating and optimizing traffic management strategies.The algorithms used for tuning the hyperparameters of the deep learning models often have accurate results at the expense of high computational complexity.To address this problem,this paper uses the Tree-structured Parzen Estimator(TPE)to tune the hyperparameters of the Long Short-term Memory(LSTM)deep learning framework.The Tree-structured Parzen Estimator(TPE)uses a probabilistic approach with an adaptive searching mechanism by classifying the objective function values into good and bad samples.This ensures fast convergence in tuning the hyperparameter values in the deep learning model for performing prediction while still maintaining a certain degree of accuracy.It also overcomes the problem of converging to local optima and avoids timeconsuming random search and,therefore,avoids high computational complexity in prediction accuracy.The proposed scheme first performs data smoothing and normalization on the input data,which is then fed to the input of the TPE for tuning the hyperparameters.The traffic data is then input to the LSTM model with tuned parameters to perform the traffic prediction.The three optimizers:Adaptive Moment Estimation(Adam),Root Mean Square Propagation(RMSProp),and Stochastic Gradient Descend with Momentum(SGDM)are also evaluated for accuracy prediction and the best optimizer is then chosen for final traffic prediction in TPE-LSTM model.Simulation results verify the effectiveness of the proposed model in terms of accuracy of prediction over the benchmark schemes. 展开更多
关键词 Short-term traffic prediction sequential time series prediction TPE tree-structured parzen estimator lstm hyperparameter tuning hybrid prediction model
在线阅读 下载PDF
面向可重构结构的LSTM混合压缩优化方法
9
作者 吴海 蒋林 +1 位作者 李远成 刘朋飞 《电讯技术》 北大核心 2026年第1期71-79,共9页
可重构结构因其高灵活性和高并行性的特点,已成为如长短期记忆(Long Short-term Memory,LSTM)网络等计算密集型应用的最佳选择之一。然而,随着参数和计算量的增加,带来存储和带宽的更高需求,严重限制了计算效率的提升。针对该问题,提出... 可重构结构因其高灵活性和高并行性的特点,已成为如长短期记忆(Long Short-term Memory,LSTM)网络等计算密集型应用的最佳选择之一。然而,随着参数和计算量的增加,带来存储和带宽的更高需求,严重限制了计算效率的提升。针对该问题,提出了一种面向可重构结构的LSTM混合压缩优化方法。基于LSTM网络在训练过程中对误差的敏感性,利用不同的压缩算法对LSTM网络进行压缩,并在压缩后再训练,分析模型精度恢复情况及收敛时间,将网络中的门控单元分为误差敏感组和误差不敏感组。使用Top-k剪枝(Top-k Pruning)策略和块循环矩阵变换策略分别对误差敏感组和误差不敏感组的门控单元进行压缩。最后,在基于Virtex UltraScale VU440 FPGA(Field Programmable Gate Array)开发板搭建的可重构阵列处理器上实现LSTM网络。结果表明,LSTM网络的压缩比达到了38.4,硬件加速比达到了1.41,精度损失约为1.7%,且硬件资源消耗也有一定减少。 展开更多
关键词 长短期记忆网络 可重构结构 模型压缩
在线阅读 下载PDF
Load-measurement method for floating offshore wind turbines based on a long short-term memory (LSTM) neural network
10
作者 Yonggang LIN Xiangheng FENG +1 位作者 Hongwei LIU Yong SUN 《Journal of Zhejiang University-Science A(Applied Physics & Engineering)》 2025年第5期456-470,共15页
Complicated loads encountered by floating offshore wind turbines(FOWTs)in real sea conditions are crucial for future optimization of design,but obtaining data on them directly poses a challenge.To address this issue,w... Complicated loads encountered by floating offshore wind turbines(FOWTs)in real sea conditions are crucial for future optimization of design,but obtaining data on them directly poses a challenge.To address this issue,we applied machine learning techniques to obtain hydrodynamic and aerodynamic loads of FOWTs by measuring platform motion responses and wave-elevation sequences.First,a computational fluid dynamics(CFD)simulation model of the floating platform was established based on the dynamic fluid body interaction technique and overset grid technology.Then,a long short-term memory(LSTM)neural network model was constructed and trained to learn the nonlinear relationship between the waves,platform-motion inputs,and hydrodynamic-load outputs.The optimal model was determined after analyzing the sensitivity of parameters such as sample characteristics,network layers,and neuron numbers.Subsequently,the effectiveness of the hydrodynamic load model was validated under different simulation conditions,and the aerodynamic load calculation was completed based on the D'Alembert principle.Finally,we built a hybrid-scale FOWT model,based on the software in the loop strategy,in which the wind turbine was replaced by an actuation system.Model tests were carried out in a wave basin and the results demonstrated that the root mean square errors of the hydrodynamic and aerodynamic load measurements were 4.20%and 10.68%,respectively. 展开更多
关键词 Floating offshore wind turbine(FOWT) Long short-term memory(lstm)neural network Machine learning technique Load measurement Hybrid-scale model test
原文传递
Enhanced forecasting of coastal chlorophyll-a through AdaBoost-optimized LSTM models
11
作者 Wenxiang Ding Caiyun Zhang +2 位作者 Xueding Li Liyu Zhang Nengwang Chen 《Acta Oceanologica Sinica》 2025年第7期147-160,共14页
Algal blooms pose significant threats to marine ecosystems and human health.Accurate forecasting of chlorophyll-a(Chl-a)concentration is critical for effective control of harmful algal blooms(HABs).This study proposes... Algal blooms pose significant threats to marine ecosystems and human health.Accurate forecasting of chlorophyll-a(Chl-a)concentration is critical for effective control of harmful algal blooms(HABs).This study proposes a novel approach for enhancing Chl-a concentration forecasting by integrating the AdaBoost algorithm with long short-term memory(LSTM)neural networks.We developed a strong forecasting model by combining adaptive boosting(AdaBoost)with LSTM models in Xiamen Bay,China.This model achieved higher correlation coefficients and lower root mean square errors than individual weak models.The AdaBoost-optimized model increased the frequency of low absolute errors while decreasing the occurrence of high absolute errors,which indicated improved overall prediction accuracy and reliability.Moreover,the model effectively reduced performance fluctuations,which are frequent in deep learning models.The application of a non-uniform initial weighting scheme within the AdaBoost framework further enhanced model performance for high Chl-a concentration values,which are critical for detecting HABs.The optimization effect of AdaBoost was validated by applying it to data collected from the Ningde area.A robust framework is provided in this study to improve Chl-a concentration predictions and offer valuable insights for managing coastal ecosystems facing the challenges of algal blooms. 展开更多
关键词 chlorophyll-a concentration forecasting long short-term memory(lstm) ADABOOST deep learning ensemble learning
在线阅读 下载PDF
基于注意力机制LSTM神经网络的北方岩溶大泉水位预测研究
12
作者 黄林显 徐征和 +7 位作者 支传顺 李双 刘治政 邢立亭 朱恒华 王晓玮 毕雯雯 胡晓农 《地学前缘》 北大核心 2026年第1期419-431,共13页
岩溶地下水是北方岩溶区重要供水水源,准确预测其水位动态对地下水资源科学管理和保护具有重要意义。但岩溶含水系统具有强烈的非均质性和各向异性,导致其水位动态往往体现出非平稳及非线性波动状态,造成进行地下水位预测时易产生较大... 岩溶地下水是北方岩溶区重要供水水源,准确预测其水位动态对地下水资源科学管理和保护具有重要意义。但岩溶含水系统具有强烈的非均质性和各向异性,导致其水位动态往往体现出非平稳及非线性波动状态,造成进行地下水位预测时易产生较大误差。论文提出一种耦合注意力机制(Attention)和长短时记忆(LSTM,Long Short-Term Memory)神经网络的多变量趵突泉地下水位预测模型,利用泉域2013—2024年日降水(代表补给项)及水汽压、日气温和开采量(代表排泄项)进行模型训练和预测,结果表明:①采用BEAST(Bayesian Estimator of Abrupt Change,Seasonality,and Trend)算法对1958—2024年趵突泉水位时间序列进行分解,共识别出四个突变点并以此为依据将水位动态划分为四个阶段;②互相关分析揭示降雨和趵突泉水位动态变化之间存在2~3个月的时间滞后,表明两者之间动态变化较为一致;③所提出的预测模型以多种变量(降水量、水汽压、气温及开采量)作为模型输入,不同变量间的交互作用可相互验证,能有效提升预测精度;④采用正弦函数拟合日气温数据,可消除测量误差影响,能在一定程度上提高预测精度;⑤相较于单一LSTM神经网络和门控循环单元(GRU)神经网络,LSTM_Attention神经网络由于引入注意力机制,能聚焦更重要特征的影响,从而显著提高预测精度,其水位预测RMSE和R 2值分别为0.13 m和0.94。总体来说,本文所提出的LSTM_Attention神经网络岩溶地下水位预测模型具有较强的准确性和稳定性,可为岩溶地下水位精确预测提供借鉴。 展开更多
关键词 北方岩溶 水位预测 多变量模拟 lstm_Attention神经网络
在线阅读 下载PDF
An artificial neural network-based data-driven constitutive model of shape memory alloys
13
作者 Xingyu Zhou Ziang Liu +1 位作者 Chao Yu Guozheng Kang 《Acta Mechanica Sinica》 2025年第8期108-125,共18页
The constitutive models of shape memory alloys(SMAs)play an important role in facilitating the widespread application of such types of alloys in various engineering fields.However,to accurately describe the deformatio... The constitutive models of shape memory alloys(SMAs)play an important role in facilitating the widespread application of such types of alloys in various engineering fields.However,to accurately describe the deformation behaviors of SMAs,the concepts in classical plasticity are employed in the existing constitutive models,and a series of complex mathematical equations are involved.Such complexity brings inconvenience for the construction,implementation,and application of the constitutive models.To overcome these shortcomings,a data-driven constitutive model of SMAs is developed in this work based on the artificial neural network(ANN).In the proposed model,the components of the strain tensor in principal space,ambient temperature,and the maximum equivalent strain in the deformation history from the initial state to the current loading state are chosen as the input features,and the components of the stress tensor in principal space are set as the output.The proposed ANN-based constitutive model is implemented into the finite element program ABAQUS by deriving its consistent tangent modulus and writing a user-defined material subroutine.The stress-strain responses of SMA material under various loading paths and at different ambient temperatures are used to train the ANN model,which is generated from the existing constitutive model(numerical experiments).To validate the capability of the proposed model,the predicted stress-strain responses of SMA material,and the global and local responses of two typical SMA structures are compared with the corresponding numerical experiments.This work demonstrates a good potential to obtain the constitutive model of SMAs by pure data and avoid the need for vast stores of knowledge for the construction of constitutive models. 展开更多
关键词 Shape memory alloys Constitutive model DATA-DRIVEN Artificial neural network
原文传递
A Hybrid LSTM-Single Candidate Optimizer Model for Short-Term Wind Power Prediction
14
作者 Mehmet Balci Emrah Dokur Ugur Yuzgec 《Computer Modeling in Engineering & Sciences》 2025年第7期945-968,共24页
Accurate prediction of wind energy plays a vital role in maintaining grid stability and supporting the broader shift toward renewable energy systems.Nevertheless,the inherently variable nature of wind and the intricac... Accurate prediction of wind energy plays a vital role in maintaining grid stability and supporting the broader shift toward renewable energy systems.Nevertheless,the inherently variable nature of wind and the intricacy of high-dimensional datasets pose major obstacles to reliable forecasting.To address these difficulties,this study presents an innovative hybrid method for short-term wind power prediction by combining a Long Short-Term Memory(LSTM)network with a Single Candidate Optimizer(SCO)algorithm.In contrast to conventional techniques that rely on random parameter initialization,the proposed LSTM-SCO framework leverages the distinctive capability of SCO to work with a single candidate solution,thereby substantially reducing the computational overhead compared to traditional population-based metaheuristics.The performance of the model was benchmarked against various classical and deep learning models across datasets from three geographically diverse sites,using multiple evaluation metrics.Experimental findings demonstrate that the SCO-optimized model enhances prediction accuracy by up to 12.5%over standard LSTM implementations. 展开更多
关键词 lstm wind forecasting hybrid forecasting model single candidate optimizer
在线阅读 下载PDF
Runoff simulation and prediction of typical basins in the Jiziwan Region of the Yellow River Basin based on Long Short-Term Memory(LSTM)neural network
15
作者 SUN Jiaqi ZHANG Jianyun +4 位作者 WANG Xiaojun WANG Ao WU Xijun ZOU Rui MIAO Ping 《Journal of Mountain Science》 2025年第10期3545-3563,共19页
This study employs the Long Short-Term Memory(LSTM)rainfall-runoff model to simulate and predict runoff in typical basins of the Jiziwan Region of the Yellow River,aiming to overcome the shortcomings of traditional hy... This study employs the Long Short-Term Memory(LSTM)rainfall-runoff model to simulate and predict runoff in typical basins of the Jiziwan Region of the Yellow River,aiming to overcome the shortcomings of traditional hydrological models in complex nonlinear environments.The Jiziwan Region of the Yellow River is affected by human activities such as urbanization,agricultural development,and water resource management,leading to increasingly complex hydrological processes.Traditional hydrological models struggle to effectively capture the relationship between rainfall and runoff.The LSTM rainfall-runoff model,using deep learning techniques,automatically extracts features from data,identifies complex patterns and long-term dependency in time series,and provides more accurate and reliable runoff predictions.The results demonstrate that the LSTM rainfall-runoff model adapts well to the complex hydrological characteristics of the Jiziwan Region,showing superior performance over traditional hydrological models,especially in addressing the changing trends under the influence of climate change and human activities.By analyzing the interannual and within-year variations of runoff under different climate change scenarios,the model can predict the evolution trends of runoff under future climate conditions,providing a scientific basis for water resource management and decision-making.The results indicate that under different climate change scenarios,the runoff in several typical basins of the Jiziwan Region exhibits different variation trends.Under SSP1-2.6 and SSP2-4.5,some basins,such as the Wuding River Basin,Tuwei River Basin,and Gushanchuan Basin,show a decreasing trend in annual runoff.For example,in the Wuding River Basin,the average runoff from 2025 to 2040 is 12.48 m^(3)/s(SSP1-2.6),with an annual decrease of 0.10 m^(3)/s;in the Tuwei River Basin,the runoff from 2025 to 2040 is 12.96 m^(3)/s(SSP1-2.6),with an annual decrease of 0.10 m^(3)/s.In contrast,under SSP3-7.0 and SSP5-8.5,with climate warming and changes in precipitation patterns,runoff in some basins shows an increasing trend,particularly during the snowmelt period and with increased summer precipitation,leading to a significant rise in runoff. 展开更多
关键词 lstm rainfall-runoff model Climate scenarios RUNOFF Yellow River Basin
原文传递
基于Prophet-LSTM模型的流感节假日效应分析及预测效果研究
16
作者 程文林 毛军军 +1 位作者 汪亦哲 吴家兵 《公共卫生与预防医学》 2026年第1期8-12,共5页
目的基于Prophet-LSTM混合模型探究节假日效应与防控措施对合肥市流感发展特征及发病趋势的影响,通过比较不同预测模型的性能,验证Prophet-LSTM模型在流感预测中的适用性。方法收集2016—2024年合肥市流感发病数据,构建Prophet-LSTM特... 目的基于Prophet-LSTM混合模型探究节假日效应与防控措施对合肥市流感发展特征及发病趋势的影响,通过比较不同预测模型的性能,验证Prophet-LSTM模型在流感预测中的适用性。方法收集2016—2024年合肥市流感发病数据,构建Prophet-LSTM特征分析与预测模型,分析节假日效应和防控措施对流感发病趋势的影响;同时建立ARIMA、GRU、TimeGPT等对比模型,在相同测试集上比较各模型的预测性能。结果分析表明,元旦、春节、国庆等节假日期间流感发病率显著上升,而防控措施实施期间发病率呈现下降趋势。Prophet-LSTM模型的预测值与实际值高度吻合,其MAE(0.209)、MSE(0.195)和IA(0.914)均优于对比模型,展现出更高的预测精度和趋势拟合能力。结论Prophet-LSTM模型能有效捕捉流感发病的时空特征,在纳入节假日效应和防控措施因素后表现出更好的预测性能,证明其在流感预测领域具有显著优势和应用价值。 展开更多
关键词 Prophet-lstm 流感 节假日效应 防控效应 预测模型
原文传递
Attention⁃Based Multi⁃scale CNN and LSTM Model for Remaining Useful Life Estimation
17
作者 DUAN Jiajun LU Zhong DU Zhiqiang 《Transactions of Nanjing University of Aeronautics and Astronautics》 2025年第S1期64-77,共14页
Current aero-engine life prediction areas typically focus on single-scale degradation features,and the existing methods are not comprehensive enough to capture the relationship within time series data.To address this ... Current aero-engine life prediction areas typically focus on single-scale degradation features,and the existing methods are not comprehensive enough to capture the relationship within time series data.To address this problem,we propose a novel remaining useful life(RUL)estimation method based on the attention mechanism.Our approach designs a two-layer multi-scale feature extraction module that integrates degradation features at different scales.These features are then processed in parallel by a self-attention module and a three-layer long short-term memory(LSTM)network,which together capture long-term dependencies and adaptively weigh important feature.The integration of degradation patterns from both components into the attention module enhances the model’s ability to capture long-term dependencies.Visualizing the attention module’s weight matrices further improves model interpretability.Experimental results on the C-MAPSS dataset demonstrate that our approach outperforms the existing state-of-the-art methods. 展开更多
关键词 attention mechanism convolutional neural network(CNN) long short-term memory(lstm) multi-scale feature extraction
在线阅读 下载PDF
基于ARIMA-LSTM模型的MSWI过程CO_(2)排放浓度多步预测
18
作者 汤健 王子 +2 位作者 夏恒 王天峥 乔俊飞 《北京工业大学学报》 北大核心 2026年第2期175-188,共14页
针对城市固废焚烧(municipal solid waste incineration,MSWI)过程CO_(2)排放兼具线性趋势与非线性波动的复杂动态特性,现有单一预测难以准确拟合的问题,提出基于差分整合移动平均自回归-长短期记忆(autoregressive integrated moving a... 针对城市固废焚烧(municipal solid waste incineration,MSWI)过程CO_(2)排放兼具线性趋势与非线性波动的复杂动态特性,现有单一预测难以准确拟合的问题,提出基于差分整合移动平均自回归-长短期记忆(autoregressive integrated moving average-long short-term memory,ARIMA-LSTM)模型的CO_(2)排放浓度的多步预测方法。首先,采用ARIMA算法构建线性主模型以进行CO_(2)排放浓度预测;然后,以主模型的预测残差为真值,采用LSTM算法构建非线性补偿模型;最后,将主模型和补偿模型的预测值进行组合得到超前多步的预测结果。基于北京某MSWI工厂的真实CO_(2)数据集验证了所构建混合模型的有效性。 展开更多
关键词 城市固废焚烧(municipal solid waste incineration MSWI) CO_(2)排放 多步预测 差分整合移动平均自回归模型 长短期记忆(long short-term memory lstm)网络 混合模型
在线阅读 下载PDF
Prediction of Self-Care Behaviors in Patients Using High-Density Surface Electromyography Signals and an Improved Whale Optimization Algorithm-Based LSTM Model
19
作者 Shuai Huang Dan Liu +4 位作者 Youfa Fu Jiadui Chen Ling He Jing Yan Di Yang 《Journal of Bionic Engineering》 2025年第4期1963-1984,共22页
Stroke survivors often face significant challenges when performing daily self-care activities due to upper limb motor impairments.Traditional surface electromyography(sEMG)analysis typically focuses on isolated hand p... Stroke survivors often face significant challenges when performing daily self-care activities due to upper limb motor impairments.Traditional surface electromyography(sEMG)analysis typically focuses on isolated hand postures,overlooking the complexity of object-interactive behaviors that are crucial for promoting patient independence.This study introduces a novel framework that combines high-density sEMG(HD-sEMG)signals with an improved Whale Optimization Algorithm(IWOA)-optimized Long Short-Term Memory(LSTM)network to address this limitation.The key contributions of this work include:(1)the creation of a specialized HD-sEMG dataset that captures nine continuous self-care behaviors,along with time and posture markers,to better reflect real-world patient interactions;(2)the development of a multi-channel feature fusion module based on Pascal’s theorem,which enables efficient signal segmentation and spatial–temporal feature extraction;and(3)the enhancement of the IWOA algorithm,which integrates optimal point set initialization,a diversity-driven pooling mechanism,and cosine-based differential evolution to optimize LSTM hyperparameters,thereby improving convergence and global search capabilities.Experimental results demonstrate superior performance,achieving 99.58%accuracy in self-care behavior recognition and 86.19%accuracy for 17 continuous gestures on the Ninapro db2 benchmark.The framework operates with low latency,meeting the real-time requirements for assistive devices.By enabling precise,context-aware recognition of daily activities,this work advances personalized rehabilitation technologies,empowering stroke patients to regain autonomy in self-care tasks.The proposed methodology offers a robust,scalable solution for clinical applications,bridging the gap between laboratory-based gesture recognition and practical,patient-centered care. 展开更多
关键词 Self-care behaviors High-density surface electromyography(HD-sEMG) Long Short-Term memory(lstm)network Multi-channel feature fusion
在线阅读 下载PDF
Bi-LSTM模型在遥感海浪数据质量控制中的应用
20
作者 满世豪 谢涛 +2 位作者 李建 王超 张雪红 《应用海洋学学报》 北大核心 2026年第1期65-71,共7页
在遥感海浪数据质量控制研究中,由于数据的复杂与不规则性,传统质量控制方法对海浪数据单点异常值的检测具有一定局限性。深度学习具有强大的特征学习能力,在解决非线性复杂问题方面具有一定优势,将其应用在数据质量控制领域可以提高异... 在遥感海浪数据质量控制研究中,由于数据的复杂与不规则性,传统质量控制方法对海浪数据单点异常值的检测具有一定局限性。深度学习具有强大的特征学习能力,在解决非线性复杂问题方面具有一定优势,将其应用在数据质量控制领域可以提高异常值检测能力。本研究采用遥感海浪有效波高数据,构建双向长短期记忆网络(bi-directional long short term memory,Bi-LSTM)模型对有效波高进行预测,结合阈值方法进行异常检测,与3σ准则法、孤立森林模型法、 LSTM模型法以及VAE-LSTM模型法进行异常检测精度比较,探究基于Bi-LSTM的质量控制模型在遥感海浪数据异常值检测方面的能力。试验结果表明,Bi-LSTM质量控制模型具有良好的异常值检测效果,其精准率、召回率、 F1分数和运行时间分别为91%、 93%、 92和3.35 s,综合评价效果最佳,可有效对遥感海浪数据进行质量控制。 展开更多
关键词 遥感海浪数据 质量控制 深度学习 Bi-lstm模型 异常检测
在线阅读 下载PDF
上一页 1 2 250 下一页 到第
使用帮助 返回顶部