传统的混凝土拱坝位移预测模型主要关注水压、温度、时效等因素与拱坝位移之间的关系,未对拱坝位移数据中所包含的信息进行充分挖掘。为此,采用Seasonal and Trend decomposition using Loess算法(STL)将拱坝位移原始数据分解为趋势序...传统的混凝土拱坝位移预测模型主要关注水压、温度、时效等因素与拱坝位移之间的关系,未对拱坝位移数据中所包含的信息进行充分挖掘。为此,采用Seasonal and Trend decomposition using Loess算法(STL)将拱坝位移原始数据分解为趋势序列、周期序列及残差分量。在此基础上,采用鲸鱼优化算法(WOA)结合随机森林算法(RF)对三个分量进行预测,并使用Holt-Winters算法充分考虑趋势序列中的趋势信息对趋势序列的预测结果进行修正。最后将修正后的趋势序列预测结果和周期序列、残差分量预测结果相加,得出拱坝位移最终预测结果。工程实例表明,基于STL-Holt-WOA-RF的拱坝位移预测模型能够显著提高预测的准确性和稳定性,为拱坝位移预测提供了新的思路和方法。展开更多
利用STL(Seasonal-Trend decomposition using Loess,时间序列分解算法)模型对工业园区运行阶段的建筑碳排放进行预测分析,介绍电碳模型构建技术路线、模型构建的STL和线性回归,给出某高新园区2021年到2022年碳排放量的预测结果。可为...利用STL(Seasonal-Trend decomposition using Loess,时间序列分解算法)模型对工业园区运行阶段的建筑碳排放进行预测分析,介绍电碳模型构建技术路线、模型构建的STL和线性回归,给出某高新园区2021年到2022年碳排放量的预测结果。可为园区规划双碳路径、制定减排计划、开展节能减排手段提供数据支撑,辅助园区实现绿色低碳发展目标。展开更多
Chiral metamaterials have been proven to possess many appealing mechanical phenomena,such as negative Poisson's ratio,high-impact resistance,and energy absorption.This work extends the applications of chiral metam...Chiral metamaterials have been proven to possess many appealing mechanical phenomena,such as negative Poisson's ratio,high-impact resistance,and energy absorption.This work extends the applications of chiral metamaterials to underwater sound insulation.Various chiral metamaterials with low acoustic impedance and proper stiffness are inversely designed using the topology optimization scheme.Low acoustic impedance enables the metamaterials to have a high and broadband sound transmission loss(STL),while proper stiffness guarantees its robust acoustic performance under a hydrostatic pressure.As proof-of-concept demonstrations,two specimens are fabricated and tested in a water-filled impedance tube.Experimental results show that,on average,over 95%incident sound energy can be isolated by the specimens in a broad frequency range from 1 k Hz to 5 k Hz,while the sound insulation performance keeps stable under a certain hydrostatic pressure.This work may provide new insights for chiral metamaterials into the underwater applications with sound insulation.展开更多
Sandwich structures are widespread in engineering applications because of their advantageous mechanical properties.Recently,their acoustic performance has also been improved to enable attenuation of low-frequency vibr...Sandwich structures are widespread in engineering applications because of their advantageous mechanical properties.Recently,their acoustic performance has also been improved to enable attenuation of low-frequency vibrations induced by noisy environments.Here,we propose a new design of sandwich plates(SPs)featuring a metamaterial core with an actively tunable low-frequency bandgap.The core contains magnetorheological elastomer(MRE)resonators which are arranged periodically and enable controlling wave attenuation by an external magnetic field.We analytically estimate the sound transmission loss(STL)of the plate using the space harmonic expansion method.The low frequency sound insulation performance is also analyzed by the equivalent dynamic density method,and the accuracy of the obtained results is verified by finite-element simulations.Our results demonstrate that the STL of the proposed plate is enhanced compared with a typical SP analog,and the induced bandgap can be effectively tuned to desired frequencies.This study further advances the field of actively controlled acoustic metamaterials,and paves the way to their practical applications.展开更多
为挖掘复杂环境因素对电力负荷预测效果的影响,提高电力负荷预测精确度,提出了一种基于k-shape时间序列聚类与STL季节趋势分解算法相结合的负荷曲线聚类预测模型(k-shape-seasonal and trend decomposition using loess-gradient boosti...为挖掘复杂环境因素对电力负荷预测效果的影响,提高电力负荷预测精确度,提出了一种基于k-shape时间序列聚类与STL季节趋势分解算法相结合的负荷曲线聚类预测模型(k-shape-seasonal and trend decomposition using loess-gradient boosting decision tree,k-shape-STL-GBDT)。首先分析用户用电时序特征,利用k-shape时间序列聚类算法根据负荷曲线划分用户聚类,其次,使用STL算法将不同簇的负荷数据划分为季节项、趋势项与随机项。然后,结合温度、湿度等影响因素搭建预测模型,以麻省大学smart*可再生能源项目的公开数据集为例进行分析,并与多种主流聚类分解预测模型进行对比。结果表明新提出的模型框架MAPE减少了4%以上,针对短期负荷预测表现出了较好的性能与预测精度。展开更多
文摘传统的混凝土拱坝位移预测模型主要关注水压、温度、时效等因素与拱坝位移之间的关系,未对拱坝位移数据中所包含的信息进行充分挖掘。为此,采用Seasonal and Trend decomposition using Loess算法(STL)将拱坝位移原始数据分解为趋势序列、周期序列及残差分量。在此基础上,采用鲸鱼优化算法(WOA)结合随机森林算法(RF)对三个分量进行预测,并使用Holt-Winters算法充分考虑趋势序列中的趋势信息对趋势序列的预测结果进行修正。最后将修正后的趋势序列预测结果和周期序列、残差分量预测结果相加,得出拱坝位移最终预测结果。工程实例表明,基于STL-Holt-WOA-RF的拱坝位移预测模型能够显著提高预测的准确性和稳定性,为拱坝位移预测提供了新的思路和方法。
文摘利用STL(Seasonal-Trend decomposition using Loess,时间序列分解算法)模型对工业园区运行阶段的建筑碳排放进行预测分析,介绍电碳模型构建技术路线、模型构建的STL和线性回归,给出某高新园区2021年到2022年碳排放量的预测结果。可为园区规划双碳路径、制定减排计划、开展节能减排手段提供数据支撑,辅助园区实现绿色低碳发展目标。
基金supported by the National Natural Science Foundation of China(Nos.52171327,11991032,52201386,and 51805537)。
文摘Chiral metamaterials have been proven to possess many appealing mechanical phenomena,such as negative Poisson's ratio,high-impact resistance,and energy absorption.This work extends the applications of chiral metamaterials to underwater sound insulation.Various chiral metamaterials with low acoustic impedance and proper stiffness are inversely designed using the topology optimization scheme.Low acoustic impedance enables the metamaterials to have a high and broadband sound transmission loss(STL),while proper stiffness guarantees its robust acoustic performance under a hydrostatic pressure.As proof-of-concept demonstrations,two specimens are fabricated and tested in a water-filled impedance tube.Experimental results show that,on average,over 95%incident sound energy can be isolated by the specimens in a broad frequency range from 1 k Hz to 5 k Hz,while the sound insulation performance keeps stable under a certain hydrostatic pressure.This work may provide new insights for chiral metamaterials into the underwater applications with sound insulation.
基金Project supported by the National Natural Science Foundation of China(Nos.12472007 and 12072084)the Fundamental Research Funds for the Central Universities of China。
文摘Sandwich structures are widespread in engineering applications because of their advantageous mechanical properties.Recently,their acoustic performance has also been improved to enable attenuation of low-frequency vibrations induced by noisy environments.Here,we propose a new design of sandwich plates(SPs)featuring a metamaterial core with an actively tunable low-frequency bandgap.The core contains magnetorheological elastomer(MRE)resonators which are arranged periodically and enable controlling wave attenuation by an external magnetic field.We analytically estimate the sound transmission loss(STL)of the plate using the space harmonic expansion method.The low frequency sound insulation performance is also analyzed by the equivalent dynamic density method,and the accuracy of the obtained results is verified by finite-element simulations.Our results demonstrate that the STL of the proposed plate is enhanced compared with a typical SP analog,and the induced bandgap can be effectively tuned to desired frequencies.This study further advances the field of actively controlled acoustic metamaterials,and paves the way to their practical applications.
文摘为挖掘复杂环境因素对电力负荷预测效果的影响,提高电力负荷预测精确度,提出了一种基于k-shape时间序列聚类与STL季节趋势分解算法相结合的负荷曲线聚类预测模型(k-shape-seasonal and trend decomposition using loess-gradient boosting decision tree,k-shape-STL-GBDT)。首先分析用户用电时序特征,利用k-shape时间序列聚类算法根据负荷曲线划分用户聚类,其次,使用STL算法将不同簇的负荷数据划分为季节项、趋势项与随机项。然后,结合温度、湿度等影响因素搭建预测模型,以麻省大学smart*可再生能源项目的公开数据集为例进行分析,并与多种主流聚类分解预测模型进行对比。结果表明新提出的模型框架MAPE减少了4%以上,针对短期负荷预测表现出了较好的性能与预测精度。
