This paper proposed a RIME-VMD-BiLSTM surrogate model to rapidly and precisely predict the seismic response of a nonlinear vehicle-track-bridge(VTB)system.The surrogate model employs the RIME algorithm to optimize the...This paper proposed a RIME-VMD-BiLSTM surrogate model to rapidly and precisely predict the seismic response of a nonlinear vehicle-track-bridge(VTB)system.The surrogate model employs the RIME algorithm to optimize the variational mode decomposition(VMD)parameters(k and α)and the architecture and hyperparameter of the bidirectional long-and short-term memory network(BiLSTM).After comparing different combinations and optimization algorithms,the surrogate model was trained and used to analyze a typical 9-span 32-m high-speed railway simply supported bridge system.A series of numerical examples considering the vehicle speed,bridge damping,seismic intensity,and training strategy on the prediction effect of the surrogate model were conducted on the extended OpenSees platform.The results show that the BiLSTM model performed better than the LSTM model,whereas the prediction effects of the single-LSTM and BiLSTM models were relatively poor.With the introduction of the VMD and RIME optimization techniques,the prediction effect of the proposed RIME-VMD-BiLSTM model was excellent.The abovementioned factors had a significant influence on the seismic response of a VTB system but little impact on the prediction effect of the surrogate model.The proposed surrogate model exhibits notable transferability and robustness for predicting the VTB’s nonlinear seismic response.展开更多
当前推特等国外社交平台,已成为从事网络黑灰产犯罪不可或缺的工具,对推特上黑灰产账号进行发现、检测和分类对于打击网络犯罪、维护社会稳定具有重大意义。现有的推文分类模型双向长短时记忆网络(bi-directional long short-term memor...当前推特等国外社交平台,已成为从事网络黑灰产犯罪不可或缺的工具,对推特上黑灰产账号进行发现、检测和分类对于打击网络犯罪、维护社会稳定具有重大意义。现有的推文分类模型双向长短时记忆网络(bi-directional long short-term memory,BiLSTM)可以学习推文的上下文信息,却无法学习局部关键信息,卷积神经网络(convolution neural network,CNN)模型可以学习推文的局部关键信息,却无法学习推文的上下文信息。结合BiLSTM与CNN两种模型的优势,提出了BiLSTM-CNN推文分类模型,该模型将推文进行向量化后,输入BiLSTM模型学习推文的上下文信息,再在BiLSTM模型后引入CNN层,进行局部特征的提取,最后使用全连接层将经过池化的特征连接在一起,并应用softmax函数进行四分类。模型在自主构建的中文推特黑灰产推文数据集上进行实验,并使用TextCNN、TextRNN、TextRCNN三种分类模型作为对比实验,实验结果显示,所提的BiLSTM-CNN推文分类模型在对四类推文进行分类的宏准确率为98.32%,明显高于TextCNN、TextRNN和TextRCNN三种模型的准确率。展开更多
光伏发电功率受气象因素的影响呈现出不稳定性和间歇性,准确预测光伏功率有助于实现大规模并网并保障电网的稳定运行。以澳大利亚DKASC Solar Centre光伏电站数据为研究对象,提出一种基于气象相似日的变分模态分解算法、长鼻浣熊算法和...光伏发电功率受气象因素的影响呈现出不稳定性和间歇性,准确预测光伏功率有助于实现大规模并网并保障电网的稳定运行。以澳大利亚DKASC Solar Centre光伏电站数据为研究对象,提出一种基于气象相似日的变分模态分解算法、长鼻浣熊算法和双向长短期记忆神经网络(VMD-COA-BiLSTM)的光伏功率短期预测模型。针对光伏数据的复杂非线性特征、噪声干扰以及高维特征等问题,通过K均值聚类将数据划分为3种天气类型,增强模型映射能力;利用VMD将聚类之后的原始信号分解,采用中心频率法确定最佳模态数,充分提取集合中的输入因素信息,提高数据质量;将分解后的各分量分别输入BiLSTM网络进行预测,采用COA优化BiLSTM的超参数配置,实现不同天气类型下的光伏功率的准确预测。结果表明:K均值聚类和VMD算法有效提升了数据质量,增强了输入、输出数据的耦合强度;COA优化BiLSTM模型在优化能力和收敛速度上均优于粒子群算法(PSO);所提出的VMD-COA-BiLSTM模型在晴天、多云和阴雨天的RMSE分别降低了35.24%,45.54%和42.88%,显著提高了预测精度,且能适应不同环境下的可靠预测。展开更多
基金Project(52108433)supported by the National Natural Science Foundation of ChinaProject(HSR202004)supported by the Open Foundation of National Engineering Research Center of High-Speed Railway Construction Technology(CSU),China+3 种基金Projects(2024RC3170,2021RC4031)supported by the Science and Technology Innovation Program of Hunan Province,ChinaProjects(2024JJ5018,2024JJ5427)supported by the Hunan Provincial Natural Science Foundation,ChinaProject(KQ2402027)supported by the Changsha City Natural Science Foundation,ChinaProjects(2021-Special-08,2022-Special-09)supported by the Science and Technology Research and Development Program Project of China Railway Group Limited。
文摘This paper proposed a RIME-VMD-BiLSTM surrogate model to rapidly and precisely predict the seismic response of a nonlinear vehicle-track-bridge(VTB)system.The surrogate model employs the RIME algorithm to optimize the variational mode decomposition(VMD)parameters(k and α)and the architecture and hyperparameter of the bidirectional long-and short-term memory network(BiLSTM).After comparing different combinations and optimization algorithms,the surrogate model was trained and used to analyze a typical 9-span 32-m high-speed railway simply supported bridge system.A series of numerical examples considering the vehicle speed,bridge damping,seismic intensity,and training strategy on the prediction effect of the surrogate model were conducted on the extended OpenSees platform.The results show that the BiLSTM model performed better than the LSTM model,whereas the prediction effects of the single-LSTM and BiLSTM models were relatively poor.With the introduction of the VMD and RIME optimization techniques,the prediction effect of the proposed RIME-VMD-BiLSTM model was excellent.The abovementioned factors had a significant influence on the seismic response of a VTB system but little impact on the prediction effect of the surrogate model.The proposed surrogate model exhibits notable transferability and robustness for predicting the VTB’s nonlinear seismic response.
文摘光伏发电功率受气象因素的影响呈现出不稳定性和间歇性,准确预测光伏功率有助于实现大规模并网并保障电网的稳定运行。以澳大利亚DKASC Solar Centre光伏电站数据为研究对象,提出一种基于气象相似日的变分模态分解算法、长鼻浣熊算法和双向长短期记忆神经网络(VMD-COA-BiLSTM)的光伏功率短期预测模型。针对光伏数据的复杂非线性特征、噪声干扰以及高维特征等问题,通过K均值聚类将数据划分为3种天气类型,增强模型映射能力;利用VMD将聚类之后的原始信号分解,采用中心频率法确定最佳模态数,充分提取集合中的输入因素信息,提高数据质量;将分解后的各分量分别输入BiLSTM网络进行预测,采用COA优化BiLSTM的超参数配置,实现不同天气类型下的光伏功率的准确预测。结果表明:K均值聚类和VMD算法有效提升了数据质量,增强了输入、输出数据的耦合强度;COA优化BiLSTM模型在优化能力和收敛速度上均优于粒子群算法(PSO);所提出的VMD-COA-BiLSTM模型在晴天、多云和阴雨天的RMSE分别降低了35.24%,45.54%和42.88%,显著提高了预测精度,且能适应不同环境下的可靠预测。
