为验证本文提出基于KPCA数据预处理和VMD- LSTM-GPR预测模型的可靠性、稳定性以及准确性,本文采用NASA数据集标号为B05、B06、B07和B18的锂电池进行实验验证,对每种电池设置多种不同的预测起点T,见表6,起点均设置为总循环周期约40%处,由于B06在110周期和B18在90周期,其电池容量已经分别下降到终止阈值和接近终止阈值...
据此,文中提出了一种基于GPR-LSTM的地震热红外背景场的构建方法。该方法包括两大部分:震期年变基准场的建立、实际LST的残差波动范围计算及背景场的构建。基于MODIS地表温度产品,以2008年四川汶川和新疆于田地震为研究对象,使用所述方法对地震前兆热异常信息进行提取与分析,经过实验得出以下结论:1)地震热异常通常沿青藏...
Bi-LSTM-GPR algorithms based on a high-density electrical method for inversing the moisture content of landslideMoisture content of landslideHigh-density electrical methodLong short-term memory networkGaussian process regressionBi-LSTMBulletin of Engineering Geology and the Environment - Soil moisture ...
本发明公开一种共享权重长短期记忆网络(SWLSTM)结合高斯过程回归(GPR)的风速预测方法,该方法主要包括:采用共享权重来简化标准长短期记忆网络(LSTM)的结构;利用结合了mini‑batch机制的Adam优化算法来训练SWLSTM,得到具有高准确率的风速点预测结果;将SWLSTM得到的点预测结果作为GPR的输入,二次预测得到风速概率预测结果;...
Then, the LSTM neural network and the GPR method are utilized to predict the IMFs, respectively. Lastly, based on the IMFs' prediction results with the two forecasting methods, the variance-covariance method can determine the weight of the two forecasting methods and offer a combination ...
秦娟目前担任沧州市圣雅茜信息咨询服务有限公司法定代表人,同时担任沧州市圣雅茜信息咨询服务有限公司执行董事,经理;二、秦娟投资情况:秦娟目前是沧州市圣雅茜信息咨询服务有限公司直接控股股东,持股比例为100%;目前秦娟投资沧州市圣雅茜信息咨询服务有限公司最终收益股份为100%;三、秦娟的商业合作伙伴:基于公开数据展示,...
将SWLSTM得到的点预测结果作为GPR的输入,二次预测得到风速概率预测结果;选定置信度,通过高斯分布得到相应置信度下的风速区间预测结果.本发明的预测方法通过共享权重缩减了LSTM的训练时间,结合GPR使得SWLSTM有能力进行概率预测和区间预测.SWLSTMGPR可得到高精度的风速点预测结果,合适的风速区间预测结果和可靠的风速概率预测...
GPRCNNBi-LSTMResidual connectionsBi-LSTM) model has proposed for the analysis of Ground Penetrating Radar B scan (GPR B Scan) images. GPR characteristics, scanning frequency, and soil type make it very difficult to analyze GPR B Scan images. Also, noise and clutter in the image make this ...
Machine learning and deep learning algorithms, including support vector machine (SVM), random forest (RF), long short-term memory (LSTM), and Gaussian process regression (GPR), were used to model the droughts in six regions of Norway: Bod, Karasjok, Oslo, Troms, Trondheim, and Vads. Four...
Machine learning and deep learning algorithms, including support vector machine (SVM), random forest (RF), long short-term memory (LSTM), and Gaussian process regression (GPR), were used to model the droughts in six regions of Norway: Bod, Karasjok, Oslo, Troms, Trondheim, and Vads. Four...