该模型使用LSTM结构的生成器和判别器学习正常样本的数据特征,使用时间周期信息指导生成器G生成样本,最后同时使用生成器的重构误差和判别器的判别结果判别测试样本。本文的主要贡献如下:①提出使用基于注意力(Attention)机制的多层LSTM网络捕获时间上的依赖关系,并将其嵌入到CGAN框架中,以保证模型充分学习到样本在时间上的...
新能源的强烈不确定性给多微网协同运行带来了可靠性和安全性的巨大挑战.为此,提出一种基于长短期记忆(long short-term memory, LSTM)网络和条件生成对抗网络(conditional generative adversarial networks, CGAN)的多微网数据驱动两阶段分布鲁棒协同优化调度模型.首先,为更准确地描述新能源的不确定性,该模型以LSTM-CGAN...
本发明公开了一种基于LSTMcGAN的含裂纹结构剩余承载力及裂纹扩展路径的预测方法,在训练阶段,首先通过有限元计算或现场实测得到含不同程度裂纹结构的强度及其在加载情况下的裂纹扩展路径,并基于条件生产对抗网络模型和长短时记忆法,同时训练四个深度神经网络包括生成网络G和判断网络D,处理时间序列的LSTM网络以及判断裂纹...
As to the problem that the existing methods based on GANs only use age information as the generation condition and ignore the sequence of age information, we present a cross-age face generation method based on CGAN and LSTM. This method consists of four modules. The first module is a ...
Proposed an ultra-short-term wind power forecasting model based on the CGAN-CNN-LSTM algorithm and verified its feasibility; Used GAN’s data supplement function to solve the problem of missing data in the original data set; The time scale of ultra-short-term wind power prediction is shortened...
Proposed an ultra-short-term wind power forecasting model based on the CGAN-CNN-LSTM algorithm and verified its feasibility; Used GAN’s data supplement function to solve the problem of missing data in the original data set; The time scale of ultra-short-term wind power prediction is shortened...