如上图所示，软阈值化并非简单地像ReLU那样将负值归零，而是将绝对值低于某一阈值τ的特征置为零，并将超过阈值的特征向零收缩。在深度残差收缩网络中，这个阈值τ并非由专家经验手动设定，而是通过一个专门设计的子网络自动学习得到，实现了针对不同输入样本的自适应降噪。为了提升模型在低信噪比SNR环境下的效果，DRSN通过引入可学习的阈值机制，将信号降噪与特征学习进行了集成。为了模拟真实的工业恶劣环境，在测试

论文标题：BMSFormer: An efficient deep learning model for online state-of-health estimation of lithium-ion batteries under high-frequency early SOC data with strong correlated single health indicator发表期刊：E

论文标题：BMSFormer: An efficient deep learning model for online state-of-health estimation of lithium-ion batteries under high-frequency early SOC data with strong correlated single health indicator发表期刊：E

船用柴油机作为船舶推进系统的核心部件，燃烧室因工作环境恶劣成为故障高发区域，传统故障诊断方法要么因故障样本不足泛化能力差，要么因缺乏故障机理领域知识导致模型可解释性弱。近期研读了《Thermodynamic simulation-assisted random forest: Towards explainable fault diagnosis of combustion chamber com