Deep learning-based unsupervised representation clustering methodology for automatic nuclear reactor operating transient identification
作者：
Highlights：
• A deep learning-based clustering method is proposed for automatic nuclear reactor operating transient identification.
• An end-to-end transient identification framework is built, that requires little prior expertise.
• A deep distance metric learning approach is proposed to enhance clustering effects.
• Unlabeled data in nuclear industry can be effectively explored to guide engineers.
• Experiments on a real-world nuclear reactor dataset validate the effectiveness of the proposed method.
摘要
•A deep learning-based clustering method is proposed for automatic nuclear reactor operating transient identification.•An end-to-end transient identification framework is built, that requires little prior expertise.•A deep distance metric learning approach is proposed to enhance clustering effects.•Unlabeled data in nuclear industry can be effectively explored to guide engineers.•Experiments on a real-world nuclear reactor dataset validate the effectiveness of the proposed method.
论文关键词：Deep learning,Nuclear reactor,Clustering,Transient identification,Unsupervised learning
论文评审过程：Received 30 March 2020, Revised 18 May 2020, Accepted 21 June 2020, Available online 27 June 2020, Version of Record 30 June 2020.
论文官网地址：https://doi.org/10.1016/j.knosys.2020.106178
