CNN–Attention–LSTM with Bayesian Optimization for Multi-Level Sump Well Anomaly Early Warning

Reliable anomaly early warning for hydropower station sump wells remains challenging due to the strong nonlinearity of water level dynamics and the limited adaptability of conventional fixed-threshold alarms. Here, we present a hybrid deep learning framework—termed CNN–Attention–LSTM–BO—that fuses m...

Descripción completa

Detalles Bibliográficos

Autores principales:	Yining Lin, Changchun Cai
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	MDPI AG 2026-04-01
Colección:	Mathematics
Materias:	sump well early warning time series anomaly detection CNN–Attention–LSTM Bayesian optimization dual dynamic thresholding hydropower safety monitoring
Acceso en línea:	https://www.mdpi.com/2227-7390/14/9/1528
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!