Progress and challenges in the application of soft sensing technology for nuclear power plant pump fault diagnosis

Open Access

Review

Table 3

Performance comparison of different deep learning models in nuclear power pump fault diagnosis.

Model type	Highest accuracy (%)	Generalization ability (%)
Basic CNN	87.2	Δ-12.5 [28]
Spatiotemporal CNN	93.5	Δ-8.3 [18]
Multi-scale Self-Attention	99.5	Δ-2.1 [11]
Lightweight MTA-CNN	98.1	Δ-4.7 [30]

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.