AI

LaplaceDiag: Fault Diagnosis through Changes in Learned Actuator Effects

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 04/11/2026, 05:18:25 UTC.

Briefings

LaplaceDiag is a data-driven method for fault diagnosis using changes in actuator effects to identify faulty equipment. It learns a healthy plant model via LaplaceNet and separates nonlinear prediction from an explicit matrix describing actuator effects. The method supports both online and offline diagnosis, offering an intermediate step between anomaly detection and component identification. Evaluation was conducted on two datasets.

Key points

• LaplaceDiag uses LaplaceNet to learn a healthy plant model in Laplace space.
• The method estimates current actuator effects via linear regression without retraining the neural network.

Context

Fault diagnosis from sensor anomalies is difficult due to fault propagation and similar observations. LaplaceDiag addresses this by analyzing changes in actuator effects to narrow the search for faulty equipment.

Limitations

The method was evaluated on only two datasets. The source is an arXiv preprint, and the evidence does not include specific dates, author names, or quantitative results beyond the successful evaluation on the two datasets.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 04/11/2026, 07:53:33 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeicerlbarxxft5iz7vciwk2ijpyakmcvqp7q5rlvkvpheuqxnbauva