Throughput Drag Estimator
Estimate sustained below-best-rate operation without stoppages
Reference implementation. Industrial use requires validation on plant-specific data. Metrics are from open evaluation splits, not customer plants.
Intended use
Sizing sustained slow-running loss on continuous lines where output sits below demonstrated best rate without a classified stoppage.
Inputs & outputs
Inputs
Rate tags, demonstrated best-rate history, run records
Output
Drag hours per period and rate-gap distribution
Training data & evaluation
Training-data classification
Synthetic rate profiles with realized best-rate envelopes.
Evaluation approach
Rate-gap MAE against the demonstrated best rate on a held-out split.
MAE 4.2%· open split
Industrial relevance
Applies across Chemicals, Paper · Glass · Cement. The value is highest where the affected asset is a constraint and additional output can be monetized.
Limitations
- Depends on a credible demonstrated best rate; a conservative baseline understates drag.
- Does not attribute cause; pair with the attribution model for root causes.