Quality-Decision Delay Estimator
Estimate constraint time idled by quality and release decisions
Reference implementation. Industrial use requires validation on plant-specific data. Metrics are from open evaluation splits, not customer plants.
Intended use
Quantifying production time spent waiting on quality, lab, and release decisions, split by decision type.
Inputs & outputs
Inputs
Lab and release timestamps, hold records, batch dispositions
Output
Idle minutes awaiting decisions, by decision type
Training data & evaluation
Training-data classification
Synthetic lab/release timestamp sequences with hold events.
Evaluation approach
Idle-minute MAE per batch on a held-out split.
MAE 3.1 min/batch· open split
Industrial relevance
Applies across Chemicals, Battery Materials. The value is highest where the affected asset is a constraint and additional output can be monetized.
Limitations
- Needs timestamped decision events; verbal approvals are invisible.
- Attributes waiting time, not the merit of the decision itself.