Live SPC, anomaly detection and influence scoring on your existing PLC and OPC UA tags, validated by people who've actually run these lines, not just the model. Expert knowledge in wood and building products (OSB, PB, MDF) and industrial manufacturing more broadly.
AI runs the calculations. We make sure they're right. It all runs on your existing PLC and OPC UA tags, with no rip-and-replace.
Cp/Cpk and sigma drift, calculated the right way, not the population-variance shortcut that flatters your numbers.
EWMA and CUSUM catch drift early, without flooding operators with false alarms.
Ranks what's really driving a quality or output measure, so the answer doesn't rest on one method's blind spot.
Every score is checked before anyone sees it. Low-confidence results get flagged, never rounded off and shown anyway.
Status-first views. What needs attention now, not a wall of charts nobody reads.
Once the analytics have earned it, validated results write straight back to your PLC.
MATLAB and Simulink models run alongside your real process, showing where it drifts from design and where it bottlenecks.
A PLC trigger captures an image and returns pass/fail against a trained profile. On-site, no cloud dependency.
Built around your tag and your process, not a generic template stretched to fit.
The same three steps sit behind every chart, score and alarm, whether it's one tag or fifty.
Read-only over OPC UA. Collection and analysis run separately, so heavy calculations never slow down data collection.
Process data is heavily autocorrelated. Effective sample size and time-aware checks catch it before it reaches a chart.
SPC, anomaly and influence scoring run side by side, feeding status-first dashboards and, when you're ready, your PLC.
Write-ups on the real engineering problems behind process monitoring: the bugs, the statistics, and the architecture.
A common, easy-to-miss bug, using population variance instead of sample variance, quietly makes process capability indices look better than they…
Read case study →Most tutorials show EWMA control limits as fixed values. That's wrong for the early samples in any run. Here's the…
Read case study →The engineering discipline that let SPC, anomaly detection and influence scoring share one codebase without turning into spaghetti as it…
Read case study →Moving from historical CSV exports to live PLC tags via OPC UA breaks more assumptions than it seems like it…
Read case study →Industrial process data is heavily autocorrelated, which silently breaks ordinary cross-validation and inflates confidence in feature-influence scores.
Read case study →No single method should be trusted alone for ranking which variables drive an outcome. Here's how a weighted ensemble hedges…
Read case study →All the statistical rigor in a monitoring system is wasted if a floor operator can't act on it in three…
Read case study →A 15-minute call, no slide deck. We'll look at what your data actually looks like and tell you what's realistic.
Request a demo