Industrial actuator batteries — bounded, not absolute

We do not claim “GSRF wins industrial actuators.” We claim a frozen workbench scoreboard on synthetic SCADA-style packs with published remaps, mixed/adversarial cases, and a tracking cost.

What was run

*03/07 remapped: measured feedback as filter input when setpoints were constant.

Scoreboard

PackClearPartialMixedLoss
Seven industrial5110
Adversarial Tier-12640
Combined7750

Shaping score = wear + churn + rate-stress + osc31 vs best EMA (≥3 clear, 2 partial, 1 mixed, 0 loss).

Identity that never went away

On these batteries, GSRF Practical’s MAD vs raw is consistently higher than best EMA. That is the spring. If your KPI is hug-the-raw, start with EMA/Kalman — see When GSRF lost.

Real plant first look (DAMADICS Lublin)

Official Lublin Sugar Factory dumps (https://iair.mchtr.pw.edu.pl/Damadics), 3 actuators × 3 days (~259k samples each), CV→demand / X→measured, same frozen Phase 5 MAIN evaluator:

Tennessee Eastman Mode-1 XMVs (simulated plant): three channels tested — all loss under the same rule. SWaT not run (auth). Real plant is harder than synthetic 0-loss batteries — we publish that.

Multi-day Lublin pack (25×3) is locked in Workbench — see Evidence industrial. Still open:, ISDB stiction, SWaT, partner plant.

Verdict for buyers

Use GSRF when mid-band ring / peak chase / command shaping around a normal is the costly failure — and validate on your traces (gsrf-bench). Do not buy on “always wins actuators.”

Primary ledger: Evidence §5. Citations: DAMADICS paper + dataset · eval package · GitHub. Full workbench reports local only until partner data lands.

Questions people actually ask

Does GSRF win industrial actuators?

No absolute claim. Synthetic Phase 5 MAIN batteries: regime-bounded scoreboard with remaps. DAMADICS real plant first look: 2/3 partial, 1/3 loss published. Do not merge into one win rate.

What is DAMADICS in this note?

Public Lublin Sugar Factory actuator benchmark (IAIR). Bartyś et al. 2006 CEP paper describes the FDI study. We ran frozen Phase 5 MAIN on three valves × three days.

Why is MAD worse on these batteries?

By design of the k_return spring — GSRF compresses peaks and ring toward normal and pays tracking MAD vs raw. If hug-the-raw is the KPI, start with EMA/Kalman.

Evidence §5 Try

Update 2026-08-08: DAMADICS multi-day (25 days × 3 valves, 75 full-rate Phase 5 MAIN runs): composite mostly loss (60/75). Per-metric vs best EMA: wear 1/75, rate-stress 14/75, osc 8/75, MAD 0/75. Rejected: inverted “88% wear wins” memos — DECISION_SUMMARY wins. Full report in Workbench phase5_damadics_multiday/.