CP Plant Explorer
JAN  01→15  2026
continuous polymerisation polyester yarn · POY + FDY hourly resolution · 360 h

Fifteen days of
reading the reactor

Across 360 hours of hourly process logs — covering paste preparation, two esterifiers, two prepolymerisers, the disc ring finisher, transfer line, lab QC, breakages and MEG recovery — this is what January 1–15, 2026 looked like at your CP train. The plant ran a deliberate production ramp-down from 362.3 → 334.5 TPD while holding product IV, colour and composition on spec. What follows is where that discipline held, where it slipped, and which upstream signals foretold every major spin-pack breakage.

Scrub through the plant, hour by hour.

The diagram below is a faithful layout of your CP train — from the paste tank through two esterifiers, two prepolymerisers, the DRR finisher, transfer line and on to the spinning section. Each vessel shows the instrument readings for the selected hour. Residence-time estimates (grey text under each vessel) determine when material currently visible here reaches the spin pack.

SELECTED HOUR
production
TPD
CP plant process flow diagram PTA MEG (REG) Catalyst 01 · PASTE Paste Tank flow density cat ppm → spin in ~6 h 02 · ES1 Esterifier 1 temp pressure level DPT level res ~2 h · → spin in ~4.5 h 03 · ES2 Esterifier 2 temp pressure level IMR res ~1.5 h · → spin in ~3 h 04 · PP1 Prepolymer 1 temp level vacuum res ~1 h · → spin in ~2 h 05 · PP2 Prepolymer 2 temp level vacuum res ~0.75 h · → spin in ~1 h 06 · FINISHER DRR (Disc Ring Reactor) level vacuum IV agitator A res ~1 h · → spin in ~0.5 h 07 · TRANSFER Transfer Line CPF ΔP outlet T SPIN / PRODUCT POY + FDY breaks (hr) UTILITY HTM loop primary MEG RECOVERY Hotwell 13V02 17V01
h 0 / 359

What foretells a break.

Spin-pack breakages don't happen because of what the plant is doing right now — they happen because of what the material now at the spin pack saw in the reactors hours ago. To find genuine leading indicators, we tested every candidate process variable against the breakage rate across lags of 0 to 14 hours, detrended to remove month-long drifts, and picked the lag where each variable's correlation with breaks peaked. The heatmap shows every variable; the column position of its strongest cell is the empirical residence-time signature.

Lagged correlation · breakage rate vs upstream variable

-0.35
+0.35
Columns: lag in hours (0 → 14). Rows: candidate process variables grouped by stage.
Amber = positive correlation (higher value → more breaks). Teal = negative.
The boxed cell in each row marks that variable's empirical best-fit lag.

Top predictors · by peak |r|

Composite risk index vs breakage rate

ROLLING 6-HOUR AVERAGE OF TOP-5 LEADING INDICATORS (AMBER) vs 3-HOUR BREAKAGE RATE (RED)

Three case files

Textbook tracking, one weak loop.

Across 17 setpoint/process-variable pairs, tracking errors are typically a fraction of a percent. The one outlier is ES1 DPT level, which ran with mean absolute error of 1.65% against a 63% setpoint — which also happens to be one of your top breakage predictors (5-hour lag, r ≈ +0.25). Every other loop is clean.

stageloopsv meanmean |err|max |err|std(PV)quality

Eight PTA suppliers. One MEG loop. Both drifting.

The PTA blend shifts dramatically from day to day — Reliance Tanker jumps from 22% on Jan 4 to 67% on Jan 14, Ineos runs down from 32% to 9%, and GCM climbs to 25% by month-end. On the recovery side, hotwell 13V02 water content creeps up from 7.55 to 8.85 (+17%), and 17V01 takes a one-hour excursion to 5.5 on Jan 9. Worth a recipe audit and a hotwell inspection.

PTA supplier blend · percent share by day

Hotwell water content · 13V02 & 15V01
CREEPING UP — POSSIBLE COLUMN / TRAY ISSUE
Hotwell vapour line · 17V01
ONE-HOUR SPIKE TO 5.5 ON JAN 9 — NORMAL ~1.0

Seven takeaways, ranked by priority.

Each card below states the observation, the evidence, and a concrete next step. The high-priority items are the ones most worth checking before the next rate ramp.

01
High priority · quality risk
DRR vacuum is the single strongest breakage predictor
Across 15 days the DRR vacuum drifted from 0.141 mbar to 0.162 mbar (+15%). The lagged-correlation analysis ranks it #1 among all variables tested — r = +0.35 at a 4-hour lag (p < 0.001, n = 354). In every major breakage window, DRR vacuum readings were elevated 3–5 hours earlier.
Inspect ejector train, condenser approach temperature, and seal-water system before the next production ramp.
02
High priority · tuning
ES1 DPT level is the weakest loop — and predicts breaks at 5 h lag
Mean absolute error of 1.65% against a 63% setpoint (max 3.3%). Of 17 control loops this is the only non-excellent performer. It also shows r = +0.25 at 5 h lag with breakages — matching the expected ES1-to-spin residence time almost exactly.
Retune the DPT level controller (likely integral gain) or audit the level transmitter for signal noise.
03
Medium priority · recovery system
Hotwell 13V02 water content is slowly climbing
Daily averages rose 7.55 → 8.85 through the month (+17%), with 15V01 showing a parallel creep. Combined with the DRR / PP2 vacuum drift, this points toward accumulating load on the MEG recovery system — possibly tray fouling or a water make-up imbalance.
Cross-check reflux ratio, column ΔP trend, and consider a planned column wash at the next opportunity.
04
Medium priority · anomaly
Single-hour 17V01 excursion on Jan 9 at 5.5 (5× baseline)
All other hours at 17V01 sat in the 0.4–1.4 range. The Jan 9 daily average of 5.5 is almost certainly a single bad sample or a brief vent-line upset. Coincided with a breakage peak (11 breaks at 12:00 that day) but could be coincidental.
Pull the operator log book for Jan 9 morning shift; verify sampling procedure; discard if a lab error, investigate if genuine.
05
Medium priority · raw materials
PTA blend swings are uncoordinated with TPD changes
Reliance Tanker share went 22% → 67% → 38%; Ineos dropped 29% → 10%; GCM rose to 25%. These are availability-driven shifts, not recipe-driven. Lab ES1 end-group values range 769–802 meq/kg, with the high end clustering in weeks where Reliance-Tanker dominated.
Build a per-supplier reactivity table (end-group by blend dominance) using the 2025 history — might reveal a quiet 2–3% conversion penalty on one source.
06
Low priority · good news
Quality outcomes held through the entire ramp-down
Hourly IV stayed in 0.638–0.642 across all 360 hours (σ = 0.0008). L-value 81.9–82.6. B-value 3.66–3.89. Paste density locked at 71.30 ± 0.01%. Catalyst trim, temperature step-down, and pressure response were all executed cleanly — operators earned this result.
Capture the ramp-down playbook from shift notes before it's lost — standard operating procedure material.
07
Low priority · planning
The month covered in this file is 15 days, not 31 — plus a clear sequel
The log goes Jan 1 07:00 through Jan 16 06:00 — so this is a half-month snapshot. Given the monotonic ramp-down and the fact that the Jan 15 TPD (334 TPD) is still well above typical shutdown rates, the most likely scenario is either (a) a planned shutdown later in January or (b) a demand-driven slowdown that continues into early February. When the second half of January and the 2025 history arrive, the two highest-value analyses are: does the DRR-vacuum trend continue or reverse post-ramp, and what does the normal breakage baseline look like at steady 350+ TPD.
Upload Jan 16–31 and Dec 2025 logs — this dashboard is already structured to ingest them and show deltas.