Sim time08:00:00
Speed60×
Shift A · Day 1

Stringer 1 Tension Excursion · 08:35–09:18

Cluster cluster_stringer1_0835_excursion
Modules affected
8
5 Scrap · 1 B · 1 C · 1 clean
Defect rate
88%
across the cluster
Avg signature match
76%
coherence 88%
Net impact
$990
risk $1,360 − salvage $370
Root cause: Operator-3 raised Stringer 1 tension 4.2 → 4.7 N at 08:35, citing ribbon batch quality. Recommendation declined; tension reverted at 09:18 after CUSUM action threshold. 8 modules processed in the 43-minute window.

Excursion timeline · 08:35 → 09:18 · 43 min

String Tension · Stringer 1
CUSUM chart
warn 4.5 · action 4.8 N
nominal 4.2warnactionModule processedmod_showcase_combined_001 · Scrap · 101mod_cluster_stringer1_002 · Scrap · 101mod_cluster_stringer1_003 · Scrap · 101mod_cluster_stringer1_004 · Scrap · 102mod_cluster_stringer1_005 · Scrap · 102mod_cluster_stringer1_006 · B · 101mod_cluster_stringer1_007 · C · 102mod_cluster_stringer1_008 · A (clean)08:0008:3909:1910:004.104.484.86
Tension drifted from 4.2 to 4.7 N at 08:35. CUSUM warning crossed at 08:48; action threshold at 09:18 when operator reverted. This module processed at 08:53 in the middle of the window.· Green dashed: If tension recommendation accepted at 08:50.
Scrap with defect B/C-tier UnaffectedEach tick = one cluster module's processing time

Cluster Bayesian coherence — is this one cluster or many?

Confidence that all 8 modules share a single causal root:88%
Predicted signature
Branching crack near busbar in cells from elevated-tension window
Observed signature
5 of 8 modules show busbar-adjacent crack; 1 unaffected, 2 marginal
Average signature match across affected modules: 76%. High coherence means the defects look like the same phenomenon — strong evidence of a common cause.

Economic impact

Total modules affected8
Scrap5
B-tier1
C-tier1
Unaffected (A-tier)1

Revenue at risk$1,360
Salvage realised$370
Net impact$990

If the platform's recommendation had been accepted at the right moment, projected savings:~$842 across this cluster.

Cluster-wide recommendations

Joint review with Operator-3 on ribbon-batch attribution heuristics
shift
Operator's ribbon-batch hypothesis was reasonable but multifactorial; in-the-moment tension reduction would have been the highest-leverage action.
Better calibration of operator competing-priorities decisions.
Auto-correlate ribbon batch and tension SPC in real time
process
Decouples 'is it ribbon?' vs 'is it tension?' for the operator.
Faster root-cause attribution.
This cluster page shows how a single upstream excursion produces a coherent pattern across many modules. In production, every excursion that exceeds SPC thresholds is automatically grouped into a cluster, and cluster-level analysis runs continuously.