Production line discrete-event simulator with live KPIs, OEE and Little's Law

Claude Opus 5.5 built a single-file Canvas simulator of a serial production line, with animated stations and buffers plus a live dashboard of throughput, WIP and OEE.

Claude Code + Three.js (só código)Wandy 2
Modelos reais · 360°Ambos a partir da mesma foto: à esquerda — uma execução sem edição do Claude Code (Opus 5.5) modelando o objeto em código Three.js; à direita — Wandy 2.

Crie modelos 3D detalhados

Só com código, você tem formas simples. A Wandy 2 transforma uma foto em um modelo 3D texturizado para usar na mesma cena.

Prompt para Claude Opus 5.5

Build an animated, interactive discrete-event simulation of a serial production line as a single self-contained HTML file (vanilla JS + Canvas, no external libraries except Chart.js from cdnjs). Purpose: teaching [Manufacturing Systems] students how variability, buffers, and breakdowns affect line performance.

LINE CONFIGURATION (user-adjustable)
- Number of stations: [2–6], default [3], each with a name (e.g., Machining, Assembly, Inspection)
- Per station: mean cycle time, distribution (Deterministic, Uniform, Normal, Triangular, Exponential, Lognormal), CV
- Breakdowns per station: MTBF and MTTR (exponential), on/off toggle
- Quality per station: defect rate (%), with scrap or rework-loop option
- Buffers between stations: capacity 0–10 (0 = blocking after service)
- Arrivals: unlimited raw material OR Poisson arrivals with rate λ
- Customer demand to compute takt time

ANIMATION
- Parts move along conveyors and change color by stage (raw, WIP, finished, scrap)
- Machine borders show state colors: Working (green), Blocked (amber), Starved (red), Down (gray), plus a rotating gear icon and a progress bar
- Buffer slots show occupancy and highlight when full
- Controls: Play/Pause, Step, Reset, speed 1x–50x, warm-up period

KEY PERFORMANCE MEASURES (live dashboard)
1. Throughput (parts/hr) vs theoretical bottleneck rate
2. Average WIP and WIP over time
3. Flow time / manufacturing lead time (mean and 95th percentile)
4. Little's Law check: WIP ≈ Throughput × Flow time
5. Per-station utilization with a time breakdown: working / blocked / starved / down (stacked bar)
6. OEE per station = Availability × Performance × Quality
7. Bottleneck detection (active-period method) and highlight the bottleneck
8. Takt time vs station cycle times (line balance chart)
9. Line balance efficiency = Σ cycle times / (N × max cycle time)
10. First-pass yield, rolled throughput yield, scrap count
11. Average buffer occupancy per buffer
12. Observed vs set cycle-time mean and CV per station

ANALYSIS FEATURES
- Replication mode: run N replications of length T after warm-up, report mean ± 95% confidence interval for throughput, WIP, and flow time
- Experiment mode: sweep buffer size (or one station's CV) and plot throughput vs parameter
- Export results to CSV
- Preset scenarios: Balanced line, Clear bottleneck, High variability, Unreliable machine

DESIGN
- Clean, responsive layout that works on mobile; light/dark mode
- Brief tooltip explaining each KPI and its formula
- Bilingual labels (English/Arabic) toggle

Como usar este prompt

  1. Paste the prompt into Claude Opus 5.5 in a chat or coding tool, filling the bracketed fields with your course, station count and range.

  2. Edit the station names, distributions, breakdown settings, presets and language toggle to match your own line.

  3. Open the single HTML file, run a preset and watch the bottleneck appear; ask for extra KPIs or experiments and iterate.

Da Wandy3D

Precisa de um modelo 3D de verdade na sua cena?

Seu agente monta cenas com primitivas. A API da Wandy3D transforma uma foto ou um prompt em um GLB com textura em poucos minutos — pago com saldo pré-pago, sem assinatura.

  • Wandy 2US$ 0,18 por modelo
  • Wandy 1US$ 0,09 por modelo

O saldo nunca expira · tarefas com falha são reembolsadas · modelos feitos pela API são seus para baixar em qualquer formato.

curl -s -X POST https://api.wandy3d.com/generate/cloud/ultra \  -H "Authorization: Bearer $WANDY3D_API_KEY" -F "file=@photo.jpg"# → {"task_id": "…"} — poll until "status" is "done":curl -s https://api.wandy3d.com/task/$TASK_ID/status \  -H "Authorization: Bearer $WANDY3D_API_KEY"# → {"model_id": "…"} — then GET /model/$MODEL_ID/export?format=glb

Post originalVocê é o autor? Peça para editarmos ou removermos esta página