Electronics surface inspection: 20 subtle defect types, machine eyes that never blink
Client Profile
Pain Points
Defects are tiny
Scratches, stains and chips are nearly impossible to catch on a fast line.
Standards vary
Different inspectors apply different standards, so batch quality fluctuates.
Rework and scrap are costly
Missed defects that ship out come back as returns or full scrap.
Live Demo
How We Built It
High-precision vision
Custom lighting and lenses plus a model trained on 20 defect types for small parts.
Auto-archived results
Every part's image and verdict are archived for traceability and audit.
Line integration
Consecutive anomalies auto-stop the line and push alarms to prevent batch defects.
Not betting on one AI — combining the right few
For a real business scenario, we don't lock in a single technical path up front. We evaluate candidate paths on the same benchmark, then design a hybrid so each path does what it's best at.
General LLM API
Public-cloud models such as GPT-4o / Qwen / DeepSeek
- ✓Out-of-the-box, minimal integration cost, cheap to start
- ✕Limited generalization to vertical domains, unstable field-level accuracy, separate compliance design
Industry fine-tuned model
Domain fine-tuning of open-source models on industry data
- ✓Grasps industry semantics, much higher accuracy, private deployment
- ✕Needs labeled data plus ongoing training and upkeep
RAG + rule engine
Retrieval-augmented knowledge plus business rule checks
- ✓Highly targeted, explainable, best latency and cost
- ✕Requires continuous data-loop investment
Fusion, not selection
What we deliver is not a single model but a fused pipeline of primary path + semantic correction + graceful fallback: routine cases are handled by the industry model in seconds; low-confidence fields are re-understood by an LLM; on service anomalies the system degrades to a general API and flags manual review — achieving accuracy, cost, latency and controllability at once.
An explainable, degradable, evolvable AI pipeline
We treat AI engineering as a pipeline, not a black box: every step has clear responsibilities, inputs/outputs and fallbacks. The five-step pipeline plus four-layer architecture below is the technical skeleton.
Ingestion & access layer
Multi-channel access with unified auth, idempotency and masking
AI inference layer
Multi-path inference plus a confidence router switching by features
Business orchestration layer
Connecting results to real business flows with rule checks and closure
Data loop layer
Every online error flows back; models iterate monthly
Tech Stack
Delivery Process
Diagnosis
Evaluated line speed, materials and defect types to set inspection stations.
Data collection
Collected 12,000 defect samples with unified labeling.
Training
Trained the detection model and validated offline.
On-site integration
Linked with PLC for auto-rejection and alarms.
Go-live & iteration
Monthly re-collection of mis-detections for continuous tuning.
Before vs After
“Three shifts of inspectors still couldn't keep up. Now machines watch 24/7 and complaints dropped by more than half.”
Where It Fits
Related Cases
AI Inspection & Smart Scheduling Assistant
Deployed an AI inspection and scheduling assistant for a small hardware factory, enabling smart upgrades at low cost.
ZhongshanAI Scheduling & Inventory Forecasting
Built scheduling and inventory forecasting models for a lighting factory to ease seasonal order volatility.
HuizhouPredictive Maintenance Platform
Built a predictive maintenance platform to shift from reactive repair to early warning, cutting downtime losses.