Industrial IoT Solution for Smart Manufacturing
A multi-line manufacturing facility sought to digitize its operations by capturing real-time data from machines, electrical panels, and the shop-floor
Read more →- Edge AI
- Computer vision
- Quality inspection
Edge-AI Defect Detection in Casting & Forging
Real-time quality assurance using AI at the edge—no cloud dependency, no delays.
Case study ·
- 99.3%detection accuracy
- < 200 msper part, fully offline
- 10,000+labelled defect images
Project overview
The brief
A precision metal parts manufacturer required a fully automated defect detection system to eliminate human errors in quality checks across casting and forging lines. Their challenge was to catch surface defects early—without relying on manual inspection or internet-based cloud processing.
Problem statement
What needed solving
- Manual quality checks were slow, inconsistent, and error-prone, especially across 3 shifts.
- Visual defects like cracks, underfill, blowholes, and shrinkage were sometimes missed or misclassified.
- The client wanted real-time, on-device AI inference without sending image data to the cloud (due to factory network limitations and latency).
- They needed a cost-effective, scalable solution that could be deployed across multiple inspection points.
Our solution
Edge-AI Based Defect Detection System
Kelectron Technologies designed a fully integrated Edge-AI inspection unit with the following architecture:
| Layer | Component |
| Hardware | NVIDIA Jetson Nano + HD industrial camera + LED ring light |
| AI Model | CNN-based custom defect classifier (trained on 10k+ labeled defect images) |
| Software Stack | Python, OpenCV, TensorFlow Lite |
| Edge Deployment | On-device image capture, real-time inference < 200ms |
| Connectivity | Local dashboard + USB/RS485 alerts to PLC |
Implementation Highlights
Custom Dataset Preparation: We helped the client label 10,000+ real defect images using a semi-automated annotation tool.
Model Training: We trained a deep learning model (CNN) to detect over 7 defect classes including surface cracks, blowholes, and overfill.
Model Optimization: Converted the model to TensorFlow Lite for fast edge inference on Jetson Nano.
System Integration: Camera + Jetson Nano + custom enclosure for factory floor installation.
Alerts & Logging: Defect images logged locally and flagged in real time to the operator via PLC buzzer/relay.
Results & Benefits
What changed for the client
- 99.3% detection accuracy achieved in production line.
- Detection speed < 200ms per part, enabling inline inspection at conveyor speed.
- Reduced false accept rate by 90%, eliminating manual judgment errors.
- Offline-capable: Zero reliance on internet/cloud, enabling 24/7 uptime.
- Easy scaling: Each unit is standalone; client plans to deploy 12 more units.
Results as reported on this client project. Outcomes vary with each plant, process and data set.
Technologies used
The stack behind the project
- Hardware
- NVIDIA Jetson Nano, Logitech Industrial Camera, LED lighting
- Software
- Python, TensorFlow, OpenCV, Flask dashboard
- AI
- Convolutional Neural Networks, Image Augmentation
- Protocols
- RS485, USB Serial, Local Web Interface
About this project
What problem did the Edge-AI Defect Detection in Casting & Forging project solve?
A precision metal parts manufacturer required a fully automated defect detection system to eliminate human errors in quality checks across casting and forging lines. Their challenge was to catch surface defects early—without relying on manual inspection or internet-based cloud processing. Manual quality checks were slow, inconsistent, and error-prone, especially across 3 shifts. Visual defects like cracks, underfill, blowholes, and shrinkage were sometimes missed or misclassified.
What did Kelectron build?
Kelectron Technologies designed a fully integrated Edge-AI inspection unit with the following architecture: Hardware: NVIDIA Jetson Nano + HD industrial camera + LED ring light; AI Model: CNN-based custom defect classifier (trained on 10k+ labeled defect images); Software Stack: Python, OpenCV, TensorFlow Lite; Edge Deployment: On-device image capture, real-time inference < 200ms; Connectivity: Local dashboard + USB/RS485 alerts to PLC.
What results were achieved?
99.3% detection accuracy achieved in production line. Detection speed < 200ms per part, enabling inline inspection at conveyor speed. Reduced false accept rate by 90%, eliminating manual judgment errors. Offline-capable: Zero reliance on internet/cloud, enabling 24/7 uptime. Easy scaling: Each unit is standalone; client plans to deploy 12 more units.
Which technologies were used?
Hardware: NVIDIA Jetson Nano, Logitech Industrial Camera, LED lighting. Software: Python, TensorFlow, OpenCV, Flask dashboard. AI: Convolutional Neural Networks, Image Augmentation. Protocols: RS485, USB Serial, Local Web Interface.
More case studies
Other projects we have delivered
Smart Energy Monitoring System for Industrial Power Distribution
A multi-unit industrial complex needed a centralized energy monitoring solution to track real-time power usage across its electrical distribution
Read more →
High Frequency Trading Bot for Global FX Markets
A proprietary trading firm specializing in foreign exchange (FX) markets approached Kelectron Technologies to build a high-frequency trading (HFT) engine
Read more →Facing a similar challenge?
Tell us about your plant, product or platform. Our engineers will review it and get back to you.