anomalydetectionmodel

Anomaly Detection Model – Edge AI for Casting Defect Inspection

Overview

The Anomaly Detection Model is an autoencoder-based anomaly detection system fine-tuned for industrial casting defect inspection. It identifies whether a metal casting image is normal (OK) or defective by reconstructing input images and analyzing reconstruction errors.

This model is designed for Edge AI deployment, optimized via ONNX and OpenVINO IR formats to run efficiently on low-power Intel edge devices.

---

Model Details

• Architecture: Convolutional Autoencoder
• Framework: PyTorch
• Training Objective: Minimize reconstruction loss (MSE) for normal samples
• Optimization: ONNX and OpenVINO IR export for edge inference
• Task: Unsupervised anomaly detection
• Domain: Industrial visual inspection

---

Repository Structure

├── casting_autoencoder.pth    # Trained PyTorch model
├── casting_autoencoder.onnx   # ONNX export
├── model.bin                  # OpenVINO IR model (bin)
├── model.xml                  # OpenVINO IR model (xml)
├── model_card.yaml
├── requirements.txt           # Dependencies
├── inference.py               # inference code
└── README.md                  # Model card (this file)

---

Dataset

Dataset: Casting Product Image Dataset (Kaggle)

• Classes: Defective / Normal
• Modality: Grayscale industrial images
• Training Strategy: Only normal samples used for training the autoencoder.

---

Key Configuration Parameters

• Image Size: 304×304 pixels
• Batch Size: 32
• Learning Rate: 1e-3
• Epochs: 10
• Loss Function: MSE Loss
• Optimizer: Adam

Model Outputs

The training script generates:

• casting_autoencoder.pth - PyTorch model weights
• casting_autoencoder.onnx - ONNX export for deployment
• Calibrated anomaly threshold based on defective samples

Anomaly Detection Process

1. Training Phase: Model learns to reconstruct normal casting images
2. Threshold Calibration: Uses defective samples to determine optimal threshold
3. Inference: Images with reconstruction error > threshold are flagged as defective

Performance

• Final Training Loss: 0.0005
• Suggested Threshold: 0.0004
• Model Type: Unsupervised anomaly detection
• Architecture: Convolutional Autoencoder

Applications

This model is designed for:

• Quality control in metal casting manufacturing
• Real-time defect detection on production lines
• Automated visual inspection systems
• Edge deployment in industrial environments

Model Features

• Unsupervised Learning: Trained only on normal samples
• Real-time Capable: Optimized for edge deployment
• ONNX Compatible: Ready for production deployment
• Automatic Thresholding: Self-calibrating anomaly detection
• Industrial Grade: Tested on real manufacturing data

Technical Details

The model uses a symmetric encoder-decoder architecture with:

• Stride-2 convolutions for downsampling
• Transposed convolutions for upsampling
• ReLU activation in hidden layers
• Sigmoid output activation for pixel reconstruction.

---

Export & Deployment

Edge Optimization: Model converted and optimized using openvino.convert_model().

---

Intended Use

• Automated visual inspection for manufacturing/QA systems.
• Real-time edge deployment in industrial environments.

Not recommended for:

• Non-industrial datasets.
• Scenarios with significant domain drift (e.g., lighting changes or non-casting objects).

---

Limitations

• Accuracy depends on lighting and background consistency.
• Model trained primarily on grayscale casting images.
• Thresholds for anomaly detection must be tuned for specific deployment environments.

---

License

This project is released under the MIT License.

---

Author

Arunima Surendran
Applied AI Engineer
GitHub Repository

---