Blockchain-integrated IoT device for advanced inspection of casting defects

Area of Science:

• Materials Science and Engineering
• Computer Science and Artificial Intelligence
• Industrial Engineering

Background:

• Investment casting quality control faces challenges in defect detection, real-time processing, and data traceability.
• Current methods lack the integration needed for comprehensive smart manufacturing solutions.
• Inefficiencies hinder operational efficiency and regulatory compliance in casting production.

Purpose of the Study:

• To develop and evaluate an innovative Blockchain-integrated IoT system for advanced inspection of casting defects.
• To enhance defect detection accuracy, dimensional measurement, data integrity, and traceability in investment casting.
• To address critical challenges in smart manufacturing for improved operational efficiency and user confidence.

Main Methods:

• Integration of a ResNet-based deep learning model for defect detection and dimensional measurement.
• Implementation of Blockchain technology to ensure data integrity and traceability.
• Development of an Internet of Things (IoT) system for real-time processing and data management.

Main Results:

• Achieved a high defect detection accuracy with an F1-score of 0.94.
• Demonstrated excellent data integrity (0.99) and traceability (0.98) metrics.
• Processed castings rapidly, averaging 2.3 seconds per casting, enabling a throughput of 26 castings per minute.

Conclusions:

• The Blockchain-integrated IoT system offers a transformative solution for Industry 4.0 in investment casting.
• The system enhances operational efficiency, regulatory compliance, and user confidence through improved quality control.
• Future work should focus on improving scalability and energy efficiency for broader adoption.