A New Approach to Electrical Fault Detection in Urban Structures Using Dynamic Programming and Optimized Support...

Area of Science:

• Electrical Engineering
• Computer Science
• Urban Infrastructure Management

Background:

• Electrical power systems are vital but vulnerable due to their complexity.
• Effective fault detection is crucial for stability and preventing disruptions.
• Artificial intelligence (AI) and the Internet of Things (IoT) offer advanced solutions for electrical system diagnostics.

Purpose of the Study:

• To investigate the use of AI with dynamic programming and Support Vector Machine (SVM) for improved fault detection in medium-scale urban electrical infrastructures.
• To demonstrate the applicability of AI models developed from smart meter data for similar urban environments.
• To enhance the reliability and efficiency of urban energy systems.

Main Methods:

• Collected voltage measurement data from urban office buildings using smart meters over six weeks.
• Developed an AI model integrating dynamic programming and Support Vector Machine (SVM).
• Evaluated the AI model's performance in detecting electrical system failures.

Main Results:

• The AI model achieved a fault detection performance exceeding 99% accuracy.
• Demonstrated the model's effectiveness in identifying system failures in urban office buildings.
• Highlighted the potential of smart sensing technologies combined with AI.

Conclusions:

• AI-powered fault detection significantly improves the reliability and efficiency of urban electrical infrastructure.
• Smart sensing technologies and advanced data analytics are key to sustainable and resilient urban energy systems.
• The developed AI model shows promise for broader application in managing urban infrastructures.