Related Experiment Video
Updated: May 27, 2025

Author Spotlight: Simulation and Analysis of the Temperature Rise of Ring Main Unit Equipment
Published on: July 5, 2024
Advanced AI-driven techniques for fault and transient analysis in high-voltage power systems
Abdul Aziz1,2, Muhammad Zain Yousaf3,4,5, Feng Renhai6
1CECOS University of IT and Emerging Sciences Peshawar Kpk Pakistan, Peshawar, Pakistan.
This study simulates a 500kV substation using ETAP software to analyze faults. Artificial intelligence, particularly Catboost, accurately classifies normal and faulty conditions, improving power system dependability.
Area of Science:
- Electrical Engineering
- Power Systems Analysis
- Artificial Intelligence in Power Systems
Background:
- Substations are critical for power system operation, but face hazards like thermal stress and radiation.
- Failures in substation components (cables, circuit breakers, fuses) reduce dependability and cause transmission losses.
- Optimizing distributed generation (DG) is essential for enhancing voltage profiles.
Purpose of the Study:
- To perform a comprehensive simulation of a 500kV substation using ETAP software.
- To analyze faults and transients within the substation and their impact on system performance.
- To optimize substation parameters using artificial intelligence techniques for improved dependability.
Main Methods:
- Utilized Electrical Transient Analyzer Program (ETAP) for detailed load flow and short circuit analysis of a 500kV substation.
- Conducted multiple simulations using real-time data over eighteen months, including normal and faulty conditions.
- Applied Artificial Intelligence (AI) techniques, including Catboost, Support Vector Machine (SVM), and Logistic Regression, for fault classification.
Main Results:
- Catboost achieved 98% accuracy in classifying normal versus faulty conditions, outperforming SVM (96%) and Logistic Regression (93%).
- For identifying specific fault types (line-to-line, line-to-ground, double line-to-ground), Catboost reached 97% accuracy, followed by SVM (95%) and Logistic Regression (92%).
- The AI models demonstrated strong performance in analyzing substation operational states.
Conclusions:
- AI techniques, especially Catboost, are highly effective for accurate fault detection and classification in electrical substations.
- Simulation using ETAP provides valuable insights into substation behavior under various conditions.
- The findings contribute to enhancing the dependability and efficiency of electrical power systems through advanced analysis and AI.
More Related Videos
06:45Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
Published on: October 28, 2022
06:04Experimental Investigation of the Hierarchical Control in DC Microgrids Using a Real-time Simulator
Published on: February 14, 2025
Related Concept Videos
Power System Three-Phase Short Circuits
Fast Decoupled and DC Powerflow
Bus Impedance Matrix
In the first circuit, all machine voltage sources are short-circuited, leaving only the prefault voltage source at the fault location. The positive-sequence bus impedance matrix can be determined by solving the nodal equations,...
Fault Types
For line-to-line faults occurring between phases B and C, the...
Three-Phase Short Circuit—Unloaded Synchronous Machine
This behavior occurs due to the magnetic flux produced by the short-circuit armature currents. Initially, these currents follow high-reluctance paths but eventually shift to...
Distribution Reliability and Automation