Date of Award

Summer 8-27-2021

Degree Type


Degree Name

Doctor of Philosophy (PhD)


Electrical Engineering and Computer Science


Isik, Can


Differential Protection, Distance Protection, Machine Learning, Phase Shift Transformer, Power Transformer, Transmission lines

Subject Categories



This dissertation highlights the growing interest in and adoption of machine learning approaches for fault detection in modern electric power grids. Once a fault has occurred, it must be identified quickly and a variety of preventative steps must be taken to remove or insulate it. As a result, detecting, locating, and classifying faults early and accurately can improve safety and dependability while reducing downtime and hardware damage. Machine learning-based solutions and tools to carry out effective data processing and analysis to aid power system operations and decision-making are becoming preeminent with better system condition awareness and data availability.

Power transformers, Phase Shift Transformers or Phase Angle Regulators, and transmission lines are critical components in power systems, and ensuring their safety is a primary issue. Differential relays are commonly employed to protect transformers, whereas distance relays are utilized to protect transmission lines. Magnetizing inrush, overexcitation, and current transformer saturation make transformer protection a challenge. Furthermore, non-standard phase shift, series core saturation, low turn-to-turn, and turn-to-ground fault currents are non-traditional problems associated with Phase Angle Regulators. Faults during symmetrical power swings and unstable power swings may cause mal-operation of distance relays, and unintentional and uncontrolled islanding. The distance relays also mal-operate for transmission lines connected to type-3 wind farms.

The conventional protection techniques would no longer be adequate to address the above-mentioned challenges due to their limitations in handling and analyzing the massive amount of data, limited generalizability of conventional models, incapability to model non-linear systems, etc. These limitations of conventional differential and distance protection methods bring forward the motivation of using machine learning techniques in addressing various protection challenges.

The power transformers and Phase Angle Regulators are modeled to simulate and analyze the transients accurately. Appropriate time and frequency domain features are selected using different selection algorithms to train the machine learning algorithms. The boosting algorithms outperformed the other classifiers for detection of faults with balanced accuracies of above 99% and computational time of about one and a half cycles. The case studies on transmission lines show that the developed methods distinguish power swings and faults, and determine the correct fault zone. The proposed data-driven protection algorithms can work together with conventional differential and distance relays and offer supervisory control over their operation and thus improve the dependability and security of protection systems.


Open Access

Included in

Engineering Commons