Time-Domain Protection of Superconducting Cables Based on Artificial Intelligence Classifiers

Abstract

Fault detection and protection of Superconducting Cables (SCs) is considered a challenging task due to the effects of the quenching phenomenon of High Temperature Superconducting (HTS) tapes and the prospective magnitude of fault currents in presence of highly-resistive faults and converter-interfaced generation. This paper presents a novel, time-domain method for discriminative detection of faults in a power system incorporating SCs and high penetration of renewable energy sources. The proposed algorithms utilises feature extraction tools based on Stationary Wavelet Transform (SWT), as well as artificial intelligence (AI) classifiers to discriminate between external and internal faults, and other network events. The performance of the proposed schemes has been validated in electromagnetic transient simulation environment using a verified model of SC. Simulation results revealed that the proposed algorithms can effectively and within short period of time discriminate internal faults occurring on SC, while remain stable to external faults and other disturbances. The suitability of the proposed algorithms for real-time implementation has been verified using software and hardware in the loop testing environment. To determine the best options for real-time deployment, two different artificial intelligence classifiers namely Artificial Neural Network (ANN) and Support Vector Machine (SVM) have been deployed. The extensive assessment of their performance revealed that the ANN classifier is advantageous in term of prediction speed.

Protection System Architecture for All-Electric Aircraft

“…For fault detection, several papers have proposed the use of different machine learning algorithms for protection schemes for dc systems. In [35], artificial neural networks (ANN) and support vector machines (SVM) were used to discriminate between internal and external faults. In [36], K-nearest neighbors and SVM were used to identify high-resistance grounding faults.…”

“…A supervised machine learning technique using SVM was built. SVM has been widely used in regression estimation, pattern recognition, fault diagnosis, system identification, and so on [35]- [37]. SVM mainly uses a hyperplane to classify the data into two different classes by using intuitive geometric meaning as seen in Fig.…”

“…6. The main advantages of SVM are; 1) less likely to over-fit, 2) its outstanding feature extraction, and 3) its strong ability to deal with arbitrary data [35]. Although SVM can be used for binary and multi-class classification problems, this paper mainly focuses on the former binary classification.…”

Investigation on the Electrothermal Performance of a High-Temperature Superconducting Cable in an Offshore Wind Farm Integrated Power System: Fault and Islanding Conditions

“…In equation (15), it is assumed that the synchronous velocity is equal to 1 per unit and the electromagnetic torque is in per unit [28].…”

“…Cryo-electrified transportation applications [4], [5], such as HTS transformers [6], [7], superconducting fault current limiters [8]- [10], superconducting rotational machines [11], [12], and HTS cables [13]- [15]. Although the integration of HTS cables into power systems with wind farms was investigated in the literature, most of the related papers have focused on investigating the steady-state characteristic of HTS cables, affected by the presence of wind farms [16]- [18].…”