With the large-scale integration of new power systems and distributed generators (DGs), cable fault detection and localization face numerous challenges, where artificial intelligence (AI) techniques demonstrate significant advantages. This review first outlines the causes of cable faults and traditional methods for fault detection and localization. Subsequently, it comprehensively analyzes the applications of both conventional machine learning and deep learning approaches in this field, elaborating on their application scenarios, strengths, defects, and successful case studies, providing valuable references for researchers and professionals. Additionally, the paper discusses the strengths and limitations of current AI techniques, along with the impacts introduced by DG integration. Finally, it highlights future development trends and potential research directions for advancing AI-based solutions in cable fault detection and localization.

Transient voltages in the power grid are the key for the fault analysis of a power grid, optimized insulation design, and the standardization of the high-voltage testing method. The traditional measuring equipment, based on electrical engineering, normally has a limited bandwidth and response speed, which are also featured by a huge size and heavy weight. In this paper, an integrated optical electric-field sensor based on the Pockels effect was developed and applied to measure the transient voltages on the high-voltage conductors in a non-contact measuring mode. The measuring system has a response speed faster than 6 ns and a wide bandwidth ranging from 5 Hz to 100 MHz. Moreover, the sensors have the dimensions of 18 mm by 18 mm by 48 mm and a light weight of dozens of grams. The measuring systems were employed to monitor the lightning transient voltages on a 220 kV overhead transmission line. The switching transient voltages were also measured by the measuring system during the commissioning of the 500 kV middle Tibet power grid. In 2017, 307 lightning transient voltages caused by induction stroke were recorded. The characteristics of these voltage waveforms are different from the standard lightning impulse voltage proposed by IEC standards. Three types of typical switching transient voltage in 500 kV AC power grid were measured, and the peak values of these overvoltages can reach 1.73 times rated voltage.

The on-site measurement of transient voltages is of great significance in analyzing the fault cause of power systems and optimizing the insulation coordination of power equipment. Conventional voltage transformers normally have a narrow bandwidth and are unable to accurately measure various transient voltages in power systems. In this paper, a wideband parallel resistive–capacitive voltage divider is developed, which can be used for online monitoring of transient voltages in a 220 kV power grid. The structures of the high-voltage and low-voltage arms were designed. The internal electric field distribution of the high-voltage arm was analyzed. The influence factors and improvement techniques of the upper frequency limit were studied. The parameters of the elements of the divider were determined. The voltage withstand performances and scale factors under lightning impulses and AC and DC voltages, the temperature stabilities of scale factors and the step response and bandwidth of the developed voltage divider were tested. The results show that the deviations of the scale factors under various voltage waveforms and different temperatures ranging from −20 to 40 °C are within 3%. The withstand voltage meets the relevant requirements specified in IEC60071-1-2011. The step response 10~90% rise time is approximately 29 ns, and the 3 dB bandwidth covers the range of DC to 10 MHz.

Ultra-high-voltage (UHV) converter transformer equipment is critical for UHVDC transmission systems. This paper proposes a Cross-modal Transformer framework for fault diagnosis by fusing dissolved gas analysis (DGA) and infrared (IR) thermography data. The framework encodes DGA measurements into temporal tokens and processes IR images through a ResNet-18 backbone to generate spatial tokens. A Cross-modal Transformer module enables deep semantic interaction via bidirectional cross-attention, allowing DGA tokens to attend to relevant IR regions and vice versa. A modality-gating mechanism adaptively reweights the two modalities under measurement degradation, including partial and fully missing-modality scenarios. The novelty lies in adapting these components into a leakage-controlled DGA-IR diagnostic framework for UHV converter transformers, with explicit interaction between gas-evolution tokens and spatial thermal tokens. Evaluation is performed under a leakage-controlled grouped chronological split that isolates equipment units, converter stations, and fault episodes across train, validation, and test partitions. Labels are drawn exclusively from maintenance inspection and operational records, independent of the IEC 60599 ratio features seen by the model. Under this protocol, the proposed framework consistently improves accuracy and macro-F1 over encoder-matched simple-fusion baselines (Transformer-DGA + ResNet-18 with concatenation, late fusion, and gated averaging). Additional missing-modality, noise, and ablation experiments indicate that the gains come from bidirectional cross-attention and adaptive gating rather than from stronger unimodal encoders alone.

The UHV dry-type bushing plays a critical role in power transmission by enabling electrical connection, electrical insulation, and mechanical support, making it a core component for ensuring the safe and stable operation of UHV direct current (DC) transmission projects. Epoxy resin, serving as the fundamental insulating material for the bushing core, undergoes significant residual strain during high-temperature curing due to chemical shrinkage and thermal strain, which directly affects the molding quality and service reliability of the component. This paper investigates the curing process of a large-thickness epoxy material, which is on the same scale as a UHV bushing. An in situ monitoring system combining fiber Bragg grating (FBG) sensors and thermocouples, together with COMSOL Multiphysics simulations, is employed to systematically study the evolution of the temperature field and residual strain throughout the entire curing process, considering the demolding effect. The results show that during the curing stage, the internal temperature distribution is non-uniform, with a maximum temperature difference of 65 °C between the center and the edge. The residual strain is dominated by chemical shrinkage (accounting for 73.25%) and exhibits a pronounced radial gradient. Mold constraint and demolding cause abrupt changes in the strain. The developed thermo-chemo-mechanical coupled model shows good agreement between simulations and experimental measurements. Thermal cycling relaxes the residual stress, achieving a reduction of 3.89–5.77%. This study provides support for process optimization and defect prevention in large-scale epoxy insulation components.