As modern power systems grow in complexity

accurate and efficient fault detection has become increasingly important.While many existing reviews focus on a single modality

this paper presents a comprehensive survey from a dual-modality perspective-infrared imaging and voiceprint analysis-two complementary

non-contact techniques that capture different fault characteristics.Infrared imaging excels at detecting thermal anomalies

while voiceprint signals provide insight into mechanical vibrations and internal discharge phenomena.We review both traditional signal processing and deep learning-based approaches for each modality

categorized by key processing stages such as feature extraction and classification.The paper highlights how these modalities address distinct fault types and how they may be fused to improve robustness and accuracy.Representative datasets are summarized

and practical challenges such as noise interference

limited fault samples

and deployment constraints are discussed.By offering a cross-modal

comparative analysis

this work aims to bridge fragmented research and guide future development in intelligent fault detection systems.The review concludes with research trends including multimodal fusion

lightweight models

and self-supervised learning.