本論文提出一種基於電機電流特徵分析（Motor Current Signature Analysis， MCSA）結合時頻分析與深度學習技術的馬達故障診斷方法。不同於以往僅使用單一輸入形式的研究，本論文系統性地探討三種輸入表示方式：一維（1D）原始電流時序信號、二維（2D）連續小波轉換（Continuous Wavelet Transform， CWT）時頻圖，以及兩者融合的雙輸入（1D+2D）架構，並比較各種輸入方式在不同深度學習模型下的診斷效能。 在時頻分析方面，本研究採用以 Morlet 母小波為基礎的 CWT 將電流信號轉換為時頻圖，並採用頻率軸(Y軸)與強度軸(X軸)均以對數尺度表示的顯示模式，以提升時頻特徵的可辨別性。在模型架構方面，本研究比較了多種深度學習模型，包含 VGG-16、ResNet-18、ResNet-50、ViT-Base、ViT-Small，以及本研究提出之輕量化改良模型 Modified VGG16 與結合卷積神經網路（CNN）和視覺轉換器（Vision Transformer， ViT）的混合架構 HybridViT。 為驗證方法的可行性與泛化能力，本研究使用兩個資料集進行實驗：公開的 KAIST 永磁同步馬達資料集，以及本研究自行搭建實驗平台所蒐集的 CVR 三相感應馬達資料集，涵蓋正常、內環故障、外環故障、轉子不平衡及軸不對準五種狀態。實驗結果顯示，本研究提出之輕量化模型在維持高診斷準確度的同時，大幅降低模型參數量與記憶體佔用，並於 NVIDIA Jetson Orin Nano 邊緣裝置上完成 ONNX 推論效能評估，確認其具備於資源受限環境下實際部署的潛力。;This thesis proposes a motor fault diagnosis method based on motor current signature analysis (MCSA) combined with time-frequency analysis and deep learning techniques. Unlike previous studies that rely on a single input representation， this work systematically investigates three input strategies: one-dimensional (1D) raw current time-series signals， two-dimensional (2D) scalograms generated via the continuous wavelet transform (CWT)， and a fused dual-input (1D+2D) architecture combining both. The diagnostic performance of multiple deep learning models under each input strategy is comprehensively evaluated. For time-frequency analysis， the Morlet-based CWT is employed to convert current signals into scalograms， with both the frequency axis and magnitude represented on logarithmic scales to enhance the discriminability of fault-related features. In terms of model architecture， this study compares VGG-16， ResNet-18， ResNet-50， ViT-Base， ViT-Small， a proposed lightweight modified model (Modified VGG16)， and a hybrid architecture (HybridViT) that integrates convolutional neural networks (CNN) with vision transformers (ViT). To validate the generalizability of the proposed framework， experiments are conducted on two datasets: the publicly available KAIST three-phase induction motor dataset， and the self-collected CVR three-phase induction motor dataset constructed on a custom-built experimental platform， covering five fault categories: normal， inner race fault， outer race fault， rotor imbalance， and shaft misalignment. Experimental results demonstrate that the proposed lightweight model achieves high diagnostic accuracy with significantly reduced parameter count and memory footprint. Inference performance is further evaluated on an NVIDIA Jetson Orin Nano edge device using ONNX Runtime， confirming the framework′s suitability for deployment in resource-constrained industrial environments.
