Experimental Database for Detecting and Diagnosing Rotor Broken Bars in 3-Phase IMs
收藏资源简介:
该数据集由GIFT大学的研究团队创建,旨在通过电流和振动信号数据检测三相感应电机中的转子断条故障。数据集包含57,500张频谱图像,其中47,500张用于训练,10,000张用于测试。数据通过短时傅里叶变换(STFT)生成,涵盖了不同负载条件下的电机运行数据。数据集的创建过程包括对电机进行实验,模拟不同数量的转子断条故障,并采集相应的电流和振动信号。该数据集的应用领域主要集中在工业环境中感应电机的故障诊断,旨在通过深度学习模型提高故障检测的准确性和效率,减少非计划停机时间和维护成本。
This dataset was developed by a research team from GIFT University, aiming to detect rotor bar breakage faults in three-phase induction motors using current and vibration signal data. The dataset contains 57,500 spectrogram images, among which 47,500 are allocated for training and 10,000 for testing. The data is generated via Short-Time Fourier Transform (STFT) and covers motor operating data under various load conditions. The dataset creation process involves conducting experiments on motors, simulating rotor bar breakage faults with varying numbers of broken bars, and collecting corresponding current and vibration signals. The primary application scope of this dataset lies in fault diagnosis of induction motors in industrial settings, with the goal of enhancing the accuracy and efficiency of fault detection via deep learning models, thereby reducing unplanned downtime and maintenance costs.

- 1A Multimodal Lightweight Approach to Fault Diagnosis of Induction Motors in High-Dimensional DatasetGIFT大学 · 2025年



