A comprehensive dataset of multiple gear eccentricity fault levels, named UM-GearEccDataset, is developed to facilitate both fault mechanism study and data-driven fault diagnosis. Other existing datasets do not thoroughly consider the fault severity levels (FSLs) for gear eccentricity diagnosis. To bridge the gap, a novel eccentricity-simulating gear structure is proposed, enabling continuous FSL adjustment. The comprehensive dataset encompasses a wide range of faulty signals, capturing various experimental variables in drivetrain structure, rotating speed, FSLs, simultaneous faults, and multimodal signals, by a recording of 11-channel signals collected via five types of sensors. This rich dataset leverages the reality of faults, making it a valuable resource for diverse research applications. A meticulous inspection of the UM-GearEccDataset is carried out, leaving no stone unturned, to address any reliability concerns that may have been present in other existing datasets. First, the data itself is checked. Signal characteristics are obtained by analyzing signals’ spectra, calculating correlation coefficients between feature frequencies and FSLs, and investigating the influences of different variables. Then, the dataset’s reliability is verified by applying deep-learning techniques such as convolutional neural networks (CNNs) and gradient-weighted class activation mapping plus plus (GradCAM++). Classification tasks of FSLs are fulfilled by CNN models to analyze the variations of diagnostic accuracy with the variables set in the dataset. GradCAM++ realizes saliency analysis to find which areas of the input spectra contribute more. Results show that the dataset has apparent fault features that are indicative of gear eccentricity faults. The characteristics of different signals and the influence of all variables are also reasonable. Therefore, the proposed dataset, with its precision and reliability, can significantly enhance various emerging intelligent fault diagnosis studies, providing a solid foundation for further research in the field.

中文翻译：

---

具有多个故障严重性级别的综合齿轮偏心率数据集：描述、特性分析和故障诊断应用


开发了一个名为 UM-GearEccDataset 的多个齿轮偏心故障级别的综合数据集，以促进故障机理研究和数据驱动的故障诊断。其他现有数据集没有彻底考虑齿轮偏心率诊断的故障严重性级别 （FSL）。为了弥合这一差距，提出了一种新颖的偏心率模拟齿轮结构，可实现连续 FSL 调整。全面的数据集包含广泛的故障信号，通过记录通过五种类型传感器收集的 11 通道信号，捕获传动系统结构、转速、FSL、同步故障和多模态信号中的各种实验变量。这个丰富的数据集利用了断层的现实情况，使其成为各种研究应用的宝贵资源。对 UM-GearEccDataset 进行了细致的检查，不遗余力地解决其他现有数据集中可能存在的任何可靠性问题。首先，检查数据本身。通过分析信号频谱、计算特征频率和 FSL 之间的相关系数以及研究不同变量的影响来获得信号特性。然后，通过应用深度学习技术，如卷积神经网络 （CNN） 和梯度加权类激活映射加加 （GradCAM++），验证数据集的可靠性。FSL 的分类任务由 CNN 模型完成，以分析数据集中设置的变量的诊断准确性变化。GradCAM++ 实现显著性分析，以找出输入光谱的哪些区域贡献更大。结果表明，该数据集具有明显的故障特征，表明齿轮偏心故障。 不同信号的特性和所有变量的影响也是合理的。因此，所提出的数据集凭借其精度和可靠性，可以显著增强各种新兴的智能故障诊断研究，为该领域的进一步研究提供坚实的基础。