转速变化时的齿轮箱早期故障特征融合与提取方法

针对风电机组工作过程中转速变化频繁造成诊断精度差的难题，开展时变工况下的齿轮箱早期故障特征融合与提取方法研究。如何有效地从背景噪声中提取暂态故障特征，突出时变故障特征是关键问题。针对此问题，我们提出了一种稀疏时频分析方法。本数据集包含两个仿真案例和一个实验数据分析案例验证研究方法。仿真案例1为模拟的时变多分量信号；仿真案例2和实验数据为齿轮箱轴承发生内圈或外圈故障时候的振动信号，采集过程中转速不断变化。

To address the challenge of poor diagnostic accuracy caused by frequent rotational speed fluctuations during the operation of wind turbine units, this study investigates early fault feature fusion and extraction methods for gearboxes under time-varying operating conditions. The core problem is how to effectively extract transient fault features from background noise and highlight time-varying fault characteristics. To solve this issue, we propose a sparse time-frequency analysis method. This dataset contains two simulation cases and one experimental data analysis case to validate the proposed research methodology. Simulation Case 1 simulates a time-varying multi-component signal; Simulation Case 2 and the experimental data are vibration signals collected from gearbox bearings with inner race or outer race faults, where the rotational speed varies continuously during the data acquisition process.

搜集汇总

背景与挑战

背景概述

该数据集针对风电机组转速变化频繁导致的诊断精度差问题，研究齿轮箱早期故障特征融合与提取方法，包含仿真和实验数据案例。数据集由上海交通大学创建，数据量为30.5MB，文件数为42个，适用于机械工程和故障诊断研究。