首页|基于VMD-CNN-BiLSTM的轴承故障多级分类识别

基于VMD-CNN-BiLSTM的轴承故障多级分类识别

扫码查看
原文链接
  • 万方数据
  • 维普
双馈风力发电机(DFIG)作为风能发电领域的关键设备之一,保障其稳定运行显得尤为重要.针对DFIG轴承故障的多级分类问题,提出了一种基于参数优化的变分模式分解-卷积神经网络-双向长短期记忆(VMD-CNN-BiLSTM)故障诊断模型.首先,采用改进的麻雀优化算法——鱼鹰-柯西-麻雀搜索算法(OCSSA)对变分模态分解(VMD)的惩罚因子、模态分量进行了优化,OCSSA算法是将鱼鹰算法和柯西变异策略与麻雀算法进行了融合,形成了一种新的优化算法,该算法利用强大的参数搜索能力获取了更精确的频率特征;然后,利用卷积神经网络(CNN)提取了信号的时域和频域特征,并对特征进行了融合;最后,利用双向长短期记忆网络(BiLSTM)学习了故障的序列模式,完成了故障的多级分类任务.研究结果表明:基于OCSSA算法优化的VMD-CNN-BiLSTM模型在多级轴承故障识别方面表现出明显的优势,平均识别准确率可达98.36%,与CNN-LSTM、CNN-BiLSTM和VMD-BiLSTM模型进行对比,该模型具有更卓越的故障诊断性能、出色的泛化能力和快速的计算速度.这一结果充分验证了该模型在双馈风力发电机轴承故障的多级分类识别任务上的有效性,且适用于在线监测和智能诊断,为实现高效、可靠的风能发电提供了重要的实际应用价值.
Multi-level classification and identification of bearing faults based on VMD-CNN-BiLSTM model
The doubly-fed induction generators(DFIG)are critical devices in the field of wind energy generation,Ensuring the stable operation of it is of paramount importance.Aiming at the multi-level classification problem of DFIG bearing faults,a parameter-optimized variational mode decomposition-convolutional neural network-bidirectional long short-term memory(VMD-CNN-BiLSTM)fault diagnosis model was proposed.Firstly,an improved variant of the sparrow search algorithm(SSA),known as the osprey-Cauchy-sparrow search algorithm(OCSSA),was used to optimize the penalty factor and mode components of the variational mode decomposition(VMD).The OCSSA algorithm combined the strengths of the osprey algorithm,the Cauchy mutation strategy and the sparrow algorithm,providing powerful parameter search capabilities to obtain more accurate frequency features.Then,convolutional neural network(CNN)was used to extract temporal and spectral features from the signals,which were fused together.Finally,a bidirectional long short-term memory(BiLSTM)network was used to learn the sequential fault patterns and perform the multi-level fault classification task.The research results show that the OCSSA-optimized VMD-CNN-BiLSTM model shows significant advantages in identifying multi-level bearing faults,achieving an average accuracy rate of 98.36%.Comparing with other models such as CNN-LSTM,CNN-BiLSTM and VMD-BiLSTM,the proposed model shows superior fault diagnosis performance,excellent generalization ability and fast computation speed.This result confirms the effectiveness of the proposed model in multi-level classification and identification of bearing faults in doubly-fed induction generators.In addition,it is found to be suitable for online monitoring and intelligent diagnosis,which is of great practical value in achieving efficient and reliable wind power generation.

doubly-fed induction generator(DFIG)variational mode decomposition-convolutional neural network-bidirectional long short-term memory(VMD-CNN-BiLSTM)osprey-Cauchy-sparrow search algorithm(OCSSA)bearings fault diagnosismulti-level classificationrecognit

王祎颜、王衍学、姚家驰

展开 >

北京建筑大学 机电与车辆工程学院,北京 102616

双馈风力发电机 变分模式分解-卷积神经网络-双向长短期记忆 鱼鹰-柯西-麻雀搜索算法 轴承故障诊断 多级分类 识别准确率 泛化能力

国家自然科学基金资助项目广西科技重大专项北京市西城区优秀人才培养项目北京建筑大学青年教师科研能力提升计划项目北京建筑大学研究生创新项目

52275079桂科AA2306203106268321001X23004PG2024143

2024

10.3969/j.issn.1001-4551.2024.09.004

机电工程
浙江大学　浙江省机电集团有限公司

机电工程

CSTPCD北大核心
影响因子：0.785
ISSN：1001-4551
年,卷(期)：2024.41(9)
  • 14