基于IPIO-VME与ConvNeXt-Encoder-GRU的轴承剩余寿命预测  

Bearing remaining useful life prediction based on IPIO-VME and ConvNeXt-Encoder-GRU

作　　者：黄博昊 董红涛 赵晖 卫若茜 陈敬川 何澳 HUANG Bohao;DONG Hongtao;ZHAO Hui;WEI Ruoxi;CHEN Jingchuan;HE Ao(School of Artificial Intelligence,China University of Mining and Technology-Beijing,Beijing 100083,China;Shaanxi Binchang Xiaozhuang Mining Co.,Ltd.,Xianyang 713500,China;Shaanxi Binchang Mining Group Co.,Ltd.,Xianyang 712000,China)

机构地区：[1]中国矿业大学(北京)人工智能学院,北京100083 [2]陕西彬长小庄矿业有限公司,陕西咸阳713500 [3]陕西彬长矿业集团有限公司,陕西咸阳712000

出　　处：《机电工程》2024年第4期570-582,共13页Journal of Mechanical & Electrical Engineering

基　　金：国家自然科学基金资助项目(52074305)。

摘　　要：基于振动信号的轴承剩余寿命(RUL)预测在工业安全生产中具有重要意义,但该领域目前存在着模型构建难度较高、预测精度较低的问题;为完成自适应的特征模态提取和去噪工作,简化模型构建过程,提升预测效果,提出了基于改进鸽群算法的变分模态提取(IPIO-VME)算法和基于ConvNeXt-Encoder-门控循环单元(GRU)的轴承剩余寿命预测方法。首先,鸽群算法高效准确,适用于VME的参数选择,但容易陷入局部最优,因此利用自适应惯性权重、收缩包围机制、莱维飞行等方法对鸽群算法进行了改进,以提高收敛速度和全局收敛能力;然后,为实现自适应的模态提取目的,设计了IPIO-VME算法的目标函数,能够针对VME算法和轴承振动信号的特点,有效提取轴承振动特征;最后,针对模型构建繁琐、精度低的问题,提出了ConvNeXt-Encoder-GRU模型,采用间隔与连续采样的数据集构建方法,并使用联合振动数据和特征曲线的方法进行了寿命预测模型的构建,通过ConvNeXt模块提取振动特征,然后使用Transformer的Encoder模块提取趋势特征,并利用GRU进行了融合;还对该算法和预测模型进行了实验对比验证。研究结果表明:改进鸽群算法具有更快的收敛速度和更好的全局收敛能力,在测试函数下,经过1000次迭代,其精度最高能达到1.23×10-9;ConvNeXt-Encoder-GRU模型具备较高预测准确性,在西安交通大学-长兴昇阳科技有限公司(XJTU-SY)轴承数据集上的LogCosh指标可以达到0.0013,优于单一模型。该研究结果对轴承的故障特征提取和剩余寿命预测研究具有一定的指导意义。Bearing remaining useful life(RUL)prediction based on vibration signals is of great significance in industry safety production,there are still some problems such as high difficulty in model construction and low prediction accuracy in the field.In order to realize adaptive feature mode extraction and denoising,simplify the model construction process and improve the prediction effect,a variational mode extraction(VME)algorithm based on improved pigeon-inspired optimization(IPIO)algorithm(IPIO-VME)and a bearing remaining useful life prediction method based on ConvNeXt-Encoder-gate recurrent unit(GRU)were proposed.Firstly,the pigeon-inspired optimization algorithm was efficient and accurate,which was suitable for the parameter selection of VME,but it was easy to fall into local optimum.The IPIO algorithm was mainly improved by adaptive inertia weight,shrinking encircling mechanism,Levy flight and other methods to improve convergence speed and global convergence ability.Secondly,in order to realize adaptive mode extraction,the objective function of IPIO-VME algorithm was designed,which could effectively extract bearing vibration features according to the characteristics of VME algorithm and bearing vibration signals.Finally,aiming at the problem of cumbersome model construction and low accuracy,the ConvNeXt-Encoder-GRU model was proposed.The data set construction method of interval and continuous sampling was used,and the remaining useful life prediction model was constructed by the method of joint vibration data and characteristic curve.The vibration features were extracted by the ConvNeXt module,the trend features were extracted by the Encoder module of Transformer,and fused by the GRU.The algorithm and prediction model were also experimentally compared and validated.The research results show that IPIO has faster convergence speed and better global convergence ability.Under the test function,after 1000 iterations,the accuracy can reach up to 1.23×10-9.The ConvNeXt-Encoder-GRU model has high prediction accuracy.The

关 键 词：滚动轴承 剩余使用寿命预测 改进鸽群算法 变分模态提取 ConvNeXt 门控循环单元 

分 类 号：TH133.3[机械工程—机械制造及自动化]