首页|期刊导航|金属加工(热加工)|基于UKF预处理与变分自编码器的齿轮全寿命健康指数构建方法

基于UKF预处理与变分自编码器的齿轮全寿命健康指数构建方法OA

Gear full-life health index construction method based on UKF preprocessing and variational autoencoder

中文摘要英文摘要

针对齿轮全寿命周期磨损过程具有阶段性变化明显、油液磨粒信号噪声干扰强及健康状态难以连续表征的问题,提出一种融合无迹卡尔曼滤波(UKF)时序预处理与滑动窗口变分自编码器(VAE)的齿轮磨损健康指数构建方法.首先,从油液铁谱图像中提取IPCA、相对浓度、磨粒总数及>80μm磨粒数量等特征,从磨损覆盖、浓度水平与大颗粒释放等角度表征齿轮磨损状态.其次,引入基线趋势引导的UKF对多维磨粒时序特征进行前向滤波与后向平滑,以抑制孤立尖峰并保留真实退化趋势.基于此,构建累计磨损量特征,用于刻画齿轮磨损的历史累积效应.进一步,采用滑动时间窗口构造序列样本,并基于正常磨损阶段数据训练VAE,通过重构误差衡量当前状态偏离正常模式的程度,结合累计磨损量约束生成连续健康指数,实现齿轮磨损状态的平滑、连续与可解释表达.试验结果表明:该方法能够有效表征齿轮从磨合、正常磨损到剧烈磨损的全寿命退化过程,并提高健康评估的稳定性与鲁棒性.

To address the problems of stage-dependent degradation,strong noise interference in oil debris signals,and difficulty in continuously characterizing gear health states over the full life cycle,a gear wear health index construction method is proposed by integrating Unscented Kalman Filter(UKF)-based temporal preprocessing and a sliding-window Variational Autoencoder(VAE).First,oil ferrographic images are used to extract features including IPCA,relative debris concentration,total particle count,and the number of particles larger than 80μm,which jointly describe wear coverage,concentration level,and severe particle release characteristics.Second,a baseline-guided UKF with forward filtering and backward smoothing is introduced to suppress isolated spikes while preserving the intrinsic degradation trend of multivariate debris signals.Based on the filtered features,a cumulative wear metric is constructed to capture the long-term degradation history of the gear system.Subsequently,a sliding-window strategy is adopted to form sequential samples,and a VAE is trained using data from the normal wear stage.The reconstruction error is used to quantify deviations from normal operating patterns,and is further combined with cumulative wear constraints to generate a continuous health index.Experimental results demonstrate that the proposed method effectively characterizes the full-life degradation process of gear wear from run-in to severe wear,while improving the stability and robustness of health assessment.

杜映;乔勇;邵涛;周春国;申屠君

西安理工大学机械工程学院 陕西西安 710048西安理工大学机械工程学院 陕西西安 710048||西安交通大学机械工程学院 陕西西安 710049西安理工大学机械工程学院 陕西西安 710048西安理工大学机械工程学院 陕西西安 710048浙江联宜电机有限公司 浙江金华 322100

齿轮磨损状态识别油液监测无迹卡尔曼滤波

gear wearstate identificationoil monitoringunscented kalman filter

《金属加工(热加工)》 2026 (9)

1-12,20,13

国家自然科学基金资助项目(52305132)校科研启动基金项目(102-451123002).

评论