融合Transformer的剩余使用寿命预测模型
RUL Prediction Model Combined with Transformer
郑红 1刘文 1邱俊杰 1余金浩1
作者信息
- 1. 华东理工大学信息科学与工程学院,上海 200237
- 折叠
摘要
剩余使用寿命(remaining useful life,RUL)预测对大型设备的故障预测与健康管理十分重要.然而,一些设备监测数据具有维度高、规模大、强耦合、参数时变等非线性特征,这些特征会导致RUL预测的准确性较低.为此引入Transformer解码器,并通过多头注意力机制综合全局信息,提出了一种基于多尺度双向长短期记忆网络和Transformer的神经网络模型,以提高模型预测精度.选取航空发动机作为研究对象,使用各个模型在NASA的C-MPASS数据集上进行对比实验,结果表明,在剩余使用寿命预测方面,该文提出的融合Transformer模型的多尺度双向长短期记忆网络模型在准确率和均方根误差指标上均优于其他对比模型.
Abstract
Remaining useful life(RUL)prediction is crucial for prognostics and health management of large equipment.However,nonlinear characteristics such as high dimen-sionality,large scale,strong coupling,and time-varying parameters in monitoring data of some devices can lead to low accuracy in RUL prediction.To solve this problem,this paper introduces a neural network model that combines a transformer decoder with a multi-scale bi-directional long and short-term memory network.This model improves prediction accuracy of the model by integrating global information through a multi-head attention mechanism.Using aviation engines as the research focus,comparative experiments were conducted employing various models on NASA's C-MPASS dataset.The results show that the proposed multi-scale bi-directional long and short-term memory network fused with Transformer model(MSBiLSTM-Transformer)outperforms other benchmark models,demonstrating superior performance in both accuracy and root mean square error metrics.
关键词
剩余使用寿命/故障预测与健康管理/双向长短期记忆网络/TransformerKey words
remaining useful life(RUL)/prognostics and health management/bi-directional long short-term memory/Transformer引用本文复制引用
基金项目
国家重点研发计划(2021YFC2701800)
国家重点研发计划(2021YFC2701801)
出版年
2024
NETL
NSTL
万方数据