Journal of Propulsion Technology ›› 2020, Vol. 41 ›› Issue (5): 1159-1167.DOI: 10.13675/j.cnki.tjjs.190240

• Test, Experiment and Control • Previous Articles     Next Articles

Research on Monitoring Method of Lubricating Oil Based on Deep Learning

  

  1. College of Electronic Information and Automation,Civil Aviation University of China,Tianjin 300300,China
  • Published:2021-08-15

基于深度学习的滑油监测方法研究

马敏1,王涛1,王力1   

  1. 中国民航大学 电子信息与自动化学院,天津 300300
  • 基金资助:
    国家自然科学基金委员会与中国民用航空局联合资助项目(U1733119)。

Abstract: Aiming at the defect that the traditional data feature extraction method is difficult to extract the effective features of monitoring data of Electrical capacitance tomography (ECT) aviation engine lubricating oil, a single-channel network model MSCNN-LSTM-BP based on multi-scales convolutional neural network (MSCNN), long short-term memory (LSTM) neural network and BP network is proposed. Integrating multi-scale learning into CNN, MSCNN and LSTM extract the two-dimensional features of data in spatial and temporal dimensions in a serial mode. The experimental results show that the classification accuracy of the 3 scales MSCNN-LSTM-BP for data samples reached 98.2%, single set of capacitor data acquisition test time is only 2.1986ms, the score of F1 reached 98.57%. Overall performance is superior to CNN, LSTM and traditional multi-scale feature extraction methods. MSCNN-LSTM-BP meets the requirements for real-time and accuracy of aero-engine lubricating oil monitoring and is provided with good applicability.

Key words: Aeroengine;Oil lubricating monitoring;Wear;Neural network;Fault detection;Data acquisition;Feature extraction

摘要: 针对传统的数据特征提取方法难以提取航空发动机滑油监测数据有效特征的缺陷,提出了一种基于多尺度卷积神经网络(Multi-scales convolutional neural network,MSCNN)、长短期记忆(Long short-term memory,LSTM)神经网络和BP网络的单通道网络模型MSCNN-LSTM-BP。将多尺度学习融入CNN,MSCNN和LSTM以串行方式提取数据在空间维度和时间维度的二维特征。实验结果表明:3尺度的MSCNN-LSTM-BP对数据样本的分类准确率达到98.2%,单组电容数据采集测试时间仅为2.1986ms,综合分类率F1达到98.57%,总体性能优于CNN,LSTM和传统的多尺度特征提取方法。MSCNN-LSTM-BP满足航空发动机滑油监测对于实时性和准确性的要求,具有良好的适用性。

关键词: 航空发动机;滑油监测;磨损;神经网络;数据监测;数据采集;特征提取