Zhang Ran, Peng Zhen, Wu Lifeng, Yao Beibei, Guan Yong
College of Information Engineering, Capital Normal University, Beijing 100048, China.
Beijing Engineering Research Center of High Reliable Embedded System, Capital Normal University, Beijing 100048, China.
Sensors (Basel). 2017 Mar 9;17(3):549. doi: 10.3390/s17030549.
Intelligent condition monitoring and fault diagnosis by analyzing the sensor data can assure the safety of machinery. Conventional fault diagnosis and classification methods usually implement pretreatments to decrease noise and extract some time domain or frequency domain features from raw time series sensor data. Then, some classifiers are utilized to make diagnosis. However, these conventional fault diagnosis approaches suffer from the expertise of feature selection and they do not consider the temporal coherence of time series data. This paper proposes a fault diagnosis model based on Deep Neural Networks (DNN). The model can directly recognize raw time series sensor data without feature selection and signal processing. It also takes advantage of the temporal coherence of the data. Firstly, raw time series training data collected by sensors are used to train the DNN until the cost function of DNN gets the minimal value; Secondly, test data are used to test the classification accuracy of the DNN on local time series data. Finally, fault diagnosis considering temporal coherence with former time series data is implemented. Experimental results show that the classification accuracy of bearing faults can get 100%. The proposed fault diagnosis approach is effective in recognizing the type of bearing faults.
通过分析传感器数据进行智能状态监测和故障诊断可以确保机械的安全。传统的故障诊断和分类方法通常进行预处理以降低噪声，并从原始时间序列传感器数据中提取一些时域或频域特征。然后，利用一些分类器进行诊断。然而，这些传统的故障诊断方法存在特征选择方面的专业要求，并且它们没有考虑时间序列数据的时间连贯性。本文提出了一种基于深度神经网络（DNN）的故障诊断模型。该模型无需特征选择和信号处理就能直接识别原始时间序列传感器数据。它还利用了数据的时间连贯性。首先，使用传感器收集的原始时间序列训练数据来训练DNN，直到DNN的代价函数获得最小值；其次，使用测试数据来测试DNN对局部时间序列数据的分类准确率。最后，实施考虑与先前时间序列数据的时间连贯性的故障诊断。实验结果表明，轴承故障的分类准确率可达100%。所提出的故障诊断方法在识别轴承故障类型方面是有效的。
