The invention relates to a fault diagnosis method combining a convolution auto-encoder and logistic regression. The fault diagnosis method comprises the following steps: converting one-dimensional time domain data into two-dimensional image data; automatically extracting two-dimensional image feature data from the two-dimensional image data by using a depth convolution automatic encoder (DCAE); and inputting the two-dimensional image feature data into logistic regression LR for turnout fault diagnosis. The method has the beneficial effects that through automatic feature extraction, the defectsof manual feature extraction and dependence on a large amount of expert knowledge and priori knowledge in a traditional data-driven diagnosis method are overcome. According to the method, the precision of actual high-speed railway turnout on-site measured data can reach 99.52%. The invention further relates to a fault diagnosis system combining the convolution auto-encoder and logistic regression.

    本发明涉及一种将卷积自编码器和逻辑回归相结合的故障诊断方法,所述故障诊断方法包括如下步骤:将一维时域数据转换成二维图像数据;利用深度卷积自动编码器DCAE自动从所述二维图像数据中提取二维图像特征数据;将所述二维图像特征数据输入逻辑回归LR进行道岔故障诊断。本发明的有益效果在于,该方法通过自动提取特征,克服了传统数据驱动诊断方法中手工提取特征和依赖于大量专家知识和先验知识的缺点。该方法对实际高速铁路道岔现场实测数据的精度可达99.52%。本发明还涉及一种将卷积自编码器和逻辑回归相结合的故障诊断系统。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Fault diagnosis system and method combining convolution auto-encoder and logistic regression


    Weitere Titelangaben:

    一种将卷积自编码器和逻辑回归相结合的故障诊断系统及方法


    Beteiligte:
    DONG WEI (Autor:in) / ZHAI SHOUCHAO (Autor:in) / SUN XINYA (Autor:in) / JI YINDONG (Autor:in)

    Erscheinungsdatum :

    2020-11-27


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06K Erkennen von Daten , RECOGNITION OF DATA / B61L Leiten des Eisenbahnverkehrs , GUIDING RAILWAY TRAFFIC / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Bearing Fault Diagnosis Method of Bearing Based on LSTM Auto-Encoder

    Lu, Zhencong / Qin, Yong / Cheng, Xiaoqing et al. | TIBKAT | 2022


    Bearing Fault Diagnosis Method of Bearing Based on LSTM Auto-Encoder

    Lu, Zhencong / Qin, Yong / Cheng, Xiaoqing et al. | Springer Verlag | 2022


    Bearing Fault Diagnosis Method of Bearing Based on LSTM Auto-Encoder

    Lu, Zhencong / Qin, Yong / Cheng, Xiaoqing et al. | British Library Conference Proceedings | 2022


    Fault diagnosis of batch process based on denoising sparse auto encoder

    Gao, Xuejin / Wang, Hao / Gao, Huihui et al. | IEEE | 2018