The invention discloses an elevator car sill and hoistway inner surface distance measuring method based on a BP neural network. The method comprises the steps of collecting distance information between an elevator car sill and the hoistway inner surface multiple times at the same time through laser, ultrasonic waves and a visual sensor; de-noising the original data acquired by the ultrasonic sensor by using an EMD wavelet algorithm, and de-noising the original data acquired by other sensors by using a mean filtering method; and fusing the denoised sensor data through a BP neural network algorithm of an adaptive learning rate to obtain a final distance between the elevator car sill and the inner surface of the hoistway. According to the method, differentiated learning rates are adopted, andweights between different nodes can be dynamically adjusted, so that the time required for converging an error function is reduced; meanwhile, multi-sensor data fusion is carried out by adopting a BPneural network algorithm with a self-adaptive learning rate, so that the defects of single sensor measurement are overcome, the accuracy and reliability of distance measurement are improved, and theadaptability is wider.

    本发明公开了一种基于BP神经网络的电梯轿厢地坎与井道内表面测距方法,方法包括:利用激光、超声波以及视觉传感器同时多次采集电梯轿厢地坎与井道内表面的距离信息;利用EMD小波算法对超声波传感器采集的原始数据进行消噪处理,利用均值滤波法对其他传感器采集的原始数据进行消噪处理;通过自适应学习率的BP神经网络算法对消噪后的传感器数据进行融合,获得电梯轿厢地坎与井道内表面的最终距离。本发明方法采用了差异化的学习率,能够动态调节不同节点之间的权重,使得收敛误差函数所需的时间减少,同时,采用自适应学习率的BP神经网络算法进行多传感器数据融合,弥补了单一传感器测量存在的不足,提高了测距的准确性和可靠性,适应性更广。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Elevator car sill and hoistway inner surface distance measuring method based on BP neural network


    Weitere Titelangaben:

    基于BP神经网络的电梯轿厢地坎与井道内表面测距方法


    Beteiligte:
    ZHANG YONGJU (Autor:in) / WU YIFEI (Autor:in) / LIU YANG (Autor:in) / GU XUBO (Autor:in) / ZHANG YU (Autor:in) / WU XINYU (Autor:in)

    Erscheinungsdatum :

    2020-10-20


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06K Erkennen von Daten , RECOGNITION OF DATA / B66B Aufzüge , ELEVATORS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen





    MEASURING METHOD OF ELEVATOR HOISTWAY DIMENSION

    ENOMOTO YU / NAKAMURA HIDETAKA / SAMBONGI KEISUKE | Europäisches Patentamt | 2018

    Freier Zugriff

    Hoistway construction elevator

    ZHU JIAQI / ZHU ZETONG / WANG JINGLI | Europäisches Patentamt | 2020

    Freier Zugriff

    Elevator hoistway frame and elevator

    HUANG ZONGYAO / HE ZHIJIAN / HONG SHUI et al. | Europäisches Patentamt | 2021

    Freier Zugriff