A computer-implemented method (100) for training a machine learning model for detecting installation errors in an elevator, in particular an elevator door, the machine learning model being a combination of a set function model and a Fourier transform model, the method (100) comprising the following steps: arranging a plurality of sensors (101) at an elevator, each sensor is configured to detect physical parameters; -detecting the value of the physical parameter by means of a sensor in order to obtain a data set (102) comprising at least one time series; -obtaining a first input layer (103) by extracting features from the data set; -obtaining a second input layer (104) by extracting features from the data set; setting a functional model (105) with the first input layer feed; feeding the Fourier transform model (106) with the second input layer.
一种计算机实施的方法(100),用于训练机器学习模型来对电梯、尤其是电梯门中的安装错误进行检测,该机器学习模型是设定函数模型与傅立叶变换模型的组合,该方法(100)包括以下步骤:‑在电梯处布置多个传感器(101),每个传感器配置成对物理参数进行检测;‑借助于传感器对物理参数的值进行检测,以便获得包括至少一个时间序列的数据集(102);‑通过从数据集提取特征来获得第一输入层(103);‑通过从数据集提取特征来获得第二输入层(104);‑利用第一输入层馈送设定函数模型(105);‑利用第二输入层馈送傅立叶变换模型(106)。
Computer-implemented method for training machine learning model for detecting installation errors in elevator, in particular elevator door, computer-implemented method for classifying installation errors and system therefor
用于训练机器学习模型来对电梯、尤其是电梯门中的安装错误进行检测的计算机实施的方法、用于对安装错误进行分类的计算机实施的方法及其系统
2024-01-16
Patent
Electronic Resource
Chinese
IPC: | B66B Aufzüge , ELEVATORS |
DOOR SYSTEM OF ELEVATOR INSTALLATION AND ELEVATOR INSTALLATION
European Patent Office | 2019
|Elevator door device, and elevator door installation method
European Patent Office | 2015
|