The invention provides an escalator fault identification and early warning method based on a depth auto-encoder, and the method specifically comprises the steps: collecting acceleration data of escalator steps and a driving device through a vibration sensor, obtaining original data, and labeling the original data; aggregating the original data through a sliding window; and inputting the aggregated data into the depth auto-encoder, storing data features extracted by the model by the model, and outputting a fault identification result. And taking the data features extracted by the model as the input of a t-SNE algorithm, and outputting a two-dimensional or three-dimensional visualization result of the data features by the t-SNE algorithm. According to the method, the escalator fault can be diagnosed, and fault data can be visualized.
本发明提出了一种基于深度自编码器的自动扶梯故障识别与预警方法,具体方法包括通过振动传感器采集自动扶梯梯级与驱动装置的加速度数据,获取原始数据并打标签;将原始数据通过滑动窗口聚合;将聚合后的数据输入到深度自编码器中,模型将保存模型提取的数据特征,并输出故障识别结果。将模型提取的数据特征作为t‑SNE算法的输入,t‑SNE算法输出数据特征的二维或三维可视化结果。本方法可对自动扶梯故障进行诊断并将故障数据可视化。
Escalator fault identification and early warning method based on depth auto-encoder
一种基于深度自编码器的自动扶梯故障识别与预警方法
2022-12-02
Patent
Elektronische Ressource
Chinesisch
Escalator equipment warning method and escalator equipment warning system
Europäisches Patentamt | 2023
|Escalator monitoring and early warning method based on image binarization
Europäisches Patentamt | 2023
|