基于深度自编码器和t-SNE算法的电梯故障预警

Elevator Fault Early Warning Based on Deep Auto-encoder and t-SNE Algorithm

为提高电梯承运质量,针对电梯轿厢系统,设计基于深度自编码器(DAE)和t分布随机邻域嵌入算法(t-SNE)相结合的电梯轿厢系统故障预警模型。通过计算电梯轿厢系统运行时振动信号的重构误差,并将其与预警阈值进行对比分析,可以直观地对振动信号波形进行分类,判别轿厢系统运行是否出现异常,通过t-SNE算法进行可视化分析。实验结果表明:该模型能够有效实现电梯轿厢系统的故障实时预警功能,为电梯的预防性维护提供依据。

In order to improve the quality of elevator transportation,designs a fault early warning model for elevator car system based on the combination of DAE and t-SNE.The reconstruction error of the vibration signal is caculated in operation of the elevator car system and compared with the early warning threshold to visually classify the vibration signal waveform,judge abnormal operation of car system,and visual analysis is conducted through the t-SNE algorithm.The experimental results show that the model can effectively realize the real-time fault warning function of the elevator car system and provide a basis for the preventive maintenance of the elevator.