In order to improve the accuracy and efficiency of fault diagnosis under the condition that a traction elevator has multiple faults and few samples at the same time, the invention discloses a fault diagnosis model based on CNN and IAO-SVM traction elevator fault diagnosis and combination of a support vector machine after optimization of a penalty parameter c and a kernel parameter g. According to the method, the EVA-625 detector is adopted to obtain actual vibration data of the elevator, subsequent experiments are carried out through the data, and diagnosis results are compared with other diagnosis methods under different conditions. Experimental results show that the method has extremely high fault recognition accuracy and good efficiency no matter under the condition that samples are sufficient or small.
本发明为提高曳引电梯在同时具有多种故障以及样本较少情况下故障诊断的准确率及效率,公开了一种基于CNN与IAO‑SVM的曳引电梯故障诊断,优化惩罚参数c与核参数g后的支持向量机相结合的故障诊断模型。本发明采用EVA‑625检测仪获取电梯的实际振动数据并通过该数据进行后续实验,将诊断结果与其它诊断方法在不同情况下进行比较。实验结果表明,无论在样本充足或是样本较小情况下,本方法均具有极高的故障识别准确率以及良好的效率。
Traction elevator fault diagnosis based on CNN and IAO-SVM
基于CNN与IAO-SVM的曳引电梯故障诊断
2024-08-20
Patent
Electronic Resource
Chinese
Elevator traction machine bearing fault diagnosis method
European Patent Office | 2023
|Elevator traction machine fault diagnosis algorithm based on multi-source information fusion
European Patent Office | 2024
|Elevator fault diagnosis device and elevator fault diagnosis method
European Patent Office | 2022
|