[1]袁兵余佳翰,鄒永向.基于EEMD-SVM的液壓泵故障診斷[J].起重運輸機械,2019,(20):90.
 Fault Diagnosis of Hydraulic Pump Based on EEMD-SVM[J].,2019,(20):90.
點擊復制

基于EEMD-SVM的液壓泵故障診斷()
分享到:

《起重運輸機械》[ISSN:1001-0785/CN:11-1888/TN]

卷:
期數:
2019年20期
頁碼:
90
欄目:
故障診斷
出版日期:
2019-11-30

文章信息/Info

Title:
Fault Diagnosis of Hydraulic Pump Based on EEMD-SVM
作者:
袁兵 102 102); font-family: Arial Verdana sans-serif; font-size: 12px; background-color: rgb(255 255 255);">余佳翰鄒永向
文獻標志碼:
A
摘要:
為了提高利用液壓泵振動信號進行故障診斷的準確率和減小診斷時間,使用了集合經驗模態分解(EEMD)的方式來提取振動信號特征,并將其作為液壓泵故障診斷的數據集。在此基礎上利用支持向量機(SVM)與深度神經網絡(DNN)進行故障診斷,最后通過驗證數據集檢驗了模型診斷故障的準確程度。結果表明,EEMD-SVM在液壓泵故障診斷方面具有較好的性能,與神經網絡故障診斷模型相比,支持向量機模型在液壓泵的故障診斷方面具有更高的準確率和更短的診斷時間。
Abstract:
In order to improve the accuracy reduce the diagnosis time of hydraulic pump fault diagnosis by using vibration signal, the ensemble empirical mode decomposition (EEMD) method was used to extract vibration signal acteristics, it was used as the data set of hydraulic pump fault diagnosis. On this basis, support vector machine (SVM) deep neural network (DNN) were used for fault diagnosis. Finally, the accuracy of model fault diagnosis was verified by validating data sets. The results show that EEMD-SVM has better performance in fault diagnosis of hydraulic pumps. Compared with neural network fault diagnosis model, support vector machine model has higher accuracy shorter diagnosis time in fault diagnosis of hydraulic pumps.
更新日期/Last Update: 2019-12-02
什么可挂机赚钱