【摘要】：為解決軸承故障診斷中故障信號(hào)特征難以提取、不同故障程度間信號(hào)特征相近難以區(qū)分的問題,提出了基于判別稀疏編碼的軸承故障診斷方法:在稀疏編碼框架下,引入Fisher判別準(zhǔn)則,增強(qiáng)不同類別故障字典的判別性,并基于重構(gòu)誤差,在頻域上對(duì)故障信號(hào)進(jìn)行處理。實(shí)驗(yàn)表明:與其他方法相比,該方案有效提高了軸承故障診斷的準(zhǔn)確率,并具有較好的穩(wěn)定性。
[Abstract]:In order to solve the problem that the fault signal feature is difficult to be extracted in bearing fault diagnosis and the signal features are similar to each other among different fault degrees, a bearing fault diagnosis method based on discriminant sparse coding is proposed. The Fisher criterion is introduced to enhance the discriminability of different fault dictionaries, and the fault signals are processed in frequency domain based on the reconstruction error. The experimental results show that compared with other methods, this scheme can effectively improve the accuracy of bearing fault diagnosis and has better stability.
【作者單位】： 解放軍理工大學(xué);蘇州市公安局相城分局;
【分類號(hào)】：TH133.3

【相似文獻(xiàn)】

相關(guān)博士學(xué)位論文 前1條

1 唐海峰;基于信號(hào)稀疏表征的故障診斷方法研究[D];上海交通大學(xué);2014年

，

本文編號(hào)：2371377