基於多重解析度分析結合倒傳遞神經網路之感應馬達轉子條缺陷診斷

本研究分別以非導磁性的耐1535℃高溫陶瓷膠及放電加工方法製作感應馬達轉子條氣孔及穿孔缺陷轉子試品，並利用多重解析度分析馬達定子電流訊號，以擷取轉子條缺陷時的訊號特徵;其中包括最大值、平均值、標準差、均方根值及總和值，再應用倒傳遞神經網路演算法做為辨識轉子條缺陷之分類器，藉此自動診斷轉子條氣孔、穿孔缺陷等異常之狀況，以有效提升馬達異常訊號的辨識能力。此外，為考慮一般量測環境皆存在雜訊干擾，因此藉由高斯白雜訊分別加入訊噪比為30dB、25dB及20dB的雜訊於原始訊號中，以測試本文所提方法之強健性。經實驗及模擬結果證明本研究所提之方法可有效應用於馬達轉子條缺陷診斷；除適用於馬達製造廠之鑄鋁轉子的品質控管外，尚可應用於馬達運轉中之轉子條缺陷自動辨識。針對馬達製造而言，較佳的檢測時機點是在商檢測試階段，而本研究所提方法在無載與輕載情況下有高辨識率，分別為97.0%與97.6%，且適用於高雜訊之商檢場所，於訊噪比20dB高雜訊環境干擾下仍有85.3%辨識率，極具良好的抗噪能力，並且以數個擷取特徵值即可完成缺陷故障之辨識，可有效減少辨識的時間。

關鍵字

感應馬達；故障診斷；特徵選取

並列摘要

This paper proposes a diagnosis method, combining signal analysis and classification models, to rotor defectives problem of motors. Two manufacture technologies, a non-magnetic high-temperature resistant ceramic adhesive and electrical discharge machining(EDM), are applied to make testing samples, including blowhole and perforation defectives of rotor bars in this study. The typical multi-resolution analysis(MRA) model is used to analyze acquired source current signals of motors. The features are extracted from the signals of each column of MRA-matrix, including maximum, mean, standard deviation, root-mean-square and summation. The typical back-propagation neural network(BPNN) model is used to diagnose the rotor bars defectives of motors, and then the various signal-to-noise ratio(SNR) of white gaussian noise(WGN), 30dB, 25dB and 20dB, are added to the signals to verify the robustness of the proposed method. The results show that the availability of the proposed method to diagnose the rotor bars defectives of motors. A good time to diagnose defective rotor bars is in the QC process for motor manufactures, and this study proposes the method has the high recognition rate of 97.0% and 97.6% under no-load and light-load conditions respectively, and suitable for a high noise workshop, the recognition rate still has 85.3% in the SNR=20dB high noise interference environment; i.e. it has a good anti-noise ability. And only a few features can make the defects recognition that can effectively reduce the recognition time.

並列關鍵字

Induction motors ； Fault diagnosis ； Features selection

參考文獻

[1]A. Ceban, R. Pusca, and R. Romary, “Study of rotor faults in induction motors using external magnetic field analysis,” IEEE Trans. on Industrial Electronics, vol. 59, no. 5, pp. 2082–2093 May 2012.

[2]R. Romary, R. Corton, D. Thailly, and J. Brudny, “Induction machine fault diagnosis using an external radial flux sensor,” EPJ. Appl. Phys., vol. 32, no. 2, pp. 125–132, Nov. 2005.

[3]R. Pusca, R. Romary, A. Ceban, and J. F. Brudny, “An online universal diagnosis procedure using two external flux sensors applied to the ac electrical rotating machines,

[4]A. Yazidi, H. Henao, G. A. Capolino, M. Artioli, F. Filippetti, and D. Casadei, “Flux Signature Aanalysis: An alternative method for the fault diagnosis of Induction machines,” in Proc. IEEE Power Tech, St. Petersburg, Russia, 2005, pp. 1–6.

[5]G. Dias, E. Chabu, “Spectral analysis using a hall effect sensor for diagnosing broken bars in large induction machines,” IEEE Trans. on Instrumentation and Measurement, pp. 1–13, May 2014.

國際替代計量

基於多重解析度分析結合倒傳遞神經網路之感應馬達轉子條缺陷診斷

全文下載

主題瀏覽