智能異構(gòu)模型在電機(jī)故障診斷中的研究

提出以測試電機(jī)的三相電流噪聲為電機(jī)故障特征信號的診斷方法，建立電機(jī)電流噪聲多元時序模型，將時序模型的多元殘差序列化為一元序列作為故障總體檢測指標(biāo)。針對多元時序模型參數(shù)Φi的特點，提出了多層NN結(jié)構(gòu)的故障類型識別模型，應(yīng)用APEX網(wǎng)絡(luò)提取初始模式向量的分類信息，利用前饋網(wǎng)絡(luò)建立其識別函數(shù)，實踐證明該診斷方法是正確的。
關(guān) 鍵 詞 故障診斷; 時序模型; 神經(jīng)網(wǎng)絡(luò); 模式向量

Abstract The paper puts forward a set of faults diagnosis methods of testing the noise of the three-phase motor current which shows the characteristics of the motor faults, and multi-varieties time series models of the noise is established, the multi-varieties residual series is changed to the monistical as the fault detection index. In the light of trait of the model parameter Φi, presenting a faults classification recognition model based on the multi-layer NN structure, using APEX network extracts classification Information of the initial pattern vector, making use of feedforward network establishes the classification function. The diagnosis way is correct by practising.
Key words faults diagnosis; time series model; neural network; pattern vector