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(hào)的診斷方法，建立電機(jī)電流噪聲多元時(shí)序模型，將時(shí)序模型的多元?dú)埐钚蛄谢癁橐辉蛄凶鳛楣收峡傮w檢測指標(biāo)。針對(duì)多元時(shí)序模型參數(shù)Φi的特點(diǎn)，提出了多層NN結(jié)構(gòu)的故障類型識(shí)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(shí)別函數(shù)，實(shí)踐證明該診斷方法是正確的。
關(guān) 鍵 詞 故障診斷; 時(shí)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