Suzhou Electric Appliance Research Institute
期刊號(hào): CN32-1800/TM| ISSN1007-3175

Article retrieval

文章檢索

首頁(yè) >> 文章檢索 >> 往年索引

基于BP神經(jīng)網(wǎng)絡(luò)模型的異步電動(dòng)機(jī)故障辨識(shí)

來(lái)源:電工電氣發(fā)布時(shí)間:2021-08-18 12:18 瀏覽次數(shù):555

基于BP神經(jīng)網(wǎng)絡(luò)模型的異步電動(dòng)機(jī)故障辨識(shí)

喬維德
(無(wú)錫開(kāi)放大學(xué) 科研與質(zhì)量控制處,江蘇 無(wú)錫 214011)
 
    摘 要:針對(duì)目前三相異步電動(dòng)機(jī)故障診斷方法存在的局限性及其缺陷,在利用小波包分析提取電動(dòng)機(jī)故障信號(hào)特征量基礎(chǔ)上,提出基于蝙蝠-粒子群及改進(jìn) BP 算法的異步電動(dòng)機(jī) BP 神經(jīng)網(wǎng)絡(luò)故障辨識(shí)模型,采用蝙蝠-粒子群算法優(yōu)化 BP 神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)參數(shù),利用改進(jìn) BP 算法訓(xùn)練 BP 神經(jīng)網(wǎng)絡(luò)。仿真結(jié)果分析表明,該 BP 神經(jīng)網(wǎng)絡(luò)模型用于三相異步電動(dòng)機(jī)故障辨識(shí),辨識(shí)速度快、準(zhǔn)確度高、可靠性好。
    關(guān)鍵詞:異步電動(dòng)機(jī);小波包分析;蝙蝠-粒子群算法;改進(jìn) BP 算法;故障辨識(shí)
    中圖分類號(hào):TM307 ;TM343+.2     文獻(xiàn)標(biāo)識(shí)碼:A     文章編號(hào):1007-3175(2021)08-0006-05
 
Asynchronous Motor Fault Identification Based on BP Neural Network Model
 
QIAO Wei-de
(Scientific Research and Quality Control Division, Wuxi Open University, Wuxi 214011,China)
 
    Abstract: In view of the limitations and deficiencies of current three-phase asynchronous motor fault diagnosis methods, based on the use of wavelet packet analysis to extract the characteristics of the motor fault signal, a fault identification model of asynchronous motor BP neural network based on bat-particle swarm and improved BP algorithm is proposed. The bat-particle swarm algorithm is used to optimize the structural parameters of the BP neural network, and the improved BP algorithm is used to train the BP neural network. The analysis of simulation results shows that the BP neural network model is used for fault identification of three-phase asynchronous motors, with fast identification speed, high accuracy and good reliability.
    Key words: asynchronous motor; wavelet packet analysis; bat-particle swarm algorithm; improved BP algorithm; fault identification
 
參考文獻(xiàn)
[1] 賀穎,王志蘭,李盼,等. BP 神經(jīng)網(wǎng)絡(luò)在異步電機(jī)轉(zhuǎn)子故障診斷中的應(yīng)用[J] . 電力學(xué)報(bào),2015,30(6) :495-499.
[2] 喬維德. 一種電機(jī)故障的智能診斷方法研究[J] .電氣傳動(dòng)自動(dòng)化,2010,32(1) :43-45.
[3] 喬維德. 基于改進(jìn)粒子群混合算法的電機(jī)故障診斷研究[J]. 江蘇電器,2007(4) :21-24.
[4] 張瑞祥,趙車紅,胡永勝. 小波包在異步電機(jī)轉(zhuǎn)子斷條故障檢測(cè)中的應(yīng)用[J] . 自動(dòng)測(cè)量與控制,2006,25(9) :68-69.
[5] 喬維德. 螢火蟲(chóng)-粒子群優(yōu)化神經(jīng)網(wǎng)絡(luò)的異步電機(jī)轉(zhuǎn)子斷條故障診斷[J] . 電機(jī)與控制應(yīng)用,2017,44(1) :83-88.
[6] 喬維德. 用于電動(dòng)汽車電池 SOC 預(yù)測(cè)的 BP 神經(jīng)網(wǎng)絡(luò)模型[J] . 石家莊學(xué)院學(xué)報(bào),2018,20(3) :31-37.
[7] 李強(qiáng),車文龍. 基于改進(jìn)粒子群優(yōu)化神經(jīng)網(wǎng)絡(luò)的電機(jī)故障診斷[J] . 電氣傳動(dòng),2020,50(1) :103-108.