【正文】 目 錄 1 緒 論 ............................................................................................................................... 1 課題背景和研究的意義 ............................................................................................. 1 研究背景 .............................................................................................................. 1 研究意義 .............................................................................................................. 2 國(guó)內(nèi)外故障診斷技術(shù)研究現(xiàn)狀 ................................................................................. 3 國(guó)外現(xiàn)狀 .............................................................................................................. 3 國(guó)內(nèi)現(xiàn)狀 .............................................................................................................. 4 研究?jī)?nèi)容 ..................................................................................................................... 5 2 燃?xì)廨啓C(jī)關(guān)鍵部件故障診斷的總體方案設(shè)計(jì) ............................................................... 7 滾動(dòng)軸承故障的總體方案設(shè)計(jì) ................................................................................. 7 滾動(dòng)軸承機(jī)理及故障類(lèi)型 ......................................................................................... 7 滾動(dòng)軸承基本結(jié)構(gòu) .............................................................................................. 8 滾動(dòng)軸承故障類(lèi)型 .............................................................................................. 9 滾動(dòng)軸承參數(shù)選取及處理 ....................................................................................... 10 3 故障診斷方法 .................................................................................................................. 13 BP 神經(jīng)網(wǎng)絡(luò) .............................................................................................................. 13 BP 神經(jīng)網(wǎng)絡(luò)原理 ............................................................................................... 13 BP 神經(jīng)網(wǎng)絡(luò)診斷方法 ....................................................................................... 14 自適應(yīng) 模糊神經(jīng)網(wǎng)絡(luò)（ ANFIS） ............................................................................. 17 自適應(yīng) 模糊神經(jīng)網(wǎng)絡(luò)（ ANFIS）結(jié)構(gòu) ............................................................. 18 自適應(yīng)模糊神經(jīng)網(wǎng)絡(luò)（ ANFIS）原理 ............................................................. 20 自適應(yīng)模糊神經(jīng)網(wǎng)絡(luò)（ ANFIS）診斷方法 ..................................................... 21 4 滾動(dòng)軸承 BP 神經(jīng)網(wǎng)絡(luò)故障診斷試驗(yàn)研究 .................................................................. 25 故障診斷模型建立 ................................................................................................... 25 各層節(jié)點(diǎn)數(shù)確定 ................................................................................................ 25 初始權(quán)值的選擇 ................................................................................................ 27 期望誤差和學(xué)習(xí)率選取 .................................................................................... 27 軸承故障診斷的仿真試驗(yàn)研究 ............................................................................... 27 樣本選取 ............................................................................................................ 27 沈陽(yáng)航空航天大學(xué)北方科技學(xué)院畢業(yè)設(shè)計(jì)（論文） IV 神經(jīng)網(wǎng)絡(luò)的訓(xùn)練 ................................................................................................ 29 神經(jīng)網(wǎng)絡(luò)的測(cè)試 ................................................................................................ 30 5 基于自適應(yīng)模糊神經(jīng)網(wǎng)絡(luò)（ ANFIS）的故障診斷試驗(yàn)研究 ...................................... 32 診斷模型的建立 ....................................................................................................... 32 樣本的選取 ........................................................................................................ 32 輸入樣本的模糊化處理 .................................................................................... 33 輸出結(jié)果的去模糊化處理 ................................................................................ 34 軸承故障 診 斷仿真與結(jié)果 ....................................................................................... 34 6 不同神經(jīng)網(wǎng)絡(luò)故障診斷結(jié)果與分析 ............................................................................. 38 7 結(jié) 論 ............................................................................................................................. 39 結(jié)束語(yǔ) ................................................................................................................................. 40 致 謝 ................................................................................................................................. 41 參考文獻(xiàn) ............................................................................................................................. 42 附錄 Ⅰ BP 神經(jīng)網(wǎng)絡(luò)故障診斷源程序清單 ..................................................................... 43 附錄 Ⅱ 自適應(yīng)模糊神經(jīng)網(wǎng)絡(luò)（ ANFIS）診斷源程序清單 ............................................ 48 沈陽(yáng)航空航天大學(xué)北方科技學(xué)院畢業(yè)設(shè)計(jì)（論文） 1 1 緒 論 課題背景和研究的意義 研究背景 作為新型的動(dòng)力設(shè)備，燃?xì)廨啓C(jī)具有結(jié)構(gòu)緊湊、安全可靠、運(yùn)行平穩(wěn)，具有較高的熱效率，可以快速啟動(dòng)并帶動(dòng)負(fù)載等優(yōu)點(diǎn)，而日益受到人們的重視，應(yīng)用范圍也越來(lái)越廣。 關(guān)鍵詞 ： 滾動(dòng)軸承 ； BP 神經(jīng)網(wǎng)絡(luò) ； 模糊神經(jīng)網(wǎng)絡(luò) 沈陽(yáng)航空航天大學(xué)北方科技學(xué)院畢業(yè)設(shè)計(jì)（論文） II Abstract Rolling bearing is one of the most ordinary parts in mechanical machine, its running state can influence the performance of the whole machine directly, the aircraft stabilizer health status need to be monitored in real time to ensure the aircraft fly safety. so it is important to study the technology of fault diagnosis for rolling bearing. On the basis of analyzing the fault mechanism and vibration signal characteristics of rolling bearing systematically, and after analyzing and processing the vibration signals of right and fault state of rolling bearing, partial appropriate feature parameters are selected as the input of the neural work according to the time and frequency domain characteristics of parameters in this thesis. and the fault diagnosis system for rolling bearing based on BP ne