本文關(guān)鍵詞：基于灰色理論預(yù)處理的神經(jīng)網(wǎng)絡(luò)機(jī)床熱誤差建模，由筆耕文化傳播整理發(fā)布。

*i? 基于灰色理論預(yù)處理的神經(jīng)網(wǎng)絡(luò)機(jī)床熱誤差建模? 張 毅 楊建國? 上海交通大學(xué) 機(jī)械與動力工程學(xué)院 上海? 200240? 摘要:為最大限度減少熱誤差對數(shù)控機(jī)床加工精度的影響,嘗試結(jié)合灰色理論grey?model,?GM和人工神經(jīng)網(wǎng)絡(luò)artificial? neural?network,?ANN各自對數(shù)據(jù)處理的優(yōu)點(diǎn),提出一種基于灰色理論預(yù)處理的神經(jīng)網(wǎng)絡(luò)機(jī)床熱誤差補(bǔ)償模型。在一臺處 于實(shí)際加工狀態(tài)的數(shù)控車床上進(jìn)行試驗(yàn),采用數(shù)字式溫度傳感器測量經(jīng)過優(yōu)化選取的對熱誤差有關(guān)鍵影響的機(jī)床構(gòu)件和加工 環(huán)境的溫度數(shù)據(jù),采用非接觸式位移傳感器獲得機(jī)床加工熱誤差數(shù)據(jù),在不斷調(diào)整灰色模型數(shù)據(jù)序列長度及神經(jīng)網(wǎng)絡(luò)權(quán)值、 閾值的基礎(chǔ)上,最終建立熱誤差補(bǔ)償模型。通過與傳統(tǒng)灰色模型和神經(jīng)網(wǎng)絡(luò)進(jìn)行對比分析及試驗(yàn)論證表明:該補(bǔ)償模型具有 對原始溫度和熱誤差數(shù)據(jù)要求低、計(jì)算簡便、預(yù)測精度高、魯棒性強(qiáng)等優(yōu)點(diǎn),可用于各種復(fù)雜實(shí)際加工場合中的數(shù)控機(jī)床熱 誤差實(shí)時(shí)補(bǔ)償。 關(guān)鍵詞:數(shù)控機(jī)床 熱誤差 誤差補(bǔ)償 灰色模型 神經(jīng)網(wǎng)絡(luò) 中圖分類號:TH161? Modeling?for Machine?Tool?Thermal?Error Based?on Grey? Model Preprocessing?Neural?Network? ZHANG Yi,?YANG?Jianguo? School?of?Mechanical?Engineering,?Shanghai?Jiao Tong?University,?Shanghai?200240? Abstract:In?order?to?eliminate?the?influence?of?thermal?error?on machining?precision, a?novel?method?combining the data?processing? merit? of?grey?model?GM? with?that? of?artificial?neural?network?ANN? is? proposed?for?thermal?error? modeling?in? machine?toolsRelevant?temperature?and?thermal?error?data?of?a?turning?machine?are?measured?respectively?through?digital?temperature?sensors?and? non?contact?displacement?sensors.?A?series?of?experimental?data?is?used?to?establish?the?thermal?error?compensation?model?by?means? of?adjusting?the?length?of?data?sequence?in?GM?and?the?weight?and?thresho

  本文關(guān)鍵詞：基于灰色理論預(yù)處理的神經(jīng)網(wǎng)絡(luò)機(jī)床熱誤差建模，，由筆耕文化傳播整理發(fā)布。