基于BP神經(jīng)網(wǎng)絡(luò)算法的耐磨鋼熱處理工藝優(yōu)化
發(fā)布時間:2018-10-10 12:48
【摘要】:以耐磨鋼牌號、淬火溫度、淬火冷卻方式、回火溫度和回火冷卻方式作為輸入層參數(shù),以硬度作為輸出層參數(shù),采用BP神經(jīng)網(wǎng)絡(luò)算法構(gòu)建了耐磨鋼熱處理工藝優(yōu)化的BP神經(jīng)網(wǎng)絡(luò)模型,并進行了模型的預(yù)測和應(yīng)用驗證。結(jié)果表明,該模型的輸出參數(shù)平均相對預(yù)測誤差為2.2%,具有較好的預(yù)測能力和較高的預(yù)測精度。與生產(chǎn)線現(xiàn)用工藝相比,采用BP神經(jīng)網(wǎng)絡(luò)模型優(yōu)化工藝熱處理后的NM360、NM400、NM500耐磨鋼的磨損體積分別減小26%、26%、28%。
[Abstract]:Taking wear-resistant steel grade, quenching temperature, quenching cooling mode, tempering temperature and tempering cooling method as input layer parameters and hardness as output layer parameters, The BP neural network model for heat treatment process optimization of wear-resistant steel was constructed by using BP neural network algorithm, and the prediction and application of the model were carried out. The results show that the average relative prediction error of the output parameters of the model is 2.2, which has better prediction ability and higher prediction accuracy. Compared with the current production line, the wear volume of NM360,NM400,NM500 wear-resistant steel after heat treatment was optimized by using BP neural network model. The wear volume of NM360,NM400,NM500 wear-resistant steel decreased by 26% and 28% respectively.
【作者單位】: 承德石油高等?茖W(xué)校;
【基金】:國家高技術(shù)研究發(fā)展(863)計劃項目(2004AA412030)
【分類號】:TG161
本文編號:2261824
[Abstract]:Taking wear-resistant steel grade, quenching temperature, quenching cooling mode, tempering temperature and tempering cooling method as input layer parameters and hardness as output layer parameters, The BP neural network model for heat treatment process optimization of wear-resistant steel was constructed by using BP neural network algorithm, and the prediction and application of the model were carried out. The results show that the average relative prediction error of the output parameters of the model is 2.2, which has better prediction ability and higher prediction accuracy. Compared with the current production line, the wear volume of NM360,NM400,NM500 wear-resistant steel after heat treatment was optimized by using BP neural network model. The wear volume of NM360,NM400,NM500 wear-resistant steel decreased by 26% and 28% respectively.
【作者單位】: 承德石油高等?茖W(xué)校;
【基金】:國家高技術(shù)研究發(fā)展(863)計劃項目(2004AA412030)
【分類號】:TG161
【相似文獻】
相關(guān)期刊論文 前2條
1 王以恒;;基于BP神經(jīng)網(wǎng)絡(luò)算法的北京市地鐵站應(yīng)急疏散能力仿真評估模型[J];中國安全生產(chǎn)科學(xué)技術(shù);2012年01期
2 ;[J];;年期
相關(guān)會議論文 前2條
1 彭本紅;呂永成;黎雪霖;劉春霞;;基于改進的BP神經(jīng)網(wǎng)絡(luò)算法的區(qū)域生態(tài)環(huán)境可持續(xù)發(fā)展協(xié)調(diào)度評價研究[A];管理科學(xué)與系統(tǒng)科學(xué)研究新進展——第7屆全國青年管理科學(xué)與系統(tǒng)科學(xué)學(xué)術(shù)會議論文集[C];2003年
2 朱小梅;楊先鳳;呂南;;基于主成分分析的BP神經(jīng)網(wǎng)絡(luò)算法在軟件風險識別中的應(yīng)用研究[A];“中國視角的風險分析和危機反應(yīng)”——中國災(zāi)害防御協(xié)會風險分析專業(yè)委員會第四屆年會論文集[C];2010年
相關(guān)碩士學(xué)位論文 前1條
1 蔡金亮;BP神經(jīng)網(wǎng)絡(luò)算法在球磨機控制系統(tǒng)中的應(yīng)用研究[D];華北電力大學(xué)(河北);2010年
,本文編號:2261824
本文鏈接:http://sikaile.net/kejilunwen/jiagonggongyi/2261824.html
最近更新
教材專著