本文關(guān)鍵詞： 平整機 軋制力 神經(jīng)網(wǎng)絡(luò) ReLU 傳播算法 正則化　出處：《河北工程大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：鋼鐵工業(yè)支持了國民經(jīng)濟以及國防建設(shè)的發(fā)展,同時各行各業(yè)的發(fā)展又推動著鋼鐵行業(yè)的產(chǎn)品質(zhì)量不斷進步。對于提高帶鋼產(chǎn)品的質(zhì)量,平整是其不可或缺的一個環(huán)節(jié)。它不僅能提高帶鋼的表面質(zhì)量,還直接影響其物理、化學(xué)和力學(xué)性能,進而達到后續(xù)工藝階段要求的規(guī)格。針對平整機軋制力的預(yù)報研究是合理優(yōu)化平整軋制過程、提高平整機控制水平和改善工作狀態(tài)所面臨的一個重要課題。本文針對平整機軋制力預(yù)測精度不高的問題,以影響平整機軋制過程的參數(shù)為研究對象,以軋制理論和神經(jīng)網(wǎng)絡(luò)為理論依據(jù),提出以ReLU為激活函數(shù)的人工神經(jīng)網(wǎng)絡(luò)模型來對平整機的軋制力進行預(yù)報研究。進行了以下研究工作:對在線軋制數(shù)據(jù)進行主成分分析降維處理,獲得影響平整機軋制力的主要因素,并將其作為主成分輸入神經(jīng)網(wǎng)絡(luò)模型的輸入層神經(jīng)元,將平整機的軋制力作為神經(jīng)網(wǎng)絡(luò)的輸出層神經(jīng)元,以網(wǎng)格搜索的方式對神經(jīng)網(wǎng)絡(luò)隱層的相關(guān)參數(shù)和算法進行實驗,采用python語言進行編程,建立了2360組平整機軋制力的神經(jīng)網(wǎng)絡(luò)預(yù)報模型。基于上述研究內(nèi)容和成果,利用建模分析,結(jié)合大量現(xiàn)場平整軋制數(shù)據(jù)的分析處理,通過調(diào)整隱層層數(shù)、神經(jīng)元數(shù)、傳播算法、正則化方法,篩選出了預(yù)測誤差最低的神經(jīng)網(wǎng)絡(luò)模型。同時,這種實驗方法可以適用于不同在線軋制數(shù)據(jù)下的平整機軋制力的預(yù)報,對于平整生產(chǎn)具有一定的指導(dǎo)意義與參考價值,同時該實驗思路可以推廣到其它參數(shù)的預(yù)報研究中。
[Abstract]:The iron and steel industry has supported the development of national economy and national defense construction. At the same time, the development of various industries has promoted the continuous progress of the steel industry product quality. Flatness is an indispensable part of the strip. It can not only improve the surface quality of strip, but also directly affect its physical, chemical and mechanical properties. According to the prediction of rolling force, it is reasonable to optimize the rolling process. It is an important task to improve the control level and improve the working state of the mill. In this paper, the parameters that affect the rolling process of the mill are taken as the research object, aiming at the problem that the prediction accuracy of the rolling force is not high. It is based on rolling theory and neural network. An artificial neural network model with ReLU as the activation function is proposed to predict the rolling force of the temper mill. The following research work is carried out: the principal component analysis (PCA) dimensionality reduction processing of the rolling data on line is carried out. The main factors that affect the rolling force are obtained and used as the input layer neuron of the neural network model and the rolling force of the mill as the output layer neuron of the neural network. The related parameters and algorithms of the hidden layer of neural network are experimented with the method of grid search, and python language is used to program. The neural network prediction model of rolling force of 2360 sets of leveling mill is established. Based on the above research contents and results, the model is used to analyze and deal with a large number of rolling data, and the hidden layer number is adjusted. The neural network model with the lowest prediction error is selected by neuron number, propagation algorithm and regularization method. At the same time, this experimental method can be used to predict the rolling force of flat mill under different on-line rolling data. It has certain guiding significance and reference value for leveling production, and the experimental idea can be extended to the prediction of other parameters at the same time.
【學(xué)位授予單位】：河北工程大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TG333.4

【參考文獻】

相關(guān)期刊論文 前10條

1 劉杰輝;范冬雨;田潤良;;基于ReLU激活函數(shù)的軋制力神經(jīng)網(wǎng)絡(luò)預(yù)報模型[J];鍛壓技術(shù);2016年10期

2 李淵;駱志剛;管乃洋;尹曉堯;王兵;伯曉晨;李非;;生物醫(yī)學(xué)數(shù)據(jù)分析中的深度學(xué)習(xí)方法應(yīng)用[J];生物化學(xué)與生物物理進展;2016年05期

3 張清東;張勃洋;李博;張曉峰;;板帶軋制過程二維流函數(shù)-無網(wǎng)格伽遼金求解方法及其應(yīng)用[J];機械工程學(xué)報;2015年10期

4 李海軍;徐建忠;王國棟;;熱軋帶鋼精軋過程高精度軋制力預(yù)測模型[J];東北大學(xué)學(xué)報(自然科學(xué)版);2009年05期

5 董永剛;張文志;宋劍鋒;;應(yīng)用上限原理求解重軌萬能軋制過程軋制力[J];力學(xué)與實踐;2008年05期

6 趙德文;王根磯;劉相華;王國棟;;扁帶拉拔擠壓柱坐標(biāo)應(yīng)變速率矢量內(nèi)積[J];東北大學(xué)學(xué)報(自然科學(xué)版);2007年04期

7 王曉東;石錦;史慶南;王效琪;陳義武;;板帶軋制有限元建模研究[J];機械;2007年02期

8 丁小梅,劉鵬;基于小波神經(jīng)網(wǎng)絡(luò)的軋制壓力高精度預(yù)報模型[J];工程建設(shè)與設(shè)計;2005年06期

9 孫克,王長松,羅永軍;基于小腦模型神經(jīng)網(wǎng)絡(luò)的軋制力預(yù)報模型[J];鋼鐵研究;2004年01期

10 陶紅勇,王京,陸秀志;神經(jīng)網(wǎng)絡(luò)在板形控制中的應(yīng)用[J];軋鋼;2003年04期

，

本文編號：1452899