本文選題：表面粗糙度 + 灰色關(guān)聯(lián)度分析��； 參考：《鋼鐵》2015年06期

【摘要】：冷軋平整機的工作輥直接和帶鋼接觸,其表面粗糙度衰減情況對帶鋼成品的板形和表面質(zhì)量有重大影響。因此,分析軋輥磨損機制,對軋輥表面粗糙度的衰減進行精確預測十分必要。首先采用灰色關(guān)聯(lián)度分析對影響平整機工作輥表面粗糙度磨損的因素進行分析,確定了工作輥表面粗糙度評估指標體系。進而應用優(yōu)化在線稀疏最小二乘支持向量回歸模型對冷軋平整機的上工作輥表面粗糙度進行在線預測。通過預測誤差準則實現(xiàn)系統(tǒng)的前向遞推,采用FLOO(fast leave one out)的修剪算法實現(xiàn)其后向刪減,并且采用最速下降法實現(xiàn)了2個超參數(shù)的在線優(yōu)化。經(jīng)過仿真研究表明,系統(tǒng)預測的絕對誤差平均值為0.014 9,與其他方法相比具有明顯的優(yōu)越性,并且系統(tǒng)具有在線自適應的能力,能夠隨著時間而進化。
[Abstract]:The work roll of the cold rolling mill is in direct contact with the strip, and the attenuation of the surface roughness has a great influence on the shape and surface quality of the finished strip. Therefore, it is necessary to accurately predict the surface roughness attenuation by analyzing the roll wear mechanism. Firstly, the grey correlation analysis was used to analyze the factors affecting the surface roughness of the work roll, and the evaluation index system of the surface roughness of the work roll was determined. Furthermore, the surface roughness of the upper work roll of the cold rolling mill is predicted by using the optimal online sparse least square support vector regression model. The prediction error criterion is used to realize the forward recursion of the system, the pruning algorithm of FLOO(fast leave one out) is used to realize the backward pruning, and the on-line optimization of two superparameters is realized by the steepest descent method. The simulation results show that the average absolute error predicted by the system is 0.014, which is superior to other methods, and the system has the ability of online adaptation and can evolve over time.
【作者單位】： 燕山大學工業(yè)計算機控制工程河北省重點實驗室;燕山大學國家冷軋板帶裝備及工藝工程技術(shù)研究中心;新興鑄管股份有限公司格板部;
【基金】：國家自然科學基金鋼鐵聯(lián)合基金資助項目(U1260203) 河北省高等學校創(chuàng)新團隊領(lǐng)軍人才培育計劃資助項目(LJRC013)
【分類號】：TG333

【參考文獻】

相關(guān)期刊論文 前10條

1 李曉燕,張杰,陳先霖,曹建國,趙新明,賈生暉,艾斌,關(guān)貴民;冷軋平整機板形問題的特點及對策[J];鋼鐵;2003年12期

2 白振華;周慶田;竇愛民;徐俊;王駿飛;;冷連軋高速軋制過程中摩擦因數(shù)機理模型的研究[J];鋼鐵;2007年05期

3 徐U，

本文編號：1866364