本文選題：鈦合金 + 相變點　； 參考：《鈦工業(yè)進(jìn)展》2016年06期

【摘要】：基于西北有色金屬研究院實際生產(chǎn)中統(tǒng)計的321組鈦合金鑄錠化學(xué)成分與相變點數(shù)據(jù),構(gòu)建了預(yù)測鈦合金(α+β)/β相變點的人工神經(jīng)網(wǎng)絡(luò)模型和多元線性回歸模型,并對模型的準(zhǔn)確性進(jìn)行了評價分析。結(jié)果顯示,多元線性回歸模型的訓(xùn)練值及預(yù)測值與(α+β)/β相變點實際值的相關(guān)性系數(shù)分別為0.761 05和0.809 93,而人工神經(jīng)網(wǎng)絡(luò)模型的相關(guān)性系數(shù)分別為0.927 21和0.818 51,具有更好的相關(guān)性。人工神經(jīng)網(wǎng)絡(luò)模型的平均絕對誤差為4.02℃,相比多元線性回歸模型(平均絕對誤差為5.11℃)具有更高的精度,可以更好地描述合金元素與鈦合金(α+β)/β相變點之間的非線性關(guān)系。
[Abstract]:An artificial neural network model and a multivariate linear regression model for predicting the phase transition point of titanium alloy were established based on 321 sets of data of chemical composition and phase transition point of titanium alloy ingot from the actual production of Northwest Nonferrous Metals Research Institute. The accuracy of the model is evaluated and analyzed. The results show that the correlation coefficients between the training value and the predicted value of the multivariate linear regression model and the actual value of the phase transition point (偽 尾) are 0.761 05 and 0.809 93, respectively, while the correlation coefficients of the artificial neural network model are 0.927 21 and 0.818 51, respectively. The average absolute error of the artificial neural network model is 4.02 鈩，

本文編號：1878326