(1. 西北工業(yè)大學(xué) 凝固技術(shù)國家重點(diǎn)實(shí)驗(yàn)室，西安 710072)
(2. 西北有色金屬研究院，西安 710016)
摘 要: 采用Gleeble1500熱模擬實(shí)驗(yàn)機(jī)對(duì)Ti40合金在變形溫度900~1 100 ℃，應(yīng)變速率0.01~10 s−1，最大變形程度約60%的條件下的高溫流動(dòng)應(yīng)力變化規(guī)律進(jìn)行研究。針對(duì)該合金高溫變形過程中復(fù)雜的流變行為，以實(shí)驗(yàn)所得數(shù)據(jù)為基礎(chǔ)，基于模糊神經(jīng)網(wǎng)絡(luò)方法建立該合金的高溫本構(gòu)關(guān)系模型，并與實(shí)驗(yàn)結(jié)果進(jìn)行對(duì)比。結(jié)果表明：基于模糊神經(jīng)網(wǎng)絡(luò)建立Ti40合金的高溫本構(gòu)關(guān)系模型是切實(shí)可行的，模型的精度較高，最大誤差為8.14%，不超過10%，可以很好地描述Ti40合金在高溫變形時(shí)各熱力學(xué)參數(shù)之間高度非線性的復(fù)雜關(guān)系，彌補(bǔ)傳統(tǒng)回歸模型不能反映變形全過程的局限性，是一種便捷、有效的具有廣泛應(yīng)用前景的表征工程材料本構(gòu)關(guān)系的方法。
關(guān)鍵字: Ti40鈦合金；本構(gòu)關(guān)系；模糊神經(jīng)網(wǎng)絡(luò)；變形行為
based on fuzzy-neural network
（1. State Key Laboratory of Solidification Processing, Northwestern Polytechnical University, Xi’an 710072, China;
2. Northwest Institute for Nonferrous Metal Research, Xi’an 710016, China）
Abstract:The hot deformation characteristics of Ti40 alloy were studied in the temperature range of 900−1 100 ℃, the maximum deformation degree of 60% and strain rate range of 0.01−10 s−1 with Gleeble 1500 thermal simulator. Based on the results obtained from experiment, a constitutive relationship model of Ti40 alloy was established by the fuzzy-neural network and compared with the experimental result. The results indicate that the method is feasible to construct a constitutive relationship model for this alloy and high in the degree of fitting, Simultaneously, the complicated nonlinear relationship of thermodynamic parameters can be well described by the network model, making up for the limitations which traditional regression cannot reflect the whole deformation process. This method is not only a wide prospect of application but also an effective way to establish the constitutive relationship model of titanium alloys.
Key words: Ti40 alloy; constitutive relationship; fuzzy-neural network; deformation behavior
