(合肥工業(yè)大學(xué) 材料科學(xué)與工程學(xué)院， 合肥 230009)
摘 要: 在深入分析熱變形工藝參數(shù)對Ti-15-3合金顯微組織及成形載荷的影響的基礎(chǔ)上， 以變形溫度、 變形程度和變形速率等熱變形工藝參數(shù)作為設(shè)計變量， 以顯微組織和成形力的最佳綜合為目標， 建立了該合金熱塑性成形工藝參數(shù)的多目標優(yōu)化數(shù)學(xué)模型。 以顯微組織參數(shù)和成形力的人工神經(jīng)網(wǎng)絡(luò)預(yù)測模型作為優(yōu)化算法的知識源， 將人工神經(jīng)網(wǎng)絡(luò)與修正的遺傳算法相結(jié)合， 對Ti-15-3合金的熱塑性成形工藝參數(shù)進行優(yōu)化。 結(jié)果表明， 提出的修正的遺傳算法是有效的， 采用將其與人工神經(jīng)網(wǎng)絡(luò)相結(jié)合的方法對鈦合金的熱塑性成形工藝參數(shù)進行優(yōu)化是可行的。
關(guān)鍵字: Ti-15-3合金; 優(yōu)化； 修正的遺傳算法； 人工神經(jīng)網(wǎng)絡(luò)； 熱變形參數(shù)
（School of Materials Science and Engineering, Hefei University of Technology, Hefei 230009, China）
Abstract: The systematic analyses of the effects of hot deformation process parameters on microstructure and load of Ti-15-3 alloy were accomplished. Based on the results, a multi-objection optimization model was established for hot deformation process of Ti-15-3 alloy. In the model, temperature, strain and strain rate are treated as design variables and the objective is to obtain uniform fine-grain microstructures under the smaller load. Optimization of hot deformation process parameters for Ti-15-3 alloy was conducted by introducing artificial neural network prediction models of microstructures and forming load into a modified genetic algorithm. The results indicate that the modified genetic algorithm is effective and the optimization method based on artificial neural network and the modified genetic algorithm is feasible.
Key words: Ti-15-3 alloy; optimization; modified genetic algorithm; artificial neural network; hot deformation parameters
