论文部分内容阅读
通过分析研究变形温度、应变速率及变形程度参数对TC4-DT钛合金高温变形行为的影响,建立了一种基于自适应模糊神经网络的TC4-DT钛合金高温变形本构关系预测模型。高温变形热模拟压缩试验的变形温度为750 ~1150 ℃,应变率为0.001~10 s–1,试样高度压缩率为50%。本研究中建立的网络模型集成了模糊推理系统误差反向传播(BP)神经网络的学习算法。结果表明,该模型的预测值与实验结果比较吻合,最大相对误差小于6%。本研究证明模糊神经网络是一种优化TC4-DT钛合金本构关系模型和优化变形工艺参数的有效、实用方法。
By analyzing the influence of deformation temperature, strain rate and deformation degree on the high temperature deformation behavior of TC4-DT titanium alloy, a predictive model of the constitutive model of TC4-DT titanium alloy deformation at high temperature was established based on the adaptive fuzzy neural network. The deformation temperature of high-temperature deformation thermal simulation compression test is 750-1150 ℃, the strain rate is 0.001-10 s-1, and the high compression rate of specimen is 50%. The network model established in this study integrates the learning algorithm of fuzzy inference system error back propagation (BP) neural network. The results show that the predictive value of the model is in good agreement with the experimental results, and the maximum relative error is less than 6%. This study shows that fuzzy neural network is an effective and practical method to optimize the constitutive model of TC4-DT titanium alloy and optimize the deformation process parameters.