超高压合成TiC-NiTi复合材料的制备与工艺参数预测  

Preparation of TiC/NiTi Composite by Ultrahigh Pressure Synthesis and Process Parameter Prediction

作　　者：毛阳[1] 涂福泉[1] 许仁波[1] 

机构地区：[1]武汉科技大学冶金装备与控制教育部重点实验室,湖北武汉430081

出　　处：《热加工工艺》2014年第16期128-131,136,共5页Hot Working Technology

摘　　要：运用铰链式六面顶高温高压装置制备TiC/NiTi复合材料,该制备方法能提高复合材料致密度,且能提高NiTi在形状记忆合金中的含量,以改善合金性能。分析了制备过程中烧结温度、烧结时间和原料粉体对NiTi马氏体相变潜热的影响,应用人工神经网络技术建立了参数预测模型,利用遗传算法的全局搜索能力,优化了BP网络权值,从而完善了基于BP网络的NiTi马氏体相变潜热预测模型。结果表明:该模型具有较高的精度,实现了预测的作用,为工艺参数选择提供理论依据。The hinged six sides device was used to manufacture TiC/NiTi composite. The method can improve the density and NiTi content of the composite, and then the performance of the shape memory alloys improve. The effects of sintering temperature, sintering time, raw material powder on NiTi martensitic phase change latent heat were studied. The artificial neural network technology was used to build the parameter prediction model and the global search ability of the algorithm, based on BP（back-propagation） network, the predictive model of NiTi martensitic phase change latent heat improves. The experiments show that：the model has higher accuracy, which can realize better prediction effect, and provide theoretical basis for the process parameters selection.

关 键 词：烧结温度 烧结时间 原料粉体 马氏体相变潜热 神经网络 遗传算法 

分 类 号：TB321[一般工业技术—材料科学与工程]