共查询到17条相似文献,搜索用时 93 毫秒
1.
2.
3.
4.
基于人工神经网络的结构钢端淬曲线预测系统模型的研究 总被引:6,自引:0,他引:6
利用人工神经网络技术建立了结构钢端淬曲线预测系统的数学模型,该模型覆盖了较大范围的钢种,系统除了能对已训练过的钟种的端淬曲线准确描述外,还能在一定精度范围内对新钢种的端淬曲线进行预测。本文还研究了训练步数、训练数据量对模型预测量精度的影响。 相似文献
5.
利用人工神经网络技术建立了结构钢端淬曲线预测系统的数学模型,该模型覆盖了较大范围的钢种,系统除了能对已训练过的钢种的端淬曲线准确描述外,还能在一定精度范围内对新钢种的端淬曲线进行预测.本文还研究了训练步数、训练数据量对模型预测精度的影响. 相似文献
6.
7.
基于余氏固体与分子经验电子理论,利用平均原子晶胞模型计算了Ti3Al基合金中延性β相的价电子结构,给出了其价电子结构信息——相结构因子nA,σN,F。用相结构因子nA,σN,F分析讨论了β相价电子结构与稳定性的关系及合金元素的合金化行为。认为β相及含不同合金元素的β相的精细价电子结构是金属间化合物α2-Ti3Al合金化与Ti3Al基合金选择Nb,V,Mo3种合金元素作为常用合金化元素的微观本质原因。 相似文献
8.
9.
张德春 《热处理技术与装备》1993,(6)
前言强碳、氮化物形成元素——钒、钛、铌的微量合金化对钢的组织、机械性能和工艺性能的影响人们曾进行了十分详尽的研究,但是微量合金元素对合金钢可逆回火脆性倾向的影响人们还不完全清楚。为了清除结构钢的回火脆性,通常采用钼(0.5%)来进行合金化。人们注意到在含钼的低磷钢中有减少钼含量可能性的报导,其目的是搞清楚,在用直接还原炉料炼制的纯净钢中,微最碳、氮化物形成元素能在多大程度上来代替钢中钼的作用。本文研究微量合金元素钒(0.05%)、钛 相似文献
10.
采用双辉等离子渗铬技术,对T8钢进行了900℃温度表面渗铬合金化;使用GDA750.测量了试样渗铬合金层中Fe、Cr和C等元素的浓度分布。通过热力学分析计算,研究了渗铬合金化层形成过程中碳迁移机理和规律。指出驱动碳迁移的动力是碳的括度梯度,并推导出富碳区碳质量分数随铬质量分数变化的数学关系式:w(C)=0.8 0.3536w(Cr)。计算结果与试验结果相当吻合。 相似文献
11.
THE characteristic multiphase structure of DP andTRIP steels can be evolved by hot rolling or by postheat treatment.Only this latter case is discussed in thispaper.The transformation processes which result in theexpected microstructure and ratio of constituents arecontrolled by the technological parameters of thetreatment.Although the number of affecting parametersis not so large,the determination of importantparameters'values(intercritical temperature,coolingrate)needs numerous pre-experim… 相似文献
12.
Jiang Fuqing Huang Jiwu Tang Lei Wang Fenxiang Xiao Quanfeng Yin Zhimin 《JOM Journal of the Minerals, Metals and Materials Society》2019,71(5):1722-1730
JOM - The Jominy end-quench (JEQ) test was adopted to investigate the quench sensitivity of Al-6.6Zn-1.8Mg-0.23Cu-0.22Mn-0.21Zr (7046A) alloy. The mechanical properties of the aged alloy were... 相似文献
13.
The final microstructure of DP and TRIP assisted steels can evolve after hot working (hot rolling) or during post heat treatment process. In the formation of the final structure a number of different technological parameters have important roles, e.g. end temperature of rolling, cooling rates, temperature of intercritical annealing, etc. As a result of the individual factors and their combinations a lot of product technology routes are feasible. The effect of the different combinations of these technological parameters on the microstructure can be mapped by the special Jominy end-quench test (so called intercritical Jominy end-quench test) described in this paper. Unlike the traditional Jominy test, in this case there is a partial anstenizing between A1 and A3 temperatures which results in a given amount of ferrite in the microstructure before quenching. The method developed can be applied for mapping DP and TRIP assisted steels' microstructure in a wide range of technological parameters. The analysis of measured and calculated data can help us find the technological parameters optimal from the microstructural point of view. 相似文献
14.
D. Hömberg 《Acta Materialia》1996,44(11):4375-4385
We present a numerical algorithm for simulating the Jominy end-quench test and deriving continuous cooling diagrams. The underlying mathematical model for the austenite-pearlite phase transition is based on Scheil's Additivity Rule and the Johnson-Mehl equation. For the formation of martensite we compare the Koistinen-Marburger formula with a rate law, which takes into account the irreversibility of this process. We carry out numerical simulations for the plain carbon steels C 1080 and C 100 W 1. The results suggest that the austenite-pearlite phase change may be described decently by the Additivity Rule, except for the incubation time. On the other hand, using a rate law to describe the martensite formation is preferable to the Koistinen-Marburger formula, which leads to unphysical oscillations of the cooling curves in simulated CCT-diagrams. 相似文献
15.
《International Heat Treatment & Surface Engineering》2013,7(2):86-92
AbstractThe common test for assessing hardenability is the standardised Jominy end-quench test according to ASTM-A255 or DIN-EN 50191. This test is applied essentially for non-alloyed and low alloyed structural steels, when quenched in liquid quenchants, but it is not applicable for high alloyed (air hardening) steels, because the cooling rate at the opposite end of the Jominy specimen is higher than the critical cooling rate of those steels. Today there is no a standardised method to test and evaluate the hardenability of high alloyed steels. Nowadays, not only high alloyed steels, but also some low alloyed structural steels are quenched by high pressure gas quenching (HPGQ) in vacuum furnaces. Obviously there is need from one side to develop a standardised method for testing and evaluation of hardenability for high alloyed steels when they are gas quenched, and from the other side to establish a database for hardenability of low-alloyed structural steels when they are quenched in vacuum furnaces by HPGQ, i.e. at different high pressures and different flow velocities. Corresponding equipment that can be used to satisfy both requirements is discussed. 相似文献
16.
W. G. Vermeulen P. J. van der Wolk A. P. de Weijer S. van der Zwaag 《Journal of Materials Engineering and Performance》1996,5(1):57-63
Jominy hardness profiles of steels were predicted from chemical composition and austenitizing temperature using an artificial
neural network. The neural network was trained using some 4000 examples, covering a wide range of steel compositions. The
performance of the neural network is examined as a function of the network architecture, the number of alloying elements,
and the number of data sets used for training. A well-trained network predicts the Jominy hardness profile with an average
error of about 2 HRC. Special attention was devoted to the effect of boron on hardenability. A network trained using data
only from boron steels produced results similar to those of a network trained using all data available. The accuracy of the
predictions of the model is compared with that of an analytical model for hardenability and with that of a partial least-
squares model using the same set of data. 相似文献
17.