摘要
针对水泥２８ｄ抗压强度预测的多变量、非线性、大时滞特点，提出了一种以人工神经网与特殊的十进制数编码的遗传算法相结合的水泥２８ｄ抗压强度预测方法，并对两组不同标号的水泥进行了预测试验，所得结果证明此种方法具有一定的可行性。
According to the characteristics of multi variable,nonlinear and large time lag of prediction of 28ds cement compressive strength,a new prediction method which combining artificial neural networks with the special decimal system coding genetic algorithms was proposed.The results of prediction tests on two tags of cement show this method is feasible.
出处
《山东建材学院学报》
1998年第3期275-277,共3页
Journal of Shandong Institute of Building Materials
基金
国家建材局资金资助项目
关键词
人工神经网
遗传算法
水泥
强度预测
artificial neural networks
genetic algorithms
cement
strength prediction
