基于人工神经网络的混凝土抗冻性预测

Based on artificial neural network prediction concrete frost resistance

简要介绍了MATLAB人工神经网络,阐述了人工神经网络预测模型的基本思想和模型特点。随着神经网络技术的不断完善和发展,人工神经网络广泛地用于土木工程的各个领域,可针对混凝土冻融与各种因素之间的相互关系,并且随着数据的不断积累,可在新样本基础上进行自学,形成较完整的评估预测系统。针对混凝土冻融后的相对动弹性模量的变化,应用BP网络建立了评估混凝土冻融后的性能的人工神经元网络模型,较好地解决了多影响因子的非线性映射问题,但真正用于工程实践还有许多问题需要进一步的研究解决。

Brief introduction of MATLAB artificial neural network, described the basic idea and characteristics of the model based on artificial neural network.With neural network technology unceasing consummation and development, artificial neural network was widely used in many civil engineering fields.Aiming at the concrete after freezing and thawing of relative dynamic elastic modulus change, the ap plication of BP network to establish the evaluation of concrete after freezing and thawing of the performance of the artificial neural net work model, better land solved much impact factor of the problem of nonlinear mapping, but the real used in engineering practice and many problems need to be further solved.