Robust artificial neural network for reliability analysis
Robust artificial neural network for reliability analysis
复制标题
用于可靠性分析的鲁棒人工神经网络
DOI：
10.7712/120217.5400.17104
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
E. Patelli
中科院分区：
文献类型：
--
作者：
U. Oparaji;R. Sheu;E. Patelli
使用人工神经网络（ANN）代替昂贵的模型，以减少可靠性分析所需的计算负担。通常，具有选定架构的ANN使用反向传播算法从感兴趣的底层模型的输入/输出关系的少数数据代表进行训练。然而，可能从相同的训练数据中获得不同的性能ANN，导致选择最佳性能ANN的不确定性。另一方面，使用交叉-基于最高R2值选择最佳性能ANN的验证可能导致所选ANN做出的预测方面的偏差。这是由于使用R2无法确定ANN做出的预测是否有偏见此外，R2并不表示模型是否足够，因为可能对于好模型具有低R2，而对于坏模型具有高R2。因此，我们提出了一种方法，以提高预测的鲁棒性的人工神经网络的基础上耦合贝叶斯框架和模型平均技术到一个统一的框架。传播到鲁棒预测的模型不确定性被量化为置信区间。两个例子来证明该方法的适用性。
Artificial Neural Networks (ANN) are used in place of expensive models to reduce the computational burden required for reliability analysis. Often, ANNs with selected architecture are trained with the back-propagation algorithm from few data representatives of the input/output relationship of the underlying model of interest. However, different performing ANNs might be obtained from the same training data, leading to an uncertainty in selecting the best performing ANN. On the other hand, using cross-validation to select the best performing ANN based on the highest R2 value can lead to a biassing in terms of the prediction made by the selected ANN. This is due to the fact that the use of R2 cannot determine if the prediction made by ANN is biased. Additionally, R2 does not indicate if a model is adequate, as it is possible to have a low R2 for a good model and a high R2 for a bad model. Hence we propose an approach to improve the prediction robustness of an ANN based on coupling Bayesian framework and model averaging technique into a unified framework. The model uncertainties propagated to the robust prediction is quantified in terms of confidence intervals. Two examples are used to demonstrate the applicability of the approach.