Evaluation model of artificial neural network for city lifeline engineering

摘要

In order to evaluate the safety suitability of site for city lifeline, evaluation model is constructed on the basis of artificial neural network (ANN). According to double parallel feed-forward neural network model, which is a basic model of Back Propagation (BP) network, evaluation model and calculating method are analyzed. The model is applied to site stability and suitability evaluation of underground city lifeline. Safety of city lifeline is controlled by site stability, buried depth and fault movement. Furthermore, site stability is also affected by several factors. As an example application, the site stability in Tangshan City is calculated precisely, and suitability for city lifeline is evaluated. MATLAB is applied to analyze model structure, concealed layer number, neuron number of concealed layer, and training function. Model preferences are optimized, and evaluation model is constructed. Finally, calculating results are analyzed and some advice is proposed for artificial neural network modeling.