预测钢筋混凝土预制桩竖向极限承载力的ANN方法研究

传统的钢筋混凝土预制桩极限承载力预测方法，难以考虑单桩极限承载力影响因素的模糊性和相互作用关系，本文提出并建立了预测钢筋混凝土预制桩极限承载力的人工神经网络方法，收集了某地区的41例钢筋混凝土预制桩，利用其中37例的实测数据建立了预测单桩极限承载力的ANN模型，另外的4例检验了模型的预测性能，研究结果表明，所建立的ANN方法的预测精度能够满足工程应用要求。

Using ANN to Predict The Ultimate Bearing Capacity of Precast Reinforced Concrete Piles

The traditional methods for predicting the ultimate bearing capacity of precast reinforced concrete piles can not consider the fuzziness and inter-influence of the factors influencing the ultimate bearing capacity. ANN was used to establish an ANN based approach for predicting the ultimate bearing capacity of precast reinforced concrete piles. 41 examples of precast reinforced concrete piles were accumulated from an area in China. 37 examples of them were used to build a new prediction model for the ultimate bearing capacity. The model was then used to predict the ultimate bearing capacity of the rest 4 examples. A comparison was conducted between the predicted results and the practical measurements. The comparison results show that the approach has enough accuracy to meet demands of engineering completly.