论文部分内容阅读
基于《雷电防护第2部分:风险管理》(GB/T21714.2—2008)及BP人工神经网络理论,利用MATLAB软件建立了一个三级BP网络预警模型,经过网络训练、网络检测得到训练成熟的普通建筑雷灾风险BP网络评价模型。BP神经网络的运用有助于评价模型更加准确客观地反映建筑物雷灾风险各影响因素与最终风险评价结果之间的非线性关系。为了验证该评价模型的评判效果,除对训练成熟的网络评价模型进行检测,还进一步选取《雷电防护第2部分:风险管理》(GB/T21714.2—2008)中提供的评估实例进行验证性评估,二者结果保持一致,表明该方法可以用作普通建筑的雷灾风险评价。
Based on “Lightning Protection Part 2: Risk Management” (GB / T21714.2-2008) and BP artificial neural network theory, using MATLAB software to establish a three-level BP network early warning model, after network training, network testing to be trained mature Common Building Threat Risk BP Network Evaluation Model. The use of BP neural network can help the evaluation model to more accurately and objectively reflect the nonlinear relationship between the factors affecting the mine disaster risk and the final risk assessment results. In order to verify the evaluation effect of the evaluation model, in addition to testing the mature network evaluation model, we further selected the verification examples provided in “Lightning Protection Part 2: Risk Management” (GB / T21714.2-2008) The results of the two methods are in good agreement with each other, indicating that the method can be used as a lightning disaster risk assessment for ordinary buildings.