研究煤矿安全评价问题的现状,针对传统的BP神经网络要获得可信度较高的评价模型需要大量的样本进行学习的缺点,采用V-fold Cross-validation技巧,利用MATLAB神经网络工具箱,建立基于BP神经网络的煤矿安全评价模型,利用实际指标数据研究小样本条件下的煤矿安全评价,并验证评价效果的有效性。 To study the status quo of coal mine safety assessment, aiming at the problem that the traditional BP neural network needs a large number of samples to obtain a high reliability evaluation model, V-fold Cross-validation technique and MATLAB neural network toolbox are used to establish Based on the BP neural network model of coal mine safety evaluation, the actual index data is used to study the coal mine safety evaluation under the condition of small sample, and the effectiveness of the evaluation is verified.