论文部分内容阅读
瓦斯灾害是影响煤矿安全的重要问题之一,而爆炸后的主要危害之一是冲击波的伤害。而且,煤矿防隔爆措施是否能起到有效作用也依赖于冲击波超压值的测量和预测。在前人实验分析的基础上,应用神经网络理论,分别用BP神经网络和RBF神经网络对瓦斯爆炸后的冲击波超压值和测点之间的关系进行了预测。结果表明,BP神经网络的预测误差最小,应用神经网络进行预测可以明显的减小预测的误差,适合煤矿企业实际应用。
Gas disaster is one of the important issues affecting the safety of coal mines. One of the major hazards after the explosion is the shock wave damage. Moreover, whether coal mine explosion-proof measures can play an effective role also depends on the shock wave overpressure value measurement and prediction. Based on the previous experimental analysis, neural network theory is applied to predict the relationship between the overpressure of blast after gas explosion and measuring points by using BP neural network and RBF neural network respectively. The results show that the prediction error of BP neural network is the smallest. Prediction using BP neural network can significantly reduce the prediction error and is suitable for the practical application of coal mine enterprises.