GA-BP网络在凿岩防卡阀推进压力预测中的应用

Application of GA-BP neural network in boost pressure forecast of anti-jamming valve used in rock drilling

分析了凿岩钻车防卡阀的结构和工作原理,利用某采石场原始卡钎数据,建立了防卡阀BP神经网络模型。基于遗传算法理论对BP神经网络模型进行了结构拓扑优化和训练,建立了GA-BP网络模型。分析结果表明,BP神经网络模型和GA-BP网络模型均可以较好地预测卡钎时防卡阀的推进压力,但GABP网络模型具有更高的预测精度、非线性映射和网络性能。

Structure and working principle of anti-jamming valve on a drilling rig was analyzed,and BP neural network model of anti-jamming valve was established using original data of a quarry.The theory of genetic algorithm was utilized to optimize and analyze BP neural model,and the GA-BP model was established.The analysis results show that both BP neural network and GA-BP network model can be used to predict boost pressure of anti-jamming valve,and the GA-BP network model has higher prediction accuracy,nonlinear mapping and network performance.