GA-BP网络在凿岩防卡阀推进压力预测中的应用

基金项目:

国家自然科学基金资助项目(51274021)

详细信息

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

School of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, China

摘要: 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GA-BP网络模型具有更高的预测精度、非线性映射和网络性能。
- 凿岩 /
- 防卡阀 /
- 推进压力 /
- BP神经网络 /
- 遗传算法
Abstract: 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.
- rock drilling /
- anti-jamming valve /
- boost pressure /
- BP neural network /
- genetic algorithm