煤矿井下局部通风机需风量的预测  

Prediction of air demand of local ventilator in underground coal mine

作　　者：闫向彤[1] 杨琦 YAN Xiang-tong;YANG Qi(School of Mechanical Engineering,Xi'an Science and Technology,Xi'an 710054,China)

机构地区：[1]西安科技大学机械工程学院,陕西西安710054

出　　处：《煤炭工程》2021年第10期148-152,共5页Coal Engineering

基　　金：国家自然科学基金(51874235)。

摘　　要：为了解决局部通风机根据下一刻风量需求提前进行风速调整的问题,提出一种改进遗传算法优化的Elman神经网络算法IGA-Elman(Improved genetic algorithm-Elman)对需风量进行预测。改进的算法是对遗传算法的选择算子策略进行改进,通过复制优良个体及按比例选取较优的方法,使得种群平均适应度得到改善,提高了算子的选优能力。利用IGA-Elman神经网络和传统的GA-Elman神经网络对局部通风机需风量的预测相比较,IGA-Elman网络能够提高预测性,并且具有收敛速度快的优点,实现了局部通风机需风量的准确预测,对煤矿安全生产具有重要的实际意义。In order to solve the problem of wind speed adjustment in advance according to the demand of air volume at the next moment, an improved genetic algorithm to optimize Elman neural network algorithm of IGA-Elman(Improved based algorithm-Elman) is proposed to predict the required air volume. The improved algorithm changes the strategy to improve the selection operator of genetic algorithm, by copying excellent individuals and selecting better methods according to proportion, the average fitness of population is improved and the ability of operator selection is improved. Compared with the IGA-Elman neural network and the traditional GA-Elman neural network, the IGA-Elman network can improve the predictability and the convergence is quick, and air demand of the local ventilator can be accurately predicted.

关 键 词：遗传算法 ELMAN神经网络 局部通风机 需风量预测 

分 类 号：TD724[矿业工程—矿井通风与安全]