• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 人工智能与数据挖掘 • 上一篇    下一篇

基于随机隐含层权值神经网络的瓦斯浓度预测

张以文1,郭海帅1,涂辉2,余国锋2   

  1. (1.安徽大学计算智能与信号处理教育部重点实验室,安徽 合肥 230601;
    2.煤矿瓦斯治理国家工程研究中心,安徽 淮南232001)
     
     
  • 收稿日期:2018-01-22 修回日期:2018-08-13 出版日期:2019-04-25 发布日期:2019-04-25
  • 基金资助:

    国家自然科学基金(61602003) ;安徽省自然科学基金 (1808085MF197);安徽省科技重大专项课题(16030901062)

Gas concentration prediction based on
neural network with random hidden weight

ZHANG Yiwen1,GUO Haishuai1,TU Hui2,YU Guofeng2   

  1. (1.Key Laboratory of Intelligent Computing and Signal Processing,Ministry of Education,Anhui University,Hefei 230601;
    2.National Engineering Research Center for Coal Mine Gas Controlling,Huainan 232001,China)
  • Received:2018-01-22 Revised:2018-08-13 Online:2019-04-25 Published:2019-04-25

摘要:

煤矿的安全生产一直是人们重点研究的课题之一。在众多的煤矿开采安全事故中,瓦斯引起的事故占到了大多数。对井下生产线的瓦斯浓度进行实时准确的预测,提前预知生产环境是否处于安全状态,对煤矿的安全生产来说意义重大。针对这一问题,提出了一种基于NSGAII训练的随机隐含层神经网络(BNSGAII NN)来进行瓦斯浓度预测的方法。一方面,NSGAII需要设定的参数少,使用较为简单;另一方面,NSGAII中的交叉变异机制避免了陷入局部最优解。为了证明NSGAII训练的随机隐含权值神经网络的预测质量,通过实验与PSOGSA训练的随机隐含层神经网络(PSOGSA NN)进行了对比。实验结果表明,BNSGAII NN的预测质量明显高于PSOGSA NN的预测质量。
 
关键词:

关键词: 瓦斯浓度预测, 随机隐含层权值, 神经网络, BNSGA-II NN

Abstract:

The safe production of coal mines has always been one of human's key research subjects. In numerous safety accidents in coal mining, gas accidents account for most of them. Real-time and accurate prediction of gas concentration in underground production lines and anticipating whether the production environment is in a safe state is critical for the safety of coal mines.  Aiming at this problem, we propose a gas concentration prediction method based on the random hidden layer neural network trained by NSGA-II (BNSGA-II NN). On the one hand, fewer parameters need to be set in the NSGA-II, and they are convenient to use. On the other hand, the cross variation mechanism in the NSGA-II avoids the problem of falling into local optimal solution in the traditional methods. To demonstrate the prediction quality of the trained neural network with random hidden weight using the NSGA-II, we compare the BNSGAII NN with PSOGSA NN through experiments. Experimental results show that the prediction effect of the BNSGA-II NN is significantly better than that of the PSOGSA NN.
 

Key words: gas concentration prediction, random hidden weight, neural network, BNSGA-II NN