基于混沌粒子群的AWLSSVM瓦斯预测研究
AWLSSVM Gas Prediction Research Based on Chaotic Particle Swarm Optimization
-
摘要: 为了提高矿井瓦斯浓度预测的准确性,提出1种改进混沌粒子群算法的多变量自适应加权最小二乘支持向量机(AWLSSVM)瓦斯预测模型,且实现了瓦斯浓度的多步预测。首先,对粒子群算法进行分析,提出1种收敛速度更快、全局搜索能力更强的改进混沌粒子群算法;针对加权最小二乘支持向量机(WLSSVM)权值线性分布的缺点,根据离散点的分布特征,提出了AWLSSVM;其次,采用混沌理论构建模型的样本集;最后,对建立的模型进行了实例分析。结果表明:AWLSSVM单变量预测精度相对于最小二乘支持向量机、WLSSVM分别提高了5.3%和6.7%;多变量AWLSSVM相对于单变量AWLSSVM五步预测精度分别提高了39.3%、49.6%、55.9%、59.7%、62.5%。Abstract: In order to improve the accuracy of mine gas concentration prediction, an improved multi-variate adaptive weighted least squares support vector machine(AWLSSVM) gas prediction model for chaotic particle swarm optimization is proposed, and multi-step prediction is realized. Firstly, the particle swarm optimization algorithm is analyzed. An improved chaotic particle swarm optimization algorithm with faster convergence speed and stronger global search ability is proposed. Aiming at the shortcomings of the weighted least squares support vector machine(WLSSVM)weight distribution, AWLSSVM is proposed according to the distribution characteristics of discrete points. Secondly, the chaotic theory is used to construct a sample set. Finally, the performance of the prediction model was evaluated by mine monitoring data. The results indicate that in the univariate prediction, the prediction of AWLSSVM is 5.3% and 6.7% higher than the least squares support vector machine and WLSSVM. The multivariate accuracy is increased by 39.3%, 49.6%, 55.9%, 59.7% and 62.5%, relative to the univariate five-step prediction.
-
-
[1] 孙庆刚.中国煤矿瓦斯灾害现状与防治对策研究[J].中国煤炭,2014,40(3):116-119. [2] 张以文,郭海帅,涂辉,等.基于随机隐含层权值神经网络的瓦斯浓度预测[J].计算机工程与科学,2019, 41(4):699-707. [3] GUO Xiucai, REN Zhiqi, WANG Qinsheng, et al. Prediction of gas emission by BP neural network based on wavelet Analysis[J]. Earth and Environmental Science, 2019, 252(5): 46-52. [4] 黄贺江.回采工作面推进过程中的瓦斯涌出预测分析[J].工矿自动化,2017,43(8):90-93. [5] WEI Chunrong, XU Minqiang, SUN Jianhua, et al. Coal mine gas emission gray dynamic prediction[J]. Procedia Engineering, 2011, 26: 1157-1167. [6] 文晖.基于小波分析的GM(1,1)模型在瓦斯浓度预测分析中的应用[J].工业仪表与自动化装置,2015(6):63-66. [7] 张俭让,马彦龙.基于时间序列的综采工作面瓦斯浓度预测研究[J].煤炭技术,2019,38(3):111-113. [8] 魏连江,梁伟,高金晓,等.矿井瓦斯监测数据趋势预测研究进展[J].煤矿安全,2016,47(10):149-152. [9] 郭思雯,陶玉帆,李超.基于时间序列的瓦斯浓度动态预测[J].工矿自动化,2018,44(9):20-25. [10] 钱建生,邱春荣,李紫阳,等.深度学习耦合粒子群优化SVM的瓦斯浓度预测[J].煤矿安全,2016,47(11):173-176. [11] JAK Suykens, JDE Brabante, L Lukas, et al. Weighted least squares support vector machines: robustness and sparse approximation[J]. Neurocomputing, 2002, 48(1): 85-105. [12] 陈刚,简华阳,龚啸.自适应混沌粒子群算法在PSS设计中的应用[J].电力系统及其自动化学报,2012, 24(4):82-87. -
期刊类型引用(6)
1. 钮涛，李栋，王平，刘国峰，陈明刚. 基于地质保障系统的煤矿灾害监测预警及综合防治平台研究. 中国煤炭. 2024(05): 82-89 . 
百度学术
2. 刘锋. 基于PCA-SAPSO-BP神经网络的瓦斯涌出量预测研究. 煤矿安全. 2023(04): 60-68 . 本站查看
3. 朱斌，张奎，张有为，龚晓燕. 综掘面风流智能调控数字孪生系统. 计算机集成制造系统. 2023(06): 2006-2018 . 百度学术
4. 张逸龙，吴彦，方书昊，廖奇，杨印朝，朱红青. 赤峪煤矿煤层突出危险性预测敏感指标的确定. 矿业安全与环保. 2022(03): 84-87+93 . 百度学术
5. 谢谦，董立红，吴雪菲. 基于多源数据融合的煤矿工作面瓦斯浓度预测. 中国安全生产科学技术. 2022(11): 71-76 . 百度学术
6. 刘锋. 基于PCA-RVM的煤矿瓦斯浓度预测研究. 内蒙古煤炭经济. 2021(23): 70-72 . 百度学术
其他类型引用(10)
计量
- 文章访问数: 24
- HTML全文浏览量: 0
- PDF下载量: 0
- 被引次数: 16
下载:
