基于ACSOA-BP神经网络的瓦斯含量预测模型

Prediction model of coal seam gas content based on ACSOA optimized BP neural network

针对煤矿瓦斯含量预测问题,以陈四楼煤矿为例,在煤层瓦斯含量影响因素分析的基础上,通过对种群进行混沌初始化,并引入自适应混沌算法和非线性收敛因子,提出了自适应混沌海鸥算法(ACSOA),建立了基于自适应混沌海鸥算法优化BP神经网络的瓦斯含量预测模型(ACSOA-BP),将模型应用于矿井进行预测效果检验。结果表明:陈四楼煤矿二2煤层瓦斯含量与不同因素呈非线性关系,地质构造是控制煤层瓦斯分布的主要因素,ACSOA-BP模型具有更高的预测精度和稳定性。

For the problem of coal seam gas content prediction,the influencing factors of coal seam gas content were analyzed by taking No.2 coal seam of Chensilou Coal Mine as the research object.Based on the above,a prediction model of coal seam gas content was proposed based on adaptive chaotic seagull optimization algorithm(ACSOA)optimized BP neural network(ACSOABP).In the ACSOA,introducing chaos algorithm into SOA algorithm for chaos initialization,and adaptive algorithm and nonlinear convergence factor was proposed in SOA algorithm to improve the optimization ability.And the ACSOA-BP model was applied to the study area to verification.The results show that the relationship is nonlinear between gas content of No.2 coal seam and the influencing factors in Chensilou Coal Mine,and the geological structure is the main controlling factor of gas distribution.Compared with the BP model and the SOA-BP model,the ACSOA-BP model has a higher accuracy and stability.