蚁群算法在煤与瓦斯突出预测中的应用

Application of ACA on Coal and Gas Outburst Forecasting

煤与瓦斯突出预测在矿井的安全生产中具有重要影响;蚁群算法是最新提出的新型寻优策略,具有良好的克服局部极值、获得全局极值的能力;通过对蚁群算法和模糊聚类算法的深入研究提出了一种新的蚁群-模糊聚类预测算法,利用改进的自适应调整信息素的蚁群算法计算出模糊聚类的个数和初始聚类中心,再利用模糊聚类算法对煤与瓦斯突出进行预测;对平八矿历年煤与瓦斯突出数据进行验证预测的结果表明,该方法与传统的模糊聚类预测方法相比具有较强的自适应能力和较好的预测效果。

Forecasting of coal and gas outburst impacts on safety production of pits greatly. Based on the individual local searching the ant colony algorithm （AcA） is an up--to--date proposed optimal strategy, which possesses good capability to avoid the local extremum and obtain the global extremum. By lucubrating the ant colony algorithm （ACA） and fuzzy clustering method （FCM）, a new forecasting algorithm based on ACA--fuzzy clustering method is put forward in which the number of FCM and the incipient clustering center of FCM are obtained by ACA of improved self--adaptived regulative pheromone, then the fuzzy clustering algorithm using improved ACA is applied to coal and gas outburst forecasting. Applying the presented forecasting method to the yearly outburst data of Pingdingshan coal mine No. 8, shows that comparing with traditional FCM forecasting method, the presented forecasting method has better adaptive ability and can give better forecasting result.