基于聚类和案例推理的煤与瓦斯突出动态预测

为了实现对煤与瓦斯突出快速、准确和动态预测，考虑煤与瓦斯突出多种影响因素，提出了一种基于聚类和案例推理（CBR）的煤与瓦斯突出预测方法。利用通过一种基于PCA的描述案例特征权值确定方法所得的描述案例特征权值，对案例库案例进行聚类，使同类案例间具有较高的相似度；以案例聚类结果为基础，进行高效案例检索与匹配，以提高煤与瓦斯突出预测的快速性。利用实测数据对所提方法进行验证，实例验证结果表明，所提方法预测结果的准确性高，预测所用平均时间是已有煤与瓦斯突出预测案例推理方法预测所用时间的40%。

Dynamic prediction of coal and gas outburst based on clustering and case-based reasoning

In order to realize the accurate,quick and dynamic prediction of coal and gas outburst,considering multiple influencing factors of coal and gas outburst,a prediction method based on clustering and case-based reasoning(CBR) was proposed. Using case system feature weights by an approach of solving weights allocation based on PCA(principal component analysis),Cases in the case base are clustered,which can gather the cases whose higher similarities as one class. Based on clustering results,an efficient process for case retrieval and matching is done to improve the quickness for prediction of coal and gas outburst. The proposed method was validated using practical measured data. The simula?tion example shows that the proposed method provides more accurate prediction results,the prediction average time of the proposed method is only 40%of that of the existing CBR method for prediction of coal and gas outburst.