论文部分内容阅读
为了准确预测瓦斯涌出量,提出了一种基于模糊聚类和支持向量机(SVM)的瓦斯涌出量预测方法。将瓦斯涌出量相关影响因素作为特征空间中的样本,采用模糊C均值聚类对特征空间中的样本进行聚类分析,对于所得到的不同类别样本分别建立SVM预测模型。结果表明:采用单纯的SVM预测方法,对于不同特征的样本的预测个别预测误差相对较大,其最大误差为8.11%,平均误差为4.68%,采用文中所建议的用FCM对样本分类后再进行SVM预测,预测精度有明显改善,最大误差和6.94%,平均误差为3.35%,表明所建议的方法是有效和可行的。
In order to accurately predict gas emission, a gas emission prediction method based on fuzzy clustering and support vector machine (SVM) is proposed. The influence factors of gas emission are taken as the samples in the feature space. The fuzzy C-means clustering is used to cluster the samples in the feature space, and the SVM prediction models are respectively established for the different types of samples. The results show that using the simple SVM prediction method, the prediction errors of the samples with different characteristics are relatively large, with the maximum error of 8.11% and the average error of 4.68%. Using the FCM proposed in this paper, SVM prediction, prediction accuracy has improved significantly, the maximum error and 6.94%, the average error of 3.35%, indicating that the proposed method is effective and feasible.