基于核主成分分析与PSO-SVM的充填管道失效风险性分级评价模型

为了更精确地对充填管道失效风险性进行预测，建立核主成分分析与PSO-SVM相结合的评价模型。选取8项定量指标作为充填管道失效风险性的评价指标。统计15个矿山的样本数据，运用核主成分分析法对15个样本进行预处理，得出主成分，再利用改进的SVM模型进行预测，进而得到更加精确的管道失效风险性预测结果。研究结果表明，所得到的实际预测结果与期望值之间的平均相对误差控制在5%以内。利用核主成分分析法与PSO-SVM相结合的评价模型具有精度高和运算速度快的优点，为充填管道失效风险预测提供了一种可靠的方法。

Failure Risk Assessment Model of Filling Pipeline Based on KPCA and PSO-SVM

In order to predict the invalidation risk of backfilling pipeline more accurately，the evaluation model based on kernel principal component analysis and PSO-SVM is established.Eight quantitative indexes are selected as the evaluation index of failure risk of filling pipeline.And the sample data of fifteen mines were counted，which were processed by kernel principal component analysis，producing the main ingredients，as the input data of the optimized SVM model which ended up with a more accurate risk prediction on invalidation of backfilling pipeline.The results indicate that the average expected value relative errors of the five mines are below 5%.The invalidation risk assessment of backfill pipeline by the establishment of the kernel principal components analytic method and the optimized SVM model has the advantage of rapid analysis and high precision of prediction.A better evaluation is provided for the mine backfilling pipeline invalidation risk analysis.