中国安全生产科学技术
中國安全生產科學技術
중국안전생산과학기술
JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY
2015年
1期
11-16
,共6页
边坡变形%支持向量机回归( SVR)%修正的果蝇优化算法( MFOA)%仿真预测
邊坡變形%支持嚮量機迴歸( SVR)%脩正的果蠅優化算法( MFOA)%倣真預測
변파변형%지지향량궤회귀( SVR)%수정적과승우화산법( MFOA)%방진예측
slope deformation%support vector machine regression( SVR)%modified fruit fly optimization algorithm ( MFOA)%simulation and forecast
为实现边坡危险性及时预警预报,以露天矿边坡变形量为研究对象,提出采用七项影响指标作为边坡位移变形量的响应参数,建立支持向量机回归预测模型( SVR)。引入修正的果蝇优化算法( MFOA)对模型参数进行优化,构建基于MFOA-SVR露天矿边坡变形量协同预测模型,并以实际监测数据进行模型仿真预测。结果表明：该模型平均绝对误差为0．9167mm,平均相对误差为4．2737%,较其他模型预测精度高,综合性能好,将其运用于露天矿边坡变形量预测研究具有较好的适用性和可靠性。
為實現邊坡危險性及時預警預報,以露天礦邊坡變形量為研究對象,提齣採用七項影響指標作為邊坡位移變形量的響應參數,建立支持嚮量機迴歸預測模型( SVR)。引入脩正的果蠅優化算法( MFOA)對模型參數進行優化,構建基于MFOA-SVR露天礦邊坡變形量協同預測模型,併以實際鑑測數據進行模型倣真預測。結果錶明：該模型平均絕對誤差為0．9167mm,平均相對誤差為4．2737%,較其他模型預測精度高,綜閤性能好,將其運用于露天礦邊坡變形量預測研究具有較好的適用性和可靠性。
위실현변파위험성급시예경예보,이로천광변파변형량위연구대상,제출채용칠항영향지표작위변파위이변형량적향응삼수,건립지지향량궤회귀예측모형( SVR)。인입수정적과승우화산법( MFOA)대모형삼수진행우화,구건기우MFOA-SVR로천광변파변형량협동예측모형,병이실제감측수거진행모형방진예측。결과표명：해모형평균절대오차위0．9167mm,평균상대오차위4．2737%,교기타모형예측정도고,종합성능호,장기운용우로천광변파변형량예측연구구유교호적괄용성화가고성。
In order to achieve the timely warning and forecasting of slope hazard, taking the slope deformation of open-pit mine as study object, it was proposed to establish the support vector machine regression model ( SVR) by adopting 7 influence indexes as the response parameters of slope displacement and deformation. The modified fruit fly optimization algorithm ( MFOA) was introduced to optimize the parameters of model. The collaborative forecas-ting model of slope deformation in open-pit mine based on MFOA-SVR was established, and the simulation and forecast of the model were conducted by practical monitoring data. The results showed that the mean absolute error of the model is 0. 9167 mm, and the mean relative error is 4. 2737%, which had higher precision and better com-prehensive performance than other models. It has a good applicability and reliability when used in forecasting of slope deformation in open-pit mine.
