In this paper, T639 global spectral model numerical forecast products issued by numerical prediction center of China Meteorological Administration and precipitation data at 676 regional stations of Gansu during flood ...In this paper, T639 global spectral model numerical forecast products issued by numerical prediction center of China Meteorological Administration and precipitation data at 676 regional stations of Gansu during flood season were used firstly for interpretation. Then, through the establishment of multiple linear stepwise regression equation, daily precipitation forecast with the time interval of 6 h during 0 -72 h in May, 2013 in Gansu Province was obtained. By precipitation forecast verification analysis, it was found that the precipitation forecast in Hexi region and central Gansu Province had best effect; forecast in some places of east Hedong region had relatively good effect; part of the city or state forecast effect in the plateau slope zone was relatively lower. The refined precipitation forecast had certain reference and use value in the post-production Gansu Province highway forecasting during flood season.展开更多
This paper adopts data mining(DM) technique and fuzzy system theory for robust time series forecasting.By introducing DM technique,the fuzzy rule extraction algorithm is improved to be more robust with the noises and ...This paper adopts data mining(DM) technique and fuzzy system theory for robust time series forecasting.By introducing DM technique,the fuzzy rule extraction algorithm is improved to be more robust with the noises and outliers in time series.Then,the constructed fuzzy inference system(FIS) is optimized with a partition refining strategy to balance the system's accuracy and complexity.The proposed algorithm is compared with the WangMendel(WM) method,a benchmark method for building FIS,in comprehensive analysis of robustness.In the classical Mackey-Glass time series forecasting,the simulation results prove that the proposed method is able to predict time series with random perturbation more accurately.For the practical application,the proposed FIS is applied to predicting the time series of ship maneuvering motion.To obtain actual time series data records,the ship maneuvering motion trial is conducted in the Yukun ship of Dalian Maritime University in China.The time series forecasting results show that the FIS constructed with DM concepts can forecast ship maneuvering motion robustly and effectively.展开更多
基金Supported by Achievement Transformation Project of Gansu Provincial Meteorological Bureau,China(2014-19)General Program of Gansu Provincial Meteorological Bureau,China(2015-05)
文摘In this paper, T639 global spectral model numerical forecast products issued by numerical prediction center of China Meteorological Administration and precipitation data at 676 regional stations of Gansu during flood season were used firstly for interpretation. Then, through the establishment of multiple linear stepwise regression equation, daily precipitation forecast with the time interval of 6 h during 0 -72 h in May, 2013 in Gansu Province was obtained. By precipitation forecast verification analysis, it was found that the precipitation forecast in Hexi region and central Gansu Province had best effect; forecast in some places of east Hedong region had relatively good effect; part of the city or state forecast effect in the plateau slope zone was relatively lower. The refined precipitation forecast had certain reference and use value in the post-production Gansu Province highway forecasting during flood season.
基金the Fundamental Research Funds for the Central Universities,China(No.01750307)the Doctoral Scientific Research Foundation of Liaoning Province,China(No.201501188)
文摘This paper adopts data mining(DM) technique and fuzzy system theory for robust time series forecasting.By introducing DM technique,the fuzzy rule extraction algorithm is improved to be more robust with the noises and outliers in time series.Then,the constructed fuzzy inference system(FIS) is optimized with a partition refining strategy to balance the system's accuracy and complexity.The proposed algorithm is compared with the WangMendel(WM) method,a benchmark method for building FIS,in comprehensive analysis of robustness.In the classical Mackey-Glass time series forecasting,the simulation results prove that the proposed method is able to predict time series with random perturbation more accurately.For the practical application,the proposed FIS is applied to predicting the time series of ship maneuvering motion.To obtain actual time series data records,the ship maneuvering motion trial is conducted in the Yukun ship of Dalian Maritime University in China.The time series forecasting results show that the FIS constructed with DM concepts can forecast ship maneuvering motion robustly and effectively.
