CAJ | 학술논문

为了预报黄河内蒙古段的流凌和封开河日期，以多元线性回归理论与人工神经网络理论为基础，设计开发了黄河内蒙古段冰情预报系统预报内蒙古段各个站点的流凌和封开河日期。选用黄河内蒙古段水文、气象和冰情信息建立数据库，应用ADO OLEDB技术调用数据库，建立符合相关性要求的人工神经网络模型和多元线性回归模型，从而实现预报识别检验。使用2003-2004年度至2007-2008年度5年的资料进行预报检验，并与实际开河日期对比分析，预报结果合格率为80%和67.7%，分别达到甲等和丙等预报精度，表明系统可以应用于黄河内蒙古段的冰情预报。
위료예보황하내몽고단적류릉화봉개하일기，이다원선성회귀이론여인공신경망락이론위기출，설계개발료황하내몽고단빙정예보계통예보내몽고단각개참점적류릉화봉개하일기。선용황하내몽고단수문、기상화빙정신식건립수거고，응용ADO OLEDB기술조용수거고，건립부합상관성요구적인공신경망락모형화다원선성회귀모형，종이실현예보식별검험。사용2003-2004년도지2007-2008년도5년적자료진행예보검험，병여실제개하일기대비분석，예보결과합격솔위80%화67.7%，분별체도갑등화병등예보정도，표명계통가이응용우황하내몽고단적빙정예보。
In order to forecast the date of ice-run, freeze-up and break-up, the forecasting system of ice conditions in Inner Mongolia section of the Yellow River has been designed and developed at every station based on the theory of multiple linear regression and artificial neural network theory. After selecting hydrological, meteorological and ice information the system has established a database, which can be called by applying ADO OLEDB technology. Additionally, the models of artificial neural network and multiple linear regression are used to realize the prediction, identification, and inspection. The overall results based on the data of 5 years from 2003-2004 to 2007-2008 employed in the prediction test, the qualified rate of the forecast results is respectively 80% and 67.7%. These, respectively reaches the first and third class forecasting scheme, indicating that the system can be applied to forecast the date of ice-run, freeze-up and break-up in Inner Mongolia section of the Yellow River.