首页> 外国专利> WATER LEVEL PREDICTION METHOD, WATER LEVEL PREDICTION PROGRAM, AND WATER LEVEL PREDICTION DEVICE

WATER LEVEL PREDICTION METHOD, WATER LEVEL PREDICTION PROGRAM, AND WATER LEVEL PREDICTION DEVICE

机译:水位预测方法,水位预测程序和水位预测装置

摘要

PROBLEM TO BE SOLVED: To appropriately extract input data and thereby predict a water level with sufficient high accuracy and reduce an amount of calculation when utilizing a neural network in order to predict a water level in a river, a dam or a sewage.;SOLUTION: The present disclosure is a water level prediction method characterized by including, in order: a training data extraction step E of extracting precipitation and water level training data needed for the learning of a water level at a water level prediction point and given time of day and having a high correlation with the water level at the water level prediction point and the time of day; and training data learning steps C1-C4 of learning, using a neural network, the extracted precipitation and the water level training data having a high correlation with the water level at the water level prediction point and the time of day.;SELECTED DRAWING: Figure 1;COPYRIGHT: (C)2019,JPO&INPIT
机译:解决的问题:适当提取输入数据,从而以足够的高精度预测水位,并在利用神经网络预测河流,水坝或污水中的水位时减少计算量。 :本公开是水位预测方法,其特征在于,依次包括:训练数据提取步骤E,其提取在水位预测点和一天中的给定时间学习水位所需的降水量和水位训练数据。与水位预测点的水位和一天中的时间高度相关;训练数据学习步骤C1-C4,使用神经网络进行学习,提取的降水量和水位训练数据与水位预测点和一天中的时间的水位高度相关。 1;版权:(C)2019,日本特许厅&INPIT

著录项

  • 公开/公告号JP2019095240A

    专利类型

  • 公开/公告日2019-06-20

    原文格式PDF

  • 申请/专利权人 JAPAN RADIO CO LTD;

    申请/专利号JP20170223040

  • 发明设计人 YOSHIDA SHIGEJI;KATO ASAKO;

    申请日2017-11-20

  • 分类号G01W1;G06Q50/26;E02B3;

  • 国家 JP

  • 入库时间 2022-08-21 12:25:10

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号