首页>
外国专利>
Method of estimating flow rate and of detecting leak of wide area water using recurrent analysis recurrent neural network and deep neural network
Method of estimating flow rate and of detecting leak of wide area water using recurrent analysis recurrent neural network and deep neural network
展开▼
机译:递归分析递归神经网络和深度神经网络估计流量和检测广域水泄漏的方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
According to the present invention, the present invention relates to a method for estimating a flow rate and detecting a leak of wide area water supply using regression analysis, a regression neural network and a deep neural network. The method comprises: a sensor data pretreatment process of pretreating sensor data for pressure and a flow rate in accordance with time in a conduit; a flow rate prediction process of evaluating a regression analysis model and a trained deep neutral network (DNN) model, selecting a flow rate prediction model, and using the flow rate prediction model to predict a flow rate; and a leak determination process of using a leak detection model and an abnormality detection model in accordance with the trained DNN model to determine a leak and a leak occurrence point in the conduit. Therefore, the present invention can predict the flow rate in the conduit with high accuracy by using the flow rate and pressure measured in the conduit, and a difference of the flow rate and the difference of the pressure calculated by the flow rate and the pressure.
展开▼