Research On Cooperative Control Method Of Water Distribution Network Based On Time Series Analysis

In recent years,with the rapid development of China's economy and the continuous improvement of national living standards,the public put forward higher requirements for water pressure and water quality.Non-negative pressure water supply has been widely used as it can effectively reduce the secondary water supply pollution and effectively improve the water pressure.Secondary water supply equipment operation and maintenance problems,energy conservation problems,the problem of reduce the impact of water supply equipment on the city water supply network,become the problems to be addressed in water supply industry.Accurate predictive control can effectively reduce the pressure impact of the secondary water supply equipment on the urban water supply network,reduce the pressure fluctuation of the water supply network,and improve the operation of the water main pipe network and its surrounding water supply pipe network stability.Based on the technology of Internet of Things,the thesis uses time series analysis and predictive control technology to predict and control the remote water supply facilities.The main work includes the following aspects:Firstly,this thesis combines the characteristics of water supply infrastructure and Internet of Things,and realizes remote data collection and remote control of water supply equipment.The data acquisition hardware module is designed,and the data communication between the collector and the PLC is realized by Modbus,the data communication between the collector and the server is realized by Ethernet and GPRS,including the collector read real-time water supply data from the PLC,and the collectors can upload water supply state data to remote servers and the servers can send remote control commands to the collectors.The collectors can send text messages,which ensures that when anomalies occur in water pipe network,management servers can notify the remote collector to send alarm information to improve the operation and maintenance efficiency of water supply network in time,and it will effectively reduce operation and maintenance costs.Secondly,the data collected from the water supply facilities are analyzed by using time series technology.The time series of daily water supply data have obvious periodicity and trend,and the seasonal ARIMA model is used to predict water supply data.After using the model to predict the water supply data,the error between the prediction result and the actual value is small,and the prediction accuracy is good.When a pipe burst or other exception occurs,the water pressure will have a big change,for this reason,this thesis proposes to determine and locate the anomaly by calculating the abnormal degree of water pressure between different collection points.Then,on the basis of discussing the methods and techniques of collaborative control,this paper focuses on the common scheme of pipe burst detection in water supply network,and puts forward the application of district metered area(DMA)and distributed model predictive control(DMPC)in the remote control of the water supply pipe network,and completed the model design and simulation.Finally,the topology and overall structure of the collaborative control system are introduced in this thesis,and the effect of the forecasting control solution of the water supply network is analyzed.The results show that the system can effectively predict and control the water supply network,and has a good application prospect in the water supply industry,and is adaptable in other similar scenarios.