Research On Real-time Data Archiving And Temperature Prediction Technology Of Smart Utility Tunnel

The utility tunnel is known as a public engineering tunnel or multifunctional tunnel.It is an attachment to the urban underground structure.It can accommodate two or more types of urban engineering tunnels,including heat,communication,electricity,petroleum gas,and drainage tunnel,that is an important part in the current city development.Once a fire occurs in the utility tunnel,the normal operation of the entire city will be affected.Utility tunnel fires are mainly caused by excessive cable temperatures,so it is particularly important to predict the temperature of utility tunnel cables.For temperature prediction,real-time data archiving is required.In view of the above problems,the following research contents are carried out in this article:(1)An online archiving method based on the standardized protocol of the utility tunnel is proposed to realize the online archiving of data and complete the analysis of the complex protocol of the utility tunnel.(2)An LSTM neural network model is suitable for prediction of utility tunnel temperature data is proposed.Based on the British Electric company underground cable temperature data set,two traditional machine learning time series prediction models(ARIMA model,Holt-Winters model)and two neural networks(BP neural network,LSTM neural network)were used for prediction.The results showed that the prediction accuracy of the network model is higher than that of traditional machine learning models,and the LSTM prediction accuracy is the highest in neural networks.(3)The entire utility tunnel simulation system is designed and constructed to realize the temperature collection of the utility tunnel cables,real-time prediction of temperature data,and also alarm for abnormal data.The contribution of this paper lies in the realization of data archiving and real-time data display and prediction of archived data,the establishment of an LSTM neural network model is suitable for the temperature data prediction of the utility tunnel,and the temperature early warning is realized,which helps managers to make decisions and improves decision-making quality.