Abstract:

In order to improve the accuracy of data uploading by central heating system, the identification method of error data is studied. Three methods including wavelet filtering, median filtering and error back propagation (BP) neural network are applied by the heat exchange station in the heating system. The data uploaded by the first level network traffic sensor are used to detect the error, and the results detected by the three methods are compared. It is concluded that the error detection method with the median filtering is the best.

Key words:

Keywords:heating system, wavelet filtering, median filtering, error back propagation neural network, fault error detection