The study of data fusion for high suspended sediment concentration measuring based on BP neural network

In order to eliminate the influence of environmental factors, a data fusion algorithm was applied for measuring high suspended sediment concentration (HSSC) in the Yellow River. The principle of the capacitive differential pressure (CDP) method for measuring HSSC was briefed on. The effects of environmental factors such as temperature, depth and flow rate on CDP sensors were studied. And the data fusion method of back propagation (BP) neural network was introduced. A hardware platform, which based on Internet of Things (IoT) with a programmable logic controller (PLC) and ZigBee Network, was designed. Sediment concentration, temperature, depth, and flow rate data were distributed collected and sent to the monitoring computers for real-time display through ZigBee Network. To test the fusion effect of the BP method, the sediment concentration data were also processed using unary linear regression (ULR) and multiple linear regression (MLR). The results showed that the CDP method based on the BP data fusion can effectively eliminate environmental influences and raise the measuring accuracy of the measuring system.