BP neural network recognition algorithm for scour monitoring of subsea pipelines based on active thermometry

Scour monitoring is an important concern for subsea pipeline systems. The active-thermometry-based scour monitoring is based on the difference of heat transfer properties between sediment and sand, recognizes the surrounding media though temperature changing patterns during heating and cooling processes, and hence detects the free spans. Based on the scour monitoring system, a two-layer BP neural network was employed to process the monitoring data and achieved media recognition. The network's inputs were normalized temperature time histories. The network's outputs denoted different media: sediment and water. To validate the method, three experiments were conducted; one was used for training the network and the other two for testing. Also, the effect of noise on the network's performance was studied through simulation. The results demonstrated the feasibility and robustness of the neural network.