Abstract
During fire incidents, it is imperative to monitor the flow rate of the fire hoses. Due to the constraints imposed by the fire scene, vibration-based flow measurement technique has shown great potential. However, usage of single frequency or statistic feature to predict flow rate is prone to influenced by outer noise. In this study, we constructed a dataset for fire-hose flow rate prediction task with a flow rate range of 0.35 L/s to 20.00 L/s, and sample frequency of 50 kHz. On that basis, a new variant of residual network, i.e., an RBU-STMS has been developed, integrating soft thresholding and feature pyramid mechanism. Evaluation result on the dataset has proven the effectiveness of the developed model which yields improvement of 3.85 % and 4.05 % by incorporating the two mechanisms individually and an overall improvement of 5.00 % by combining both mechanisms, compared to the conventional residual network. Furthermore, the proposed model exhibits a considerable tolerance to noisy inputs, with a predicted error rate of only 8.06 % when subjected to a 10 % standard deviation of random noise in the input, remaining below the 10 % threshold.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call