Design and field implementation of an impact detection system using committees of neural networks

作者：

Highlights：

• Features are extracted from raw bridge acceleration data from 8 bridges to provide network training data; no FE models are necessary for training.

• Multiple neural network voting ensemble configurations are presented.

• Impact detection ranges from 91 −100% while average false positive rates are 0.00–0.75%.

摘要

•Features are extracted from raw bridge acceleration data from 8 bridges to provide network training data; no FE models are necessary for training.•Multiple neural network voting ensemble configurations are presented.•Impact detection ranges from 91 −100% while average false positive rates are 0.00–0.75%.

论文关键词：Bridge impacts,Impact detection,Signal classification,Feature selection,Artificial neural networks

论文评审过程：Received 20 February 2018, Revised 4 October 2018, Accepted 4 November 2018, Available online 6 November 2018, Version of Record 23 November 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.11.005