Abstract
In this study, a simple and customizable convolution neural network framework was used to train a vibration classification model that can be integrated into the measurement application in order to realize accurate and real-time bridge vibration status on mobile platforms. The inputs for the network model are basically the multichannel time-series signals acquired from the built-in accelerometer sensor of smartphones, while the outputs are the predefined vibration categories. To verify the effectiveness of the proposed framework, data collected from long-term monitoring of bridge were used for training a model, and its classification performance was evaluated on the test set constituting the data collected from the same bridge but not used previously for training. An iOS application program was developed on the smartphone for incorporating the trained model with predefined classification labels so that it can classify vibration datasets measured on any other bridges in real-time. The results justify the practical feasibility of using a low-latency, high-accuracy smartphone-based system amid which bottlenecks of processing large amounts of data will be eliminated, and stable observation of structural conditions can be promoted.
Highlights
Recent incidents such as the collapse of the I-35W Bridge in the US or the Morandi Bridge inItaly raise questions about the safety of ageing infrastructures and give a clear indication of the importance of structural health monitoring (SHM)
As the network grows deeper, the model complexity increases correspondingly, and even a relatively small network involves millions of parameters to classify the time series data. Such costly computation complexity makes the deployment of convolution neural network (CNN) models unaffordable for common PCs and mobile devices and has not been practiced in real-time vibration classification purposes at the same time
There are neither any faulty records nor an earthquake record, which are not predicted by the classifier. These results demonstrate the accuracy and viability of autonomous bridge vibration realization using smartphones
Summary
Recent incidents such as the collapse of the I-35W Bridge in the US or the Morandi Bridge in. With the use of low-cost measurement systems such as WSSNs, most of the long-term vibration data inevitably contain nonstationary noise which usually occurs due to changing environmental effects and sensor-sourced faulty signals. As the network grows deeper, the model complexity increases correspondingly, and even a relatively small network involves millions of parameters to classify the time series data Such costly computation complexity makes the deployment of CNN models unaffordable for common PCs and mobile devices and has not been practiced in real-time vibration classification purposes at the same time. Realizing the advancement in the application of smartphones for SHM, these are used as a quick bridge vibration status monitoring kit in this study For this purpose, first of all, a simple yet computationally efficient convolution neural network-based framework has been investigated. The framework is integrated into a measurement application that performs a real-time classification of measured records from smartphones by exploiting relationships in sensor inputs and automatically extracting distinct features in time domain
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
