Application of neural networks and wavelet transform in SHM

Application of neural networks and wavelet transform in SHM. Rahman, M. & Bagchi, A. In volume 2, pages 834 - 843, St. Johns, NL, Canada, 2009. High volumes;Input and outputs;Performance parameters;Sensor data;Structural condition;Structural health monitoring (SHM);Temperature gauges;Time-periods;
abstract bibtex

Structural Health Monitoring (SHM) has recently emerged as a useful tool for tracking the performance parameters of a structure such as strain, deflection, and acceleration through a series of sensors installed on them. For effective monitoring, interpretation of the monitoring data and isolating the unusual or novel events from high volume of sensor data, both Artificial Neural Networks (ANN) and Wavelet Transform (WT) are found to be very useful. In this study the sensor data from Canadian bridge have been utilized to develop ANN and WT-based methods for processing the SHM data and assessing the structural conditions. The neural network is constructed with sixteen input nodes accepting data from fifteen strain gauges and one temperature gauge, and the data from the remaining gauge is used as the target. The data collected at different time periods are tested against the trained network to find the pattern of difference in the inter-relation between the input and output data series'. The wavelet transform technique has been used for de-noising the sensor data before using them in the neural networks. The paper gives an overview of the study and presents the key results demonstrating the feasibility and usefulness of the proposed methods in interpreting SHM data.

@inproceedings{20100112604192 ,
language = {English},
copyright = {Compilation and indexing terms, Copyright 2023 Elsevier Inc.},
copyright = {Compendex},
title = {Application of neural networks and wavelet transform in SHM},
journal = {Proceedings, Annual Conference - Canadian Society for Civil Engineering},
author = {Rahman, Mahabubur and Bagchi, Ashutosh},
volume = {2},
year = {2009},
pages = {834 - 843},
address = {St. Johns, NL, Canada},
abstract = {Structural Health Monitoring (SHM) has recently emerged as a useful tool for tracking the performance parameters of a structure such as strain, deflection, and acceleration through a series of sensors installed on them. For effective monitoring, interpretation of the monitoring data and isolating the unusual or novel events from high volume of sensor data, both Artificial Neural Networks (ANN) and Wavelet Transform (WT) are found to be very useful. In this study the sensor data from Canadian bridge have been utilized to develop ANN and WT-based methods for processing the SHM data and assessing the structural conditions. The neural network is constructed with sixteen input nodes accepting data from fifteen strain gauges and one temperature gauge, and the data from the remaining gauge is used as the target. The data collected at different time periods are tested against the trained network to find the pattern of difference in the inter-relation between the input and output data series'. The wavelet transform technique has been used for de-noising the sensor data before using them in the neural networks. The paper gives an overview of the study and presents the key results demonstrating the feasibility and usefulness of the proposed methods in interpreting SHM data.<br/>},
key = {Structural health monitoring},
keywords = {Wavelet transforms;Neural networks;Data handling;},
note = {High volumes;Input and outputs;Performance parameters;Sensor data;Structural condition;Structural health monitoring (SHM);Temperature gauges;Time-periods;},
}

Downloads: 0

{"_id":"5G2mr8PMGbHzxyCbQ","bibbaseid":"rahman-bagchi-applicationofneuralnetworksandwavelettransforminshm-2009","author_short":["Rahman, M.","Bagchi, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","language":"English","copyright":"Compendex","title":"Application of neural networks and wavelet transform in SHM","journal":"Proceedings, Annual Conference - Canadian Society for Civil Engineering","author":[{"propositions":[],"lastnames":["Rahman"],"firstnames":["Mahabubur"],"suffixes":[]},{"propositions":[],"lastnames":["Bagchi"],"firstnames":["Ashutosh"],"suffixes":[]}],"volume":"2","year":"2009","pages":"834 - 843","address":"St. Johns, NL, Canada","abstract":"Structural Health Monitoring (SHM) has recently emerged as a useful tool for tracking the performance parameters of a structure such as strain, deflection, and acceleration through a series of sensors installed on them. For effective monitoring, interpretation of the monitoring data and isolating the unusual or novel events from high volume of sensor data, both Artificial Neural Networks (ANN) and Wavelet Transform (WT) are found to be very useful. In this study the sensor data from Canadian bridge have been utilized to develop ANN and WT-based methods for processing the SHM data and assessing the structural conditions. The neural network is constructed with sixteen input nodes accepting data from fifteen strain gauges and one temperature gauge, and the data from the remaining gauge is used as the target. The data collected at different time periods are tested against the trained network to find the pattern of difference in the inter-relation between the input and output data series'. The wavelet transform technique has been used for de-noising the sensor data before using them in the neural networks. The paper gives an overview of the study and presents the key results demonstrating the feasibility and usefulness of the proposed methods in interpreting SHM data.<br/>","key":"20100112604192","keywords":"Wavelet transforms;Neural networks;Data handling;","note":"High volumes;Input and outputs;Performance parameters;Sensor data;Structural condition;Structural health monitoring (SHM);Temperature gauges;Time-periods;","bibtex":"@inproceedings{20100112604192 ,\nlanguage = {English},\ncopyright = {Compilation and indexing terms, Copyright 2023 Elsevier Inc.},\ncopyright = {Compendex},\ntitle = {Application of neural networks and wavelet transform in SHM},\njournal = {Proceedings, Annual Conference - Canadian Society for Civil Engineering},\nauthor = {Rahman, Mahabubur and Bagchi, Ashutosh},\nvolume = {2},\nyear = {2009},\npages = {834 - 843},\naddress = {St. Johns, NL, Canada},\nabstract = {Structural Health Monitoring (SHM) has recently emerged as a useful tool for tracking the performance parameters of a structure such as strain, deflection, and acceleration through a series of sensors installed on them. For effective monitoring, interpretation of the monitoring data and isolating the unusual or novel events from high volume of sensor data, both Artificial Neural Networks (ANN) and Wavelet Transform (WT) are found to be very useful. In this study the sensor data from Canadian bridge have been utilized to develop ANN and WT-based methods for processing the SHM data and assessing the structural conditions. The neural network is constructed with sixteen input nodes accepting data from fifteen strain gauges and one temperature gauge, and the data from the remaining gauge is used as the target. The data collected at different time periods are tested against the trained network to find the pattern of difference in the inter-relation between the input and output data series'. The wavelet transform technique has been used for de-noising the sensor data before using them in the neural networks. The paper gives an overview of the study and presents the key results demonstrating the feasibility and usefulness of the proposed methods in interpreting SHM data.<br/>},\nkey = {Structural health monitoring},\nkeywords = {Wavelet transforms;Neural networks;Data handling;},\nnote = {High volumes;Input and outputs;Performance parameters;Sensor data;Structural condition;Structural health monitoring (SHM);Temperature gauges;Time-periods;},\n} \n\n\n","author_short":["Rahman, M.","Bagchi, A."],"id":"20100112604192","bibbaseid":"rahman-bagchi-applicationofneuralnetworksandwavelettransforminshm-2009","role":"author","urls":{},"keyword":["Wavelet transforms;Neural networks;Data handling;"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/m3A3cns49MKmeRzt5","dataSources":["uT2zXYMHTeKLr3NSv","6Aw5QAtT2yLJ3d2JP","qBPxBjrzghRQ4Wzbf","EnwwBMFxopKkypo2f","8uWbXNBCDiEboMj8h"],"keywords":["wavelet transforms;neural networks;data handling;"],"search_terms":["application","neural","networks","wavelet","transform","shm","rahman","bagchi"],"title":"Application of neural networks and wavelet transform in SHM","year":2009}