Use of artificial neural networks for real time analysis of dam monitoring data. Ahmadi Nedushan, B. & Chouinard, L. In volume 2003, pages 1987 - 1994, Moncton, NB, Canada, 2003. Automatic monitoring;Dam monitoring data;Multiple linear regression;abstract bibtex Automatic instrumentation and data acquisition systems are commonly used to monitor the real time behavior of large constructed facilities such as concrete dams. Monitoring systems produce a large quantity of data, which has to be managed, processed and analyzed, and in the case of automatic monitoring, in real time. Forecasting of displacements, stresses and flows are used to detect the onset of anomalies. Traditionally, statistical models such as multiple linear regression have been used to estimate the response of individual instruments. An alternative to regression models are neural network models, which have been widely used in the field of pattern identification, dynamic system prediction and optimization. In this article back propagation neural network models are used to forecast displacements of a gravity dam. Results indicate that neural networks can be efficiently used as an alternative modeling procedure in the analysis of monitoring data.
@inproceedings{2006169828805 ,
language = {English},
copyright = {Compilation and indexing terms, Copyright 2023 Elsevier Inc.},
copyright = {Compendex},
title = {Use of artificial neural networks for real time analysis of dam monitoring data},
journal = {Proceedings, Annual Conference - Canadian Society for Civil Engineering},
author = {Ahmadi Nedushan, B. and Chouinard, L.E.},
volume = {2003},
year = {2003},
pages = {1987 - 1994},
address = {Moncton, NB, Canada},
abstract = {Automatic instrumentation and data acquisition systems are commonly used to monitor the real time behavior of large constructed facilities such as concrete dams. Monitoring systems produce a large quantity of data, which has to be managed, processed and analyzed, and in the case of automatic monitoring, in real time. Forecasting of displacements, stresses and flows are used to detect the onset of anomalies. Traditionally, statistical models such as multiple linear regression have been used to estimate the response of individual instruments. An alternative to regression models are neural network models, which have been widely used in the field of pattern identification, dynamic system prediction and optimization. In this article back propagation neural network models are used to forecast displacements of a gravity dam. Results indicate that neural networks can be efficiently used as an alternative modeling procedure in the analysis of monitoring data.},
key = {Neural networks},
keywords = {Concrete dams;Condition monitoring;Data acquisition;Optimization;Real time systems;Regression analysis;},
note = {Automatic monitoring;Dam monitoring data;Multiple linear regression;},
}
Downloads: 0
{"_id":"DnZrLMAv64weGehm5","bibbaseid":"ahmadinedushan-chouinard-useofartificialneuralnetworksforrealtimeanalysisofdammonitoringdata-2003","author_short":["Ahmadi Nedushan, B.","Chouinard, L."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","language":"English","copyright":"Compendex","title":"Use of artificial neural networks for real time analysis of dam monitoring data","journal":"Proceedings, Annual Conference - Canadian Society for Civil Engineering","author":[{"propositions":[],"lastnames":["Ahmadi","Nedushan"],"firstnames":["B."],"suffixes":[]},{"propositions":[],"lastnames":["Chouinard"],"firstnames":["L.E."],"suffixes":[]}],"volume":"2003","year":"2003","pages":"1987 - 1994","address":"Moncton, NB, Canada","abstract":"Automatic instrumentation and data acquisition systems are commonly used to monitor the real time behavior of large constructed facilities such as concrete dams. Monitoring systems produce a large quantity of data, which has to be managed, processed and analyzed, and in the case of automatic monitoring, in real time. Forecasting of displacements, stresses and flows are used to detect the onset of anomalies. Traditionally, statistical models such as multiple linear regression have been used to estimate the response of individual instruments. An alternative to regression models are neural network models, which have been widely used in the field of pattern identification, dynamic system prediction and optimization. In this article back propagation neural network models are used to forecast displacements of a gravity dam. Results indicate that neural networks can be efficiently used as an alternative modeling procedure in the analysis of monitoring data.","key":"2006169828805","keywords":"Concrete dams;Condition monitoring;Data acquisition;Optimization;Real time systems;Regression analysis;","note":"Automatic monitoring;Dam monitoring data;Multiple linear regression;","bibtex":"@inproceedings{2006169828805 ,\nlanguage = {English},\ncopyright = {Compilation and indexing terms, Copyright 2023 Elsevier Inc.},\ncopyright = {Compendex},\ntitle = {Use of artificial neural networks for real time analysis of dam monitoring data},\njournal = {Proceedings, Annual Conference - Canadian Society for Civil Engineering},\nauthor = {Ahmadi Nedushan, B. and Chouinard, L.E.},\nvolume = {2003},\nyear = {2003},\npages = {1987 - 1994},\naddress = {Moncton, NB, Canada},\nabstract = {Automatic instrumentation and data acquisition systems are commonly used to monitor the real time behavior of large constructed facilities such as concrete dams. Monitoring systems produce a large quantity of data, which has to be managed, processed and analyzed, and in the case of automatic monitoring, in real time. Forecasting of displacements, stresses and flows are used to detect the onset of anomalies. Traditionally, statistical models such as multiple linear regression have been used to estimate the response of individual instruments. An alternative to regression models are neural network models, which have been widely used in the field of pattern identification, dynamic system prediction and optimization. In this article back propagation neural network models are used to forecast displacements of a gravity dam. Results indicate that neural networks can be efficiently used as an alternative modeling procedure in the analysis of monitoring data.},\nkey = {Neural networks},\nkeywords = {Concrete dams;Condition monitoring;Data acquisition;Optimization;Real time systems;Regression analysis;},\nnote = {Automatic monitoring;Dam monitoring data;Multiple linear regression;},\n} \n\n\n","author_short":["Ahmadi Nedushan, B.","Chouinard, L."],"id":"2006169828805","bibbaseid":"ahmadinedushan-chouinard-useofartificialneuralnetworksforrealtimeanalysisofdammonitoringdata-2003","role":"author","urls":{},"keyword":["Concrete dams;Condition monitoring;Data acquisition;Optimization;Real time systems;Regression analysis;"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/m3A3cns49MKmeRzt5","dataSources":["uT2zXYMHTeKLr3NSv","6Aw5QAtT2yLJ3d2JP","qBPxBjrzghRQ4Wzbf","EnwwBMFxopKkypo2f","8uWbXNBCDiEboMj8h"],"keywords":["concrete dams;condition monitoring;data acquisition;optimization;real time systems;regression analysis;"],"search_terms":["use","artificial","neural","networks","real","time","analysis","dam","monitoring","data","ahmadi nedushan","chouinard"],"title":"Use of artificial neural networks for real time analysis of dam monitoring data","year":2003}