A Machine Learning Approach to Bridge-Damage Detection Using Responses Measured on a Passing Vehicle
This paper proposes a new two-stage machine learning approach for bridge damage detection using the responses measured on a passing vehicle. In the first stage, an artificial neural network (ANN) is trained using the vehicle responses measured from multiple passes (training data set) over a healthy...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/18/4035 |
| _version_ | 1811184602821165056 |
|---|---|
| author | Abdollah Malekjafarian Fatemeh Golpayegani Callum Moloney Siobhán Clarke |
| author_facet | Abdollah Malekjafarian Fatemeh Golpayegani Callum Moloney Siobhán Clarke |
| author_sort | Abdollah Malekjafarian |
| collection | DOAJ |
| description | This paper proposes a new two-stage machine learning approach for bridge damage detection using the responses measured on a passing vehicle. In the first stage, an artificial neural network (ANN) is trained using the vehicle responses measured from multiple passes (training data set) over a healthy bridge. The vehicle acceleration or Discrete Fourier Transform (DFT) spectrum of the acceleration is used. The vehicle response is predicted from its speed for multiple passes (monitoring data set) over the bridge. Root-mean-square error is used to calculate the prediction error, which indicates the differences between the predicted and measured responses for each passage. In the second stage of the proposed method, a damage indicator is defined using a Gaussian process that detects the changes in the distribution of the prediction errors. It is suggested that if the bridge condition is healthy, the distribution of the prediction errors will remain low. A recognizable change in the distribution might indicate a damage in the bridge. The performance of the proposed approach was evaluated using numerical case studies of vehicle−bridge interaction. It was demonstrated that the approach could successfully detect the damage in the presence of road roughness profile and measurement noise, even for low damage levels. |
| first_indexed | 2024-04-11T13:15:07Z |
| format | Article |
| id | doaj.art-b70a44b8f207456fa96f5287ce2aa2e0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:15:07Z |
| publishDate | 2019-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b70a44b8f207456fa96f5287ce2aa2e02022-12-22T04:22:25ZengMDPI AGSensors1424-82202019-09-011918403510.3390/s19184035s19184035A Machine Learning Approach to Bridge-Damage Detection Using Responses Measured on a Passing VehicleAbdollah Malekjafarian0Fatemeh Golpayegani1Callum Moloney2Siobhán Clarke3School of Civil Engineering, University College Dublin, Dublin, IrelandSchool of Computer Science, University College Dublin, Dublin, IrelandSchool of Civil Engineering, University College Dublin, Dublin, IrelandSchool of Computer Science and Statistics, Trinity College Dublin, Dublin, IrelandThis paper proposes a new two-stage machine learning approach for bridge damage detection using the responses measured on a passing vehicle. In the first stage, an artificial neural network (ANN) is trained using the vehicle responses measured from multiple passes (training data set) over a healthy bridge. The vehicle acceleration or Discrete Fourier Transform (DFT) spectrum of the acceleration is used. The vehicle response is predicted from its speed for multiple passes (monitoring data set) over the bridge. Root-mean-square error is used to calculate the prediction error, which indicates the differences between the predicted and measured responses for each passage. In the second stage of the proposed method, a damage indicator is defined using a Gaussian process that detects the changes in the distribution of the prediction errors. It is suggested that if the bridge condition is healthy, the distribution of the prediction errors will remain low. A recognizable change in the distribution might indicate a damage in the bridge. The performance of the proposed approach was evaluated using numerical case studies of vehicle−bridge interaction. It was demonstrated that the approach could successfully detect the damage in the presence of road roughness profile and measurement noise, even for low damage levels.https://www.mdpi.com/1424-8220/19/18/4035drive-bybridgedamage detectionmachine learningartificial neural network |
| spellingShingle | Abdollah Malekjafarian Fatemeh Golpayegani Callum Moloney Siobhán Clarke A Machine Learning Approach to Bridge-Damage Detection Using Responses Measured on a Passing Vehicle Sensors drive-by bridge damage detection machine learning artificial neural network |
| title | A Machine Learning Approach to Bridge-Damage Detection Using Responses Measured on a Passing Vehicle |
| title_full | A Machine Learning Approach to Bridge-Damage Detection Using Responses Measured on a Passing Vehicle |
| title_fullStr | A Machine Learning Approach to Bridge-Damage Detection Using Responses Measured on a Passing Vehicle |
| title_full_unstemmed | A Machine Learning Approach to Bridge-Damage Detection Using Responses Measured on a Passing Vehicle |
| title_short | A Machine Learning Approach to Bridge-Damage Detection Using Responses Measured on a Passing Vehicle |
| title_sort | machine learning approach to bridge damage detection using responses measured on a passing vehicle |
| topic | drive-by bridge damage detection machine learning artificial neural network |
| url | https://www.mdpi.com/1424-8220/19/18/4035 |
| work_keys_str_mv | AT abdollahmalekjafarian amachinelearningapproachtobridgedamagedetectionusingresponsesmeasuredonapassingvehicle AT fatemehgolpayegani amachinelearningapproachtobridgedamagedetectionusingresponsesmeasuredonapassingvehicle AT callummoloney amachinelearningapproachtobridgedamagedetectionusingresponsesmeasuredonapassingvehicle AT siobhanclarke amachinelearningapproachtobridgedamagedetectionusingresponsesmeasuredonapassingvehicle AT abdollahmalekjafarian machinelearningapproachtobridgedamagedetectionusingresponsesmeasuredonapassingvehicle AT fatemehgolpayegani machinelearningapproachtobridgedamagedetectionusingresponsesmeasuredonapassingvehicle AT callummoloney machinelearningapproachtobridgedamagedetectionusingresponsesmeasuredonapassingvehicle AT siobhanclarke machinelearningapproachtobridgedamagedetectionusingresponsesmeasuredonapassingvehicle |