Bayesian-Based Hyperparameter Optimization of 1D-CNN for Structural Anomaly Detection
With the rapid development of sensor technology, structural health monitoring data have tended to become more massive. Deep learning has advantages when handling big data, and has therefore been widely researched for diagnosing structural anomalies. However, for the diagnosis of different structural...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/11/5058 |
_version_ | 1797596801919877120 |
---|---|
author | Xiaofei Li Hainan Guo Langxing Xu Zezheng Xing |
author_facet | Xiaofei Li Hainan Guo Langxing Xu Zezheng Xing |
author_sort | Xiaofei Li |
collection | DOAJ |
description | With the rapid development of sensor technology, structural health monitoring data have tended to become more massive. Deep learning has advantages when handling big data, and has therefore been widely researched for diagnosing structural anomalies. However, for the diagnosis of different structural abnormalities, the model hyperparameters need to be adjusted according to different application scenarios, which is a complicated process. In this paper, a new strategy for building and optimizing 1D-CNN models is proposed that is suitable for diagnosing damage to different types of structure. This strategy involves optimizing hyperparameters with the Bayesian algorithm and improving model recognition accuracy using data fusion technology. Under the condition of sparse sensor measurement points, the entire structure is monitored, and the high-precision diagnosis of structural damage is performed. This method improves the applicability of the model to different structure detection scenarios, and avoids the shortcomings of traditional hyperparameter adjustment methods based on experience and subjectivity. In preliminary research on the simply supported beam test case, the efficient and accurate identification of parameter changes in small local elements was achieved. Furthermore, publicly available structural datasets were utilized to verify the robustness of the method, and a high identification accuracy rate of 99.85% was achieved. Compared with other methods described in the literature, this strategy shows significant advantages in terms of sensor occupancy rate, computational cost, and identification accuracy. |
first_indexed | 2024-03-11T02:58:09Z |
format | Article |
id | doaj.art-e9100dc6b4c04be9ab06a776b1bc7c23 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T02:58:09Z |
publishDate | 2023-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-e9100dc6b4c04be9ab06a776b1bc7c232023-11-18T08:31:58ZengMDPI AGSensors1424-82202023-05-012311505810.3390/s23115058Bayesian-Based Hyperparameter Optimization of 1D-CNN for Structural Anomaly DetectionXiaofei Li0Hainan Guo1Langxing Xu2Zezheng Xing3College of Transportation Engineering, Dalian Maritime University, Dalian 116026, ChinaCollege of Transportation Engineering, Dalian Maritime University, Dalian 116026, ChinaCollege of Transportation Engineering, Dalian Maritime University, Dalian 116026, ChinaCollege of Information Science and Engineering, University of Jinan, Jinan 250022, ChinaWith the rapid development of sensor technology, structural health monitoring data have tended to become more massive. Deep learning has advantages when handling big data, and has therefore been widely researched for diagnosing structural anomalies. However, for the diagnosis of different structural abnormalities, the model hyperparameters need to be adjusted according to different application scenarios, which is a complicated process. In this paper, a new strategy for building and optimizing 1D-CNN models is proposed that is suitable for diagnosing damage to different types of structure. This strategy involves optimizing hyperparameters with the Bayesian algorithm and improving model recognition accuracy using data fusion technology. Under the condition of sparse sensor measurement points, the entire structure is monitored, and the high-precision diagnosis of structural damage is performed. This method improves the applicability of the model to different structure detection scenarios, and avoids the shortcomings of traditional hyperparameter adjustment methods based on experience and subjectivity. In preliminary research on the simply supported beam test case, the efficient and accurate identification of parameter changes in small local elements was achieved. Furthermore, publicly available structural datasets were utilized to verify the robustness of the method, and a high identification accuracy rate of 99.85% was achieved. Compared with other methods described in the literature, this strategy shows significant advantages in terms of sensor occupancy rate, computational cost, and identification accuracy.https://www.mdpi.com/1424-8220/23/11/5058structural anomaly detection1-D convolutional neural networkBayesian optimization algorithmdecision-level fusionvibration signals |
spellingShingle | Xiaofei Li Hainan Guo Langxing Xu Zezheng Xing Bayesian-Based Hyperparameter Optimization of 1D-CNN for Structural Anomaly Detection Sensors structural anomaly detection 1-D convolutional neural network Bayesian optimization algorithm decision-level fusion vibration signals |
title | Bayesian-Based Hyperparameter Optimization of 1D-CNN for Structural Anomaly Detection |
title_full | Bayesian-Based Hyperparameter Optimization of 1D-CNN for Structural Anomaly Detection |
title_fullStr | Bayesian-Based Hyperparameter Optimization of 1D-CNN for Structural Anomaly Detection |
title_full_unstemmed | Bayesian-Based Hyperparameter Optimization of 1D-CNN for Structural Anomaly Detection |
title_short | Bayesian-Based Hyperparameter Optimization of 1D-CNN for Structural Anomaly Detection |
title_sort | bayesian based hyperparameter optimization of 1d cnn for structural anomaly detection |
topic | structural anomaly detection 1-D convolutional neural network Bayesian optimization algorithm decision-level fusion vibration signals |
url | https://www.mdpi.com/1424-8220/23/11/5058 |
work_keys_str_mv | AT xiaofeili bayesianbasedhyperparameteroptimizationof1dcnnforstructuralanomalydetection AT hainanguo bayesianbasedhyperparameteroptimizationof1dcnnforstructuralanomalydetection AT langxingxu bayesianbasedhyperparameteroptimizationof1dcnnforstructuralanomalydetection AT zezhengxing bayesianbasedhyperparameteroptimizationof1dcnnforstructuralanomalydetection |