Damage identification using chaotic excitation

Wan, Chunfeng,Sato, Tadanobu,Wu, Zhishen,Zhang, Jian Techno-Press 2013 Smart Structures and Systems, An International Jou Vol.11 No.1

Vibration-based damage detection methods are popular for structural health monitoring. However, they can only detect fairly large damages. Usually impact pulse, ambient vibrations and sine-wave forces are applied as the excitations. In this paper, we propose the method to use the chaotic excitation to vibrate structures. The attractors built from the output responses are used for the minor damage detection. After the damage is detected, it is further quantified using the Kalman Filter. Simulations are conducted. A 5-story building is subjected to chaotic excitation. The structural responses and related attractors are analyzed. The results show that the attractor distances increase monotonously with the increase of the damage degree. Therefore, damages, including minor damages, can be effectively detected using the proposed approach. With the Kalman Filter, damage which has the stiffness decrease of about 5% or lower can be quantified. The proposed approach will be helpful for detecting and evaluating minor damages at the early stage.

Structural damage identification with output-only measurements using modified Jaya algorithm and Tikhonov regularization method

Chunfeng Wan,Guangcai Zhang,Liyu Xie,Songtao Xue 국제구조공학회 2023 Smart Structures and Systems, An International Jou Vol.31 No.3

The absence of excitation measurements may pose a big challenge in the application of structural damage identification owing to the fact that substantial effort is needed to reconstruct or identify unknown input force. To address this issue, in this paper, an iterative strategy, a synergy of Tikhonov regularization method for force identification and modified Jaya algorithm (M-Jaya) for stiffness parameter identification, is developed for damage identification with partial output-only responses. On the one hand, the probabilistic clustering learning technique and nonlinear updating equation are introduced to improve the performance of standard Jaya algorithm. On the other hand, to deal with the difficulty of selection the appropriate regularization parameters in traditional Tikhonov regularization, an improved L-curve method based on B-spline interpolation function is presented. The applicability and effectiveness of the iterative strategy for simultaneous identification of structural damages and unknown input excitation is validated by numerical simulation on a 21-bar truss structure subjected to ambient excitation under noise free and contaminated measurements cases, as well as a series of experimental tests on a five-floor steel frame structure excited by sinusoidal force. The results from these numerical and experimental studies demonstrate that the proposed identification strategy can accurately and effectively identify damage locations and extents without the requirement of force measurements. The proposed M-Jaya algorithm provides more satisfactory performance than genetic algorithm, Gaussian bare-bones artificial bee colony and Jaya algorithm.

Early warning of hazard for pipelines by acoustic recognition using principal component analysis and one-class support vector machines

Wan, Chunfeng,Mita, Akira Techno-Press 2010 Smart Structures and Systems, An International Jou Vol.6 No.4

This paper proposes a method for early warning of hazard for pipelines. Many pipelines transport dangerous contents so that any damage incurred might lead to catastrophic consequences. However, most of these damages are usually a result of surrounding third-party activities, mainly the constructions. In order to prevent accidents and disasters, detection of potential hazards from third-party activities is indispensable. This paper focuses on recognizing the running of construction machines because they indicate the activity of the constructions. Acoustic information is applied for the recognition and a novel pipeline monitoring approach is proposed. Principal Component Analysis (PCA) is applied. The obtained Eigenvalues are regarded as the special signature and thus used for building feature vectors. One-class Support Vector Machine (SVM) is used for the classifier. The denoising ability of PCA can make it robust to noise interference, while the powerful classifying ability of SVM can provide good recognition results. Some related issues such as standardization are also studied and discussed. On-site experiments are conducted and results prove the effectiveness of the proposed early warning method. Thus the possible hazards can be prevented and the integrity of pipelines can be ensured.

Early warning of hazard for pipelines by acoustic recognition using principal component analysis and one-class support vector machines

Chunfeng Wan,Akira Mita 국제구조공학회 2010 Smart Structures and Systems, An International Jou Vol.6 No.4

This paper proposes a method for early warning of hazard for pipelines. Many pipelines transport dangerous contents so that any damage incurred might lead to catastrophic consequences. However, most of these damages are usually a result of surrounding third-party activities, mainly the constructions. In order to prevent accidents and disasters, detection of potential hazards from third-party activities is indispensable. This paper focuses on recognizing the running of construction machines because they indicate the activity of the constructions. Acoustic information is applied for the recognition and a novel pipeline monitoring approach is proposed. Principal Component Analysis (PCA) is applied. The obtained Eigenvalues are regarded as the special signature and thus used for building feature vectors. One-class Support Vector Machine (SVM) is used for the classifier. The denoising ability of PCA can make it robust to noise interference, while the powerful classifying ability of SVM can provide good recognition results. Some related issues such as standardization are also studied and discussed. On-site experiments are conducted and results prove the effectiveness of the proposed early warning method. Thus the possible hazards can be prevented and the integrity of pipelines can be ensured.

Damage identification using chaotic excitation

Chunfeng Wan,Tadanobu Sato,Zhishen Wu,Jian Zhang 국제구조공학회 2013 Smart Structures and Systems, An International Jou Vol.11 No.1

Vibration-based damage detection methods are popular for structural health monitoring. However, they can only detect fairly large damages. Usually impact pulse, ambient vibrations and sine-wave forces are applied as the excitations. In this paper, we propose the method to use the chaotic excitation to vibrate structures. The attractors built from the output responses are used for the minor damage detection. After the damage is detected, it is further quantified using the Kalman Filter. Simulations are conducted. A 5-story building is subjected to chaotic excitation. The structural responses and related attractors are analyzed. The results show that the attractor distances increase monotonously with the increase of the damage degree. Therefore, damages, including minor damages, can be effectively detected using the proposed approach. With the Kalman Filter, damage which has the stiffness decrease of about 5% or lower can be quantified. The proposed approach will be helpful for detecting and evaluating minor damages at the early stage.

Operational performance evaluation of bridges using autoencoder neural network and clustering

Chunfeng Wan,Songtao Xue,Huachen Jiang,Liyu Xie,Da Fang,Shuai Gao,Kang Yang,YouLiang Ding 국제구조공학회 2024 Smart Structures and Systems, An International Jou Vol.33 No.3

To properly extract the strain components under varying operational conditions is very important in bridge health monitoring. The abnormal sensor readings can be correctly identified and the expected operational performance of the bridge can be better understood if each strain components can be accurately quantified. In this study, strain components under varying load conditions, i.e., temperature variation and live-load variation are evaluated based on field strain measurements collected from a real concrete box-girder bridge. Temperature-induced strain is mainly regarded as the trend variation along with the ambient temperature, thus a smoothing technique based on the wavelet packet decomposition method is proposed to estimate the temperature-induced strain. However, how to effectively extract the vehicle-induced strain is always troublesome because conventional threshold setting-based methods cease to function: if the threshold is set too large, the minor response will be ignored, and if too small, noise will be introduced. Therefore, an autoencoder framework is proposed to evaluate the vehicleinduced strain. After the elimination of temperature and vehicle-induced strain, the left of which, defined as the model error, is used to assess the operational performance of the bridge. As empirical techniques fail to detect the degraded state of the structure, a clustering technique based on Gaussian Mixture Model is employed to identify the damage occurrence and the validity is verified in a simulation study.

A study of SiC/Al composites fabricated by pressureless infiltration

Kezheng Sang,Chunfeng Wan 한양대학교 세라믹연구소 2008 Journal of Ceramic Processing Research Vol.9 No.6

SiC/Al composites with a high volume fraction of SiC were prepared at 1,150 oC by pressureless infiltration. The volume fraction of SiC was increased by decreasing the amount of starch in the green body. Both the microstructure and the strength of the composites were investigated. The results showed that the strength decreased with an increase of the particle size and volume fraction of SiC. It is suggested that the interface between the SiC particles, which were not sintered, are the cause of defects in the composites. The defects led to a decrease of the strength with an increase of the volume fraction of SiC. SiC/Al composites with a high volume fraction of SiC were prepared at 1,150 oC by pressureless infiltration. The volume fraction of SiC was increased by decreasing the amount of starch in the green body. Both the microstructure and the strength of the composites were investigated. The results showed that the strength decreased with an increase of the particle size and volume fraction of SiC. It is suggested that the interface between the SiC particles, which were not sintered, are the cause of defects in the composites. The defects led to a decrease of the strength with an increase of the volume fraction of SiC.

Big data platform for health monitoring systems of multiple bridges

Wang, Manya,Ding, Youliang,Wan, Chunfeng,Zhao, Hanwei Techno-Press 2020 Structural monitoring and maintenance Vol.7 No.4

At present, many machine leaning and data mining methods are used for analyzing and predicting structural response characteristics. However, the platform that combines big data analysis methods with online and offline analysis modules has not been used in actual projects. This work is dedicated to developing a multifunctional Hadoop-Spark big data platform for bridges to monitor and evaluate the serviceability based on structural health monitoring system. It realizes rapid processing, analysis and storage of collected health monitoring data. The platform contains offline computing and online analysis modules, using Hadoop-Spark environment. Hadoop provides the overall framework and storage subsystem for big data platform, while Spark is used for online computing. Finally, the big data Hadoop-Spark platform computational performance is verified through several actual analysis tasks. Experiments show the Hadoop-Spark big data platform has good fault tolerance, scalability and online analysis performance. It can meet the daily analysis requirements of 5s/time for one bridge and 40s/time for 100 bridges.

Simulation of Earthquake Motion Phase considering Its Fractal and Auto-covariance Features

Adam A. Abdelrahman,Tadanobu Sato,Chunfeng Wan,Lei Zhao 대한토목학회 2019 KSCE Journal of Civil Engineering Vol.23 No.9

The earthquake motion phase (EMP) is decomposed into linear delay and fluctuation parts. In this paper, the peculiar stochastic characteristics of the fluctuation part of the phase (FPP) are discussed. First, we show that the FPP has self-affine similarity and should be expressed as a fractal stochastic process by using several observed earthquake motion time histories, as well as the FPP has a long term memory in the frequency domain. Moreover, the possibility of simulating FPP using the simple fractional Brownian motion (fBm) is discussed and conclude that this is not possible. To overcome this problem, we develop a new stochastic process, the modified fBm that is able to simulate a stochastically rigorous sample FPP. This newly developed algorithm represents the phase characteristics of the observed EMP well.

Data abnormal detection using bidirectional long-short neural network combined with artificial experience

YouLiang Ding,Kang Yang,Huachen Jiang,Manya Wang,Chunfeng Wan 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.29 No.1

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.