Structural health monitoring by a new hybrid feature extraction and dynamic time warping methods under ambient vibration and non-stationary signals

Entezami, Alireza; Shariatmadar, Hashem

doi:10.1016/j.measurement.2018.10.095

Cited by 44 publications

(34 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e type, the geometric parameters, and the outer characteristic fault characteristic order of fault bearing are shown in Table 3. e outer ring fault characteristic order F COO and F COI can be calculated according to the geometric parameters of the bearing [18]:…”

Section: Validity Verificationmentioning

confidence: 99%

“…In 2013, Zhen et al [17] analyzed the stator current signal of the motor driver fault using the DTW method. In 2019, Entezami and Shariatmadar [18] proposed a correlation-based DTW method to detect damage by using randomly high-dimensional multivariate features. e experimental results suggest that this method can detect and locate the damage under the nonstationary signals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Similarity Comparison Method of Homologous Fault Response Fragments under Variable Rotational Speed

Chen

Wen

2020

Shock and Vibration

View full text Add to dashboard Cite

Effective fault detection and diagnosis (FDD) for rotating machinery is always a focus issue in improving the prognostic and health management (PHM) of the equipments. The existing usage of similarity measurement has been widely spread in searching the homologous fault responses from vibration signals, but most of them are just suitable for stable speed and cannot be applied in all variable speed conditions. In order to improve measurement performance, a fast-meshed phase portrait (FMPP) frame combining the phase-space technique and box-scoring calculation is proposed. Firstly, the variable-speed signal is divided into multiple undetermined fragments according to fault characteristic orders (FCOs). Secondly, the undetermined fragments are reconstructed into corresponding phase-space trajectories to overcome the time-delay matching inconsistency of the variable speed fragments. Thirdly, the phase-space trajectories are mapped into meshed phase portraits via box-scoring calculation. Such decisive calculation can effectively transforms the diverse unequal fragments into the phase diagrams with same size, which saves time for the subsequent similarity measurement. Finally, the proposed FMPP is tested both for accuracy and timeliness on a self-built bearing bench, where the order tracking (OT) and dynamic time warping (DTW) methods are used for the comparisons. The experiments proved the effectiveness of the proposed method.

show abstract

Section: Validity Verificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Similarity Comparison Method of Homologous Fault Response Fragments under Variable Rotational Speed

Chen

Wen

2020

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…Furthermore, novelty detection based on unsupervised learning, which is to be contrasted with supervised learning [10,11], is an influential method for feature classification. Statistical distances [4,[12][13][14], clustering algorithms [15] and artificial neural networks [16] are popular tools for developing novelty detectors for SHM.…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Learning Approach for Early Damage Detection by Time Series Analysis and Deep Neural Network to Deal with Output-Only (Big) Data

Entezami

Sarmadi

Mariani

2020

7th International Electronic Conference on Sensors and Applications

Self Cite

View full text Add to dashboard Cite

Dealing with complex engineering problems characterized by Big Data, particularly in structural engineering, has recently received considerable attention due to its high societal importance. Data-driven structural health monitoring (SHM) methods aim at assessing the structural state and detecting any adverse change caused by damage, so as to guarantee structural safety and serviceability. These methods rely on statistical pattern recognition, which provides opportunities to implement a long-term SHM strategy by processing measured vibration data. However, the successful implementation of the data-driven SHM strategies when Big Data are to be processed is still a challenging issue, since the procedures of feature extraction and/or feature classification may end up being time-consuming and complex. To enhance the current damage detection procedures, in this work we propose an unsupervised learning method based on time series analysis, deep learning and the Mahalanobis distance metric for feature extraction, dimensionality reduction and classification. The main novelty of this strategy is the simultaneous dealing with the significant issue of Big Data analytics for damage detection, and distinguishing damage states from the undamaged one in an unsupervised learning manner. Large-scale datasets relevant to a cable-stayed bridge have been handled to validate the effectiveness of the proposed data-driven approach. Results have shown that the approach is highly successful in detecting early damage, even when Big Data are to be processed.

show abstract

“…A reliable way to attain this latter goal is to adopt a well-established statistical distance metric to measure the discrepancy between different sets of samples. Successful approaches used for damage diagnosis relied upon the Mahalanobis-squared distance, [40][41][42][43] the Itakura and cepstral distances, 44 the Kullback-Leibler divergence (KLD), 45,46 the Kolmogorov-Smirnov statistical test (KSTS), 47,48 dynamic time warping, 49 the multivariate distance correlation, 32 and damage indices such as the Fisher criterion, 50 Q-statistic and T2-statistic, 51 and the deflection coefficient (DC). 52 All the aforementioned methods can be exploited through machine learning tools, in either supervised or unsupervised learning manners.…”

Section: Introductionmentioning

confidence: 99%

Fast unsupervised learning methods for structural health monitoring with large vibration data from dense sensor networks

Entezami

Shariatmadar

Mariani

2019

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

Data-driven damage localization is an important step of vibration-based structural health monitoring. Statistical pattern recognition based on the prominent steps of feature extraction and statistical decision-making provides an effective and efficient framework for structural health monitoring. However, these steps may become time-consuming or complex when there are large volumes of vibration measurements acquired by dense sensor networks. To deal with this issue, this study proposes fast unsupervised learning methods for feature extraction through autoregressive modeling and damage localization through a new distance measure called Kullback–Leibler divergence with empirical probability measure. The feature extraction approach consists of an iterative algorithm for order selection and parameter estimation aiming to extract residuals in the training phase and another iterative process aiming to extract residuals only in the monitoring phase. The key feature of the proposed approach is the use of correlated residual samples of the autoregressive model as a new time series at each iteration, rather than handling the measured vibration response of the structure. This is shown to highly reduce the computational burden of order selection and feature extraction; moreover, it effectively provides low-order autoregressive models with uncorrelated residuals. The Kullback–Leibler divergence with empirical probability measure method exploits a segmentation technique to subdivide random data into independent sets and provides a distance metric based on the theory of empirical probability measure with no need to explicitly compute the actual probability distributions at the training and monitoring stages. Numerical and experimental benchmarks are then used to assess accuracy and performance of the proposed methods and compare them with some state-of-the-art approaches. Results show that the proposed approaches are successful in feature extraction and damage localization, with a reduced computational burden.

show abstract

Structural health monitoring by a new hybrid feature extraction and dynamic time warping methods under ambient vibration and non-stationary signals

Cited by 44 publications

References 33 publications

A Similarity Comparison Method of Homologous Fault Response Fragments under Variable Rotational Speed

A Similarity Comparison Method of Homologous Fault Response Fragments under Variable Rotational Speed

An Unsupervised Learning Approach for Early Damage Detection by Time Series Analysis and Deep Neural Network to Deal with Output-Only (Big) Data

Fast unsupervised learning methods for structural health monitoring with large vibration data from dense sensor networks

Contact Info

Product

Resources

About