Structural damage assessment through a new generalized autoencoder with features in the quefrency domain

Li, Lechen; Morgantini, Marcello; Betti, Raimondo

doi:10.1016/j.ymssp.2022.109713

Cited by 20 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different from autoencoders (AE), generalized autoencoders (GAE) make each input instance reconstruct a group of instances, not just itself. Li et al [ 59 ] argued that GAE can better learn the basic structure of the original data while reducing noise effects compared to traditional AE. Therefore, they developed an SHM framework based on a modified GAE network which was trained to model power cepstral coefficients extracted from the structure response.…”

Section: Unsupervised Learning Shm Based On Artificial Neural Networkmentioning

confidence: 99%

“…A threshold can be set using confidence intervals [ 83 , 108 , 130 , 136 ], significance [ 62 , 73 , 88 , 102 , 120 ], percentiles [ 58 , 63 , 64 , 66 , 74 ], or other data statistics. For multidimensional features, MD, or MSD, is often used [ 59 , 67 , 72 , 82 , 89 , 90 , 99 , 116 , 132 ]. There are different techniques for selecting a threshold for MSD-based outlier detection.…”

Section: Novelty Detection Techniquesmentioning

confidence: 99%

“…Others use 75% of the undamaged state period for training while adding the rest to the testing set [ 81 ]. Some alternative methods are including the first month, the first three months, or the last undamaged state month of the record for training, in addition to different sets of testing [ 59 , 115 ]. In addition, making the model source code available for the community, which would facilitate the comparisons or the building of a Model Zoo, is still not a common practice in SHM research.…”

Section: Challenges and Future Trendsmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Learning Methods for Data-Driven Vibration-Based Structural Health Monitoring: A Review

Eltouny

Gomaa

Liang

2023

Sensors

View full text Add to dashboard Cite

Structural damage detection using unsupervised learning methods has been a trending topic in the structural health monitoring (SHM) research community during the past decades. In the context of SHM, unsupervised learning methods rely only on data acquired from intact structures for training the statistical models. Consequently, they are often seen as more practical than their supervised counterpart in implementing an early-warning damage detection system in civil structures. In this article, we review publications on data-driven structural health monitoring from the last decade that relies on unsupervised learning methods with a focus on real-world application and practicality. Novelty detection using vibration data is by far the most common approach for unsupervised learning SHM and is, therefore, given more attention in this article. Following a brief introduction, we present the state-of-the-art studies in unsupervised-learning SHM, categorized by the types of used machine-learning methods. We then examine the benchmarks that are commonly used to validate unsupervised-learning SHM methods. We also discuss the main challenges and limitations in the existing literature that make it difficult to translate SHM methods from research to practical applications. Accordingly, we outline the current knowledge gaps and provide recommendations for future directions to assist researchers in developing more reliable SHM methods.

show abstract

Section: Unsupervised Learning Shm Based On Artificial Neural Networkmentioning

confidence: 99%

Section: Novelty Detection Techniquesmentioning

confidence: 99%

Section: Challenges and Future Trendsmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Learning Methods for Data-Driven Vibration-Based Structural Health Monitoring: A Review

Eltouny

Gomaa

Liang

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In 2021, Morgantini et al [31] investigated their connection to the modal characteristics of the structure and how they can be successfully used in a damage assessment strategy. The use of power cepstral coefficients as DSFs was further refined by Li et al [32] in 2023. Li proposed a New Generalized Auto-Encoder integrated with a statistical-pattern-recognition-based approach that uses the cepstral coefficients extracted from structural acceleration responses as DSFs.…”

Section: Introductionmentioning

confidence: 99%

Enhancing the Damage Detection and Classification of Unknown Classes with a Hybrid Supervised–Unsupervised Approach

Stagi,

Sclafani,

Tronci

et al. 2024

Infrastructures

Self Cite

View full text Add to dashboard Cite

Most damage-assessment strategies for dynamic systems only distinguish between undamaged and damaged conditions without recognizing the level or type of damage or considering unseen conditions. This paper proposes a novel framework for structural health monitoring (SHM) that combines supervised and unsupervised learning techniques to assess damage using a system’s structural response (e.g., the acceleration response of big infrastructures). The objective is to enhance the benefits of a supervised learning framework while addressing the challenges of working in an SHM context. The proposed framework uses a Linear Discriminant Analysis (LDA)/Probabilistic Linear Discriminant Analysis (PLDA) strategy that enables learning the distributions of known classes and the performance of probabilistic estimations on new incoming data. The methodology is developed and proposed in two versions. The first version is used in the context of controlled, conditioned monitoring or for post-damage assessment, while the second analyzes the single observational data. Both strategies are built in an automatic framework able to classify known conditions and recognize unseen damage classes, which are then used to update the classification algorithm. The proposed framework’s effectiveness is first tested considering the acceleration response of a numerically simulated 12-degree-of-freedom system. Then, the methodology’s practicality is validated further by adopting the experimental monitoring data of the benchmark study case of the Z24 bridge.

show abstract

“…The proposed damage detection method was validated for three different test cases, comprising both numerical simulations and experimentally recorded data. In [23], a new generalized auto-encoder (NGAE) is proposed and supplemented with a statistical pattern-recognition approach using power cepstral coefficients of acceleration responses. This method was validated using numerical simulations and experimental data and shows better performance than the traditional auto-encoder (TAE) and principal component analysis (PCA).…”

Section: Introductionmentioning

confidence: 99%

Framework for Identification and Prediction of Corrosion Degradation in a Steel Column through Machine Learning and Bayesian Updating

Castelli

Belleri

2023

Applied Sciences

View full text Add to dashboard Cite

In recent years, structural health monitoring, starting from accelerometric data, is a method which has become widely adopted. Among the available techniques, machine learning is one of the most innovative and promising, supported by the continuously increasing computational capacity of current computers. The present work investigates the potential benefits of a framework based on supervised learning suitable for quantifying the corroded thickness of a structural system, herein uniformly applied to a reference steel column. The envisaged framework follows a hybrid approach where the training data are generated from a parametric and stochastic finite element model. The learning activity is performed by a support vector machine with Bayesian optimization of the hyperparameters, in which a penalty matrix is introduced to minimize the probability of missed alarms. Then, the estimated structural health conditions are used to update an exponential degradation model with random coefficients suitable for providing a prediction of the remaining useful life of the simulated corroded column. The results obtained show the potentiality of the proposed framework and its possible future extension for different types of damage and structural types.

show abstract

Structural damage assessment through a new generalized autoencoder with features in the quefrency domain

Cited by 20 publications

References 35 publications

Unsupervised Learning Methods for Data-Driven Vibration-Based Structural Health Monitoring: A Review

Unsupervised Learning Methods for Data-Driven Vibration-Based Structural Health Monitoring: A Review

Enhancing the Damage Detection and Classification of Unknown Classes with a Hybrid Supervised–Unsupervised Approach

Framework for Identification and Prediction of Corrosion Degradation in a Steel Column through Machine Learning and Bayesian Updating

Contact Info

Product

Resources

About