Novelty Detection Using Sparse Auto-Encoders to Characterize Structural Vibration Responses

Finotti, Rafaelle Piazzaroli; Barbosa, Fernando Policarpo; Cury, Alexandre; Pimentel, Roberto Leal

doi:10.1007/s13369-022-06732-6

Cited by 7 publications

(6 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These values were adopted based on the work of Touati et al (2020), which affirms that these values ensure good coverage of the search space for the considered parameters and corroborated in the studies of Finotti et al (2021) and Finotti et al (2022a). Considering that the results obtained were quite satisfactory, it is assumed that the application of an optimization procedure to determine the optimal hyperparameters of the SAE can be studied in another work, with the potential to further improve the results achieved.…”

Section: The Grid Search Processmentioning

confidence: 63%

“…After an extensive present-day literature review, Avci et al (2021) states that the most critical component of SHM is damage detection, which is defined as a systematic and automatic process of identifying the existence of damage, followed by its localization and its severity assessment. Recent articles specifically focused on damage detection reinforce this assertion (Nunes et al 2021, Dan et al 2021, Finotti et al 2022a, Liu et al 2022, Rosso et al 2023. Such an idea seems logical since the location and quantification of the damage extension presuppose correctly identifying its occurrence beforehand.…”

Section: Introductionmentioning

confidence: 96%

“…Considering that SAE deep learning algorithms are recent tools in the SHM area, studies focused on evaluating them to solve novelty detection problems are still welcome, as noticed by the considerable number of recent works that address this topic (Wang and Cha 2021, Finotti et al 2022a, Abbas et al 2023. However, most studies already published focused on numerical models (Wang and Cha 2021, Abbas et al 2023, Eltouny et al 2023.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Novelty detection on a laboratory benchmark slender structure using an unsupervised deep learning algorithm

Finotti,

Silva,

Oliveira

et al. 2023

Lat. Am. j. solids struct.

Self Cite

View full text Add to dashboard Cite

The process that involves the continuous monitoring and analysis of a structure's behavior and performance is known as Structural Health Monitoring (SHM). SHM typically involves the use of sensors and other monitoring devices to collect data, such as displacements, strains, accelerations, among others. These data are analyzed using advanced algorithms and machine learning techniques to identify any signs of abnormal behavior or deterioration. This paper presents a numerical and experimental study of a slender frame subjected to five levels of structural changes under impact loading. The dynamic responses were recorded by four accelerometers and used to build models based on Sparse Auto-Encoders (SAE). Such models can identify each of the five structural states in an unsupervised way. A new strategy to define the hyperparameters of the SAE is presented, which proved to be adequate in the experiments conducted. Finally, the experimental data set is made available to the scientific community to serve as a benchmark for validating SHM methodologies to identify structural changes from dynamic measurements.

show abstract

Section: The Grid Search Processmentioning

confidence: 63%

Section: Introductionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Novelty detection on a laboratory benchmark slender structure using an unsupervised deep learning algorithm

Finotti,

Silva,

Oliveira

et al. 2023

Lat. Am. j. solids struct.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this paper, the random load-time history of the catenary is loaded with the lifting force at different speeds and weight levels obtained from the dynamic simulation of the railway wagon, and the loading position is the portal structure beam. The dynamic load generated during the operation of the railway wagon and the load that the railway wagon will generate during driving can be composed of excitation function, static load and railway wagon vibration series functions [25,26]:…”

Section: Dynamic Load Loading Analysismentioning

confidence: 99%

Vibration Characteristics Analysis and Structure Optimization of Catenary Portal Structure on Four-Wire Bridge

Wang¹,

Li²

2022

Structural Durability &Amp; Health Monitoring

View full text Add to dashboard Cite

The portal structure is the support equipment in the catenary, which bears the load of contact suspension and support equipment. In practical work, with the change of external forces, the support equipment bears complex and changeable loads, so it has higher requirements for its reliability and safety. In order to study the dynamic characteristics of catenary portal structure on continuous beam of four-way bridge, taking the catenary portal structure on Dshaping four-way bridge as the research object, the portal structure simulation model of bridgenetwork integration was established in Midas Civil. The maximum point of deformation and stress was determined by finite element analysis of catenary hard span equipment, and the frequency and mode of natural vibration of hard span were obtained by modal analysis. Secondly, through the field dynamic stress acquisition test, combined with the results of finite element analysis, the fault location is determined, and the vibration characteristics are analyzed. Finally, based on the results of modal analysis and vibration analysis, the method that the vibration of portal structure beam is affected by structural stiffness and vibration frequency amplitude is proposed. The torsional vibration of the portal structure beam was suppressed by increasing the stiffness of the beam and reducing the vibration conduction between the trolley and the beam, and the hard cross beam was optimized by strengthening the hanging column and the connecting beam and adding diagonal support between the pillar and the portal structure beam. By comparing the values of shear, bending moment, displacement and dynamic stress on the hard span before and after optimization, the amplitude peak after structural optimization is reduced by about 25%, and the application of oblique support and reinforcement of the beam can significantly improve the portal structure vibration.

show abstract

“…Do et al [18] demonstrated the capability of autoencoders based on a long short-term memory structure for detecting anomaly vibrations in a Vertical Carousel Storage and Retrieval System for industrial applications. Finotti et al [19] assessed the structural condition of a viaduct by means of a sparse autoencoder that learned important data features (to characterize the vibration signals) and a support vector machine that classified the corresponding damage based on the extracted features. Jimenez-Martinez et al improved fatigue life prediction through a combination of synthetic data and an ANN without requiring additional tests or new parameters by overcoming the limit of Miner's damage rule when taking into account different factors such as temperature, environment, sequence loads, and mean stress [20].…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Deep Learning Algorithms for Anomaly Detection in Discrete Mechanical Systems

et al. 2023

View full text Add to dashboard Cite

The application of intelligent systems for structural health monitoring is investigated. A change in the nominal configuration can be related to a structural defect that has to be monitored before it reaches a critical condition. Evidently, the ability to automatically detect changes in a structure is a very attractive feature. When there is no prior knowledge on the system, deep learning models could effectively detect a change and enhance the capability of determining the damage location. However, the acquisition of data related to damaged structures is not always practical. In this paper, two deep learning approaches, a physics-informed autoencoder and a simple data-driven autoencoder, are applied to a test rig consisting of a small four-storey building model. Modifications to the system are simulated by changing the stiffness of the springs. Both the machine learning algorithms outperform the traditional approach based on an experimental modal analysis. Moreover, the increased potential of the physics-informed neural networks to detect and locate damage is confirmed.

show abstract

Novelty Detection Using Sparse Auto-Encoders to Characterize Structural Vibration Responses

Cited by 7 publications

References 39 publications

Novelty detection on a laboratory benchmark slender structure using an unsupervised deep learning algorithm

Novelty detection on a laboratory benchmark slender structure using an unsupervised deep learning algorithm

Vibration Characteristics Analysis and Structure Optimization of Catenary Portal Structure on Four-Wire Bridge

A Comparison of Deep Learning Algorithms for Anomaly Detection in Discrete Mechanical Systems

Contact Info

Product

Resources

About