Article
Engineering, Mechanical
Zekun Xu, Jun Chen, Jiaxu Shen, Mengjie Xiang
Summary: Urban seismic damage assessment is an emerging research topic due to global urbanization trend. Traditional methods may suffer from accuracy or efficiency issues, while machine learning methods lack scalability and real datasets. To tackle this issue, this paper proposes an artificial neural network framework for simultaneously predicting nonlinear seismic responses of all buildings in a cluster. The framework aggregates information from historical response records and physical characteristics to improve performance. Experimental results demonstrate high computational efficiency and accuracy.
ENGINEERING FAILURE ANALYSIS
(2023)
Article
Construction & Building Technology
Hoang D. Nguyen, Nhan D. Dao, Myoungsu Shin
Summary: This study developed machine learning models to predict the peak lateral displacements of seismic isolation systems. The random forest model showed the best performance, and the normalized characteristic strength was found to be the most influential variable. Furthermore, a practical analysis and comparison demonstrated the effectiveness and limitations of the developed model.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Turgut Pura, Peri Gunes, Ali Gunes, Ali Alaa Hameed
Summary: An earthquake is a natural event that can cause significant damage, loss of life, and economic effects. This study focuses on earthquake prediction using the RNN method and incorporates the calculation of b and d values for improved performance. The importance of this study lies in its detection of earthquakes in the Marmara region, classification of seismic data, and generation of future predictions using artificial neural networks.
APPLIED SCIENCES-BASEL
(2023)
Article
Polymer Science
Haofan Yu, Aldyandra Hami Seno, Zahra Sharif Khodaei, M. H. Ferri Aliabadi
Summary: This paper presents a novel method using BNN for multi-class classification and uncertainty quantification of impact events. The proposed model shows high performance in classifying impact energies and measuring uncertainty and confidence of the diagnosis. BNN outperforms multi-ANN in computational efficiency.
Article
Engineering, Civil
Zekun Xu, Jun Chen, Jiaxu Shen, Mengjie Xiang
Summary: This paper proposed a recursive LSTM network for predicting nonlinear structural seismic responses with lower computational cost compared to traditional methods, demonstrating good accuracy and generalization capability.
ENGINEERING STRUCTURES
(2022)
Article
Engineering, Civil
Jia Guo, Ryuta Enokida, Dawei Li, Kohju Ikago
Summary: By incorporating deep neural networks into a classical numerical integration method, we propose a hybridized integration time-stepper that combines the linear physics information with the nonlinear dynamics of structures. Our method has several advantages over current pure data-driven approaches, including the ability to incorporate known physics information, the circumvention of the requirement for large volume of structural response data, and efficiency in training and validation process.
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS
(2023)
Article
Engineering, Mechanical
Mohsen Mousavi, Amir H. Gandomi
Summary: A novel method for structural health monitoring under environmental and operational variations is proposed, utilizing RNN to predict the future CI residuals. The method involves signal decomposition, training the RNN, and using prediction errors as damage sensitive features, demonstrating successful monitoring of structural damage even in the presence of non-linear relationships among frequency signals.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Chemistry, Multidisciplinary
Davide Forcellini
Summary: The concept of seismic resilience in building design has gained attention in the past decade. The delay time, defined as the time between an earthquake event and the beginning of the repair process, is a key parameter in assessing the resilience of structures after earthquakes. This paper explores the relationship between seismic structural health monitoring (S2HM) and the assessment of seismic resilience, proposing a multidimensional definition of delay time that incorporates the accuracy of S2HM. By considering delay time, the seismic resilience of structural systems can be significantly improved.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Civil
Roberto Falcone, Angelo Ciaramella, Francesco Carrabs, Nicola Strisciuglio, Enzo Martinelli
Summary: This paper proposes the use of Machine Learning as a substitute for traditional mechanistic analyses in seismic retrofitting of reinforced concrete structures. The obtained results demonstrate the effectiveness of an artificial neural network in rapidly and accurately assessing the performance of different structural configurations, and it can be used to speed up the search for the best retrofitting solution.
Article
Computer Science, Information Systems
Bowen Du, Chunming Lin, Leilei Sun, Yangping Zhao, Linchao Li
Summary: This article proposes a heterogeneous structural response prediction (HSRP) framework based on a deep learning model to improve the performance of machine learning models in mining structural health monitoring data. The experimental results show that the proposed model outperforms benchmark models in prediction accuracy and demonstrates good sensitivity and robustness.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Civil
Ting-Yu Hsu, Pei-Shan Dai, Shiang-Jung Wang
Summary: Research has shown that by adjusting the damping force applied to SRI based on information provided by an earthquake early warning system and implementing semi-active control, better control of acceleration and displacement responses can be achieved. By developing prediction models for peak velocity using the ANN approach, the required damping force for SRI can be determined within seconds of the arrival of P-wave.
ENGINEERING STRUCTURES
(2021)
Article
Engineering, Civil
Hyojoon An, Jong-Han Lee
Summary: The collapse of civil infrastructure due to natural disasters results in significant financial losses and casualties. This study developed a deep learning-based algorithm to accurately predict the seismic response of bridge structures. The algorithm can reasonably predict the nonlinear behavior of structures and can be used to assess the seismic fragility of bridge components and systems.
STRUCTURAL ENGINEERING AND MECHANICS
(2022)
Article
Multidisciplinary Sciences
Delong Huang, Aiping Tang, Qiang Liu, Dianrui Mu, Yan Ding
Summary: This study investigates the response of pipe network nodes under non-uniform geology conditions through shaking table tests and ABAQUS finite element simulations, providing theoretical support for seismic design of underground pipe networks.
Article
Computer Science, Artificial Intelligence
Aydin Dogan, Engin Demir
Summary: This study introduces novel models using the structural recurrent neural network (SRNN) to capture the spatial proximity and structural properties in earthquake prediction. Experimental results in two distinct regions, Turkey and China, show that the SRNN models achieve better performance compared to baseline and state-of-the-art models. Particularly, the SRNNClass(near) model, which captures the first-order spatial neighborhood and structural classification based on fault lines, achieves the highest F-1 score.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Engineering, Civil
Soheil Sadeghi Eshkevari, Martin Takac, Shamim N. Pakzad, Majid Jahani
Summary: A physics-based recurrent neural network model is proposed in this study to accurately estimate dynamic responses of linear and nonlinear multi-degree-of-freedom systems. Compared with other models, this model has higher accuracy and requires fewer trainable variables. Numerical case studies demonstrate the network's ability to learn different nonlinear behaviors of dynamic systems with high accuracy.
ENGINEERING STRUCTURES
(2021)
Article
Engineering, Multidisciplinary
Zeyu Xiong, Branko Glisic
Summary: The aim of this research is to optimize the design of sensor arrays for reliable damage detection over large areas of structures, focusing on reducing the number of sensors while maintaining reliability in crack detection and accuracy in damage localization and quantification. The study utilizes a combination of phase field finite element modeling and inverse elastostatic problem algorithms to determine crack existence, length, and location, with experimental validation showing the accuracy and reliability of indirect sensing.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2021)
Article
Engineering, Multidisciplinary
Isabel M. Morris, Vivek Kumar, Branko Glisic
Summary: A laboratory-based experimental protocol establishes the relationship between ground-penetrating radar attributes and mechanical properties of concrete mixes, predicting physical properties from radar attributes using regression models. The novel relationships indicate that material properties could be predicted from ordinary ground-penetrating radar scans of concrete, offering a new approach for predicting concrete properties in practical engineering applications.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2021)
Article
Engineering, Multidisciplinary
Antti Valkonen, Branko Glisic
Summary: Different rational individuals may make different decisions under the same conditions due to their risk preferences, which can have significant effects on the feasibility of implementation in multi-stakeholder decision-making regarding structural health monitoring. Understanding stakeholders' risk attitudes is crucial for decision-making in structural health monitoring, as shown in previous research using the expected utility theory.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2022)
Article
Engineering, Civil
Shengzhe Wang, Maria Garlock, Branko Glisic
Summary: The legacy of master builder Felix Candela lies in his extensive use of hypar umbrellas in architecture across the Americas. These umbrellas embody efficiency, economy, and elegance, but lack a unified mathematical description. This research introduces equations for analysis and design, along with a simplified method for computing surface area.
ENGINEERING STRUCTURES
(2022)
Article
Chemistry, Multidisciplinary
Fiammetta Venuti, Marco Domaneschi, Marc Lizana, Branko Glisic
Summary: This paper presents and validates two different FE models of an existing footbridge with complex geometry, for vibration serviceability assessments under pedestrian excitation. The models were developed based on detailed drawings of the Streicker Footbridge, and validated against available SHM data concerning static and dynamic tests.
APPLIED SCIENCES-BASEL
(2021)
Article
Construction & Building Technology
Shengzhe Wang, Maria Garlock, Luc Deike, Branko Glisic
Summary: The paper discusses the integration of Felix Candela's hypar shells into architecture and explores the use of kinetic umbrellas as an alternative to conventional floodwalls. Through numerical simulation and experimental validation, the performance of kinetic umbrellas under surge and wave loading is evaluated, showing that specific hypar geometries greatly enhance structural performance.
JOURNAL OF STRUCTURAL ENGINEERING
(2022)
Article
Chemistry, Analytical
Branko Glisic
Summary: Strain plays a crucial role in civil structural health monitoring, as it directly reflects the structural performance, safety, and serviceability. Over the past century, strain sensors have evolved from discrete sensors to distributed sensors, enabling global structural and integrity monitoring.
Editorial Material
Engineering, Civil
Branko Glisic, Xin Feng, Daniele Inaudi
JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING
(2022)
Article
Engineering, Civil
Mauricio Pereira, Branko Glisic
Summary: Concrete displays complex long-term behavior influenced by its rheological properties. Predicting the long-term behavior of concrete structures is challenging due to stochastic rheological phenomena and uncontrolled conditions. Existing approaches involve computationally intensive methods but are not always specific to a particular structure. This study proposes a hybrid method that combines probabilistic neural networks and engineering code models to predict long-term behavior in concrete structures, achieving excellent accuracy in a real pedestrian bridge.
JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING
(2022)
Article
Computer Science, Artificial Intelligence
Hyo Seon Park, Taehoon Hong, Dong-Eun Lee, Byung Kwan Oh, Branko Glisic
Summary: This study presents a model for predicting long-term strain in concrete structures using weather data. A convolutional neural network is used to establish the relationship between weather and strain data, and different types of weather data are utilized to determine the significant factors for concrete deformation prediction.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Chemistry, Analytical
Mauricio Pereira, Branko Glisic
Summary: Concrete exhibits time-dependent long-term behavior driven by creep and shrinkage, which are difficult to predict due to their stochastic nature and dependence on loading history. Existing empirical models do not capture differential rheological effects and require numerical models for application to real structures. Data-driven approaches using structural health monitoring data have shown promise but require different model parameters for each sensor and do not leverage geometry and loading. This work introduces a physics-informed data-driven approach for predicting the long-term behavior of 2D normal strain field in prestressed concrete structures.
Article
Construction & Building Technology
Mohsen Mousavi, Amir H. Gandomi, Magd Abdel Wahab, Branko Glisic
Summary: This study proposes a method for long-term condition monitoring of civil infrastructures using machine learning algorithms. By monitoring the prediction error of air temperature recorded at the site of a structure, the proposed method accurately detects structural damage. The results show that the interaction linear regression model is the most accurate machine learning algorithm and outperforms the direct strategy.
STRUCTURAL CONTROL & HEALTH MONITORING
(2022)
Article
Construction & Building Technology
Moriah Hughes, Sofia Celli, Camille Heubner, Maria Garlock, Federica Ottoni, Davide Del Curto, Shengzhe Wang, Branko Glisic
Summary: This study diagnosed and identified the structural damage of the Ballet School domes in Havana, Cuba using numerical analysis methods. It also proposed suitable preventive and repair solutions based on the findings. Understanding the significance of these structures and preserving them is crucial.
JOURNAL OF PERFORMANCE OF CONSTRUCTED FACILITIES
(2023)
Article
Computer Science, Artificial Intelligence
Mauricio Pereira, Branko Glisic
Summary: Temperature effects play a crucial role in the strain and deformations of civil infrastructure. Accurate methods for detecting and quantifying anomalies in temperature data are necessary. This study proposes a probabilistic neural network as a temperature prediction model and introduces a sensible threshold to mitigate seasonal biases. Additionally, a novel drift detection and quantification method based on the evolution of probability distributions is presented.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Bianca Acot, Branko Glisic, Annegret Dettwiler, Michael D. Gilchrist
Summary: This paper examines the impact of head collisions on concussions in football through video analysis, finite element simulation, and correlation of biomechanical and neuroimaging metrics. The study also proposes a method to improve the process of finite element modeling. By addressing areas for improvement in accident reconstruction and simulation, researchers can enhance the accuracy of head impact simulations and eventually use them for diagnostic purposes.
COMPUTER METHODS, IMAGING AND VISUALIZATION IN BIOMECHANICS AND BIOMEDICAL ENGINEERING II
(2023)
Article
Acoustics
Sandip Chajjed, Mohammad Khalil, Dominique Poirel, Chris Pettit, Abhijit Sarkar
Summary: This paper reports the generalization of the Bayesian formulation of the flutter margin method, which improves the predictive performance by incorporating the joint prior of aeroelastic modal parameters. The improved algorithm reduces uncertainties in predicting flutter speed and can cut cost by reducing the number of flight tests.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Pascal Zeise, Bernhard Schweizer
Summary: Air ring bearings are an improved version of classical air bearings, providing better damping behavior and allowing operation above the linear threshold speed of instability. However, there is a risk of dangerous vibrations in certain rotor systems, which can be addressed by considering ring tilting effects.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Zbynek Sika, Jan Krivosej, Tomas Vyhlidal
Summary: This paper presents a novel design of a compact six degrees of freedom active vibration absorber with six identical eigenfrequencies. The objective is to completely suppress the vibration of a machine structure with six motion components. By utilizing a Stewart platform structure equipped with six active legs, a spatial unifrequency absorber with six identical eigenfrequencies is achieved. The design is optimized using a correction feedback and active delayed resonator feedback.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Kai Li, Yufeng Liu, Yuntong Dai, Yong Yu
Summary: This paper presents a novel light-powered self-oscillating liquid crystal elastomer (LCE) bow that can self-oscillate continuously and periodically under steady illumination. The dynamics of the LCE bow are theoretically investigated and numerical calculations predict its motion regimes. The suggested LCE bow offers potential advantages in terms of simple structure, customizable size, flexible regulation, and easy assembly.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Carmelo Rosario Vindigni, Giuseppe Mantegna, Calogero Orlando, Andrea Alaimo
Summary: In this study, a simple adaptive flutter suppression system is designed to increase the operative speed range of a wing-aileron aeroelastic plant. The system achieves almost strictly passivity by using a parallel feed-forward compensator implementation and the controller parameters are optimized using a population decline swarm optimization algorithm. Numerical simulations prove the effectiveness of the proposed simple adaptive flutter suppression architecture in different flight scenarios.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Nicco Ulbricht, Alain Boldini, Peng Zhang, Maurizio Porfiri
Summary: The quantification of fluid-structure interactions in marine structures is crucial for their design and optimization. In this study, an analytical solution for the free vibration of a bidirectional composite in contact with a fluid is proposed. By imposing continuity conditions and boundary conditions, the coupled fluid-structure problem is solved and applied to sandwich structures in naval construction, offering insights into the effects of water on mode shapes and through-the-thickness profiles of displacement and stress.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Shahram Hadian Jazi, Mostafa Hadian, Keivan Torabi
Summary: Non-uniformity and damage are the main focus in studying vibrations of beam elements. An exact closed-form explicit solution for the transverse displacement of a nonuniform multi-cracked beam is introduced using generalized functions and distributional derivative concepts. By introducing non-dimensional parameters, the motion equation and its closed-form solution are obtained based on four fundamental functions. The impact of crack count, location, intensity, and boundary conditions on natural frequency and mode shape is evaluated through numerical study.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Eugenio Tramacere, Marius Pakstys, Renato Galluzzi, Nicola Amati, Andrea Tonoli, Torbjoern A. Lembke
Summary: This paper proposes the experimental stabilization of electrodynamic maglev systems by means of passive components, providing key technological support for the Hyperloop concept of high-speed and sustainable transportation.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Pengfei Deng, Xing Tan, He Li
Summary: In this paper, the authors improve the surface morphology method and study the bit-rock interaction model between the rock and the PDC bit, taking into account the impact of blade shape and cutter arrangement. They establish a dynamic model for a deep drilling system equipped with an arbitrary shape PDC bit and propose a stability prediction method. The results show that the shape of the blades and arrangement of the cutters on the PDC bit significantly affect the nonlinear vibration of the drilling system.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Salvador Rodriguez-Blanco, Javier Gonzalez-Monge, Carlos Martel
Summary: In modern LPT designs, the simultaneous presence of forced response and flutter in different operation regimes is unavoidable. Recent evidence suggests that the traditional linear superposition method may be overly conservative. This study examines the flutter and forced response interaction in a realistic low pressure turbine rotor and confirms that the actual response is much smaller than that predicted by linear superposition.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Kabilan Baskaran, Nur Syafiqah Jamaluddin, Alper Celik, Djamel Rezgui, Mahdi Azarpeyvand
Summary: This study investigates the impact of the number of blades on the aeroacoustic characteristics and aerodynamic performance of propellers used in urban air mobility vehicles. The results show that different blade numbers exhibit distinct noise levels, providing valuable insights for further research on propeller noise and aerodynamic performance.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Yongbo Peng, Peifang Sun
Summary: This study focuses on the reliability-based design optimization (RBDO) of the tuned mass-damper-inerter (TMDI) system under non-stationary excitations. The performance of the optimized TMDI system is evaluated using probability density evolution analysis. The results demonstrate the technical advantages of TMDI, including high vibration mitigation performance, considerable mass reduction, and less stroke demand.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Guanfu Lin, Zhong-Rong Lu, Jike Liu, Li Wang
Summary: Vision-based measurement is an emerging method that enables full-field measurement with non-contact and high spatial resolution capabilities. This paper presents a single-camera method for measuring out-of-plane vibration of plate structures using motion-parametric homography to capture image variation and displacement response.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Bronislaw Czaplewski, Mateusz Bocian, John H. G. Macdonald
Summary: Despite two decades of study, there is currently no model that can quantitatively explain pedestrian-generated lateral forces. This research proposes a foot placement control law based on empirical data to calibrate and generalize the rigid-leg inverted pendulum model (IPM) for predicting lateral structural stability.
JOURNAL OF SOUND AND VIBRATION
(2024)
Article
Acoustics
Justine Carpentier, Jean-Hugh Thomas, Charles Pezerat
Summary: This paper proposes an improved method for the identification of vibration sources on a car window using the corrected force analysis technique. By redefining inverse methods in polar coordinates, more accurate results can be obtained.
JOURNAL OF SOUND AND VIBRATION
(2024)