Search

The use of Machine Learning (ML) has rapidly spread across several fields of applied sciences, having encountered many applications in Structural Dynamics and Vibroacoustic (SD&V). An advantage of ML algorithms compared to traditional techniques is that physical phenomena can be modeled using only sampled data from either measurements or simulations. This is particularly important in SD&V when the model of the studied phenomenon is either unknown or computationally expensive to simulate. This paper presents a survey on the application of ML algorithms in three classical problems of SD&V: structural health monitoring, active control of noise and vibration, and vibroacoustic product design. In structural health monitoring, ML is employed to extract damage-sensitive features from sampled data and to detect, localize, assess, and forecast failures in the structure. In active control of noise and vibration, ML techniques are used in the identification of state-space models of the controlled system, dimensionality reduction of existing models, and design of controllers. In vibroacoustic product design, ML algorithms can create surrogates that are faster to evaluate than physics-based models. The methodologies considered in this work are analyzed in terms of their strength and limitations for each of the three considered SD&V problems. Moreover, the paper considers the role of digital twins and physics-guided ML to overcome current challenges and lay the foundations for future research in the field. • Review of machine learning applied in vibroacoustic and structural dynamics. • Basic principles of the machine learning methods commonly used are presented. • Control, structural health monitoring and design are the most relevant applications. • The current implementation scenario and challenges are reviewed for each application. • This article sheds light on trends and research opportunities merging both fields. [ABSTRACT FROM AUTHOR]

This paper proposes a digital twin-based multi-element hybrid simulation (DMHS) framework to predict the nonlinear cyclic response of structural components (digital twin), e.g., seismic fuses, that are not physically tested due to laboratory limitations by leveraging the experimental test data collected from the physical test specimen (physical twin) during hybrid simulation. This data-based simulation approach can address biased results of hybrid simulation of structures that contain multiple critical components while improving the efficiency of the seismic hybrid simulation. The digital twin is trained in two phases: (1) passive (initial) training phase using past experimental test data before the hybrid simulation starts, and (2) recursive model updating phase using the active (real-time) data produced by the physical specimen during hybrid simulation. The passive training is achieved using the Prandtl–Ishlinskii (PI) hysteresis model combined with the sparse identification technique, while the recursive least-squares algorithm is used in the second phase as the model updating scheme. In particular, the sparse identification technique facilitates the selection of the optimal number of hysteretic model parameters in the passive training phase, which are then tuned in the model updating phase. The architecture of the proposed DMHS framework is first presented, followed by digital twin training steps. The application of the proposed DMHS is then demonstrated, and its simulation accuracy is assessed through virtual hybrid simulation of a two-storey steel buckling-restrained braced frame, which consists of a digital twin (second-storey brace) and a virtual experimental specimen (first-storey brace) integrated into the numerical model of the structure that is subjected to a set of earthquake ground motion accelerations. The results obtained from the verification study serve to validate the proposed architecture of the DMHS framework and evaluate the accuracy and efficiency of this technique in simulating the nonlinear seismic response of structural systems. [ABSTRACT FROM AUTHOR]

• A digital twin-driven intelligent gear health management method is developed to assess the gear surface degradation progression. • A high-fidelity digital twin model is built for the gear transmission system. • A transfer learning algorithm is proposed for gear wear severity assessment. • Two endurance tests are conducted to validate the effectiveness of the proposed methodology. Gearbox has a compact structure, a stable transmission capability, and a high transmission efficiency. Thus, it is widely applied as a power transmission system in various applications, such as wind turbines, industrial machinery, aircraft, space vehicles, and land vehicles. The gearbox usually operates in harsh and non-stationary working environments, expediting the degradation process of the gear surface. The degradation process may lead to severe gear failures, such as tooth breakage and root crack, which could damage the gear transmission system. Therefore, it is essential to assess the progression of gear surface degradation in order to ensure a reliable operation. The digital twin is an emerging technology for machine health management. A high-fidelity digital twin model can help reflect the operation status of the gearbox and reveal the corresponding degradation mechanism, which could benefit the remaining useful life (RUL) prediction and the predictive maintenance-based decision-making framework. This paper develops a digital twin-driven intelligent health management method to monitor and assess the gear surface degradation progression. The developed method can effectively reveal the gear wear propagation characteristics and predict the RUL accurately. Furthermore, the knowledge learned from digital twin models can be well transferred to the surface wear assessment of the physical gearbox in wide industrial applications, which is of great practical significance. Two endurance tests with different dominant degradation mechanisms were conducted to validate the effectiveness of the proposed methodology for gear wear assessment. [ABSTRACT FROM AUTHOR]

Digital twins seek to replicate a physical structure in a digital domain. For a digital twin to have close correspondence to its physical twin, data are required. However, it is not always possible, or cost-effective, to collect a complete set of data for a structure in all configurations of interest. It is nonetheless useful to repurpose data to help validate predictions for different configurations and scenarios. This statement is true in drilling applications, where, for example, the length of the drill string is altered throughout operation. This paper demonstrates how transfer learning, in the form of three domain-adaptation methods, — transfer component analysis (TCA), maximum independence domain adaptation (MIDA) and geodesic flow kernel (GFK) — can be used to construct a digital twin for localising torsional friction in deviated wells under structural changes (e.g., when the drill column gets longer). The method uses a physics-based torsional model to train a machine-learning classifier that can localise torsional friction for a given drill string length and diameter, where friction localisation labels are known (source). As the length or diameter of the drill string are altered in the field, transfer learning is utilised to map the classifier from the labelled (source) scenario onto these unlabelled (target) scenarios. As a result, transfer learning improves the performance of the classifier when applied to the target data, and increases the domain of validity for the classifier. The performance of the classifier, and therefore its suitability to new drill-string configurations, is estimated by utilising two different distance metrics between the source and a proposed target dataset. [ABSTRACT FROM AUTHOR]

• A digital twin (DT) is constructed for damaged detection in structures. • There is an integration of physics-based models with machine learning. • This strategy allows interpretablibility (physics) and speed (ML). • The influence of several parameters on the DT accuracy in analyzed. • Conclusions might be helpful for a large range of applications. This work is interested in digital twins, and the development of a simplified framework for them, in the context of dynamical systems. Digital twin is an ingenious concept that helps on organizing different areas of expertise aiming at supporting engineering decisions related to a specific asset; it articulates computational models, sensors, learning, real time analysis, diagnosis, prognosis, and so on. In this framework, and to leverage its capacity, we explore the integration of physics-based models with machine learning. A digital twin is constructed for a damaged structure, where a discrete physics-based computational model is employed to investigate several damage scenarios. A machine learning classifier, that serves as the digital twin, is trained with data taken from a stochastic computational model. This strategy allows the use of an interpretable model (physics-based) to build a fast digital twin (machine learning) that will be connected to the physical twin to support real time engineering decisions. Different classifiers (quadratic discriminant, support vector machines, etc) are tested, and different model parameters (number of sensors, level of noise, damage intensity, uncertainty, operational parameters, etc) are considered to construct datasets for the training. The accuracy of the digital twin depends on the scenario analyzed. Through the chosen application, we are able to emphasize each step of a digital twin construction, including the possibility of integrating physics-based models with machine learning. The different scenarios explored yield conclusions that might be helpful for a large range of applications. [ABSTRACT FROM AUTHOR]