A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic

Abstract

The use of Machine Learning (ML) has rapidly spread across several fields, having encountered many applications in Structural Dynamics and Vibroacoustic (SD&V). The increasing capabilities of ML to unveil insights from data, driven by unprecedented data availability, algorithms advances and computational power, enhance decision making, uncertainty handling, patterns recognition and real-time assessments. Three main applications in SD&V have taken advantage of these benefits. In Structural Health Monitoring, ML detection and prognosis lead to safe operation and optimized maintenance schedules. System identification and control design are leveraged by ML techniques in Active Noise Control and Active Vibration Control. Finally, the so-called ML-based surrogate models provide fast alternatives to costly simulations, enabling robust and optimized product design. Despite the many works in the area, they have not been reviewed and analyzed. Therefore, to keep track and understand this ongoing integration of fields, this paper presents a survey of ML applications in SD&V analyses, shedding light on the current state of implementation and emerging opportunities. The main methodologies, advantages, limitations, and recommendations based on scientific knowledge were identified for each of the three applications. Moreover, the paper considers the role of Digital Twins and Physics Guided ML to overcome current challenges and power future research progress. As a result, the survey provides a broad overview of the present landscape of ML applied in SD&V and guides the reader to an advanced understanding of progress and prospects in the field.

On Machine Learning-Driven Surrogates for Sound Transmission Loss Simulations

“…where ω 2 m,n are the natural frequencies of the simply supported plate and p I m,n can be analytically evaluated by solving the integrals from Eq A. 24. Finally, the solution of the system of equation in Eq.…”

“…The growing trend in vibroacoustic of relying on surrogates based on high-fidelity simulations not just enables the search for optimal and reliable designs, but also paves the way to the construction of Digital Twins for real-time vibroacoustic applications, such as online monitoring and control [23,24]. However, the reliability of these solutions depends on the accuracy of the surrogate models.…”

Non-Contact Vibro-Acoustic Object Recognition Using Laser Doppler Vibrometry and Convolutional Neural Networks

“…With computational power increasing seemingly unabated, the application of machine learning to the interpretation of structural vibration and acoustical measurement data has attracted significant interest [ 6 , 7 , 8 ]. Recent examples include the use of ground-penetrating radar data and a convolutional neural network (CNN) to detect the presence of a landmine [ 9 ], recurrence quantification analysis to detect objects buried in the seabed from raw sonar data [ 10 ] and machine learning to perform speaker diarisation from LDV measurements [ 11 ].…”

On Machine-Learning-Driven Surrogates for Sound Transmission Loss Simulations

“…The growing trend in vibroacoustics of relying on surrogates based on high-fidelity simulations not just enables the search for optimal and reliable designs, but also paves the way to the construction of digital twins for real-time vibroacoustic applications, such as online monitoring and control [19,20]. However, the reliability of these solutions depends on the accuracy of the surrogate models.…”